diff --git a/.vscode/extensions.json b/.vscode/extensions.json new file mode 100644 index 00000000..7e257db9 --- /dev/null +++ b/.vscode/extensions.json @@ -0,0 +1,3 @@ +{ + "recommendations": [] +} \ No newline at end of file diff --git a/.vscode/settings.json b/.vscode/settings.json new file mode 100644 index 00000000..642ff51b --- /dev/null +++ b/.vscode/settings.json @@ -0,0 +1,3 @@ +{ + "python.REPL.enableREPLSmartSend": false +} \ No newline at end of file diff --git a/Group 4 Power Point Presentation.pdf b/Group 4 Power Point Presentation.pdf new file mode 100644 index 00000000..c887f582 Binary files /dev/null and b/Group 4 Power Point Presentation.pdf differ diff --git a/README.md b/README.md index 5dd0f84d..cbae186d 100644 --- a/README.md +++ b/README.md @@ -1,285 +1,148 @@ -# Phase 2 Project Description - -Another module down - you're almost half way there! - -![awesome](https://raw.githubusercontent.com/learn-co-curriculum/dsc-phase-2-project-v2-3/main/halfway-there.gif) - -All that remains in Phase 2 is to put your newfound data science skills to use with a large project! - -In this project description, we will cover: - -* Project Overview: the project goal, audience, and dataset -* Deliverables: the specific items you are required to produce for this project -* Grading: how your project will be scored -* Getting Started: guidance for how to begin working +# REAL ESTATE SALES PREDICTION MODEL +![intro](images/intro.png) ## Project Overview -For this project, you will use multiple linear regression modeling to analyze house sales in a northwestern county. +In the fast-paced world of real estate, it's crucial for agencies to provide clients with precise information. Clients, whether they're looking to become homeowners or investors, rely on real estate companies for guidance on important decisions such as pricing, market trends, and property evaluations. To meet this need, real estate agencies can benefit from a sophisticated regression-based tool. This tool uses various property variables like the number of bedrooms, year built, floor count, living area, condition, location, and amenities to accurately predict property prices. By employing regression analysis, agencies can offer clients more precise pricing estimates, leading to better-informed decisions. Ultimately, this tool aims to improve client satisfaction, streamline decision-making processes, and drive success for real estate agencies. ### Business Problem -It is up to you to define a stakeholder and business problem appropriate to this dataset. - -If you are struggling to define a stakeholder, we recommend you complete a project for a real estate agency that helps homeowners buy and/or sell homes. A business problem you could focus on for this stakeholder is the need to provide advice to homeowners about how home renovations might increase the estimated value of their homes, and by what amount. - -### The Data - -This project uses the King County House Sales dataset, which can be found in `kc_house_data.csv` in the data folder in this assignment's GitHub repository. The description of the column names can be found in `column_names.md` in the same folder. As with most real world data sets, the column names are not perfectly described, so you'll have to do some research or use your best judgment if you have questions about what the data means. - -It is up to you to decide what data from this dataset to use and how to use it. If you are feeling overwhelmed or behind, we recommend you **ignore** some or all of the following features: - -* `date` -* `view` -* `sqft_above` -* `sqft_basement` -* `yr_renovated` -* `zipcode` -* `lat` -* `long` -* `sqft_living15` -* `sqft_lot15` - -### Key Points - -* **Your goal in regression modeling is to yield findings to support relevant recommendations. Those findings should include a metric describing overall model performance as well as at least two regression model coefficients.** As you explore the data and refine your stakeholder and business problem definitions, make sure you are also thinking about how a linear regression model adds value to your analysis. "The assignment was to use linear regression" is not an acceptable answer! You can also use additional statistical techniques other than linear regression, so long as you clearly explain why you are using each technique. - -* **You should demonstrate an iterative approach to modeling.** This means that you must build multiple models. Begin with a basic model, evaluate it, and then provide justification for and proceed to a new model. After you finish refining your models, you should provide 1-3 paragraphs in the notebook discussing your final model. - -* **Data visualization and analysis are no longer explicit project requirements, but they are still very important.** In Phase 1, your project stopped earlier in the CRISP-DM process. Now you are going a step further, to modeling. Data visualization and analysis will help you build better models and tell a better story to your stakeholders. - -## Deliverables - -There are three deliverables for this project: - -* A **non-technical presentation** -* A **Jupyter Notebook** -* A **GitHub repository** - -The deliverables requirements are almost the same as in the Phase 1 Project, and you can review those extended descriptions [here](https://github.com/learn-co-curriculum/dsc-phase-1-project-v2-3#deliverables). In general, everything is the same except the "Data Visualization" and "Data Analysis" requirements have been replaced by "Modeling" and "Regression Results" requirements. - -### Non-Technical Presentation - -Recall that the non-technical presentation is a slide deck presenting your analysis to ***business stakeholders***, and should be presented live as well as submitted in PDF form on Canvas. - -We recommend that you follow this structure, although the slide titles should be specific to your project: - -1. Beginning - - Overview - - Business and Data Understanding -2. Middle - - **Modeling** - - **Regression Results** -3. End - - Recommendations - - Next Steps - - Thank you - -Make sure that your discussion of modeling and regression results is geared towards a non-technical audience! Assume that their prior knowledge of regression modeling is minimal. You don't need to explain how linear regression works, but you should explain why linear regression is useful for the problem context. Make sure you translate any metrics or coefficients into their plain language implications. - -The graded elements for the non-technical presentation are the same as in [Phase 1](https://github.com/learn-co-curriculum/dsc-phase-1-project-v2-3#deliverables). - -### Jupyter Notebook - -Recall that the Jupyter Notebook is a notebook that uses Python and Markdown to present your analysis to a ***data science audience***. You will submit the notebook in PDF format on Canvas as well as in `.ipynb` format in your GitHub repository. - -The graded elements for the Jupyter Notebook are: - -* Business Understanding -* Data Understanding -* Data Preparation -* **Modeling** -* **Regression Results** -* Code Quality - -### GitHub Repository - -Recall that the GitHub repository is the cloud-hosted directory containing all of your project files as well as their version history. - -The requirements are the same as in [Phase 1](https://github.com/learn-co-curriculum/dsc-phase-1-project-v2-3#github-repository), except for the required sections in the `README.md`. - -For this project, the `README.md` file should contain: - -* Overview -* Business and Data Understanding - * Explain your stakeholder audience here -* **Modeling** -* **Regression Results** -* Conclusion - -Just like in Phase 1, the `README.md` file should be the bridge between your non technical presentation and the Jupyter Notebook. It should not contain the code used to develop your analysis, but should provide a more in-depth explanation of your methodology and analysis than what is described in your presentation slides. - -## Grading - -***To pass this project, you must pass each project rubric objective.*** The project rubric objectives for Phase 2 are: - -1. Attention to Detail -2. Statistical Communication -3. Data Preparation Fundamentals -4. Linear Modeling - -### Attention to Detail - -Just like in Phase 1, this rubric objective is based on your completion of checklist items. ***In Phase 2, you need to complete 70% (7 out of 10) or more of the checklist elements in order to pass the Attention to Detail objective.*** - -**NOTE THAT THE PASSING BAR IS HIGHER IN PHASE 2 THAN IT WAS IN PHASE 1!** - -The standard will increase with each Phase, until you will be required to complete all elements to pass Phase 5 (Capstone). - -#### Exceeds Objective - -80% or more of the project checklist items are complete - -#### Meets Objective (Passing Bar) - -70% of the project checklist items are complete - -#### Approaching Objective - -60% of the project checklist items are complete - -#### Does Not Meet Objective - -50% or fewer of the project checklist items are complete - -### Statistical Communication - -Recall that communication is one of the key data science "soft skills". In Phase 2, we are specifically focused on Statistical Communication. We define Statistical Communication as: - -> Communicating **results of statistical analyses** to diverse audiences via writing and live presentation - -Note that this is the same as in Phase 1, except we are replacing "basic data analysis" with "statistical analyses". - -High-quality Statistical Communication includes rationale, results, limitations, and recommendations: - -* **Rationale:** Explaining why you are using statistical analyses rather than basic data analysis - * For example, why are you using regression coefficients rather than just a graph? - * What about the problem or data is suitable for this form of analysis? - * For a data science audience, this includes your reasoning for the changes you applied while iterating between models. -* **Results:** Describing the overall model metrics and feature coefficients - * You need at least one overall model metric (e.g. r-squared or RMSE) and at least two feature coefficients. - * For a business audience, make sure you connect any metrics to real-world implications. You do not need to get into the details of how linear regression works. - * For a data science audience, you don't need to explain what a metric is, but make sure you explain why you chose that particular one. -* **Limitations:** Identifying the limitations and/or uncertainty present in your analysis - * This could include p-values/alpha values, confidence intervals, assumptions of linear regression, missing data, etc. - * In general, this should be more in-depth for a data science audience and more surface-level for a business audience. -* **Recommendations:** Interpreting the model results and limitations in the context of the business problem - * What should stakeholders _do_ with this information? +Real estate experts in King County need help understanding what factors influence property values and market trends. This study aims to analyze property features, locations, buyer preferences, and market changes over time. By gaining insights from this analysis, real estate professionals can make informed decisions about buying, selling, and positioning themselves in the dynamic King County market. The goal is to provide practical advice to help them succeed in this ever-changing real estate landscape. -#### Exceeds Objective +### The Data Understanding -Communicates the rationale, results, limitations, and specific recommendations of statistical analyses +King County, Washington, situated in the northwest of the United States, is known for its vibrant housing market centered around Seattle. The county has experienced significant growth due to its strong economy and cultural importance, attracting a large number of residents and creating high demand for housing in both urban and suburban areas. Seattle, with its impressive skyline, is especially sought after by tech professionals and city lovers. King County's real estate market is competitive, offering a range of neighborhoods to suit different preferences, from historic areas to modern suburban developments -> See above for extended explanations of these terms. +**Target Variable** +price: Sale price of the house . -#### Meets Objective (Passing Bar) +**Property Characteristics:** +![property-characteristics](images/property-characteristics.png) -Successfully communicates the results of statistical analyses without any major errors -> The minimum requirement is to communicate the _results_, meaning at least one overall model metric (e.g. r-squared or RMSE) as well as at least two feature coefficients. See the Approaching Objective section for an explanation of what a "major error" means. +**Main Objective:** -#### Approaching Objective +The primary aim of this project is to develop a predictive regression model to support real estate agencies in advising clients on house prices. This model is intended to anticipate potential changes in property value based on property characteristics, furnishing clients with valuable insights to facilitate informed investment decisions. -Communicates the results of statistical analyses with at least one major error -> A major error means that some aspect of your explanation is fundamentally incorrect. For example, if a feature coefficient is negative and you say that an increase in that feature results in an increase of the target, that would be a major error. Another example would be if you say that the feature with the highest coefficient is the "most statistically significant" while ignoring the p-value. One more example would be reporting a coefficient that is not statistically significant, rather than saying "no statistically significant linear relationship was found" +#**Statistical Analysis** +Statistical analysis plays a crucial role in understanding relationships within datasets, identifying patterns, and gaining insights. In this regression modeling project aimed at predicting property values, several key steps in statistical analysis are essential: -> "**If a coefficient's t-statistic is not significant, don't interpret it at all.** You can't be sure that the value of the corresponding parameter in the underlying regression model isn't really zero." _DeVeaux, Velleman, and Bock (2012), Stats: Data and Models, 3rd edition, pg. 801_. Check out [this website](https://web.ma.utexas.edu/users/mks/statmistakes/TOC.html) for extensive additional examples of mistakes using statistics. +<<<<<<< HEAD +Descriptive Statistics +Correlation matrix +Distribution Analysis +Inferential Statistics using Hypothesis Testing and Analysis of Variance +MultiColinierity -> The easiest way to avoid making a major error is to have someone double-check your work. Reach out to peers on Slack and ask them to confirm whether your interpretation makes sense! -#### Does Not Meet Objective +# *Modelling** +Baseline model - simple linear model. -Does not communicate the results of statistical analyses -> It is not sufficient to just display the entire results summary. You need to pull out at least one overall model metric (e.g. r-squared, RMSE) and at least two feature coefficients, and explain what those numbers mean. -### Data Preparation Fundamentals +======= +1. Descriptive Statistics +2. Correlation matrix +3. Distribution Analysis +4. Inferential Statistics using Hypothesis Testing and Analysis of Variance +5. MultiColinierity -We define this objective as: +# **Modelling** -> Applying appropriate **preprocessing** and feature engineering steps to tabular data in preparation for statistical modeling +1. Baseline model - simple linear model. +>>>>>>> 0a440037de0b20dcd0b9a308c1a7d88dff9cfac8 +2. log transformation. -The two most important components of preprocessing for the Phase 2 project are: -* **Handling Missing Values:** Missing values may be present in the features you want to use, either encoded as `NaN` or as some other value such as `"?"`. Before you can build a linear regression model, make sure you identify and address any missing values using techniques such as dropping or replacing data. -* **Handling Non-Numeric Data:** A linear regression model needs all of the features to be numeric, not categorical. For this project, ***be sure to pick at least one non-numeric feature and try including it in a model.*** You can identify that a feature is currently non-numeric if the type is `object` when you run `.info()` on your dataframe. Once you have identified the non-numeric features, address them using techniques such as ordinal or one-hot (dummy) encoding. +3. Multiple Linear Regression -There is no single correct way to handle either of these situations! Use your best judgement to decide what to do, and be sure to explain your rationale in the Markdown of your notebook. +4. Residual modelling. -Feature engineering is encouraged but not required for this project. +# **REGRESSION RESULTS** -#### Exceeds Objective +**SIMPLE LINEAR REGRESSION** +R-squared (0.48): Indicates that approximately 48% of the variability in house prices is explained by the square footage of living space. It measures how well the model captures patterns in the data. +Mean Squared Error (MSE) (68845100756.11): Represents the average squared difference between actual and predicted house prices. Lower values indicate better accuracy, but here, the MSE is quite large, suggesting room for improvement. +Root Mean Squared Error (RMSE) (262383.50): This is the square root of the MSE, providing a measure of typical deviation between predicted and actual house prices. The RMSE is approximately 262,383.50 units. +Intercept (540631.16): Estimated house price when all independent variables are zero. It's around 540,631.16 units, suggesting a baseline value. +Coefficient (259767.82): Represents the change in house prices for a one-unit increase in square footage of living space, with other variables held constant. For every one-unit increase in square footage, house prices are expected to increase by approximately 259,767.82 units. -Goes above and beyond with data preparation, such as feature engineering or merging in outside datasets +# **Multiple Linear Regresion** +![Multiple-Linear-Regression](images/Multiple-Linear-Regression.png) -> One example of feature engineering could be using the `date` feature to create a new feature called `season`, which represents whether the home was sold in Spring, Summer, Fall, or Winter. +# **RESIDUALS** +![Residuals](images/Residuals.png) +A p-value of 3.975373048166964e-258, which is extremely close to zero, indicates strong evidence against the null hypothesis of homoscedasticity. In other words, there is a significant presence of heteroscedasticity in your data. +We can see the positive correlation between the house prices and all other features except the year built which indicates a negative correlation. -> One example of merging in outside datasets could be finding data based on ZIP Code, such as household income or walkability, and joining that data with the provided CSV. +# **Log transformation**. +Transforming the dependent variable or one or more independent variables can sometimes stabilize the variance. Common transformations include taking the natural logarithm, square root, or reciprocal of the variables. -#### Meets Objective (Passing Bar) +*Log transformation of the multiple linear regression.* -Successfully prepares data for modeling, including converting at least one non-numeric feature into ordinal or binary data and handling missing data as needed +![Log-transformation](images/Log-transformation.png) -> As a reminder, you can identify the non-numeric features by calling `.info()` on the dataframe and looking for type `object`. -> Your final model does not necessarily need to include any features that were originally non-numeric, but you need to demonstrate your ability to handle this type of data. +# **REGRESSION Results** -#### Approaching Objective +From all the models observed,We can see the positive correlation between the house prices and all other features except the year built which indicates a negative correlation. -Prepares some data successfully, but is unable to utilize non-numeric data +Polynomial Regression is the preferred model beacuse from the evaluation it has the highest R-squared value of 0.73 -> If you simply subset the dataframe to only columns with type `int64` or `float64`, your model will run, but you will not pass this objective. +The features below impact price such that an increase will cause an increase in the price of the property. 'bedrooms','bathrooms', 'sqft_living','floors', 'waterfront','view''condition', 'grade', 'sqft_above','sqft_basement', 'yr_renovated', 'sqft_living15','renovated', 'basement' -#### Does Not Meet Objective +<<<<<<< HEAD +Independence of errors: The errors (residuals) from the regression model should be independent of each other. In other words, the residual for one observation should not predict the residual for another observation. -Does not prepare data for modeling +Normality of errors: The errors are normally distributed. This implies that the residuals should follow a normal distribution with a mean of zero. -### Linear Modeling +No perfect multicollinearity: There should be no perfect linear relationship between the independent variables. In other words, no independent variable should be a perfect linear combination of other independent variables. +# **Limitations** +Despite its effectiveness in predicting property prices, the model has several limitations that need to be addressed: -According to [Kaggle's 2020 State of Data Science and Machine Learning Survey](https://www.kaggle.com/kaggle-survey-2020), linear and logistic regression are the most popular machine learning algorithms, used by 83.7% of data scientists. They are small, fast models compared to some of the models you will learn later, but have limitations in the kinds of relationships they are able to learn. +Limited Property Characteristics: The dataset may lack comprehensive property-based characteristics, potentially limiting the model's ability to capture the full range of factors influencing housing prices. -In this project you are required to use linear regression as the primary statistical analysis, although you are free to use additional statistical techniques as appropriate. +Multicollinearity Concerns: The presence of correlated predictors, such as square footage and number of bedrooms, can introduce multicollinearity issues. This makes it difficult to discern the individual impact of each feature accurately, potentially affecting the model's reliability. -#### Exceeds Objective +Assumption Violations: Polynomial regression relies on the assumption of linearity between predictors and the target variable. However, in reality, this assumption may not always hold true, leading to biased estimates and less dependable predictions.Also heteroscedasticity was present. -Goes above and beyond in the modeling process, such as recursive feature selection +Overfitting Risk: Polynomial regression models, especially those with high degrees, are prone to overfitting. This occurs when the model fits the training data too closely, capturing noise rather than underlying patterns. As a result, the model may struggle to generalize well to unseen data, impacting its predictive performance. +======= +>>>>>>> 0a440037de0b20dcd0b9a308c1a7d88dff9cfac8 -#### Meets Objective (Passing Bar) +**Limitations** +1. The dataset could have more property based characteristics +2. Multicollinearity:The presence of correlated predictors (e.g., square footage and number of bedrooms) can lead to multicollinearity issues, making it challenging to interpret the individual effects of each feature accurately +3. Assumption Violations:Polynomial regression assumes linearity between predictors and the target variable, which may not hold true in all cases. Violations of this assumption can lead to biased estimates and unreliable predictions. +4. Overfitting: Polynomial regression models, particularly those with high degrees, are susceptible to overfitting, where the model fits the training data too closely and may not generalize well to unseen data. +Overall the model was the best fit model for this predictions -Successfully builds a baseline model as well as at least one iterated model, and correctly extracts insights from a final model without any major errors +# **RECOMENDATIONS** -> We are looking for you to (1) create a baseline model, (2) iterate on that model, making adjustments that are supported by regression theory or by descriptive analysis of the data, and (3) select a final model and report on its metrics and coefficients +1.Invest in Larger Properties: Investors seeking maximum returns should focus on larger houses, as there's a positive correlation between total square footage and price. Such properties have the potential for higher profits upon resale or rental. -> Ideally you would include written justifications for each model iteration, but at minimum the iterations must be _justifiable_ -> For an explanation of "major errors", see the description below +2.Upgrade Existing Properties: Homeowners can increase their property's value by investing in upgrades that increase square footage, such as adding extra rooms or expanding living spaces. -#### Approaching Objective -Builds multiple models with at least one major error +3.Optimize Bedroom and Bathroom Ratios: It's essential to find the right balance between bedrooms and bathrooms to maximize property value. Consulting with real estate professionals can help determine the optimal ratio based on market trends and buyer preferences. -> The number one major error to avoid is including the target as one of your features. For example, if the target is `price` you should NOT make a "price per square foot" feature, because that feature would not be available if you didn't already know the price. -> Other examples of major errors include: using a target other than `price`, attempting only simple linear regression (not multiple linear regression), dropping multiple one-hot encoded columns without explaining the resulting baseline, or using a unique identifier (`id` in this dataset) as a feature. +4.Focus on Quality Over Quantity: Prioritize quality improvements that enhance functionality and aesthetics, such as renovating bathrooms with modern fixtures or upgrading kitchen appliances, to add perceived value to the property. -#### Does Not Meet Objective -Does not build multiple linear regression models +5.Highlight Features in Listings: Emphasize the number of bedrooms and bathrooms in property listings to attract buyers who prioritize space and convenience. Highlight unique features that add versatility to the property. -## Getting Started -Please start by reviewing the contents of this project description. If you have any questions, please ask your instructor ASAP. +6.Differentiate Marketing Strategies: Tailor marketing strategies based on property condition and grade ratings. Highlight the benefits of higher-grade properties to attract premium buyers, while emphasizing renovation potential for properties with lower condition ratings. -Next, you will need to complete the [***Project Proposal***](#project_proposal) which must be reviewed by your instructor before you can continue with the project. +# **Conclusion** -Here are some suggestions for creating your GitHub repository: +1. Property Size Matters: There is a clear positive correlation between the size of a property, indicated by total square footage, and its price. Investing in larger properties can potentially yield higher returns for investors and increase market value for homeowners. -1. Fork the [Phase 2 Project Repository](https://github.com/learn-co-curriculum/dsc-phase-2-project-v2-3), clone it locally, and work in the `student.ipynb` file. Make sure to also add and commit a PDF of your presentation to your repository with a file name of `presentation.pdf`. -2. Or, create a new repository from scratch by going to [github.com/new](https://github.com/new) and copying the data files from the Phase 2 Project Repository into your new repository. - - Recall that you can refer to the [Phase 1 Project Template](https://github.com/learn-co-curriculum/dsc-project-template) as an example structure - - This option will result in the most professional-looking portfolio repository, but can be more complicated to use. So if you are getting stuck with this option, try forking the project repository instead +2. Strategic Upgrades Add Value: Upgrading existing properties with strategic renovations and expansions, particularly those that increase square footage, can enhance their market value. Quality improvements that improve functionality and aesthetics are key to maximizing property value. -## Summary +3. Balance is Key: While adding extra bedrooms and bathrooms can increase a property's price, there's a point of diminishing returns. It's important to strike a balance between quantity and quality, optimizing the bedroom-to-bathroom ratio to align with market trends and buyer preferences. -This is your first modeling project! Take what you have learned in Phase 2 to create a project with a more sophisticated analysis than you completed in Phase 1. You will build on these skills as we move into the predictive machine learning mindset in Phase 3. You've got this! +4. Marketing Differentiation is Essential: Tailoring marketing strategies based on property condition and grade ratings is crucial. Highlighting the unique features and benefits of higher-grade properties can attract premium buyers, while emphasizing renovation potential for properties with lower ratings can appeal to savvy investors. diff --git a/images/Log-transformation.png b/images/Log-transformation.png new file mode 100644 index 00000000..9395317a Binary files /dev/null and b/images/Log-transformation.png differ diff --git a/images/Multiple-Linear-Regression.png b/images/Multiple-Linear-Regression.png new file mode 100644 index 00000000..4ef6fb5c Binary files /dev/null and b/images/Multiple-Linear-Regression.png differ diff --git a/images/Polynomial-Regression.png b/images/Polynomial-Regression.png new file mode 100644 index 00000000..851f1f82 Binary files /dev/null and b/images/Polynomial-Regression.png differ diff --git a/images/Residuals.png b/images/Residuals.png new file mode 100644 index 00000000..376e1aeb Binary files /dev/null and b/images/Residuals.png differ diff --git a/images/Simple linear Regression.png b/images/Simple linear Regression.png new file mode 100644 index 00000000..4ef6fb5c Binary files /dev/null and b/images/Simple linear Regression.png differ diff --git a/images/intro.png b/images/intro.png new file mode 100644 index 00000000..3c0c2f01 Binary files /dev/null and b/images/intro.png differ diff --git a/images/property-characteristics.png b/images/property-characteristics.png new file mode 100644 index 00000000..c88ea622 Binary files /dev/null and b/images/property-characteristics.png differ diff --git a/student.ipynb b/student.ipynb index d3bb34af..db69c240 100644 --- a/student.ipynb +++ b/student.ipynb @@ -7,26 +7,5165 @@ "## Final Project Submission\n", "\n", "Please fill out:\n", - "* Student name: \n", - "* Student pace: self paced / part time / full time\n", - "* Scheduled project review date/time: \n", - "* Instructor name: \n", - "* Blog post URL:\n" + "* Student name:\n", + "1. Winfred Kinya Bundi.\n", + "2. Carol Mundia.\n", + "3. Paul Muniu.\n", + "4. Dennis Mwenda.\n", + "* Student pace: Full time Hybrid\n", + "* Scheduled project review date/time:2/05/2024 \n", + "* Instructor name: Mwikali Maryanne.\n", + "* Blog post URL:git@github.com:winnycodegurl/dsc-phase-2-projectgroup4.git\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## INTRODUCTION\n", + "\n", + "In the fast-paced world of real estate, it's crucial for agencies to provide clients with precise information. Clients, whether they're looking to become homeowners or investors, rely on real estate companies for guidance on important decisions such as pricing, market trends, and property evaluations. To meet this need, real estate agencies can benefit from a sophisticated regression-based tool. This tool uses various property variables like the number of bedrooms, year built, floor count, living area, condition, location, and amenities to accurately predict property prices. By employing regression analysis, agencies can offer clients more precise pricing estimates, leading to better-informed decisions. Ultimately, this tool aims to improve client satisfaction, streamline decision-making processes, and drive success for real estate agencies.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## BUSINESS UNDERSTANDING\n", + "\n", + "\n", + "\n", + "The provided dataset encompasses details on homes sold, encompassing their attributes and sale prices. This dataset holds significant potential for real estate agencies across various avenues:\n", + "\n", + "\n", + "\n", + "1. \n", + "Market Analysis:\n", + "\n", + " Leveraging the dataset, agencies can discern market trends, including the demand for different property types, burgeoning neighborhoods witnessing property value escalations, and the impact obetter f featurenws or property renovations on sale prices. By employing market segmentation techniques, such as demographic or psychographic segmentation, agencies can further refine their analysis to understand the preferences and behaviors of distinct customer segments within the real estate market\n", + "\n", + "\n", + "\n", + "\n", + "2. \n", + "Property Valuation: \n", + "\n", + "By comprehending the correlation between house features and sale prices, agencies can proficiently gauge property values for both sellers and buyers, ensuring equitable and competitive pricing strategies\n", + "\n", + "\n", + "\n", + "\n", + "3. \n", + "Targeted Marketing: \n", + "\n", + "Through discerning buyer preferences from the dataset, agencies can tailor marketing endeavors to resonate with potential buyers seeking specific property types or neighborhoods, thus enhancing the efficacy of their outreach efforts. Market segmentation insights can inform the development of targeted marketing campaigns tailored to the unique needs and preferences of different customer segments, thereby maximizing the impact of marketing investments.\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## PROBLEM STATEMENT.\n", + "\n", + "\n", + "\n", + "In King County, people involved in real estate have trouble figuring out what affects property values and trends in the market.\n", + "This study wants to help by looking at things like what features a property has, where it's located, what buyers prefer,\n", + "and how things change over time. By understanding these things better, people in real estate can make smarter choices about\n", + "buying and selling property and how they position themselves in the market.\n", + "The main goal is to give them practical advice that helps them do well in King County's real estate market, \n", + "which is always changing.\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## OBJECTIVES.\n", + "\n", + "Main OBJECTIVE\n", + "\n", + "\n", + "The primary aim of this project is to develop a predictive regression model to support real estate agencies in advising clients \n", + "on house prices. This model is intended to anticipate potential changes in property value based on property characteristics, \n", + "furnishing clients with valuable insights to facilitate informed investment decisions.\n", + "\n", + "\n", + "\n", + "Specific Goals:\n", + "\n", + "\n", + "i). Identification of Key Influencing Factors on House Prices:\n", + "\n", + "\n", + "\n", + "Analyze various property features, including bedrooms, bathrooms, and square footage, to determine their impact on sale price.\n", + "\n", + "\n", + "\n", + "ii). Assessment of Model Performance:\n", + "\n", + "\n", + "Employ metrics such as mean squared error, R-squared values, and residual analysis to \n", + "evaluate the model's accuracy in predicting house prices effectively.\n", + "\n", + " \n", + "\n", + "iii). Provision of Actionable Recommendations:\n", + "\n", + "\n", + "\n", + "Offer practical recommendations to real estate agencies aimed at enhancing profitability and market presence. \n", + "Utilize insights gleaned from the model to optimize marketing strategies and enhance overall decision-making processes.\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Data Understanding.\n", + "\n", + "\n", + "King County, Washington, situated in the northwest of the United States, is known for its vibrant housing market centered around Seattle. The county has experienced significant growth due to its strong economy and cultural importance, attracting a large number of residents and creating high demand for housing in both urban and suburban areas. Seattle, with its impressive skyline, is especially sought after by tech professionals and city lovers. King County's real estate market is competitive, offering a range of neighborhoods to suit different preferences, from historic areas to modern suburban developments.\n", + "\n", + "### Whereby the dataset contains:\n", + "\n", + "### Target Variable\n", + "\n", + "price: Sale price of the house .\n", + "\n", + "### Unique identifier\n", + "\n", + "id - Unique identifier for a house\n", + "\n", + "### Property Characteristics:\n", + "\n", + "bedrooms: Number of bedrooms.\n", + "\n", + "bathrooms: Number of bathrooms.\n", + "\n", + "sqft_living: Square footage of living space in the home.\n", + "\n", + "sqft_lot: Square footage of the lot.\n", + "\n", + "floors: Number of floors (levels) in the house.\n", + "\n", + "waterfront: Indicates whether the house is on a waterfront (categorical: YES/NO).\n", + "\n", + "view: Quality of view from the house, categorized into various types.\n", + "\n", + "condition: Overall condition of the house, categorized based on maintenance.\n", + "\n", + "grade: Overall grade of the house, reflecting construction and design quality.\n", + "\n", + "### Additional Features:\n", + "\n", + "sqft_above: Square footage of house apart from the basement.\n", + "\n", + "sqft_basement: Square footage of the basement.\n", + "\n", + "yr_built: Year when the house was built.\n", + "\n", + "yr_renovated: Year when the house was renovated.\n", + "\n", + "zipcode: ZIP Code of the property.\n", + "\n", + "lat: Latitude coordinate of the property.\n", + "\n", + "long: Longitude coordinate of the property.\n", + "\n", + "sqft_living15: Square footage of interior housing living space for the nearest 15 neighbors.\n", + "\n", + "sqft_lot15: Square footage of the land lots of the nearest 15 neighbors.\n", + "\n", + "### TABLE OF CONTENTS\n", + "1.Data Preparation\n", + "\n", + "2.Data cleaning\n", + "\n", + "3.Exploratory data analysis\n", + "\n", + "4.Statistical Analysis\n", + "\n", + "5.Modelling\n", + "\n", + "6.Regression Results\n", + "\n", + "7.Conclusion\n", + "\n", + "8.Reccomendations" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 1. DATA PREPARATION" + ] + }, + { + "cell_type": "code", + "execution_count": 107, + "metadata": {}, + "outputs": [], + "source": [ + "# Importing necessary libraries for data analysis and visualization\n", + "\n", + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt # for data visualization.\n", + "%matplotlib inline\n", + "import seaborn as sns # for enhanced data visualization.\n", + "from pandas.api.types import is_numeric_dtype # Used to check if a data type is numeric.\n", + "\n", + "from statsmodels.stats.outliers_influence import variance_inflation_factor # For calculating Variance Inflation Factor (VIF).\n", + "from statsmodels.graphics.regressionplots import plot_partregress_grid # For partial regression plots.\n", + "from sklearn.model_selection import train_test_split # Used to split data into training and testing sets.\n", + "from sklearn.preprocessing import PolynomialFeatures # Generate polynomial features.\n", + "from sklearn.linear_model import LinearRegression # Linear Regression model.\n", + "from sklearn.preprocessing import StandardScaler # Standardizing/Scaling features.\n", + "from sklearn.feature_selection import RFE # Recursive Feature Elimination for feature selection.\n", + "from sklearn.metrics import mean_squared_error, r2_score # Evaluation metrics for model performance.\n", + "import statsmodels.api as sm\n", + "from scipy.stats import kstest\n", + "\n", + "# Statsmodels is used to create statistical models.\n", + "from scipy import stats # Scientific computing library for statistical tests.\n", + "from scipy.stats import f_oneway # One-way ANOVA statistical test.\n", + "from scipy.stats import ttest_ind # Independent sample t-test for comparing means." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### *loading the King County House Sales dataset*\n" + ] + }, + { + "cell_type": "code", + "execution_count": 108, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 21597 entries, 0 to 21596\n", + "Data columns (total 21 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 21597 non-null int64 \n", + " 1 date 21597 non-null object \n", + " 2 price 21597 non-null float64\n", + " 3 bedrooms 21597 non-null int64 \n", + " 4 bathrooms 21597 non-null float64\n", + " 5 sqft_living 21597 non-null int64 \n", + " 6 sqft_lot 21597 non-null int64 \n", + " 7 floors 21597 non-null float64\n", + " 8 waterfront 19221 non-null object \n", + " 9 view 21534 non-null object \n", + " 10 condition 21597 non-null object \n", + " 11 grade 21597 non-null object \n", + " 12 sqft_above 21597 non-null int64 \n", + " 13 sqft_basement 21597 non-null object \n", + " 14 yr_built 21597 non-null int64 \n", + " 15 yr_renovated 17755 non-null float64\n", + " 16 zipcode 21597 non-null int64 \n", + " 17 lat 21597 non-null float64\n", + " 18 long 21597 non-null float64\n", + " 19 sqft_living15 21597 non-null int64 \n", + " 20 sqft_lot15 21597 non-null int64 \n", + "dtypes: float64(6), int64(9), object(6)\n", + "memory usage: 3.5+ MB\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddatepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontview...gradesqft_abovesqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15
0712930052010/13/2014221900.031.00118056501.0NaNNONE...7 Average11800.019550.09817847.5112-122.25713405650
1641410019212/9/2014538000.032.25257072422.0NONONE...7 Average2170400.019511991.09812547.7210-122.31916907639
256315004002/25/2015180000.021.00770100001.0NONONE...6 Low Average7700.01933NaN9802847.7379-122.23327208062
3248720087512/9/2014604000.043.00196050001.0NONONE...7 Average1050910.019650.09813647.5208-122.39313605000
419544005102/18/2015510000.032.00168080801.0NONONE...8 Good16800.019870.09807447.6168-122.04518007503
\n", + "

5 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " id date price bedrooms bathrooms sqft_living \\\n", + "0 7129300520 10/13/2014 221900.0 3 1.00 1180 \n", + "1 6414100192 12/9/2014 538000.0 3 2.25 2570 \n", + "2 5631500400 2/25/2015 180000.0 2 1.00 770 \n", + "3 2487200875 12/9/2014 604000.0 4 3.00 1960 \n", + "4 1954400510 2/18/2015 510000.0 3 2.00 1680 \n", + "\n", + " sqft_lot floors waterfront view ... grade sqft_above \\\n", + "0 5650 1.0 NaN NONE ... 7 Average 1180 \n", + "1 7242 2.0 NO NONE ... 7 Average 2170 \n", + "2 10000 1.0 NO NONE ... 6 Low Average 770 \n", + "3 5000 1.0 NO NONE ... 7 Average 1050 \n", + "4 8080 1.0 NO NONE ... 8 Good 1680 \n", + "\n", + " sqft_basement yr_built yr_renovated zipcode lat long \\\n", + "0 0.0 1955 0.0 98178 47.5112 -122.257 \n", + "1 400.0 1951 1991.0 98125 47.7210 -122.319 \n", + "2 0.0 1933 NaN 98028 47.7379 -122.233 \n", + "3 910.0 1965 0.0 98136 47.5208 -122.393 \n", + "4 0.0 1987 0.0 98074 47.6168 -122.045 \n", + "\n", + " sqft_living15 sqft_lot15 \n", + "0 1340 5650 \n", + "1 1690 7639 \n", + "2 2720 8062 \n", + "3 1360 5000 \n", + "4 1800 7503 \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 108, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load the dataset to inspect the initial state of the data\n", + "file_path = 'data/kc_house_data.csv'\n", + "housing_data = pd.read_csv(file_path)\n", + "\n", + "# Display basic information and the first few rows of the dataset\n", + "housing_data.info()\n", + "housing_data.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### *loading the column.md dataset*\n" + ] + }, + { + "cell_type": "code", + "execution_count": 109, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Column_nameDescription
0* `id`Unique identifier for a house
1* `date`Date house was sold
2* `price`Sale price (prediction target)
3* `bedrooms`Number of bedrooms
4* `bathrooms`Number of bathrooms
5* `sqft_living`Square footage of living space in the home
6* `sqft_lot`Square footage of the lot
7* `floors`Number of floors (levels) in house
8* `waterfront`Whether the house is on a waterfront
9* `view`Quality of view from house
10* `condition`How good the overall condition of the house is...
11* `grade`Overall grade of the house. Related to the con...
12* `sqft_above`Square footage of house apart from basement
13* `sqft_basement`Square footage of the basement
14* `yr_built`Year when house was built
15* `yr_renovated`Year when house was renovated
16* `zipcode`ZIP Code used by the United States Postal Service
17* `lat`Latitude coordinate
18* `long`Longitude coordinate
19* `sqft_living15`The square footage of interior housing living ...
20* `sqft_lot15`The square footage of the land lots of the nea...
\n", + "
" + ], + "text/plain": [ + " Column_name Description\n", + "0 * `id` Unique identifier for a house\n", + "1 * `date` Date house was sold\n", + "2 * `price` Sale price (prediction target)\n", + "3 * `bedrooms` Number of bedrooms\n", + "4 * `bathrooms` Number of bathrooms\n", + "5 * `sqft_living` Square footage of living space in the home\n", + "6 * `sqft_lot` Square footage of the lot\n", + "7 * `floors` Number of floors (levels) in house\n", + "8 * `waterfront` Whether the house is on a waterfront\n", + "9 * `view` Quality of view from house\n", + "10 * `condition` How good the overall condition of the house is...\n", + "11 * `grade` Overall grade of the house. Related to the con...\n", + "12 * `sqft_above` Square footage of house apart from basement\n", + "13 * `sqft_basement` Square footage of the basement\n", + "14 * `yr_built` Year when house was built\n", + "15 * `yr_renovated` Year when house was renovated\n", + "16 * `zipcode` ZIP Code used by the United States Postal Service\n", + "17 * `lat` Latitude coordinate\n", + "18 * `long` Longitude coordinate\n", + "19 * `sqft_living15` The square footage of interior housing living ...\n", + "20 * `sqft_lot15` The square footage of the land lots of the nea..." + ] + }, + "execution_count": 109, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "column_names_file = \"data/column_names.md\"\n", + "\n", + "with open(column_names_file, \"r\") as file:\n", + " markdown_content = file.readlines()\n", + "\n", + "column_names = []\n", + "description = []\n", + "for line in markdown_content:\n", + " parts = line.split('-', 1)\n", + " if len(parts) == 2: # Check if split produces two parts\n", + " column_names.append(parts[0].strip())\n", + " description.append(parts[1].strip())\n", + "\n", + "# Create DataFrame\n", + "data = {\n", + " \"Column_name\": column_names,\n", + " \"Description\": description\n", + "}\n", + "column_name_df = pd.DataFrame(data)\n", + "\n", + "column_name_df\n" + ] + }, + { + "cell_type": "code", + "execution_count": 110, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "There are 3 columns with missing values.\n", + "waterfront 2376\n", + "view 63\n", + "yr_renovated 3842\n", + "dtype: int64\n" + ] + } + ], + "source": [ + "# Creating function to check counts of missing values\n", + "def has_missing_values(df):\n", + " missing_values = df.isnull().sum()\n", + " num_missing_values = missing_values[missing_values > 0].count()\n", + " if num_missing_values == 0:\n", + " print(\"There are no missing values in the DataFrame.\")\n", + " else:\n", + " print(f\"There are {num_missing_values} columns with missing values.\")\n", + " print(missing_values[missing_values > 0])\n", + " \n", + "has_missing_values(housing_data)" + ] + }, + { + "cell_type": "code", + "execution_count": 111, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "There are no duplicate rows in the DataFrame.\n" + ] + } + ], + "source": [ + "#creating a function to check for duplicates.\n", + "def has_duplicates(df):\n", + " num_duplicates = df.duplicated().sum()\n", + " if num_duplicates == 0:\n", + " print(\"There are no duplicate rows in the DataFrame.\")\n", + " else:\n", + " print(f\"There are {num_duplicates} duplicate rows in the DataFrame.\")\n", + "\n", + "has_duplicates(housing_data)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The dataset contains 21,597 entries and 21 features. Here’s a brief overview of the data:\n", + "\n", + "### Columns and their Data Types:\n", + "#### Numerical:\n", + "id, price, bedrooms, bathrooms, sqft_living, sqft_lot, floors, sqft_above, yr_built, yr_renovated, zipcode, lat, long, sqft_living15, sqft_lot15\n", + "\n", + "#### Categorical:\n", + "date (format object, should be datetime), waterfront, view, condition, grade, sqft_basement (format object, should be numeric)\n", + "\n", + "#### Missing Values:\n", + "waterfront: 2,376 missing values\n", + "view: 63 missing values\n", + "yr_renovated: 3,842 missing values\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 2. DATA CLEANING" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### a)Dropping columns:\n", + "We're dropping some columns during data cleaning to streamline our analysis and focus on the most relevant features. By removing unnecessary or redundant columns, we aim to simplify the dataset and improve the efficiency of subsequent analytical processes. This helps in reducing noise and enhancing the clarity of our findings." + ] + }, + { + "cell_type": "code", + "execution_count": 112, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddatepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontconditiongradesqft_abovesqft_basementyr_builtyr_renovatedsqft_living15sqft_lot15
1039160004353/16/2015218500.021.00160089611.0NOGood7 Average1390210.019490.015026798
86617668000905/25/2014195000.031.75157084591.0NOAverage7 Average15700.019910.016508844
1293641370005401/22/2015329950.042.25214088742.0NaNAverage8 Good21400.019860.021408789
68751150131011/21/2014715000.033.25306090552.0NOAverage10 Very Good2460600.019940.029909598
786434454001207/25/2014267500.031.50139021532.0NOAverage7 Average13900.020010.011002617
\n", + "
" + ], + "text/plain": [ + " id date price bedrooms bathrooms sqft_living \\\n", + "1039 16000435 3/16/2015 218500.0 2 1.00 1600 \n", + "8661 766800090 5/25/2014 195000.0 3 1.75 1570 \n", + "12936 4137000540 1/22/2015 329950.0 4 2.25 2140 \n", + "6875 11501310 11/21/2014 715000.0 3 3.25 3060 \n", + "7864 3445400120 7/25/2014 267500.0 3 1.50 1390 \n", + "\n", + " sqft_lot floors waterfront condition grade sqft_above \\\n", + "1039 8961 1.0 NO Good 7 Average 1390 \n", + "8661 8459 1.0 NO Average 7 Average 1570 \n", + "12936 8874 2.0 NaN Average 8 Good 2140 \n", + "6875 9055 2.0 NO Average 10 Very Good 2460 \n", + "7864 2153 2.0 NO Average 7 Average 1390 \n", + "\n", + " sqft_basement yr_built yr_renovated sqft_living15 sqft_lot15 \n", + "1039 210.0 1949 0.0 1502 6798 \n", + "8661 0.0 1991 0.0 1650 8844 \n", + "12936 0.0 1986 0.0 2140 8789 \n", + "6875 600.0 1994 0.0 2990 9598 \n", + "7864 0.0 2001 0.0 1100 2617 " + ] + }, + "execution_count": 112, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "housing_data = housing_data.drop(['long','lat','view', 'zipcode'], axis=1)\n", + "housing_data.sample(5)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### b)Checking for placeholders\n", + "\n", + "Placeholders are values used to denote missing, unknown, or invalid data within a dataset. Common examples include \"N/A\", \"-\", \"UNKNOWN\", \"NULL\", #, etc. It's important to identify and handle placeholders properly during data preprocessing to ensure accurate analysis and modeling" + ] + }, + { + "cell_type": "code", + "execution_count": 113, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Column 'sqft_basement': Found 454 occurrences of potential placeholder .\n" + ] + } + ], + "source": [ + "# Define a list of common placeholder values\n", + "common_placeholders = [\"\", \"na\", \"n/a\", \"nan\", \"none\", \"null\", \"-\", \"--\", \"?\", \"??\", \"unknown\", \"missing\", \"void\", \"empty\", \"#\", \"#####\"]\n", + "\n", + "# Check for potential placeholders in the DataFrame\n", + "found_placeholder = False\n", + "for column in housing_data.columns:\n", + " placeholder_count = housing_data[column].isin(common_placeholders).sum()\n", + " if placeholder_count > 0:\n", + " print(f\"Column '{column}': Found {placeholder_count} occurrences of potential placeholder .\")\n", + " found_placeholder = True\n", + "\n", + "if not found_placeholder:\n", + " print(\"No potential placeholders found in the DataFrame.\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 114, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "# Convert the common placeholders to lowercase for case-insensitive matching\n", + "common_placeholders_lower = [placeholder.lower() for placeholder in common_placeholders]\n", + "\n", + "# Replace any of the common placeholders with NaN\n", + "housing_data['sqft_basement'] = housing_data['sqft_basement'].replace(common_placeholders_lower, pd.NA)\n", + "\n", + "# Drop rows with NaN in the sqft_basement column\n", + "housing_data.dropna(subset=['sqft_basement'], inplace=True)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Counter-check" + ] + }, + { + "cell_type": "code", + "execution_count": 115, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "No potential placeholders found in the DataFrame.\n" + ] + } + ], + "source": [ + "# confirm no more placeholders\n", + "# Define a list of common placeholder values\n", + "common_placeholders = [\"\", \"na\", \"n/a\", \"nan\", \"none\", \"null\", \"-\", \"--\", \"?\", \"??\", \"unknown\", \"missing\", \"void\", \"empty\", \"#\", \"#####\"]\n", + "\n", + "# Check for potential placeholders in the DataFrame\n", + "found_placeholder = False\n", + "for column in housing_data.columns:\n", + " placeholder_count = housing_data[column].isin(common_placeholders).sum()\n", + " if placeholder_count > 0:\n", + " print(f\"Column '{column}': Found {placeholder_count} occurrences of potential placeholder .\")\n", + " found_placeholder = True\n", + "\n", + "if not found_placeholder:\n", + " print(\"No potential placeholders found in the DataFrame.\")\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "\n", + "### b) Handling Missing Values:\n", + "waterfront: \n", + "Since these are categorical, we can replace missing values with the mode or create a separate category for missing values.\n", + "
yr_renovated: \n", + "A significant number of missing values suggest that these houses might not have been renovated. Impute with 0 or a specific marker value." + ] + }, + { + "cell_type": "code", + "execution_count": 116, + "metadata": {}, + "outputs": [], + "source": [ + "# For categorical data, impute missing values with mode or specific marker\n", + "waterfront_mode = housing_data['waterfront'].mode()[0]\n", + "\n", + "housing_data['waterfront'].fillna(waterfront_mode, inplace=True)\n", + "housing_data['yr_renovated'].fillna(0, inplace=True) # Assuming no renovation if NaN" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### c) Convert Data\n", + "Convert date from object to datetime format.\n", + "sqft_basement: Convert from object to numeric, handling any non-numeric entries." + ] + }, + { + "cell_type": "code", + "execution_count": 117, + "metadata": {}, + "outputs": [], + "source": [ + "from datetime import datetime\n", + "\n", + "housing_data['date'] = pd.to_datetime(housing_data['date'])\n", + "housing_data['sqft_basement'] = pd.to_numeric(housing_data['sqft_basement'], errors='coerce') # Convert to numeric, coerce errors\n", + "housing_data['sqft_basement'].fillna(0, inplace=True) # Assuming no basement if NaN or non-numeric" + ] + }, + { + "cell_type": "code", + "execution_count": 118, + "metadata": {}, + "outputs": [], + "source": [ + "# Change waterfront to integer\n", + "housing_data['waterfront'] = housing_data['waterfront'].apply(lambda x: 0 if x == 'NO' else 1)" + ] + }, + { + "cell_type": "code", + "execution_count": 119, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['7 Average' '6 Low Average' '8 Good' '11 Excellent' '9 Better' '5 Fair'\n", + " '10 Very Good' '12 Luxury' '4 Low' '3 Poor' '13 Mansion']\n" + ] + } + ], + "source": [ + "# checking \"grade\" column\n", + "unique_grade = housing_data.grade.unique()\n", + "print(unique_grade)" + ] + }, + { + "cell_type": "code", + "execution_count": 120, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['Average' 'Very Good' 'Good' 'Poor' 'Fair']\n" + ] + } + ], + "source": [ + "# checking \"condition\"column\n", + "unique_condition = housing_data.condition.unique()\n", + "print(unique_condition)" + ] + }, + { + "cell_type": "code", + "execution_count": 121, + "metadata": {}, + "outputs": [], + "source": [ + "# Convert grade and condition into representative numbers for easier Exploratory analysis.\n", + "housing_data['condition'] = housing_data['condition'].map({'Poor': 1,'Fair': 2,'Average': 3,'Good': 4,'Very Good': 5}).astype(float)\n", + "housing_data['grade'] = housing_data['grade'].map({'3 Poor': 1,'4 Low': 2,'5 Fair': 3,'6 Low Average': 4,'7 Average': 5,'8 Good': 6,'9 Better': 7,'10 Very Good': 8,'11 Excellent': 9,'12 Luxury': 10,'13 Mansion': 11}).astype(float) " + ] + }, + { + "cell_type": "code", + "execution_count": 122, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Index: 21143 entries, 0 to 21596\n", + "Data columns (total 17 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 21143 non-null int64 \n", + " 1 date 21143 non-null datetime64[ns]\n", + " 2 price 21143 non-null float64 \n", + " 3 bedrooms 21143 non-null int64 \n", + " 4 bathrooms 21143 non-null float64 \n", + " 5 sqft_living 21143 non-null int64 \n", + " 6 sqft_lot 21143 non-null int64 \n", + " 7 floors 21143 non-null float64 \n", + " 8 waterfront 21143 non-null int64 \n", + " 9 condition 21143 non-null float64 \n", + " 10 grade 21143 non-null float64 \n", + " 11 sqft_above 21143 non-null int64 \n", + " 12 sqft_basement 21143 non-null float64 \n", + " 13 yr_built 21143 non-null int64 \n", + " 14 yr_renovated 21143 non-null float64 \n", + " 15 sqft_living15 21143 non-null int64 \n", + " 16 sqft_lot15 21143 non-null int64 \n", + "dtypes: datetime64[ns](1), float64(7), int64(9)\n", + "memory usage: 2.9 MB\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddatepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontconditiongradesqft_abovesqft_basementyr_builtyr_renovatedsqft_living15sqft_lot15
786014380001102014-06-03580135.042.50315058862.003.06.031500.020140.026505886
65043388003702014-11-17220000.031.00100060201.003.04.010000.019440.013008640
1431687319808802014-12-22340000.042.25218080001.004.07.01630550.019750.023108000
156275225000702015-02-04610000.031.00180057501.003.05.01040760.019470.013205625
1223327676018052015-02-13600000.021.00137050001.503.05.013700.019050.015005000
\n", + "
" + ], + "text/plain": [ + " id date price bedrooms bathrooms sqft_living \\\n", + "7860 1438000110 2014-06-03 580135.0 4 2.50 3150 \n", + "650 4338800370 2014-11-17 220000.0 3 1.00 1000 \n", + "14316 8731980880 2014-12-22 340000.0 4 2.25 2180 \n", + "1562 7522500070 2015-02-04 610000.0 3 1.00 1800 \n", + "12233 2767601805 2015-02-13 600000.0 2 1.00 1370 \n", + "\n", + " sqft_lot floors waterfront condition grade sqft_above \\\n", + "7860 5886 2.0 0 3.0 6.0 3150 \n", + "650 6020 1.0 0 3.0 4.0 1000 \n", + "14316 8000 1.0 0 4.0 7.0 1630 \n", + "1562 5750 1.0 0 3.0 5.0 1040 \n", + "12233 5000 1.5 0 3.0 5.0 1370 \n", + "\n", + " sqft_basement yr_built yr_renovated sqft_living15 sqft_lot15 \n", + "7860 0.0 2014 0.0 2650 5886 \n", + "650 0.0 1944 0.0 1300 8640 \n", + "14316 550.0 1975 0.0 2310 8000 \n", + "1562 760.0 1947 0.0 1320 5625 \n", + "12233 0.0 1905 0.0 1500 5000 " + ] + }, + "execution_count": 122, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "# Check transformations\n", + "housing_data.info()\n", + "housing_data.sample(5)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Feature Engineering:\n", + "\n", + "Create additional features that might be informative for our modeling:\n", + "\n", + "**House Age**: Calculate the age of the house from the 'yr_built' column to the current year.\n", + "\n", + "**Renovation Age**: If a house has been renovated ('yr_renovated' > 0), calculate the years since the renovation.\n", + "\n", + "**Total Square Footage**: Sum up 'sqft_living', 'sqft_lot', 'sqft_above', and 'sqft_basement' for a total square footage feature.\n", + "\n", + "These new features could reveal deeper insights into the housing prices and help improve the performance of our statistical models.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 123, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
house_agerenovation_agetotal_sqft
0690.08010.0
17333.012382.0
2910.011540.0
3590.08920.0
4370.011440.0
\n", + "
" + ], + "text/plain": [ + " house_age renovation_age total_sqft\n", + "0 69 0.0 8010.0\n", + "1 73 33.0 12382.0\n", + "2 91 0.0 11540.0\n", + "3 59 0.0 8920.0\n", + "4 37 0.0 11440.0" + ] + }, + "execution_count": 123, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Current year for age calculations\n", + "from datetime import datetime\n", + "\n", + "current_year = datetime.now().year\n", + "\n", + "# Feature Engineering\n", + "housing_data['house_age'] = current_year - housing_data['yr_built']\n", + "housing_data['renovation_age'] = housing_data.apply(\n", + " lambda x: 0 if x['yr_renovated'] == 0 else current_year - x['yr_renovated'], axis=1\n", + ")\n", + "housing_data['total_sqft'] = housing_data['sqft_living'] + housing_data['sqft_lot'] + \\\n", + " housing_data['sqft_above'] + housing_data['sqft_basement']\n", + "\n", + "# Display the new features\n", + "housing_data[['house_age', 'renovation_age', 'total_sqft']].head()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The new features have been successfully added:\n", + "\n", + "**House Age**: Represents the age of the house since it was built.\n", + "\n", + "**Renovation Age**: If renovated, this indicates the number of years since the last renovation; otherwise, it is 0.\n", + "\n", + "**Total Square Footage**: Sum of the living area, lot size, above-ground level area, and basement area\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### *Sample data check.*" + ] + }, + { + "cell_type": "code", + "execution_count": 124, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddatepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontconditiongradesqft_abovesqft_basementyr_builtyr_renovatedsqft_living15sqft_lot15house_agerenovation_agetotal_sqft
1394586515400402014-07-18549000.032.251920109612.003.06.019200.019810.0200010706430.014801.0
27994129000552015-05-05405000.031.75239060001.003.04.012401150.019080.0202060001160.010780.0
1480973122001202014-07-23450000.032.251760100132.004.06.017600.019830.018109768410.013533.0
1843224847001552014-10-14705000.042.00206060001.004.06.01370690.019540.020606600700.010120.0
1209438222000362014-06-24257500.022.00118092651.003.05.011800.019400.046018000840.011625.0
\n", + "
" + ], + "text/plain": [ + " id date price bedrooms bathrooms sqft_living \\\n", + "13945 8651540040 2014-07-18 549000.0 3 2.25 1920 \n", + "279 9412900055 2015-05-05 405000.0 3 1.75 2390 \n", + "14809 7312200120 2014-07-23 450000.0 3 2.25 1760 \n", + "18432 2484700155 2014-10-14 705000.0 4 2.00 2060 \n", + "12094 3822200036 2014-06-24 257500.0 2 2.00 1180 \n", + "\n", + " sqft_lot floors waterfront condition grade sqft_above \\\n", + "13945 10961 2.0 0 3.0 6.0 1920 \n", + "279 6000 1.0 0 3.0 4.0 1240 \n", + "14809 10013 2.0 0 4.0 6.0 1760 \n", + "18432 6000 1.0 0 4.0 6.0 1370 \n", + "12094 9265 1.0 0 3.0 5.0 1180 \n", + "\n", + " sqft_basement yr_built yr_renovated sqft_living15 sqft_lot15 \\\n", + "13945 0.0 1981 0.0 2000 10706 \n", + "279 1150.0 1908 0.0 2020 6000 \n", + "14809 0.0 1983 0.0 1810 9768 \n", + "18432 690.0 1954 0.0 2060 6600 \n", + "12094 0.0 1940 0.0 460 18000 \n", + "\n", + " house_age renovation_age total_sqft \n", + "13945 43 0.0 14801.0 \n", + "279 116 0.0 10780.0 \n", + "14809 41 0.0 13533.0 \n", + "18432 70 0.0 10120.0 \n", + "12094 84 0.0 11625.0 " + ] + }, + "execution_count": 124, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "housing_data.sample(5)" + ] + }, + { + "cell_type": "code", + "execution_count": 125, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Index: 21143 entries, 0 to 21596\n", + "Data columns (total 20 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 21143 non-null int64 \n", + " 1 date 21143 non-null datetime64[ns]\n", + " 2 price 21143 non-null float64 \n", + " 3 bedrooms 21143 non-null int64 \n", + " 4 bathrooms 21143 non-null float64 \n", + " 5 sqft_living 21143 non-null int64 \n", + " 6 sqft_lot 21143 non-null int64 \n", + " 7 floors 21143 non-null float64 \n", + " 8 waterfront 21143 non-null int64 \n", + " 9 condition 21143 non-null float64 \n", + " 10 grade 21143 non-null float64 \n", + " 11 sqft_above 21143 non-null int64 \n", + " 12 sqft_basement 21143 non-null float64 \n", + " 13 yr_built 21143 non-null int64 \n", + " 14 yr_renovated 21143 non-null float64 \n", + " 15 sqft_living15 21143 non-null int64 \n", + " 16 sqft_lot15 21143 non-null int64 \n", + " 17 house_age 21143 non-null int64 \n", + " 18 renovation_age 21143 non-null float64 \n", + " 19 total_sqft 21143 non-null float64 \n", + "dtypes: datetime64[ns](1), float64(9), int64(10)\n", + "memory usage: 3.4 MB\n" + ] + } + ], + "source": [ + "housing_data.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 3. EXPLORATORY DATA ANALYSIS" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Next is EDA; Exploratory Data Analysis is a crucial step in data analysis. This process will involve examining and understanding the structure, patterns, and relationships within the dataset. It will aid us uncover insights, detect anomalies, and inform subsequent analysis and modeling decisions." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### a.) Univariate Analysis" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**#Distribution of House Prices.**" + ] + }, + { + "cell_type": "code", + "execution_count": 126, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Set the style for seaborn\n", + "sns.set_style(\"whitegrid\")\n", + "\n", + "# Create subplots\n", + "fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(10, 6))\n", + "\n", + "# Histogram\n", + "sns.histplot(housing_data['price'], bins=\"auto\", kde=False, color='#003399', ax=axes[0])\n", + "axes[0].set_title('Histogram of House Prices')\n", + "axes[0].set_xlabel('Price')\n", + "axes[0].set_ylabel('Frequency')\n", + "\n", + "# Density Plot\n", + "sns.histplot(housing_data['price'], bins=\"auto\", kde=True, color='#339933', ax=axes[1])\n", + "axes[1].set_title('Density Plot of House Prices')\n", + "axes[1].set_xlabel('Price')\n", + "axes[1].set_ylabel('Density')\n", + "\n", + "# A common title\n", + "plt.suptitle('Distribution Analysis of House Prices.', fontsize=16)\n", + "\n", + "# Adjust layout\n", + "plt.tight_layout()\n", + "\n", + "# Show plots\n", + "plt.show();\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The histogram depicts the distribution of house prices, with most bars are clustered towards the left, suggesting that a significant number of houses are priced lower. The density plot illustrates a curve representing the density of house prices. Similar to the histogram, the curve peaks sharply on the left and gradually tapers off, indicating a right-skewed distribution. \n", + "
In summary, the majority of house prices are concentrated at the lower end, creating a skewed distribution.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**#Distribution of Bedrooms, Bathrooms and Floors.**" + ] + }, + { + "cell_type": "code", + "execution_count": 127, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "# Create subplots\n", + "fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(18, 6))\n", + "\n", + "# Common title for all subplots\n", + "fig.suptitle('Distribution of Bedrooms, Bathrooms, and Floors.', fontsize=16)\n", + "\n", + "# Box plot for bedrooms\n", + "sns.boxplot(x=housing_data['bedrooms'], ax=axes[0])\n", + "axes[0].set_title('Bedrooms')\n", + "axes[0].set_xlabel('Number of Bedrooms')\n", + "\n", + "# Box plot for bathrooms\n", + "sns.boxplot(x=housing_data['bathrooms'], ax=axes[1])\n", + "axes[1].set_title('Bathrooms')\n", + "axes[1].set_xlabel('Number of Bathrooms')\n", + "\n", + "# Box plot for floors\n", + "sns.boxplot(x=housing_data['floors'], ax=axes[2])\n", + "axes[2].set_title('Floors')\n", + "axes[2].set_xlabel('Number of Floors')\n", + "\n", + "# Adjust layout\n", + "plt.tight_layout()\n", + "\n", + "# Show plots\n", + "plt.show();\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "After analyzing the distribution of bedrooms, bathrooms and floors, an outlier was detected in the bedroom column. To ensure the accuracy of our analysis, the outlier value was identified and subsequently removed from the dataset. The box plot below displays the distribution of bedrooms after excluding the outlier value. " + ] + }, + { + "cell_type": "code", + "execution_count": 128, + "metadata": {}, + "outputs": [], + "source": [ + "# Identify the outlier value\n", + "outlier_value = housing_data['bedrooms'].max() \n", + "\n", + "# Filter the DataFrame to exclude the outlier\n", + "housing_data = housing_data[housing_data['bedrooms'] != outlier_value]" + ] + }, + { + "cell_type": "code", + "execution_count": 129, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Text(0.5, 0, 'Number of Bedrooms')" + ] + }, + "execution_count": 129, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Box plot for bedrooms\n", + "sns.boxplot(x=housing_data['bedrooms'])\n", + "plt.title('Bedrooms')\n", + "plt.xlabel('Number of Bedrooms')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### b.) Bivariate Analysis" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**#Total Square Footage of houses by Price Range.**" + ] + }, + { + "cell_type": "code", + "execution_count": 130, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "price_range\n", + "300K-600K 10560\n", + "600K-1M 4691\n", + "100K-300K 4433\n", + "1M-2M 1234\n", + "2M-5M 187\n", + "70K-100K 30\n", + "5M-8M 7\n", + "Name: count, dtype: int64" + ] + }, + "execution_count": 130, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Define the labels with ranges\n", + "labels = [\"70K-100K\", \"100K-300K\", \"300K-600K\", \"600K-1M\", \"1M-2M\", \"2M-5M\", \"5M-8M\"]\n", + "\n", + "# Cut the data into the specified ranges and assign labels\n", + "housing_data.loc[:,\"price_range\"] = pd.cut(housing_data.price,\n", + " bins=[70000, 100000, 300000, 600000, 1000000, 2000000, 5000000, 8000000],\n", + " labels=labels)\n", + "\n", + "# Count the occurrences of each category\n", + "housing_data['price_range'].value_counts()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 131, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddatepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontcondition...sqft_abovesqft_basementyr_builtyr_renovatedsqft_living15sqft_lot15house_agerenovation_agetotal_sqftprice_range
778010250790862014-08-20365000.021.009602238981.003.0...9600.019850.01830230868390.0225818.0300K-600K
1334235589004502014-07-11530000.042.25213086401.003.0...1430700.019690.021208826550.012900.0300K-600K
1447910414403602015-01-05299999.042.50198148282.003.0...19810.020130.019813783110.08790.0100K-300K
386177520000902015-01-13635000.041.752400100501.005.0...24000.019570.0168010050670.014850.0600K-1M
1760438763131702014-12-09436000.032.25177080001.004.0...1350420.019760.018507875480.011540.0300K-600K
\n", + "

5 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " id date price bedrooms bathrooms sqft_living \\\n", + "7780 1025079086 2014-08-20 365000.0 2 1.00 960 \n", + "13342 3558900450 2014-07-11 530000.0 4 2.25 2130 \n", + "14479 1041440360 2015-01-05 299999.0 4 2.50 1981 \n", + "3861 7752000090 2015-01-13 635000.0 4 1.75 2400 \n", + "17604 3876313170 2014-12-09 436000.0 3 2.25 1770 \n", + "\n", + " sqft_lot floors waterfront condition ... sqft_above \\\n", + "7780 223898 1.0 0 3.0 ... 960 \n", + "13342 8640 1.0 0 3.0 ... 1430 \n", + "14479 4828 2.0 0 3.0 ... 1981 \n", + "3861 10050 1.0 0 5.0 ... 2400 \n", + "17604 8000 1.0 0 4.0 ... 1350 \n", + "\n", + " sqft_basement yr_built yr_renovated sqft_living15 sqft_lot15 \\\n", + "7780 0.0 1985 0.0 1830 230868 \n", + "13342 700.0 1969 0.0 2120 8826 \n", + "14479 0.0 2013 0.0 1981 3783 \n", + "3861 0.0 1957 0.0 1680 10050 \n", + "17604 420.0 1976 0.0 1850 7875 \n", + "\n", + " house_age renovation_age total_sqft price_range \n", + "7780 39 0.0 225818.0 300K-600K \n", + "13342 55 0.0 12900.0 300K-600K \n", + "14479 11 0.0 8790.0 100K-300K \n", + "3861 67 0.0 14850.0 600K-1M \n", + "17604 48 0.0 11540.0 300K-600K \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 131, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "housing_data.sample(5)" + ] + }, + { + "cell_type": "code", + "execution_count": 132, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\categorical.py:641: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n", + " grouped_vals = vals.groupby(grouper)\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "# Set the style of seaborn\n", + "sns.set_style(\"darkgrid\")\n", + "\n", + "# Create a bar plot\n", + "plt.figure(figsize=(10, 6))\n", + "sns.barplot(x=\"price_range\", y=\"total_sqft\", data=housing_data, errorbar=None, hue=\"price_range\", palette=\"crest\")\n", + "plt.title(\"Total Square Footage by Price Range.\")\n", + "plt.xlabel(\"Price Range\")\n", + "plt.ylabel(\"Total Square Footage\")\n", + "plt.xticks(rotation=45) # Rotate x-axis labels for better readability\n", + "plt.show();\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "The bar plot illustrates the relationship between price range and total square footage. Each bar represents the total square footage of houses within different price range categories. \n", + "From the graph, it is evident that there is a positive association between house size and price. Specifically, larger houses, as indicated by higher total square footage, tend to command higher prices. \n", + "
This suggests that there is a tendency for bigger houses to have a higher price, indicating a positive correlation between the size of the property and its price.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**#Relationship between bedrooms, bathrooms, and house price**\n", + "\n", + "Created a scatter plot to visualize the relationship.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 133, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# plot for the relationship between bedrooms, bathrooms, and house price\n", + "plt.figure(figsize=(10, 6))\n", + "plt.scatter(housing_data['bedrooms'], housing_data['bathrooms'], c=housing_data['price'], cmap='winter', alpha=0.5)\n", + "plt.colorbar(label='House Price')\n", + "plt.xlabel('Number of Bedrooms')\n", + "plt.ylabel('Number of Bathrooms')\n", + "plt.title('Relationship between Bedrooms, Bathrooms, and House Price')\n", + "plt.grid(True)\n", + "plt.show();\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The scatter plot reveals a clear relationship between the number of bedrooms, bathrooms, and house prices. It indicates that houses with more bedrooms and bathrooms tend to command higher prices, reflecting buyer preferences for space and convenience. However, there's a diminishing return on the value added by additional bedrooms beyond a certain point. Understanding this relationship is crucial for both the real estate companies(sellers) and buyers in the real estate market, allowing them to make informed decisions based on their needs and market dynamics.\n", + "A house with a good balance of bedrooms and bathrooms tends to attract a wider range of potential buyers." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**#House age and house price**" + ] + }, + { + "cell_type": "code", + "execution_count": 134, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Line plot for house age vs. average house price\n", + "average_price_by_age = housing_data.groupby('house_age')['price'].mean()\n", + "plt.figure(figsize=(10, 6))\n", + "plt.plot(average_price_by_age.index, average_price_by_age.values, marker='o', linestyle='-')\n", + "plt.xlabel('House Age (Years)')\n", + "plt.ylabel('Average House Price')\n", + "plt.title('Average House Price by House Age.')\n", + "plt.grid(True)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The scatter plot depicts the relationship between house age and prices; and reveals a lack of a clear linear trend. Instead, prices exhibit significant variation across different house ages. While the graph provides insights into how house prices fluctuate based on their age, no discernible pattern emerges. \n", + "In summary, the graph shows how house prices fluctuate based on their age, but no specific pattern emerges. This suggests that other factors beyond house age play a more influential role in determining house prices." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**#Prices of houses in relation to their respective Condition and Grade**" + ] + }, + { + "cell_type": "code", + "execution_count": 135, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(14, 6), sharey=True)\n", + "\n", + "# Bar plot for condition vs. price\n", + "sns.barplot(x='condition', y='price', data=housing_data, ax=axes[0], palette='viridis')\n", + "axes[0].set_title('Condition vs. Price')\n", + "axes[0].set_xlabel('Condition')\n", + "axes[0].set_ylabel('Price')\n", + "axes[0].grid(True)\n", + "\n", + "# Bar plot for grade vs. price\n", + "sns.barplot(x='grade', y='price', data=housing_data, ax=axes[1], palette='viridis')\n", + "axes[1].set_title('Grade vs. Price')\n", + "axes[1].set_xlabel('Grade')\n", + "axes[1].grid(True)\n", + "\n", + "# Adjust layout\n", + "plt.tight_layout()\n", + "\n", + "# Show plots\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\n", + "The visualization presents comparisons between house prices and their condition and grade ratings. On the left, the condition of houses, rated from 1 to 5, shows relatively consistent prices across different condition levels, with no significant price increase observed for better conditions. Conversely, on the right, the grade of houses, ranging from 1 to 11, demonstrates a clear positive correlation with prices, indicating that higher-grade properties command higher prices." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### c.) Multivariate Analysis" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### **#Correlation matrix**" + ] + }, + { + "cell_type": "code", + "execution_count": 136, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Exclude the 'id', date and 'price_range' column from the correlation matrix\n", + "correlation_matrix = housing_data.drop(columns=['id', 'price_range', 'date']).corr()\n", + "\n", + "# Set up the matplotlib figure\n", + "plt.figure(figsize=(20, 20))\n", + "\n", + "# Create a heatmap using seaborn\n", + "sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)\n", + "\n", + "# Add a title\n", + "plt.title('Correlation Matrix')\n", + "\n", + "# Show the plot\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Price has a moderate positive correlation with sqft living (0.70), grade (0.67), sqft above (0.61). This means that as the values of these features increase, the price of the house also tends to increase." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# 4.STATISTICAL ANALYSIS.\n", + "\n", + "Statistical analysis plays a crucial role in understanding relationships within datasets, identifying patterns, and gaining insights. In this regression modeling project aimed at predicting property values, several key steps in statistical analysis are essential:\n", + "\n", + "\n", + "1. Descriptive Statistics\n", + "2. Correlation matrix\n", + "3. Distribution Analysis\n", + "4. Inferential Statistics using Hypothesis Testing and Analysis of Variance\n", + "5. MultiColinierity" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### **a.) Descriptive Statistics**\n", + "\n", + "Initial insights into the central tendency, dispersion, and shape of the data distribution.\n", + "
Understanding the characteristics of the data." + ] + }, + { + "cell_type": "code", + "execution_count": 137, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddatepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontconditiongradesqft_abovesqft_basementyr_builtyr_renovatedsqft_living15sqft_lot15house_agerenovation_agetotal_sqft
count2.114200e+04211422.114200e+0421142.00000021142.00000021142.0000002.114200e+0421142.00000021142.00000021142.00000021142.00000021142.00000021142.00000021142.00000021142.00000021142.00000021142.00000021142.00000021142.0000002.114200e+04
mean4.581107e+092014-10-29 08:57:27.7722068485.405060e+053.3711572.1160962080.9425311.508757e+041.4936150.0067163.4098485.6583101789.104437291.8380951971.02435968.2597201987.30247812739.32220252.9756410.9556811.924945e+04
min1.000102e+062014-05-02 00:00:007.800000e+041.0000000.500000370.0000005.200000e+021.0000000.0000001.0000001.000000370.0000000.0000001900.0000000.000000399.000000651.0000009.0000000.0000002.013000e+03
25%2.123049e+092014-07-22 00:00:003.220000e+053.0000001.7500001430.0000005.043000e+031.0000000.0000003.0000005.0000001200.0000000.0000001952.0000000.0000001490.0000005100.00000027.0000000.0000008.820000e+03
50%3.904940e+092014-10-16 00:00:004.500000e+053.0000002.2500001910.0000007.620000e+031.5000000.0000003.0000005.0000001560.0000000.0000001975.0000000.0000001840.0000007626.00000049.0000000.0000001.159350e+04
75%7.309100e+092015-02-18 00:00:006.450000e+054.0000002.5000002550.0000001.069575e+042.0000000.0000004.0000006.0000002210.000000560.0000001997.0000000.0000002360.00000010087.00000072.0000000.0000001.546000e+04
max9.900000e+092015-05-27 00:00:007.700000e+0611.0000008.00000013540.0000001.651359e+063.5000001.0000005.00000011.0000009410.0000004820.0000002015.0000002015.0000006210.000000871200.000000124.00000090.0000001.653959e+06
std2.876357e+09NaN3.680831e+050.9022130.768545918.5638164.121013e+040.5392520.0816800.6504221.174272828.413341442.50436429.322166362.774103685.67165527169.85997129.3221665.8246594.156724e+04
\n", + "
" + ], + "text/plain": [ + " id date price \\\n", + "count 2.114200e+04 21142 2.114200e+04 \n", + "mean 4.581107e+09 2014-10-29 08:57:27.772206848 5.405060e+05 \n", + "min 1.000102e+06 2014-05-02 00:00:00 7.800000e+04 \n", + "25% 2.123049e+09 2014-07-22 00:00:00 3.220000e+05 \n", + "50% 3.904940e+09 2014-10-16 00:00:00 4.500000e+05 \n", + "75% 7.309100e+09 2015-02-18 00:00:00 6.450000e+05 \n", + "max 9.900000e+09 2015-05-27 00:00:00 7.700000e+06 \n", + "std 2.876357e+09 NaN 3.680831e+05 \n", + "\n", + " bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "count 21142.000000 21142.000000 21142.000000 2.114200e+04 21142.000000 \n", + "mean 3.371157 2.116096 2080.942531 1.508757e+04 1.493615 \n", + "min 1.000000 0.500000 370.000000 5.200000e+02 1.000000 \n", + "25% 3.000000 1.750000 1430.000000 5.043000e+03 1.000000 \n", + "50% 3.000000 2.250000 1910.000000 7.620000e+03 1.500000 \n", + "75% 4.000000 2.500000 2550.000000 1.069575e+04 2.000000 \n", + "max 11.000000 8.000000 13540.000000 1.651359e+06 3.500000 \n", + "std 0.902213 0.768545 918.563816 4.121013e+04 0.539252 \n", + "\n", + " waterfront condition grade sqft_above sqft_basement \\\n", + "count 21142.000000 21142.000000 21142.000000 21142.000000 21142.000000 \n", + "mean 0.006716 3.409848 5.658310 1789.104437 291.838095 \n", + "min 0.000000 1.000000 1.000000 370.000000 0.000000 \n", + "25% 0.000000 3.000000 5.000000 1200.000000 0.000000 \n", + "50% 0.000000 3.000000 5.000000 1560.000000 0.000000 \n", + "75% 0.000000 4.000000 6.000000 2210.000000 560.000000 \n", + "max 1.000000 5.000000 11.000000 9410.000000 4820.000000 \n", + "std 0.081680 0.650422 1.174272 828.413341 442.504364 \n", + "\n", + " yr_built yr_renovated sqft_living15 sqft_lot15 house_age \\\n", + "count 21142.000000 21142.000000 21142.000000 21142.000000 21142.000000 \n", + "mean 1971.024359 68.259720 1987.302478 12739.322202 52.975641 \n", + "min 1900.000000 0.000000 399.000000 651.000000 9.000000 \n", + "25% 1952.000000 0.000000 1490.000000 5100.000000 27.000000 \n", + "50% 1975.000000 0.000000 1840.000000 7626.000000 49.000000 \n", + "75% 1997.000000 0.000000 2360.000000 10087.000000 72.000000 \n", + "max 2015.000000 2015.000000 6210.000000 871200.000000 124.000000 \n", + "std 29.322166 362.774103 685.671655 27169.859971 29.322166 \n", + "\n", + " renovation_age total_sqft \n", + "count 21142.000000 2.114200e+04 \n", + "mean 0.955681 1.924945e+04 \n", + "min 0.000000 2.013000e+03 \n", + "25% 0.000000 8.820000e+03 \n", + "50% 0.000000 1.159350e+04 \n", + "75% 0.000000 1.546000e+04 \n", + "max 90.000000 1.653959e+06 \n", + "std 5.824659 4.156724e+04 " + ] + }, + "execution_count": 137, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "housing_data.describe()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Price Distribution:**\n", + "\n", + "The price of houses in the dataset varies widely, ranging from $78,000 to $7,700,000, with an average price of $540,506. The standard deviation of $368,083.1 indicates a significant dispersion around the mean, suggesting a diverse range of housing prices.\n", + "\n", + "**Bedrooms and Bathrooms:** \n", + "\n", + "The average number of bedrooms is approximately 3.37, while the average number of bathrooms is about 2.12. The standard deviations for both variables are relatively small, indicating less variability compared to other features.\n", + "\n", + "**Square Footage:**\n", + "\n", + " The average square footage of living space is around 2,080, with a standard deviation of 918.56. Similarly, the average lot size is approximately 15,087 square feet, with a larger standard deviation of 41,210.13, suggesting more variability in lot sizes compared to living space.\n", + "\n", + "**Floors:**\n", + "\n", + "On average, houses have 1.49 floors, with a standard deviation of 0.54. This indicates some variability in the number of floors, although most houses seem to have either one or two floors.\n", + "\n", + "**Waterfront Property:**\n", + "\n", + " Only a small percentage (0.7%) of the houses are waterfront properties, based on the average value. This feature is likely represented as a binary variable (0 for no waterfront, 1 for waterfront), with most houses being non-waterfront properties.\n", + "\n", + "**Condition and Grade:**\n", + "\n", + "The average condition of houses is approximately 3.41, with a standard deviation of 0.65, suggesting some variability in the condition ratings. Similarly, the average grade is around 5.66, with a standard deviation of 1.17, indicating variations in the overall quality of houses.\n", + "\n", + "**Year Built and Year Renovated:**\n", + "\n", + "The houses in the dataset span a wide range of construction years, from 1900 to 2015, with an average year of construction around 1971. The standard deviation of 29.32 indicates some variability in the construction years. Additionally, the average year of renovation is approximately 68.26, with a standard deviation of 443.5, suggesting that most houses have not been renovated." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### **b.) Correlation Analysis with House Prices**" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Correlation analysis was performed to examine the relationship between various features and the target variable, 'price'. \n", + "
Here are the correlation coefficients between each feature and the price:\n" + ] + }, + { + "cell_type": "code", + "execution_count": 138, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "price 1.000000\n", + "bedrooms 0.316573\n", + "bathrooms 0.525899\n", + "sqft_living 0.702340\n", + "sqft_lot 0.087940\n", + "floors 0.256372\n", + "waterfront 0.265970\n", + "condition 0.035264\n", + "grade 0.667751\n", + "sqft_above 0.605167\n", + "sqft_basement 0.325003\n", + "yr_built 0.054471\n", + "yr_renovated 0.116721\n", + "sqft_living15 0.586441\n", + "sqft_lot15 0.083196\n", + "house_age -0.054471\n", + "renovation_age 0.082356\n", + "total_sqft 0.118225\n", + "dtype: float64" + ] + }, + "execution_count": 138, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "drop_var = ['id', 'price_range', 'date']\n", + "\n", + "correlation = housing_data.drop(drop_var, axis=1).corrwith(housing_data['price'])\n", + "correlation" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "These correlation coefficients indicate the strength and direction of the linear relationship between each feature and the price of the houses.\n", + "
Features with higher positive correlation coefficients, such as 'sqft_living', 'grade', 'bathrooms', and 'sqft_above', have a stronger positive linear relationship with the price, indicating that as these feature values increase, the price tends to increase as well. Conversely, features with low or negative correlation coefficients, such as 'condition', 'yr_built', 'sqft_lot', and 'house_age', have weaker or negative linear relationships with the price.\n", + "
However, it's imperative to underscore that correlation does not imply causation. There could be an underlying third factor driving changes in both features, underscoring the need for thorough investigation beyond correlation analysis." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### **c.) Distribution Analysis**\n", + "\n", + "Distribution analysis involves understanding the distribution of data, such as whether it follows a normal distribution and skewed distribution" + ] + }, + { + "cell_type": "code", + "execution_count": 139, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
iddatepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontcondition...sqft_abovesqft_basementyr_builtyr_renovatedsqft_living15sqft_lot15house_agerenovation_agetotal_sqftprice_range
071293005202014-10-1312.3099871.3862940.6931477.0741178.6395880.6931470.01.386294...7.0741170.00000019550.0000007.2011718.639588690.0000008.988571100K-300K
164141001922014-12-0913.1956161.3862941.1786557.8520508.8877911.0986120.01.386294...7.6829435.99396119517.5968947.4330758.941153733.5263619.424080300K-600K
256315004002015-02-2512.1007181.0986120.6931476.6476889.2104400.6931470.01.386294...6.6476880.00000019330.0000007.9087558.995041910.0000009.353661100K-300K
324872008752014-12-0913.3113311.6094381.3862947.5812108.5173930.6931470.01.791759...6.9574976.81454319650.0000007.2159758.517393590.0000009.096163600K-1M
419544005102015-02-1813.1421681.3862941.0986127.4271448.9972710.6931470.01.386294...7.4271440.00000019870.0000007.4960978.923191370.0000009.344959300K-600K
\n", + "

5 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " id date price bedrooms bathrooms sqft_living \\\n", + "0 7129300520 2014-10-13 12.309987 1.386294 0.693147 7.074117 \n", + "1 6414100192 2014-12-09 13.195616 1.386294 1.178655 7.852050 \n", + "2 5631500400 2015-02-25 12.100718 1.098612 0.693147 6.647688 \n", + "3 2487200875 2014-12-09 13.311331 1.609438 1.386294 7.581210 \n", + "4 1954400510 2015-02-18 13.142168 1.386294 1.098612 7.427144 \n", + "\n", + " sqft_lot floors waterfront condition ... sqft_above sqft_basement \\\n", + "0 8.639588 0.693147 0.0 1.386294 ... 7.074117 0.000000 \n", + "1 8.887791 1.098612 0.0 1.386294 ... 7.682943 5.993961 \n", + "2 9.210440 0.693147 0.0 1.386294 ... 6.647688 0.000000 \n", + "3 8.517393 0.693147 0.0 1.791759 ... 6.957497 6.814543 \n", + "4 8.997271 0.693147 0.0 1.386294 ... 7.427144 0.000000 \n", + "\n", + " yr_built yr_renovated sqft_living15 sqft_lot15 house_age \\\n", + "0 1955 0.000000 7.201171 8.639588 69 \n", + "1 1951 7.596894 7.433075 8.941153 73 \n", + "2 1933 0.000000 7.908755 8.995041 91 \n", + "3 1965 0.000000 7.215975 8.517393 59 \n", + "4 1987 0.000000 7.496097 8.923191 37 \n", + "\n", + " renovation_age total_sqft price_range \n", + "0 0.000000 8.988571 100K-300K \n", + "1 3.526361 9.424080 300K-600K \n", + "2 0.000000 9.353661 100K-300K \n", + "3 0.000000 9.096163 600K-1M \n", + "4 0.000000 9.344959 300K-600K \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 139, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from scipy.stats import skew\n", + "\n", + "# Select numerical variables only\n", + "numerical_data = housing_data.select_dtypes(include=['number'])\n", + "\n", + "# Compute skewness for each numerical variable\n", + "skewness = numerical_data.apply(lambda x: skew(x.dropna()))\n", + "\n", + "# Select variables with skewness above a certain threshold (e.g., 0.5)\n", + "skewed_variables = skewness[abs(skewness) > 0.5].index\n", + "\n", + "# Log transformation for skewed variables\n", + "df_log = housing_data.copy() # Create a copy of the original DataFrame to preserve the original data\n", + "df_log[skewed_variables] = housing_data[skewed_variables].apply(lambda x: np.log1p(x))\n", + "\n", + "# Check the distributions before and after transformation if needed\n", + "# For example, you can use histograms or density plots to visualize the distributions\n", + "\n", + "# Print the first few rows of the transformed data to verify\n", + "df_log.head()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 140, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n", + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n", + " with pd.option_context('mode.use_inf_as_na', True):\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Selecting numerical columns\n", + "numerical_columns = housing_data.select_dtypes(include=[np.number]).columns\n", + "\n", + "# Calculate the number of rows and columns for subplots\n", + "num_cols = len(numerical_columns)\n", + "num_rows = (num_cols + 2) // 3 # Calculate the number of rows needed, rounding up\n", + "\n", + "# Plot histograms for numerical variables\n", + "plt.figure(figsize=(12, num_rows * 4)) # Adjust the height based on the number of rows\n", + "for i, col in enumerate(numerical_columns, 1):\n", + " plt.subplot(num_rows, 3, i)\n", + " sns.histplot(housing_data[col], kde=True, edgecolor='black')\n", + " plt.title(col)\n", + " plt.xlabel('')\n", + " plt.ylabel('Frequency')\n", + "plt.tight_layout()\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Conclusion**\n", + "\n", + "In conclusion, the log transformation has effectively addressed skewness in the distribution of numerical variables within the dataset. Prior to transformation, variables such as house price, bedrooms, bathrooms, and various square footage measurements exhibited skewed distributions with long tails. However, after applying the log transformation, these distributions appear to be more symmetric and closer to a normal distribution. This transformation has enhanced the suitability of the data for statistical analysis by reducing skewness and improving the interpretability of the variables. It's important to acknowledge that while the log transformation has provided valuable improvements, it alters the scale and interpretation of the variables, necessitating careful consideration in subsequent analyses. Overall, the transformed variables are now better suited for further statistical modeling and analysis in the context of predicting property values and understanding real estate market trends." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### **d.) Inferential Statistics.**\n", + "\n", + "*We used one-way ANOVA approach*" + ] + }, + { + "cell_type": "code", + "execution_count": 141, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "1. \u001b[1mbedrooms\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "2. \u001b[1mbathrooms\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "3. \u001b[1msqft_living\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "4. \u001b[1msqft_lot\u001b[0m: Fail to reject the null hypothesis. There is no statistically significant relationship.\n", + "5. \u001b[1mfloors\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "6. \u001b[1mwaterfront\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "7. \u001b[1mcondition\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "8. \u001b[1mgrade\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "9. \u001b[1msqft_above\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "10. \u001b[1msqft_basement\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "11. \u001b[1myr_built\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "12. \u001b[1myr_renovated\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "13. \u001b[1msqft_living15\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "14. \u001b[1msqft_lot15\u001b[0m: Fail to reject the null hypothesis. There is no statistically significant relationship.\n", + "15. \u001b[1mhouse_age\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "16. \u001b[1mrenovation_age\u001b[0m: Reject the null hypothesis. There is a statistically significant relationship.\n", + "17. \u001b[1mtotal_sqft\u001b[0m: Fail to reject the null hypothesis. There is no statistically significant relationship.\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
bedroomsbathroomssqft_livingsqft_lotfloorswaterfrontconditiongradesqft_abovesqft_basementyr_builtyr_renovatedsqft_living15sqft_lot15house_agerenovation_agetotal_sqft
F-statistic1.841471e+003.7286677.7025890.7327131.662592e+001.787176e+001.0511117.293065.0981141.750817e+001.236748e+001.0467165.2099780.7098411.236748e+001.171737e+000.775778
P-value1.765957e-1390.0000000.0000001.0000001.808184e-951.258742e-1250.0262890.000000.0000001.406487e-1162.417229e-170.0379430.0000001.0000002.417229e-172.430304e-101.000000
\n", + "
" + ], + "text/plain": [ + " bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "F-statistic 1.841471e+00 3.728667 7.702589 0.732713 1.662592e+00 \n", + "P-value 1.765957e-139 0.000000 0.000000 1.000000 1.808184e-95 \n", + "\n", + " waterfront condition grade sqft_above sqft_basement \\\n", + "F-statistic 1.787176e+00 1.051111 7.29306 5.098114 1.750817e+00 \n", + "P-value 1.258742e-125 0.026289 0.00000 0.000000 1.406487e-116 \n", + "\n", + " yr_built yr_renovated sqft_living15 sqft_lot15 \\\n", + "F-statistic 1.236748e+00 1.046716 5.209978 0.709841 \n", + "P-value 2.417229e-17 0.037943 0.000000 1.000000 \n", + "\n", + " house_age renovation_age total_sqft \n", + "F-statistic 1.236748e+00 1.171737e+00 0.775778 \n", + "P-value 2.417229e-17 2.430304e-10 1.000000 " + ] + }, + "execution_count": 141, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "from scipy.stats import f_oneway\n", + "\n", + "# List of features of interest\n", + "features_of_interest = ['bedrooms', 'bathrooms', 'sqft_living',\n", + " 'sqft_lot', 'floors', 'waterfront', 'condition', \n", + " 'grade', 'sqft_above', 'sqft_basement', 'yr_built', \n", + " 'yr_renovated', 'sqft_living15', 'sqft_lot15', \n", + " 'house_age', 'renovation_age', 'total_sqft']\n", + "\n", + "# Create an empty DataFrame to store ANOVA results\n", + "anova_results = pd.DataFrame(index=['F-statistic', 'P-value'])\n", + "\n", + "# Perform ANOVA for each feature\n", + "significant_features = []\n", + "\n", + "for i, column in enumerate(features_of_interest, 1):\n", + " groups = [housing_data[column][housing_data['price'] == category]\n", + " for category in housing_data['price'].unique()]\n", + "\n", + " # Perform ANOVA\n", + " f_statistic, p_value = f_oneway(*groups)\n", + "\n", + " # Store results in the DataFrame\n", + " anova_results[column] = [f_statistic, p_value]\n", + "\n", + " # Print interpretation\n", + " if p_value < 0.05:\n", + " significant_features.append(column)\n", + " print(f\"{i}. \\033[1m{column}\\033[0m: Reject the null hypothesis. There is a statistically significant relationship.\")\n", + " else:\n", + " print(f\"{i}. \\033[1m{column}\\033[0m: Fail to reject the null hypothesis. There is no statistically significant relationship.\")\n", + "\n", + "# Display ANOVA results\n", + "anova_results\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Conclusion**\n", + "\n", + "The features listed under \"Reject the Null Hypothesis\" have a statistically significant relationship with housing prices.\n", + "\n", + "These features are important predictors of housing prices in the given dataset.\n", + "\n", + "On the other hand, features listed under \"Fail to Reject the Null Hypothesis\" do not show a statistically significant relationship with housing prices based on the ANOVA test." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "##### **e.) Multicollinearity.**\n", + "\n", + "**Assessing Multicollinearity with Variance Inflation Factor (VIF)**\n", + "
In this analysis, we utilize the Variance Inflation Factor (VIF) to investigate multicollinearity among predictor variables in our regression model. Multicollinearity occurs when predictor variables are highly correlated with each other, which can lead to unreliable coefficient estimates. By computing the VIF for each predictor variable, we identify potential multicollinearity issues among property characteristics. \n", + "
High VIF values indicate a strong correlation between a predictor variable and the other variables in the model. Hence, it's crucial to examine the VIF values to ensure the reliability of our regression analysis and to address any multicollinearity detected.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 142, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\statsmodels\\stats\\outliers_influence.py:198: RuntimeWarning: divide by zero encountered in scalar divide\n", + " vif = 1. / (1. - r_squared_i)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "\u001b[1mVariance Inflation Factor (VIF):\u001b[0m\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
FeatureVIF
0bedrooms1.688154
1bathrooms3.366371
2sqft_livinginf
3sqft_lotinf
4floors1.934470
5waterfront1.028593
6condition1.218261
7grade3.235515
8sqft_aboveinf
9sqft_basementinf
10yr_built94.556823
11yr_renovated4.226966
12sqft_living152.763013
13sqft_lot152.130997
14house_age7.743224
15renovation_age4.109794
16total_sqftinf
\n", + "
" + ], + "text/plain": [ + " Feature VIF\n", + "0 bedrooms 1.688154\n", + "1 bathrooms 3.366371\n", + "2 sqft_living inf\n", + "3 sqft_lot inf\n", + "4 floors 1.934470\n", + "5 waterfront 1.028593\n", + "6 condition 1.218261\n", + "7 grade 3.235515\n", + "8 sqft_above inf\n", + "9 sqft_basement inf\n", + "10 yr_built 94.556823\n", + "11 yr_renovated 4.226966\n", + "12 sqft_living15 2.763013\n", + "13 sqft_lot15 2.130997\n", + "14 house_age 7.743224\n", + "15 renovation_age 4.109794\n", + "16 total_sqft inf" + ] + }, + "execution_count": 142, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from statsmodels.stats.outliers_influence import variance_inflation_factor\n", + "\n", + "# Compute Variance Inflation Factor (VIF) to detect multicollinearity\n", + "\n", + "X = housing_data[['bedrooms', 'bathrooms', 'sqft_living','sqft_lot', 'floors', 'waterfront', 'condition', 'grade', 'sqft_above', 'sqft_basement', 'yr_built', 'yr_renovated', 'sqft_living15', 'sqft_lot15', 'house_age', 'renovation_age', 'total_sqft']]\n", + "# Calculate the correlation matrix\n", + "correlation_matrix = X.corr()\n", + "\n", + "# Calculate VIF for each feature\n", + "vif_data = pd.DataFrame()\n", + "vif_data[\"Feature\"] = X.columns\n", + "vif_data[\"VIF\"] = [variance_inflation_factor(X.values, i) for i in range(len(X.columns))]\n", + "\n", + "# Print VIF for each feature\n", + "print(\"\\n\\033[1mVariance Inflation Factor (VIF):\\033[0m\")\n", + "vif_data\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Variance Inflation Factor (VIF) Analysis**\n", + "
The Variance Inflation Factor (VIF) was calculated to assess multicollinearity among the features in the dataset. A VIF value greater than 5 is typically considered indicative of multicollinearity. The results revealed that most features exhibited low levels of multicollinearity, with VIF values below 5. \n", + "
However, 'yr_built' displayed a remarkably high VIF of 94.56, indicating strong multicollinearity with other features. Additionally, 'sqft_living', 'sqft_lot', 'sqft_above', 'sqft_basement', and 'total_sqft' exhibited infinite VIF values, suggesting perfect multicollinearity. \n", + "
Addressing multicollinearity in this case may require further investigation, such as feature selection, dimensionality reduction techniques or applying regularization methods to mitigate multicollinearity effects and improve model performance. \n", + "
Overall, understanding the VIF values can help refine the regression model and ensure the reliability of the coefficient estimates.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# MODELLING." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "1. Baseline model - simple linear model.\n", + "2. log transformation. \n", + "3. Multiple Linear Regression\n", + "4. Residual modelling.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Baseline model \n", + "\n", + " Baseline models provide a reference point for comparing the performance of more complex models. \n", + " Its purpose is to establish a benchmark against which the performance of more sophisticated models can be evaluated." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "FUNCTIONS TO BE USED." + ] + }, + { + "cell_type": "code", + "execution_count": 143, + "metadata": {}, + "outputs": [], + "source": [ + "#use only numeric columns.\n", + "def numeric_col(housing_data):\n", + " '''returns a dataframe with only numeric values'''\n", + " for column in housing_data.columns:\n", + " if is_numeric_dtype(housing_data[column]) == False:\n", + " housing_data = housing_data.drop(column, axis=1)\n", + " else:\n", + " continue\n", + " return housing_data\n" + ] + }, + { + "cell_type": "code", + "execution_count": 144, + "metadata": {}, + "outputs": [], + "source": [ + "#Set a function for the predictor and target variale.\n", + "def X_Y(housing_data, target):\n", + " '''Returns a series of target (y) values and a DataFrame of predictors (X)'''\n", + " y = housing_data[target] # target variable\n", + " X = housing_data.drop(target, axis=1) # predictor features\n", + " return y, X\n" + ] + }, + { + "cell_type": "code", + "execution_count": 145, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "#A higher train score indicates that the model fits the training data well.\n", + "#A high test score suggests that the model is able to make accurate predictions on data it hasn't seen before, which is the ultimate goal in machine learning.\n", + "\n", + "def get_metrics(X_train, X_test, y_train, y_test):\n", + " ''' Parameters are X train, X test, y train, & y_test\n", + " Performs multiple regression on the split test and returns metrics'''\n", + "\n", + " # Initialize Linear Regression model\n", + " lr = LinearRegression()\n", + "\n", + " lr.fit(X_train, y_train)\n", + "\n", + " train_score = lr.score(X_train, y_train)\n", + " test_score = lr.score(X_test, y_test)\n", + "\n", + " y_hat_train = lr.predict(X_train)\n", + " y_hat_test = lr.predict(X_test)\n", + "\n", + " train_rmse = np.sqrt(mean_squared_error(y_train, y_hat_train))\n", + " test_rmse = np.sqrt(mean_squared_error(y_test, y_hat_test))\n", + "\n", + " return train_score, test_score, train_rmse, test_rmse\n", + "#These scores provide insights into how well the model is performing both on the data it was trained on and on new data.\n", + "# They help assess the model's overall effectiveness and whether it is overfitting or underfitting.\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 146, + "metadata": {}, + "outputs": [], + "source": [ + "def train_test(housing_data, size=0.20):\n", + " '''Takes in dataframe, and size of test for the split\n", + " Returns the train_set and test_set'''\n", + " train_set, test_set = train_test_split(housing_data, test_size=size, random_state=42)\n", + " return train_set, test_set\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# SIMPLE LINEAR REGRESSION." + ] + }, + { + "cell_type": "code", + "execution_count": 147, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "\n", + "def simple_linear_regression(housing_data):\n", + " '''Creates a simple linear regression model with prices as the target variable \n", + " and the number of bedrooms as the predictor. Returns the model along with R-squared, \n", + " Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) for both train and test sets.'''\n", + " \n", + " # Extracting features and target variable\n", + " X = housing_data[['sqft_living']] # Predictor feature\n", + " y = housing_data['price'] # Target variable (prices)\n", + " \n", + " # Splitting the data into train and test sets\n", + " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", + " \n", + " # Create a linear regression model\n", + " model = LinearRegression()\n", + " \n", + " # Fit the model to the training data\n", + " model.fit(X_train, y_train)\n", + " \n", + " # Calculate predictions for train and test sets\n", + " y_train_pred = model.predict(X_train)\n", + " y_test_pred = model.predict(X_test)\n", + " \n", + " # Calculate R-squared for train and test sets\n", + " r2_train = r2_score(y_train, y_train_pred)\n", + " r2_test = r2_score(y_test, y_test_pred)\n", + " \n", + " # Calculate Mean Squared Error (MSE) for train and test sets\n", + " mse_train = mean_squared_error(y_train, y_train_pred)\n", + " mse_test = mean_squared_error(y_test, y_test_pred)\n", + " \n", + " # Calculate Root Mean Squared Error (RMSE) for train and test sets\n", + " rmse_train = np.sqrt(mse_train)\n", + " rmse_test = np.sqrt(mse_test)\n", + " \n", + " # Print coefficients, R-squared, MSE, and RMSE for train and test sets\n", + " print(\"Training set:\")\n", + " print(\"Intercept:\", model.intercept_)\n", + " print(\"Coefficient:\", model.coef_[0])\n", + " print(\"R-squared:\", r2_train)\n", + " print(\"Mean Squared Error:\", mse_train)\n", + " print(\"Root Mean Squared Error:\", rmse_train)\n", + " \n", + " print(\"\\nTest set:\")\n", + " print(\"R-squared:\", r2_test)\n", + " print(\"Mean Squared Error:\", mse_test)\n", + " print(\"Root Mean Squared Error:\", rmse_test)\n", + " \n", + " return model, r2_train, mse_train, rmse_train, r2_test, mse_test, rmse_test\n", + "\n", + "\n", + "# Example usage:\n", + "# Assuming housing_data is your dataset\n", + "# model, r2_train, mse_train, rmse_train, r2_test, mse_test, rmse_test = simple_linear_regression(housing_data)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 148, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Training set:\n", + "Intercept: -44593.95245340909\n", + "Coefficient: 281.4088930446383\n", + "R-squared: 0.49587806055811734\n", + "Mean Squared Error: 68601152192.940285\n", + "Root Mean Squared Error: 261918.21661148407\n", + "\n", + "Test set:\n", + "R-squared: 0.48264829402430887\n", + "Mean Squared Error: 68845100756.10751\n", + "Root Mean Squared Error: 262383.4993975565\n" + ] + }, + { + "data": { + "text/plain": [ + "(LinearRegression(),\n", + " 0.49587806055811734,\n", + " 68601152192.940285,\n", + " 261918.21661148407,\n", + " 0.48264829402430887,\n", + " 68845100756.10751,\n", + " 262383.4993975565)" + ] + }, + "execution_count": 148, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "simple_linear_regression(housing_data)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Intercept: This is like the starting point or baseline of our predictions. For example, if all other factors were zero, we'd expect the value to be around -44593.95. It's where our line would intersect the y-axis on a graph.\n", + "\n", + "\n", + "Coefficient: This tells us how much the predicted value changes for each unit increase in the independent variable. In this case, for every one-unit increase in the independent variable, we'd expect the dependent variable to increase by about 281.41.\n", + "\n", + "\n", + "R-squared: This is a measure of how well our model explains the variation in the data. An R-squared value of 0.49 means that about 49% of the variability in the dependent variable is explained by our model. So, it's doing a decent job, but there's still room for improvement.\n", + "\n", + "\n", + "Mean Squared Error (MSE): This tells us, on average, how much our predictions differ from the actual values in the training data. Here, the average squared difference is around 68601152192.94, which is quite large but it's relative to the scale of the dependent variable.\n", + "\n", + "\n", + "Root Mean Squared Error (RMSE): This is just the square root of the MSE. It gives us an idea of the average amount our predictions are off by. Here, it's around 261918.22, which is the typical difference between our predicted values and the actual values in the training data.\n", + "\n", + "\n", + "Test Set:\n", + "\n", + "R-squared: Similar to the training set, this tells us how well our model explains the variation in the test data. An R-squared value of 0.48 means that about 48% of the variability in the dependent variable is explained by our model when evaluated on the test data.\n", + "\n", + "\n", + "Mean Squared Error (MSE): This is the average squared difference between our predictions and the actual values in the test data. It's around 68845100756.11, similar to the MSE in the training set.\n", + "\n", + "\n", + "Root Mean Squared Error (RMSE): Again, this is just the square root of the MSE for the test data. It's around 262383.50, which is the typical difference between our predicted values and the actual values in the test data.\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 149, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "R-squared: 0.48264829402430875\n", + "Mean Squared Error: 68845100756.10753\n", + "Root Mean Squared Error: 262383.4993975565\n", + "Intercept: 540631.1560929463\n", + "Coefficients: [259767.82181675]\n" + ] + } + ], + "source": [ + "#STANDARDIZE OUR MODEL TO GET RID OF THE NEGATIVE INTERCEPT.\n", + "\n", + "\n", + "# Assuming you have your data loaded into X and y\n", + "# X should be your independent variables and y should be your dependent variable\n", + "\n", + "# Split data into training and test sets\n", + "X = housing_data[['sqft_living']] # Predictor feature\n", + "y = housing_data['price'] # Target variable (prices)\n", + "\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", + "\n", + "# Initialize the StandardScaler\n", + "scaler = StandardScaler()\n", + "\n", + "# Fit and transform the scaler on the training data\n", + "X_train_scaled = scaler.fit_transform(X_train)\n", + "\n", + "# Transform the test data using the scaler fitted on the training data\n", + "X_test_scaled = scaler.transform(X_test)\n", + "\n", + "# Fit the linear regression model on the scaled training data\n", + "model = LinearRegression()\n", + "model.fit(X_train_scaled, y_train)\n", + "\n", + "# Predict on the scaled test data\n", + "y_pred = model.predict(X_test_scaled)\n", + "\n", + "# Calculate R-squared and mean squared error on the test set\n", + "r_squared = r2_score(y_test, y_pred)\n", + "mse = mean_squared_error(y_test, y_pred)\n", + "rmse = np.sqrt(mse)\n", + "\n", + "# Print the metrics\n", + "print(\"R-squared:\", r_squared)\n", + "print(\"Mean Squared Error:\", mse)\n", + "print(\"Root Mean Squared Error:\", rmse)\n", + "\n", + "# Print the intercept and coefficients of the model\n", + "print(\"Intercept:\", model.intercept_)\n", + "print(\"Coefficients:\", model.coef_)\n", + "\n", + "#This code will scale your data using StandardScaler, which standardizes features by removing the mean and scaling to unit variance. \n", + "#It ensures that the intercept is not negative" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "R-squared (0.48): This value indicates that approximately 48% of the variability in the dependent variable (the house prices) is explained by the independent (sqft living). In simpler terms, the model captures about 48% of the patterns in the data.\n", + "\n", + "\n", + "Mean Squared Error (MSE) (68845100756.11): This is the average squared difference between the actual values and the predicted values from the model. It's a measure of the model's accuracy, where lower values indicate better performance. In this case, the average squared difference is quite large, indicating that there's still room for improvement in the model's predictive accuracy.\n", + "\n", + "\n", + "Root Mean Squared Error (RMSE) (262383.50): This is the square root of the MSE and provides a measure of the typical deviation of the predicted values from the actual values. It's in the same units as the dependent variable. Here, the RMSE indicates that, on average, the predicted values differ from the actual values by approximately 262,383.50 units.\n", + "\n", + "\n", + "Intercept (540631.16): This is the estimated value of the dependent variable when all independent variables are set to zero. In this case, it suggests that when all other factors are zero, we would expect the dependent variable to be around 540,631.16.\n", + "\n", + "\n", + "Coefficient (259767.82): This represents the change in the house prices for a one-unit change in the sqft living, while holding other variables constant. In this case, for every one-unit increase in the sqft living, we'd expect the house prices to increase by approximately 259,767.82 units.\n", + "\n", + "\n", + "Overall, the model suggests that there is a positive relationship between the independent and dependent variables. However, given the moderate R-squared value and the relatively high MSE and RMSE, it's clear that there may be other factors influencing the dependent variable that are not captured by the model. Further investigation or refinement of the model may be needed to improve its predictive performance." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# MULTIPLE LINEAR REGRESSION." + ] + }, + { + "cell_type": "code", + "execution_count": 150, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Mean Squared Error: 47548419769.890594\n", + "R-squared: 0.6426869041626193\n", + " Feature Coefficient\n", + "0 const 0.000000\n", + "1 bathrooms 24855.944322\n", + "2 sqft_living 117349.853313\n", + "3 floors 20057.401179\n", + "4 waterfront 63378.047594\n", + "5 condition 11809.217548\n", + "6 grade 154829.185004\n", + "7 sqft_basement 14434.666872\n", + "8 yr_built -108064.021718\n", + "9 yr_renovated 7255.426167\n", + "10 sqft_living15 25765.797630\n" + ] + } + ], + "source": [ + "\n", + "\n", + "# Define a function to keep only numeric columns\n", + "def only_numeric(housing_data):\n", + " '''returns a DataFrame with only numeric values'''\n", + " numeric_columns = [column for column in housing_data.columns if is_numeric_dtype(housing_data[column])]\n", + " return housing_data[numeric_columns]\n", + "\n", + "# Sample features and target variable\n", + "features = ['bathrooms', 'sqft_living',\n", + " 'floors', 'waterfront', 'condition', 'grade',\n", + " 'sqft_basement', 'yr_built', 'yr_renovated', 'sqft_living15']\n", + "target = 'price'\n", + "\n", + "# Load your housing data (assuming it's already loaded into 'housing_data' DataFrame)\n", + "\n", + "# Keep only numeric columns\n", + "housing_data_numeric = only_numeric(housing_data)\n", + "\n", + "# Check if all features exist in the DataFrame\n", + "missing_features = [feature for feature in features if feature not in housing_data_numeric.columns]\n", + "if missing_features:\n", + " print(\"The following features are not present in the dataset:\", missing_features)\n", + "else:\n", + " # Extract features and target variable\n", + " X = sm.add_constant(housing_data_numeric[features])\n", + " y = housing_data_numeric[target]\n", + "\n", + " # Split the data into training and testing sets\n", + " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", + "\n", + " # Standardize the features\n", + " scaler = StandardScaler()\n", + " X_train_scaled = scaler.fit_transform(X_train)\n", + " X_test_scaled = scaler.transform(X_test)\n", + "\n", + " # Build a basic linear regression model\n", + " model = LinearRegression()\n", + " model.fit(X_train_scaled, y_train)\n", + "\n", + " # Make predictions on the test set\n", + " y_pred = model.predict(X_test_scaled)\n", + "\n", + " # Evaluate the model\n", + " mse = mean_squared_error(y_test, y_pred)\n", + " r2 = r2_score(y_test, y_pred)\n", + "\n", + " # Display results\n", + " print(\"Mean Squared Error:\", mse)\n", + " print(\"R-squared:\", r2)\n", + "\n", + " # Display coefficients\n", + " coefficients = pd.DataFrame({\"Feature\": X.columns, \"Coefficient\": model.coef_})\n", + " print(coefficients)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Mean Squared Error (MSE): The MSE is a measure of the average squared difference between the actual and predicted values. In this case, the MSE is approximately \n", + "4.75\n", + "×\n", + "1\n", + "0\n", + "10\n", + "4.75×10 \n", + "10\n", + "\n", + "\n", + " , which means, on average, the squared difference between the actual housing prices and the predicted prices is \n", + "4.75\n", + "×\n", + "1\n", + "0\n", + "10\n", + "4.75×10 \n", + "10\n", + " .\n", + "\n", + "\n", + "R-squared (\n", + "𝑅\n", + "2\n", + "R \n", + "2\n", + "\n", + "\n", + " ): The \n", + "𝑅\n", + "2\n", + "R \n", + "2\n", + " score measures the proportion of the variance in the target variable (housing prices) that is explained by the independent variables (features) in the model. \n", + " \n", + " An \n", + "𝑅\n", + "2\n", + "R \n", + "2\n", + " score of 0.643 means that approximately 64.3% of the variance in housing prices is explained by the features included in the model. In other words, the model accounts for 64.3% of the variability in housing prices.\n", + "\n", + "\n", + "Coefficients:\n", + "Intercept (const): The intercept represents the estimated housing price when all independent variables are zero.\n", + "\n", + "\n", + "bathrooms: For each additional bathroom, the predicted housing price increases by approximately $24,855.\n", + "\n", + "\n", + "sqft_living: For each additional square foot of living space, the predicted housing price increases by approximately $117,350.\n", + "\n", + "\n", + "floors: Houses with an additional floor have a predicted price increase of approximately $20,057.\n", + "\n", + "\n", + "waterfront: Properties with waterfront views have a predicted price increase of approximately $63,378 compared to those without.\n", + "\n", + "\n", + "condition: Better condition properties (on a scale from 1 to 5) tend to have a predicted price increase of approximately $11,809 for each unit increase in condition.\n", + "\n", + "grade: Higher grade properties (on a scale from 1 to 13) have a predicted price increase of approximately $154,829 for each unit increase in grade.\n", + "\n", + "\n", + "sqft_basement: For each additional square foot of basement space, the predicted price increases by approximately $14,435.\n", + "\n", + "\n", + "yr_built: Each additional year of age decreases the predicted price by approximately $108,064.\n", + "\n", + "\n", + "yr_renovated: For each year renovated, the predicted price increases by approximately $7,255.\n", + "\n", + "\n", + "sqft_living15: For each additional square foot of living space in the nearest 15 neighbors' homes, the predicted price increases by approximately $25,766.\n", + "\n", + "\n", + "These coefficients indicate the strength and direction of the relationship between each feature and the target variable, holding other features constant. For example, features like square footage of living space, grade, and whether the property has a waterfront view have a substantial positive impact on the predicted housing price, while the year the property was built has a negative impact.\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 151, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: price R-squared: 0.641\n", + "Model: OLS Adj. R-squared: 0.641\n", + "Method: Least Squares F-statistic: 3768.\n", + "Date: Wed, 01 May 2024 Prob (F-statistic): 0.00\n", + "Time: 17:52:01 Log-Likelihood: -2.9014e+05\n", + "No. Observations: 21142 AIC: 5.803e+05\n", + "Df Residuals: 21131 BIC: 5.804e+05\n", + "Df Model: 10 \n", + "Covariance Type: nonrobust \n", + "=================================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "---------------------------------------------------------------------------------\n", + "const 6.604e+06 1.41e+05 46.979 0.000 6.33e+06 6.88e+06\n", + "bathrooms 3.47e+04 3547.740 9.781 0.000 2.77e+04 4.17e+04\n", + "sqft_living 129.1822 3.765 34.313 0.000 121.803 136.562\n", + "floors 3.576e+04 3886.909 9.201 0.000 2.81e+04 4.34e+04\n", + "waterfront 7.828e+05 1.88e+04 41.703 0.000 7.46e+05 8.2e+05\n", + "condition 1.788e+04 2568.771 6.961 0.000 1.28e+04 2.29e+04\n", + "grade 1.319e+05 2290.923 57.586 0.000 1.27e+05 1.36e+05\n", + "sqft_basement 27.2065 4.581 5.939 0.000 18.228 36.185\n", + "yr_built -3728.7602 71.951 -51.823 0.000 -3869.790 -3587.730\n", + "yr_renovated 18.3132 4.407 4.156 0.000 9.676 26.950\n", + "sqft_living15 34.6185 3.669 9.435 0.000 27.427 41.810\n", + "==============================================================================\n", + "Omnibus: 16539.863 Durbin-Watson: 1.978\n", + "Prob(Omnibus): 0.000 Jarque-Bera (JB): 1296266.479\n", + "Skew: 3.184 Prob(JB): 0.00\n", + "Kurtosis: 40.828 Cond. No. 3.35e+05\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 3.35e+05. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "# Fit the OLS model\n", + "model = sm.OLS(y, X).fit()\n", + "\n", + "# Get the summary\n", + "summary = model.summary()\n", + "\n", + "# Print the summary\n", + "print(summary)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "R-squared (R²): The coefficient of determination is 0.641, indicating that approximately 64.1% of the variance in the housing prices is explained by the independent variables included in the model.\n", + "\n", + "\n", + "Adjusted R-squared: The adjusted R-squared is also 0.641, which adjusts for the number of predictors in the model. It's useful when comparing models with different numbers of predictors.\n", + "\n", + "\n", + "F-statistic: The F-statistic is 3768, with a p-value close to zero, indicating that the overall model is statistically significant.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The standard errors, condition number, and other diagnostic information are also provided. \n", + "The condition number being large (3.35e+05) suggests that there may be strong multicollinearity or other numerical issues in the model. \n" + ] + }, + { + "cell_type": "code", + "execution_count": 152, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "c:\\Users\\USER\\.anaconda\\A\\New folder\\Lib\\site-packages\\seaborn\\_oldcore.py:1765: FutureWarning: unique with argument that is not not a Series, Index, ExtensionArray, or np.ndarray is deprecated and will raise in a future version.\n", + " order = pd.unique(vector)\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "inf_coefs = list(zip(coefficients[\"Feature\"], coefficients[\"Coefficient\"]))\n", + "inf_coefs.sort(key=lambda x: abs(x[1]), reverse=True) # Sort coefficients by absolute value\n", + "\n", + "# Create a color palette with the specified color\n", + "color = \"#589aff\"\n", + "colors = [color if coef[1] > 0 else \"lightgray\" for coef in inf_coefs]\n", + "\n", + "# Create the bar plot\n", + "fig, ax = plt.subplots(figsize=(18, 8))\n", + "ax = sns.barplot(x=[x[0] for x in inf_coefs], y=[x[1] for x in inf_coefs], palette=colors)\n", + "plt.xticks(rotation=45)\n", + "ax.set_ylabel(\"Price Coefficients\", fontsize=15)\n", + "ax.set_xlabel(\"House Features\", fontsize=15)\n", + "ax.set_title(\"House Features and Sale Prices\", fontsize=20);\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The model identifies the main factors that affect house prices, giving useful advice to real estate companies when they help customers. It's not perfect, but it does an okay job with a 63.1% score. We still need to check if it can predict prices well. However, the model does its job by helping with decisions and making marketing better by using details about houses and the market.\n", + "\n", + "We can see the positive correlation between the house prices and all other features except the year built which indicates a negative correlation.\n", + "\n", + "\n", + "Addressing negative correlations in house prices, such as with the year built, is crucial. Older properties often have lower prices due to depreciation and maintenance issues. However, strategic renovations, updates, and modernization efforts offer opportunities to increase their value. Homeowners and investors can enhance the appeal and value of older properties in the market by undertaking such initiatives." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# RESIDUALS" + ] + }, + { + "cell_type": "code", + "execution_count": 153, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Calculate residuals\n", + "residuals = y_test - y_pred\n", + "\n", + "# Plot residuals vs predicted values\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_pred, residuals, color='blue')\n", + "plt.title('Residuals Plot')\n", + "plt.xlabel('Predicted Values')\n", + "plt.ylabel('Residuals')\n", + "plt.axhline(y=0, color='red', linestyle='--')\n", + "plt.grid(True)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "This plot is useful in understanding the assumptions of linear regression and detecting violations. The ideal case is to see a random distribution of residuals around the y-axis, centered around zero. This suggests that the residuals are normally distributed, and there are no systematic patterns in the errors" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# POLYNOMIAL REGRESSION." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Polynomial regression is a type of regression analysis where the relationship between the independent variable (or variables) and the dependent variable is modeled as an nth degree polynomial. Unlike simple linear regression, which assumes a linear relationship between the variables, polynomial regression can capture more complex relationships by introducing polynomial terms.\n", + "\n", + "In polynomial regression, the relationship between the independent variable \n", + "𝑥\n", + "x and the dependent variable \n", + "𝑦\n", + "y is modeled as:\n", + "\n", + "𝑦\n", + "\n", + "=\n", + "𝛽\n", + "0\n", + "+\n", + "𝛽\n", + "1\n", + "𝑥\n", + "+\n", + "𝛽\n", + "2\n", + "𝑥\n", + "2\n", + "+\n", + "𝛽\n", + "3\n", + "𝑥\n", + "3\n", + "+\n", + ".\n", + ".\n", + ".\n", + "+\n", + "𝛽\n", + "𝑛\n", + "𝑥\n", + "𝑛\n", + "+\n", + "𝜀\n", + "y=β \n", + "0\n", + "​\n", + " +β \n", + "1\n", + "​\n", + " x+β \n", + "2\n", + "​\n", + " x \n", + "2\n", + " +β \n", + "3\n", + "​\n", + " x \n", + "3\n", + " +...+β \n", + "n\n", + "​\n", + " x \n", + "n\n", + " +ε" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [] + }, + { + "cell_type": "code", + "execution_count": 154, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Polynomial Model (Degree 2)- MSE: 35637716070.71762\n", + "Polynomial Model (Degree 2)- R-squared: 0.7321925161881991\n" + ] + } + ], + "source": [ + "features = ['bathrooms', 'sqft_living',\n", + " 'floors', 'waterfront', 'condition', 'grade',\n", + " 'sqft_basement', 'yr_built', 'yr_renovated', 'sqft_living15']\n", + "target = 'price'\n", + "\n", + "# Load your housing data (assuming it's already loaded into 'housing_data' DataFrame)\n", + "\n", + "# Keep only numeric columns\n", + "housing_data_numeric = only_numeric(housing_data)\n", + "\n", + "# Check if all features exist in the DataFrame\n", + "missing_features = [feature for feature in features if feature not in housing_data_numeric.columns]\n", + "if missing_features:\n", + " print(\"The following features are not present in the dataset:\", missing_features)\n", + "else:\n", + " # Extract features and target variable\n", + " X = sm.add_constant(housing_data_numeric[features])\n", + " y = housing_data_numeric[target]\n", + " \n", + " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", + "\n", + " # Polynomial Regression\n", + "# Choose the degree of the polynomial\n", + "degree = 2\n", + "\n", + "# Create polynomial features\n", + "poly = PolynomialFeatures(degree)\n", + "X_train_poly = poly.fit_transform(X_train)\n", + "X_test_poly = poly.transform(X_test)\n", + "\n", + "# Build a polynomial regression model\n", + "poly_model = LinearRegression()\n", + "poly_model.fit(X_train_poly, y_train)\n", + "\n", + "# Make predictions on the test set\n", + "y_pred_poly = poly_model.predict(X_test_poly)\n", + "\n", + "# Evaluate the polynomial model\n", + "mse_poly = mean_squared_error(y_test, y_pred_poly)\n", + "r2_poly = r2_score(y_test, y_pred_poly)\n", + "print(\"Polynomial Model (Degree {})- MSE:\".format(degree), mse_poly)\n", + "print(\"Polynomial Model (Degree {})- R-squared:\".format(degree), r2_poly)\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Mean Squared Error (MSE): This value represents the average squared difference between the actual house prices and the predicted prices by the polynomial model.\n", + " A lower MSE indicates better performance, and in this case, the MSE is lower than the previous model's MSE, suggesting that the polynomial model fits the data better.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + " \n", + "Generally,The \n", + "𝑅\n", + "2\n", + "R \n", + "2\n", + " value for the first model is 0.641, indicating that approximately 64.1% of the variance in housing prices is explained by the independent variables included in the model. On the other hand, the \n", + "𝑅\n", + "2\n", + "R \n", + "2\n", + " value for the polynomial model of degree 2 is 0.732, suggesting that approximately 73.2% of the variance in housing prices is explained by this polynomial model.\n", + "\n", + "Comparing the two \n", + "𝑅\n", + "2\n", + "R \n", + "2\n", + " values, we can see that the polynomial model of degree 2 explains more variance in housing prices compared to the first model. This suggests that the polynomial model provides a better fit to the data and captures more of the variability in housing prices." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# RESIDUALS" + ] + }, + { + "cell_type": "code", + "execution_count": 155, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Calculate residuals\n", + "residuals = y_test - y_pred_poly\n", + "\n", + "# Plot residuals vs predicted values\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_pred_poly, residuals, color='blue')\n", + "plt.title('Residuals Plot')\n", + "plt.xlabel('Predicted Values')\n", + "plt.ylabel('Residuals')\n", + "plt.axhline(y=0, color='red', linestyle='--')\n", + "plt.grid(True)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 156, + "metadata": {}, + "outputs": [], + "source": [ + "from statsmodels.stats.diagnostic import het_breuschpagan" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 157, "metadata": {}, "outputs": [], "source": [ - "# Your code here - remember to use markdown cells for comments as well!" + "#TEST FOR HOMOSCEDASCITICY" + ] + }, + { + "cell_type": "code", + "execution_count": 158, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Breusch-Pagan test p-value: 3.975373048166964e-258\n" + ] + } + ], + "source": [ + "poly = PolynomialFeatures(degree)\n", + "X_train_poly = poly.fit_transform(X_train)\n", + "X_test_poly = poly.transform(X_test)\n", + "\n", + "# Build a polynomial regression model\n", + "poly_model = LinearRegression()\n", + "poly_model.fit(X_train_poly, y_train)\n", + "\n", + "# Make predictions on the test set\n", + "y_pred_poly = poly_model.predict(X_test_poly)\n", + "\n", + "# Calculate residuals\n", + "residuals = y_test - y_pred_poly\n", + "\n", + "\n", + "\n", + "# Perform Breusch-Pagan test\n", + "lm, lm_p_value, fvalue, f_p_value = het_breuschpagan(residuals, X_test_poly)\n", + "print(\"Breusch-Pagan test p-value:\", lm_p_value)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "A p-value of 3.975373048166964e-258, which is extremely close to zero, indicates strong evidence against the null hypothesis of homoscedasticity. In other words, there is a significant presence of heteroscedasticity in your data.\n", + "\n", + "Heteroscedasticity refers to the situation where the variability of a variable is unequal across the range of values of a second variable that predicts it. In the context of regression analysis, it means that the variance of the errors is not constant across observations." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Log transformation.\n", + "Transforming the dependent variable or one or more independent variables can sometimes stabilize the variance. \n", + "Common transformations include taking the natural logarithm, square root, or reciprocal of the variables." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Log transformation of the multiple linear regression." + ] + }, + { + "cell_type": "code", + "execution_count": 159, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Mean Squared Error (Log Transformed): 0.09804039958945562\n", + "R-squared (Log Transformed): 0.6469123715948973\n" + ] + } + ], + "source": [ + "import numpy as np\n", + "\n", + "# Log transformation of features and target variable\n", + "X_log = np.log1p(X)\n", + "y_log = np.log1p(y)\n", + "\n", + "# Split the log-transformed data into training and testing sets\n", + "X_train_log, X_test_log, y_train_log, y_test_log = train_test_split(X_log, y_log, test_size=0.2, random_state=42)\n", + "\n", + "# Standardize the log-transformed features\n", + "scaler_log = StandardScaler()\n", + "X_train_scaled_log = scaler_log.fit_transform(X_train_log)\n", + "X_test_scaled_log = scaler_log.transform(X_test_log)\n", + "\n", + "# Build a linear regression model on the log-transformed data\n", + "model_log = LinearRegression()\n", + "model_log.fit(X_train_scaled_log, y_train_log)\n", + "\n", + "# Make predictions on the test set\n", + "y_pred_log = model_log.predict(X_test_scaled_log)\n", + "\n", + "# Evaluate the model\n", + "mse_log = mean_squared_error(y_test_log, y_pred_log)\n", + "r2_log = r2_score(y_test_log, y_pred_log)\n", + "\n", + "# Display results\n", + "print(\"Mean Squared Error (Log Transformed):\", mse_log)\n", + "print(\"R-squared (Log Transformed):\", r2_log)\n", + "coefficients = pd.DataFrame({\"Feature\": X.columns, \"Coefficient\": model_log.coef_})\n" + ] + }, + { + "cell_type": "code", + "execution_count": 160, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Calculate residuals\n", + "residuals_log = y_test_log - y_pred_log\n", + "\n", + "# Plot residuals vs predicted values\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_pred_log, residuals_log, color='blue',)\n", + "plt.title('Residuals Plot (Log Transformed)')\n", + "plt.xlabel('Predicted Values (Log Transformed)')\n", + "plt.ylabel('Residuals (Log Transformed)')\n", + "plt.axhline(y=0, color='red', linestyle='--')\n", + "plt.grid(True)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The model's residuals are randomly distributed, indicating no systematic bias. The log transformation visualizes residuals and patterns. A horizontal red line suggests linearity and normality are satisfied, but does not provide a definitive answer on model goodness fit and additional technique's could be used to assess the model." + ] + }, + { + "cell_type": "code", + "execution_count": 161, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Plot house prices against coefficients\n", + "plt.figure(figsize=(10, 6))\n", + "plt.barh(X.columns, model_log.coef_)\n", + "plt.xlabel('Coefficient Value')\n", + "plt.ylabel('Features')\n", + "plt.title('House Prices vs. Coefficients of Variables')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "visualization of the positive and negative coefficient variables." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Log transformation of the polynomial model" + ] + }, + { + "cell_type": "code", + "execution_count": 162, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Polynomial Model (Degree 2)- MSE: 37774083176.83915\n", + "Polynomial Model (Degree 2)- R-squared: 0.7161383140038227\n", + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: price R-squared: 0.679\n", + "Model: OLS Adj. R-squared: 0.678\n", + "Method: Least Squares F-statistic: 557.0\n", + "Date: Wed, 01 May 2024 Prob (F-statistic): 0.00\n", + "Time: 17:52:07 Log-Likelihood: -3540.2\n", + "No. Observations: 16913 AIC: 7210.\n", + "Df Residuals: 16848 BIC: 7713.\n", + "Df Model: 64 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 4987.9435 522.414 9.548 0.000 3963.957 6011.930\n", + "x1 3457.3790 362.110 9.548 0.000 2747.606 4167.152\n", + "x2 -16.5312 7.635 -2.165 0.030 -31.497 -1.566\n", + "x3 -16.9803 5.626 -3.018 0.003 -28.008 -5.953\n", + "x4 -59.7513 8.202 -7.285 0.000 -75.827 -43.675\n", + "x5 -66.7001 16.473 -4.049 0.000 -98.988 -34.412\n", + "x6 21.7086 8.506 2.552 0.011 5.036 38.381\n", + "x7 56.1227 10.699 5.246 0.000 35.152 77.093\n", + "x8 0.1415 0.453 0.313 0.755 -0.745 1.028\n", + "x9 -1530.3915 159.119 -9.618 0.000 -1842.282 -1218.501\n", + "x10 -7.2389 1.397 -5.181 0.000 -9.977 -4.500\n", + "x11 27.1030 5.183 5.229 0.000 16.943 37.263\n", + "x12 2396.4725 250.995 9.548 0.000 1904.495 2888.450\n", + "x13 -11.4586 5.292 -2.165 0.030 -21.832 -1.085\n", + "x14 -11.7699 3.900 -3.018 0.003 -19.414 -4.126\n", + "x15 -41.4165 5.685 -7.285 0.000 -52.560 -30.273\n", + "x16 -46.2330 11.418 -4.049 0.000 -68.614 -23.852\n", + "x17 15.0473 5.896 2.552 0.011 3.491 26.604\n", + "x18 38.9013 7.416 5.246 0.000 24.366 53.437\n", + "x19 0.0981 0.314 0.313 0.755 -0.517 0.713\n", + "x20 -1060.7866 110.293 -9.618 0.000 -1276.973 -844.601\n", + "x21 -5.0176 0.968 -5.181 0.000 -6.916 -3.119\n", + "x22 18.7864 3.593 5.229 0.000 11.744 25.829\n", + "x23 0.0476 0.079 0.603 0.546 -0.107 0.202\n", + "x24 0.2000 0.083 2.399 0.016 0.037 0.363\n", + "x25 -0.4148 0.109 -3.823 0.000 -0.628 -0.202\n", + "x26 0.1250 0.245 0.511 0.609 -0.355 0.605\n", + "x27 0.1981 0.122 1.628 0.104 -0.040 0.437\n", + "x28 0.2251 0.161 1.396 0.163 -0.091 0.541\n", + "x29 -0.0032 0.006 -0.531 0.595 -0.015 0.009\n", + "x30 3.1411 1.477 2.127 0.033 0.247 6.036\n", + "x31 -0.0103 0.012 -0.883 0.377 -0.033 0.013\n", + "x32 -0.1564 0.078 -2.000 0.046 -0.310 -0.003\n", + "x33 0.0859 0.039 2.183 0.029 0.009 0.163\n", + "x34 -0.0407 0.079 -0.516 0.606 -0.195 0.114\n", + "x35 0.3258 0.195 1.668 0.095 -0.057 0.709\n", + "x36 -0.2649 0.091 -2.905 0.004 -0.444 -0.086\n", + "x37 0.1059 0.111 0.957 0.339 -0.111 0.323\n", + "x38 -0.0112 0.005 -2.119 0.034 -0.022 -0.001\n", + "x39 3.2391 1.094 2.960 0.003 1.094 5.384\n", + "x40 0.0084 0.008 0.989 0.323 -0.008 0.025\n", + "x41 -0.0497 0.054 -0.924 0.355 -0.155 0.056\n", + "x42 0.6010 0.091 6.569 0.000 0.422 0.780\n", + "x43 0.1950 0.270 0.721 0.471 -0.335 0.725\n", + "x44 0.3964 0.139 2.845 0.004 0.123 0.670\n", + "x45 -0.0224 0.156 -0.143 0.886 -0.329 0.284\n", + "x46 0.0471 0.006 7.361 0.000 0.035 0.060\n", + "x47 11.9015 1.585 7.511 0.000 8.796 15.007\n", + "x48 0.0005 0.012 0.044 0.965 -0.023 0.024\n", + "x49 -0.3608 0.079 -4.586 0.000 -0.515 -0.207\n", + "x50 -46.2330 11.418 -4.049 0.000 -68.614 -23.852\n", + "x51 -0.2814 0.262 -1.074 0.283 -0.795 0.232\n", + "x52 -1.4097 0.386 -3.649 0.000 -2.167 -0.652\n", + "x53 -0.0189 0.015 -1.223 0.221 -0.049 0.011\n", + "x54 17.2366 4.274 4.033 0.000 8.859 25.614\n", + "x55 -0.0160 0.016 -1.020 0.308 -0.047 0.015\n", + "x56 0.1612 0.187 0.861 0.389 -0.206 0.528\n", + "x57 -0.0348 0.081 -0.430 0.667 -0.193 0.124\n", + "x58 -0.5518 0.172 -3.212 0.001 -0.888 -0.215\n", + "x59 0.0147 0.008 1.939 0.053 -0.000 0.030\n", + "x60 -4.5317 1.668 -2.716 0.007 -7.802 -1.261\n", + "x61 -0.0425 0.016 -2.603 0.009 -0.074 -0.010\n", + "x62 0.6652 0.082 8.073 0.000 0.504 0.827\n", + "x63 0.7108 0.132 5.394 0.000 0.452 0.969\n", + "x64 -0.0074 0.009 -0.830 0.406 -0.025 0.010\n", + "x65 -10.6811 2.084 -5.125 0.000 -14.766 -6.596\n", + "x66 -0.0058 0.016 -0.357 0.721 -0.038 0.026\n", + "x67 -0.4727 0.098 -4.817 0.000 -0.665 -0.280\n", + "x68 -0.0051 0.002 -2.881 0.004 -0.009 -0.002\n", + "x69 -0.0156 0.088 -0.178 0.859 -0.188 0.157\n", + "x70 -3.158e-05 0.001 -0.045 0.964 -0.001 0.001\n", + "x71 -0.0010 0.004 -0.221 0.825 -0.009 0.007\n", + "x72 150.7551 15.531 9.707 0.000 120.313 181.198\n", + "x73 0.7643 0.175 4.359 0.000 0.421 1.108\n", + "x74 -5.7615 1.013 -5.690 0.000 -7.746 -3.777\n", + "x75 0.6353 0.261 2.434 0.015 0.124 1.147\n", + "x76 0.0173 0.007 2.394 0.017 0.003 0.031\n", + "x77 0.3068 0.032 9.733 0.000 0.245 0.369\n", + "==============================================================================\n", + "Omnibus: 86.286 Durbin-Watson: 2.008\n", + "Prob(Omnibus): 0.000 Jarque-Bera (JB): 100.078\n", + "Skew: -0.119 Prob(JB): 1.85e-22\n", + "Kurtosis: 3.291 Cond. No. 1.52e+16\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The smallest eigenvalue is 1.69e-24. This might indicate that there are\n", + "strong multicollinearity problems or that the design matrix is singular.\n" + ] + } + ], + "source": [ + "import numpy as np\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.preprocessing import PolynomialFeatures\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.metrics import mean_squared_error, r2_score\n", + "import statsmodels.api as sm\n", + "\n", + "# Define function to keep only numeric columns\n", + "def only_numeric(df):\n", + " return df.select_dtypes(include=[np.number])\n", + "\n", + "features = ['bathrooms', 'sqft_living',\n", + " 'floors', 'waterfront', 'condition', 'grade',\n", + " 'sqft_basement', 'yr_built', 'yr_renovated', 'sqft_living15']\n", + "target = 'price'\n", + "\n", + "# Load your housing data (assuming it's already loaded into 'housing_data' DataFrame)\n", + "\n", + "# Keep only numeric columns\n", + "housing_data_numeric = only_numeric(housing_data)\n", + "\n", + "# Check if all features exist in the DataFrame\n", + "missing_features = [feature for feature in features if feature not in housing_data_numeric.columns]\n", + "if missing_features:\n", + " print(\"The following features are not present in the dataset:\", missing_features)\n", + "else:\n", + " # Extract features and target variable\n", + " X = sm.add_constant(housing_data_numeric[features])\n", + " y = housing_data_numeric[target]\n", + " \n", + " # Log transform features and target variable\n", + " X_log = np.log(X + 1) # Adding 1 to avoid log(0)\n", + " y_log = np.log(y)\n", + " \n", + " # Split the data into training and testing sets\n", + " X_train, X_test, y_train, y_test = train_test_split(X_log, y_log, test_size=0.2, random_state=42)\n", + "\n", + " # Polynomial Regression\n", + " # Choose the degree of the polynomial\n", + " degree = 2\n", + "\n", + " # Create polynomial features\n", + " poly = PolynomialFeatures(degree)\n", + " X_train_poly = poly.fit_transform(X_train)\n", + " X_test_poly = poly.transform(X_test)\n", + "\n", + " # Build a polynomial regression model\n", + " poly_model = LinearRegression()\n", + " poly_model.fit(X_train_poly, y_train)\n", + "\n", + " # Make predictions on the test set\n", + " y_pred_poly = poly_model.predict(X_test_poly)\n", + "\n", + " # Reverse log transformation for evaluation\n", + " y_pred = np.exp(y_pred_poly)\n", + " y_test_original = np.exp(y_test)\n", + "\n", + " # Evaluate the polynomial model\n", + " mse_poly = mean_squared_error(y_test_original, y_pred)\n", + " r2_poly = r2_score(y_test_original, y_pred)\n", + " print(\"Polynomial Model (Degree {})- MSE:\".format(degree), mse_poly)\n", + " print(\"Polynomial Model (Degree {})- R-squared:\".format(degree), r2_poly)\n", + " \n", + " # Convert to DataFrame for summary\n", + " #X_poly_df = pd.DataFrame(X_train_poly, columns=poly.get_feature_names(features))\n", + "\n", + " # Fit the OLS model\n", + " model = sm.OLS(y_train,X_train_poly)\n", + " results = model.fit()\n", + "\n", + " # Print the summary\n", + " print(results.summary())\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "R-squared: The R-squared value indicates that approximately 71.61% of the variance in the target variable (price) is explained by the model.\n", + "\n", + "MSE (Mean Squared Error): The MSE of approximately 37,774,083,176.84 represents the average squared difference between the predicted and actual house prices.\n", + "\n", + "Coefficients: The coefficients represent the estimated effect of each predictor variable on the target variable. For example:\n", + "The coefficient for const (intercept) is 4987.94.\n", + "The coefficient for x1 (bathrooms) is 3457.38.\n", + "The coefficient for x2 (sqft_living) is -16.53.\n", + "The coefficient for x3 (floors) is -16.98.\n", + "The coefficient for x4 (waterfront) is -59.75.\n", + "The coefficient for x5 (condition) is -66.70.\n", + "The coefficient for x6 (grade) is 21.71.\n", + "The coefficient for x7 (sqft_basement) is 56.12.\n", + "The coefficient for x8 (yr_built) and other coefficients follow.\n", + "\n", + "P-values: P-values indicate the statistical significance of the coefficients. A small p-value (typically < 0.05) suggests that the corresponding predictor variable is statistically significant in predicting the target variable. In this summary, some coefficients have p-values less than 0.05, indicating statistical significance, while others do not.\n", + "\n", + "\n", + "F-statistic: The F-statistic tests the overall significance of the model. A low p-value (typically < 0.05) suggests that at least one of the predictors has a non-zero coefficient, indicating that the model as a whole is statistically significant.\n", + "\n", + "\n", + "Overall, the summary provides valuable insights into the relationships between the predictor variables and the target variable, as well as the overall goodness-of-fit of the model.\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 163, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAqsAAAIdCAYAAAAaiDSZAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAABvPklEQVR4nO3deXxU1f3/8ffNZCMBmwAKiV+tpVWsSy1GJIqKivorNWCDVNSKiggiuIGCtMYFjVZBpOJuAW3rQr9iojQtLq1aNRrE1K+trdpWq1QSUMIiBLLN3N8fw0wyySz3TmYyd2Zez8eDh2Zy5s7J3Fk+95zP+RzDNE1TAAAAgANlJLoDAAAAQCgEqwAAAHAsglUAAAA4FsEqAAAAHItgFQAAAI5FsAoAAADHIlgFAACAYxGsAgAAwLEIVgEAfYq9aADYQbAKICVNmTJFw4cPD/h36KGHqqSkRD/+8Y/1+9//PuaPWVVVpeHDh+uLL74I2eaLL77Q8OHDVVVVFfPHX7BggU499dReHePUU0/t8bwdeeSROv3007VkyRK1trYGtF2wYIGt4//pT3/S9ddf36s+AkgvmYnuAADEy2GHHaabb77Z/7Pb7damTZv0+OOPa+7cuRowYIBOOumkmD3eySefrN/+9rfab7/9YnbMRBgzZoxmzZrl/7m1tVXr1q3Tgw8+qI0bN+qee+6J+tiPP/54DHoIIJ0QrAJIWf3799f3v//9HrePGTNGxx13nJ599tmYBqsDBw7UwIEDY3a8RBk4cGCP523UqFHatGmTqqqqtGDBgqQPyAEkD9IAAKSd7OxsZWVl9bj9mWee0ZlnnqkjjjhCJ598su677z51dHT4f79161Zdd911Gj16tI488kidddZZeu655/y/D5YG8NJLL2nChAn63ve+p/Lycn300UcBj7lu3ToNHz5c69atC7h9ypQpmjJliv/nlpYWLVmyRGeccYaOOOIIHX300Zo6dao+/PDDkH/n3//+d1100UUqKSnRiBEjdPHFF+v999+3/Dx1d8QRR8g0TTU2Ngb9/c6dO/Xzn/9cp512mo488kiVlZVp9erVAX/TO++8o3feeSfo3wwAwTCyCiBlmaYZEGz60gAeeOABNTc366yzzvL/7pFHHtHSpUt1wQUX6Kc//ak+/PBD3XfffWpsbNQdd9whSZo3b56ampq0cOFC5efna82aNbr++utVVFSkUaNG9Xj8V155RVdddZXOPPNMXXfddfroo480b968qP6W+fPna/369br22mt14IEH6rPPPtO9996rOXPmaO3atTIMI6D9rl27dOmll2rUqFFatmyZ2tvb9dBDD2natGl69dVXNWDAANt9+M9//iNJOuCAA3r8rqWlReeff762bNmiK6+8UgcccID++Mc/6oYbbtCWLVs0c+ZM3Xzzzf6//+abb9Z3vvOdKJ4JAOmGYBVAylq/fr0OP/zwgNsMw9Ahhxyie++9178YaefOnXrooYc0efJkVVRUSJJOOOEEFRQUqKKiQlOnTtXBBx+sd955R7NmzdJpp50myTs1XlBQIJfLFfTxH3jgAR1++OFasmSJJPlTDnw/W9XW1qbm5mbdeOON+uEPfyhJOvbYY9Xc3Kw777xTX331VY9p+X//+9/aunWrpkyZopKSEknSsGHDtGrVKu3atStssNo9yG9qatLrr7+uVatWady4cUFTHaqqqvTPf/5TTz31lP/xTjzxRHV0dOjBBx/Uueeeq+985zvq37+/JAVNzwCAYAhWAaSsww8/XAsXLpQkbd68Wffee6/a29u1dOlSffvb3/a3e++997Rnzx6deuqpAUGaL5itra3VwQcfrFGjRum+++7TRx99pDFjxuikk04KubK9paVFf//733XVVVcF3D5u3DjbwWp2drZWrFghSfryyy/1+eef69NPP9Wrr74qSWpvb+9xn4MPPlgDBw7U5ZdfrnHjxvnzdOfPnx/x8Z577rmA9AZJyszM1Omnn65bbrkl6H3eeecd7b///v5A1WfChAlavXq13n//fY0ZM8bCXwsAgdIiWN26dasmT56sysrKoFN1wbz44ou677779MUXX2jffffVZZddpkmTJsW5pwBiKT8/X0ceeaQk6cgjj9SIESN01lln6ZJLLlF1dbV/hHD79u2SpBkzZgQ9zpdffilJWrp0qR5++GGtXbtWL7zwgjIyMnT88cfrlltu6TE1vmPHDpmm2WMUMtqFSW+88YbuuOMOffrpp8rPz9fw4cOVn58vKXjd0vz8fD355JN66KGH9Ic//EGrVq1Sv379NGHCBN1www3KyckJ+VinnHKKZs+eLck7Et2vXz/tv//+ys3NDXmfHTt2aPDgwT1u99329ddf2/p7AcAn5YPV+vp6LViwQBs2bLB8n7q6Oi1YsEC/+MUvdNJJJ2ndunWaPn26DjnkEH3ve9+LY28BxNOgQYN000036corr9Ttt9/uH+HcZ599JEl33323DjrooB738wVcAwYM0Lx58zRv3jx9+umn+tOf/qQHH3xQCxcu1PLlywPuU1BQoIyMDG3ZsiXgdl9g7OPLNfV4PAG3Nzc3+4PRDRs2aPbs2Ro7dqweeeQRHXjggZKkJ598Um+88UbIv3fYsGFavHix3G63/vrXv+r555/X008/rf/5n/8JGZj7+u4L8q36xje+oc8//7zH7V999ZUkqbCw0NbxAMAnpasBVFdX67rrrtOcOXN6/O6tt97SpEmTdMwxx+jMM8/UmjVr/L97/PHHdeGFF2rMmDEyDEOlpaV69tln/V8QAJLXGWecoRNPPFE1NTX+1ehHHXWUsrKytHnzZh155JH+f1lZWVqyZIm++OILbdy4UWPGjNELL7wgyRsITp8+Xccff7w2bdrU43FycnI0YsQIvfTSSwEjn6+88kpAO18OZ9cV9jt27NAnn3zi//mDDz5Qa2urLrvssoDPIV+gGmxk9YUXXlBpaam++uoruVwujRgxQrfccov22WefoP3trZEjR2rjxo2qr68PuH3NmjXKysryX+hnZKT01w6AOEjpkdUTTjhB48ePV2ZmZkDA+tFHH+nyyy/X4sWLNXbsWL3//vuaNWuWCgsLdeKJJ+qvf/2rRo0apRkzZuj999/X0KFDdeWVV+qQQw5J4F8DIFZ+9rOfacKECaqsrFR1dbUKCwt16aWX6t5779WuXbs0atQof46rYRg69NBDNWDAAA0dOlSVlZXatWuXDjzwQH3wwQf685//rMsuuyzo48ydO1cXXXSRrrjiCk2ePFmfffaZHnrooYA2w4cPV1FRke6//34NGDBAGRkZevTRR9WvXz9/m8MPP1yZmZlavHixLrnkErW1tamqqkqvvfaaJGn37t09Hvvoo4+Wx+PR7NmzNWPGDOXn52vt2rXauXOnzjjjjNg9mXtNnDhRTz31lK644gpdddVVOuCAA/TKK6/o2Wef1RVXXOEfvd5nn3303nvv6e2339Zhhx2mb3zjGzHvC4DUktKXuPvuu68yM3vG46tWrdLYsWN1xhlnyOVy6eijj9Y555yjJ598UpJ3VGPFihW6/PLLVVtbq9mzZ2vOnDm9qk8IwDmGDRumKVOm6J///KeeeOIJSdI111yjBQsW6OWXX9b06dO1ePFilZSU6IknnvCvnL///vt14okn6t5779Ull1yip59+WldccYU/v7O7Y445Rr/85S+1efNmXXHFFVq1apW/DJaPy+XSsmXLtN9++2nu3LmqrKzUuHHjAgLKb37zm1qyZIk2b96syy+/XDfddJMk6Te/+Y0Mw9C7777b47H3228/LV++XAMGDNANN9ygyy67TH//+9913333qbS0NCbPY1f9+vXTb37zG5166qlatmyZLr/8ctXX1+v222/XlVde6W/3k5/8RFlZWZo+fbpef/31mPcDQOoxzGDzRylo+PDh+vWvf61Ro0Zp+vTpqqurC1hg4Ha7deCBB+r555/XiBEjdOGFFwaMxs6YMUPf+c53LK2kBQAAQGykdBpAKEOHDlV5ebluvfVW/21ffvmlP+/r29/+ttra2gLu43a7g+aFAQAAIH5SOg0glEmTJqmmpkZvvvmmPB6PPvvsM11wwQVauXKlJOm8887T008/rbfeeksej0cvvvii1q1bp7KysgT3HAAAIL2k5cjqUUcdpXvuuUf33HOPrr76avXr109lZWWaO3euJOnss89WRkaGfv7zn+uLL77Q/vvvr6VLl/bYCQcAAADxlTY5qwAAAEg+aZkGAAAAgORAsAoAAADHIlgFAACAYxGsAgAAwLFSthpAU9NO2V06ZhjSoEEDorovkg/nO71wvtMH5zq9cL6Tk++8WZGywappKuoXbW/ui+TD+U4vnO/0wblOL5zv1EUaAAAAAByLYBUAAACORbAKAAAAxyJYBQAAgGMRrAIAAMCxCFYBAADgWASrAAAAcCyCVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsTIT3QEAAAAnc7ulujqXNm82NGSIqdJSt1yuRPcqfRCsAgAAhFBTk6mKihw1NHRORhcXe1RZ2aqyso4E9ix9kAYAAAAQRE1NpqZNy1VDgxFwe2OjoWnTclVTw5hfXyBYBQAA6MbtlioqcmSakhQYrJqm9+eKihy53X3ft3RDsArAkdxuqbbWpaqqTNXWuvhCANCn6upce6f+jaC/N01DDQ0ZqqsjeTXeGL8G4DjkiAFItM2bgwep0bZD9BhZBeAo5IgBcIIhQ8yYtkP0CFYBOAY5YgCcorTUreJijwwjeDBqGKaKiz0qLeUDKd4IVgE4BjliAJzC5ZIqK1slqUfA6vu5srKVeqt9gGAVgGOQIwbAScrKOrRiRYuKigKD1aIiUytWtJBD30dI/gLgGOSIAXCasrIOjRvXwQ5WCUSwCsAxfDlijY2GP0e1K8MwVVRkkiMGoE+5XNLo0XzuJAppAAAcgxwxAEB3BKsAHIUcMQBAV6QBAHAccsQAAD4EqwAciRwxAIBEGgAAAAAcjGAVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsglUAAAA4FsEqAAAAHItgFQAAAI5FsAoAAADHIlgFAACAYxGsAgAAwLEIVgEAAOBYBKsAAABwLIJVAAAAOBbBKgAAAByLYBUAAACORbAKAAAAxyJYBQAAgGMRrAIAAMCxCFYBAADgWASrAAAAcCyCVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsglUAAAA4FsEqAAAAHItgFQAAAI5FsAoAAADHIlgFAACAYxGsAgAAwLEIVgEAAOBYBKsAAABwLIJVAAAAOBbBKgAAAByLYBUAAACORbAKAAAAxyJYBQAAgGMRrAIAAMCxCFYBAADgWASrAAAAcCyCVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsRwarH330kaZOnapjjz1Wo0eP1vz587V169ZEdwsAAAB9zHHBaktLiy699FKNGDFCb775pmpqarR9+3b97Gc/S3TXAAAA0MccF6w2NDTo0EMP1ezZs5Wdna3CwkJNnjxZ69evT3TXAAAA0McyE92B7oYNG6bly5cH3Pbiiy/q8MMPt3Ucw7D/2L77RHNfJB/Od3rhfKcPznV64XwnJzvnyzBN04xfV3rHNE394he/0FNPPaUnnnhCw4cPT3SXAAAA0IccN7Lqs2vXLv30pz/V3//+96gC1aamnbIbhhuGNGjQgKjui+TD+U4vnO/0wblOL5zv5OQ7b1Y4MljdsGGDpk+fruLiYq1evVoDBw60fQzTVNQv2t7cF8mH851eON/pg3OdXjjfqctxC6x27Nihiy66SEcffbRWrFgRVaAKAACA1OC4kdWqqio1NDRo7dq1euGFFwJ+99577yWoVwAAAEgExwWrU6dO1dSpUxPdDQAAADiA49IAAAAAAB+CVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsglUAAAA4FsEqAAAAHItgFQAAAI5FsAoAAADHIlgFAACAYxGsAgAAwLEIVgEAAOBYBKsAAABwLIJVAAAAOBbBKgAAAByLYBUAAACOlZnoDgCwzu2W6upc2rzZ0JAhpkpL3XK5Et0rAADih2AVSBI1NZmqqMhRQ0PnhEhxsUeVla0qK+tIYM8AAIgf0gCAJFBTk6lp03LV0GAE3N7YaGjatFzV1HDdCQBITQSrgMO53VJFRY5MU5ICg1XT9P5cUZEjt7vv+wYAQLwRrAIOV1fn2jv1bwT9vWkaamjIUF0dyasAgNRDsAo43ObNwYPUaNsBAJBMCFYBhxsyxIxpOwAAkgnBKuBwpaVuFRd7ZBjBg1HDMFVc7FFpKUmrAIDUQ7AKOJzLJVVWtkpSj4DV93NlZSv1VgEAKYlgFUgCZWUdWrGiRUVFgcFqUZGpFStaqLMKAEhZFGcEkkRZWYfGjetgBysAQFohWAWSiMsljR5NbioAIH2QBgAAAADHIlgFAACAYxGsAgAAwLEIVgEAAOBYBKsAAABwLIJVAAAAOBbBKgAAAByLYBUAAACORbAKAAAAxyJYBQAAgGMRrAIAAMCxCFYBAADgWASrAAAAcCyCVQAAADhWZqI7AKQ7t1uqq3Np82ZDQ4aYKi11y+VKdK8AAHAGglUggWpqMlVRkaOGhs5JjuJijyorW1VW1pHAngEA4AykAQAJUlOTqWnTctXQYATc3thoaNq0XNXUcC0JAADBKpAAbrdUUZEj05SkwGDVNL0/V1TkyO3u+74BAOAkBKtAF263VFvrUlVVpmprXXELFuvqXHun/o2gvzdNQw0NGaqrI3kVAJDemGcE9urL/NHNm4MHqdG2AwAgVTGyCqjv80eHDDFj2g4AgFRFsIq0l4j80dJSt4qLPTKM4MGoYZgqLvaotJSkVQBAeiNYhaP0Vc5oV4nIH3W5pMrKVknqEbD6fq6sbKXeKgAg7RGswjFqajJVUpKv8vI8zZzZT+XleSopybc8BR9toJuo/NGysg6tWNGioqLAYLWoyNSKFS3UWQUAQCywgkP4ckbNbrPivpzRSMFbbxZHJTJ/tKysQ+PGdbCDFQAAIRim2T08SA1btuzsEfhEYhjS4MEDorovoud2SyUl+XsXN/UcvTQMU0VFpurrm4MGcYGBrhFwP0khA13f+d68eaeOPjpfjY2GP0fVzuMjOfD+Th+c6/TC+U5OvvNmBWkASLje5IzGYnEU+aMAADgXwSoSrjc5o7FaHEX+KAAAzkTOKhKuNzmjsVwc5bT8UbdbjukLAACJQrCKhPPVHI2UMxqs5misF0e5XNLo0YmvbdqXu2kBAOBkpAEg4XqTM5qKxfX7ejctAACcjGAVjhBtzmiqLY5KxG5aAAA4GUM0cIxoc0Z9ga532rwzwCsqMpNu2rxzwVhw3gVjhurqXI5IVwAAIN4IVuEo0eaMOm1xVLQStZsWAABORbCKlOGUxVG9kcjdtAAAcCJyVgEHScUFYwAA9AbBKuAgqbZgDACA3iJYBRyG3bQAAOhEzirgQKmyYAwAgN4iWAUcKhUWjAEA0FukAQAAAMCxCFYBAADgWKQBoM+53SIXEwAAWEKwij5VU5O5d1vUzkH94mJP0m2LCgAA+gZpAOgzNTWZmjYtVw0NgVuFNjYamjYtVzU1XDulIrdbqq11qaoqU7W1LrlZMwYAsIHoAH3C7ZYqKnJkmpIUGKyapiHDMFVRkaNx4zpICUghjKQDAHqLkVX0ibo6196AxQj6e9M01NCQobo6ItVUwUg6ACAWCFbRJzZvDh6kRtsOzhZpJF3y/t5uSgApBQCQfhjaQJ8YMsSM3MhGOzhb50h6cN6RdEN1dS7LGx+QUgAA6YmRVfSJ0lK3ios9MozgwahhmCou9qi0lKGyVBDrkXRSCgAgfRGsok+4XFJlZask9QhYfT9XVrayuCpFxHIkPV4pBQCA5ECwij5TVtahFStaVFQUGKAUFZlasaKFqdwUEsuRdBbnAUB6Y+4MfaqsrEPjxnWwg1WK842kT5uWK8Mw/SOgkv2RdBbnAUB6Y2QVfc7lkkaPdmvixA6NHk2gmqpiNZLO4jwASG+MrAKIm1iMpPtSChobjYARWh/DMFVUZLI4DwBSFMEqgLjyjaT35v6xSikAACQf0gAAOB6L8wAgfTGyCiQht1tpt0iNxXkAkJ4IVoEkk847OfU2pQAAkHxIAwCSCDs5AQDSjaOD1a1bt+r000/XunXrEt0VIOHYyQkAkI4cG6zW19dr8uTJ2rBhQ6K7AjgCOzkBANKRI4PV6upqXXfddZozZ06iu4Ig3G6pttalqqpM1da6GMnrI+zkBABIR45McDvhhBM0fvx4ZWZmRh2wGlF8X/vuE81900VNTaZuuKHn4p7bb0++xT3Jdr6HDrW2Q9PQoWbS/E19KdnON6LHuU4vnO/kZOd8GaZpOnqPwuHDh+vXv/61Ro0aleiupL2qKmnSJKn7K8b3glu9Wpo4se/7lS7cbumgg6SNG3ueA8l7Hv7nf6T//EeUcwIApAxHjqzGQlPTzqBf6OEYhjRo0ICo7pvq3G7pyivz9y7k6b64x7uT0FVXmRo9ujlpAqVkPN+33ZapSy7JlWEo6E5Ot97aom3bkmuEu68k4/lGdDjX6YXznZx8582KlA1WTTP46FO875uq3n7bFTD1351pGtq40dDbb7uSrg5mMpxv3yYAra3SvHlt+s1vstTY2BmsFhWZqqxs1Zlndjj+b0m0ZDjfiA3OdXrhfKeulA1WEVss7kmcYJsAFBV5NH9+q4YN87CTEwAgpRGswpIhQ6xdrlpt1xvx3mrUSVuZ+jYB6D5asGmTocWLs7ViRUvSjWQDAGCH44PVjz/+ONFdgKTSUreKiz1qbDQCciV9DMNUUZE3sIuneG816qStTCNtAmAYpioqcjRuXAejqmH4Lj6+/NLQIYdI3/2ulOHIon0AgGD4yEYPweqoulxSZWWrpM7FPD6+nysrW+MaNMV7q9HeHD8etWfZBKD3amoyVVKSr/LyPF12WT+dcop09NH5bEsLAEmEYBUBun65z5zZT+XleSop8X65l5V1aMWKFhUVBQarRUWmVqxoievIY2+2GrUSSPbm+OGes94gT7h34n1xAwDoG3xawy9UfqTvy90XkJ5xRoceeyxLn32WoYMO8mjq1HZlZ8e3b52jjMF5RxkN1dUFViMIN60/fnxncN2b41t5zqLhpDzhZEMKBQCkDkZWIcn6yOKaNZk69th83XhjrlasyNaNN+bq2GPjP60azSijnZG1aI7fm9FYK0aOdCsjw5QUKhg1lZFhauRIFlh1RwoFAKQOglVIsv7lfumliZlWtTvKaDeQjGYUM94B0fr1Lnk8PTdh6GTI4zG0fj0BV3ekUABA6ogqWP3ggw8kSV9//bUWL16sFStWqKODXXOSmb0v7diPIkbiq0bQfXGXv0eGqeJij78agZVAcuPGDL3xRnTHl+IfEBFwRY8UCgBIHbaD1YceekgXXXSRJKmyslKvvvqqqqurddddd8W8c+g71r+0EzOtarcagdUArrExuuNL8Q+ICLiiF83FBwDAmWwHqzU1NXryySfV1tamF198Uffcc49+9atf6Q9/+EM8+oc+EunLPXTeZKB4jvKFqkZQUGBq3rw2jRvXObpvNYArKop8/FDVDnoTEFmpUEDAFT0nlFoDAMSG7WD1yy+/1KGHHqr6+noNGDBAhx56qAYNGqQ9e/bEo3/oI1a+3K2IdpTPap3SsrIO1dc3a/78VhUUeCRJ27ZlaNGinIByUVYCvf339+jEE4Mfv7p6tx5+eI+qq3ervr456Ir+aAMiq6WuCLh6J9TFR3Fx/EutAQBix3awOmTIEK1fv17PPfecjjvuOEne0dYDDjgg5p1D3wo3srh8eUvcRvns1ilduzZTixdna/v20Au9ehPouVzS6NFuTZzYodGjw2+1anc01m7tz0TWtk0FXS8+Hnlkj159VSEvPgAAzmSYZvcKkeG9+OKLmj9/vnJzc/X0009r8+bNmjFjhu677z6dfPLJceqmfVu27OxR+zISw5AGDx4Q1X1TiW97ys2bDQ0Z4t1C1eXqDLQkBWy56gv+ogmeAuuURj6m2y2VlOTvDfZCb/taX9/s73O4OquxOt+hnrPubez03e7xER7v7/TBuU4vnO/k5DtvltraDVYlqbXVO2KVk5OjXbt2affu3dpvv/3sHiauCFbjI1zwZzdQjSZ4q611qbw8L+Kxq6t3+4v3hwr0+vp8R9P3VJSowJv3d/rgXKcXzndyshOsWi6MuX79+rC///zzzzVy5Eirh0OSKivr0LhxHTEJNqLZNcrqAq7XXw/snxOCP0pRxfZiB9YxMg8gmVkOVqdMmRL294Zh6MMPP+x1h+B8vpzO3lq71trLr2vwZnUB19KlOf7/d0owlO6lqOK5NS1C4wIBQLKLKg0gGZAGECjakZV4jci43dIRR+SrqSnyGr/uU/olJflqbDQC8mY7+U5c5PzXvj7fkfoeLmc12fUmXzdWUvn9HYrdnPBUkY7nOp1xvpOTnTSAqHaw2rNnjzZt2qSGhgY1NDTo888/18svvxzNodAHgq22/+5383X33dlhd5yyu0rfjro6l6VAdfDgwAoD4Vb5e/UMhqLZYctqKS070rkUVby3pkVPdrccBgCnsh2sPvvsszruuON0yimnaOzYsRo7dqx+8IMfaOHChfHoH3opVKmk7du9tUkPOyx48Gm3xJJdVvMyzz67vUfw5ivnVFBg/RLaTjAUzyA9mUpRxTJgJ1+373GBACBV2P72ffjhh3XNNdcoPz9f69ev10UXXaTFixdr9OjR8egfeiHcyIrPtm2GLrkkVytXdgZKkUZkDMNURUWOxo3riHoU0Gpe5g9+EDxCGjeuQzfckCPvtL/1ACdSMBQqr7KhIXZ5lbFcpBYvsc5zTPd83UTgAgFAqrA9svrVV1/poosu0nHHHacNGzbo8MMP1x133KFnnnkmHv1DL0QaWfHqOR3YFyMyVrZ3DbfJQF2dS42Nkf62nsIFQ+GDe0OmKV13XfhpU6ujkVY2HohHKoIV8RhVZ+vYvscFAoBUYTtYHTRokNrb21VUVKT//Oc/kqTi4mI1NTXFvHPoHesjJoHBZ1+MyETK3zSM8Pmbdh+7azDUNQh87TVZDtIlQ1u3Zmjp0uygv41l+kA8UxHCiVeeYzrn6yYKFwgAUoXtYPV73/uebrrpJrW0tOiggw7S008/rerqahUUFMShe+gNuyMmvgCwr0ZkwuVv/vKXLSosNEOOKtp57K7B0Nq1nUHgZZf10ymnSEcf7Q0CrQbAjz6a1aM/sRyNjHe+cDjxHFVPpnzdVMAFAoBUYbt01ZdffqmKigpVVlZqw4YNmjlzplpaWvTzn/9c48ePj1c/baN0VeRyQd35SkT1dYml7uWxmpoM3XRT+HzJyCWs1OO+koKW8fGVu5o/v02LFuX0uH8wwcppxaIsU6JLPFVVZWrmzH4R2z388B5NnBhdcMkOVn0rHeuspuu5Tlec7+QU9+1Wu+ro6FB7e7v69Yv8BdeXCFa9QtVZ7CpYAOS7n6SAYDDe9Rnt1IUM1Uef/HyPZs9u15w5bZIiBe6mv7rA9u2RJxy6Bmux3EY10VuyJvrx4ykV399WpdsOVul8rtMR5zs5xWW7VZ/nnnsu5O9+9KMf2T0c4sw39XrttTnati34SJ3UczrQdz/viEzn/YqKzIgjMr3ZgMBOFYJIf9vu3YYWL87WoYd6VFhoht3aVTK0fbuh0aPbVVsbOVjtmoYQbY5vsOcp0Su4fXmOkUbVreY5pluQ5FSx2nUOABLBdrC6bNmygJ937NihPXv2qKSkhGDVoXylkpYuzdajj2YFjByGCz6jKbHUmynHznzJ4Lz5kobq6lz+L95wJay6Brhnntke9rF9/vEPlwoKPNq+Pfw0fNdgLZoc31DP0wUXWOtnvFZw+/Icp03LlWGYQUfVreY5puP0MwAg9nqdBmCapn75y19q+/btmj9/fqz61WvpngYQakTLzkiX3VGx3m7taDVf8sc/btM++0gHHeTRIYd4NHly5Gnr7GxTbW3WRiPnz2/VokW+Ff+R/w67Ob6RnqeCAlPbtyd2S9beBppO3OYzld7fCI9znV4438mpT3NWJcntduukk05SbW1tbw8VM+kcrMZiRMvuMdxu6bDD8vdOx0cXZFnNl+x+3EgLrOx6+OE9ys6Wrb/fao6vlQVUhYWmtm41ZBh9my/cXW/SORK5SCyUVHl/IzLOdXrhfCcnO8Gq7dJVwfznP/+RYbALihPEouxRNMdYujRb27ZFLnn01luhoxMrGwX4Vu53HjfcXxKdIUNMlZV1qL6+WdXVu/Xww3tUXb1b9fXNIYNEq2WZrJSG2ro1Q/PntyW8xJOVjQuCYZtPAEAs2c5ZnTJlSkBg2t7ero8//lgTJkyIacdgX7TbpHYdQdt3X1M33GDvGG63t/aoFRdemKt7723VhAk9A65w+ZKdQWrPnaVC/84uU8XFnfmodhelWMnxtbowatgwj+rrm5NycVKiF4kBAFKL7WB11KhRAT9nZGTo4osv1mmnnRazTiE6VhcovfWWSxkZ3mDh008z9JvfZO3dujSyYIuc6upclso9SVJzc4YuvTRXs2e36eab23r8PlQVAitbxgZbZGVd5F2zrIgU4FpdGPXppxlJu4KbbT4BALFkO1i94oor4tEPxIDVkapp03K7BZf2g4aujxXNCNkDD2RrxAhP0BHW7iOUzz+fqbVrI4/c5uWZ2r07umB14EBTd98d/1XqpaVuFRV5S0OFDqxNPfFElubMaUuKkdTuYl3+CgCQ3iwHqz/96U8jtvn5z3/eq86gd6yOVHnLMnVlP8Dr+lj2R8i8j7dgQY7OPLMjaEDWdVTxq68MS8Hq9de36Xvf8+jJJzO1enV2xPaSNHCgNH16q665pm8CQ5dLmjKlPcJOWT1Hr5NJLMtfAQBge4HVtm3btGbNGu3cuVMFBQVqbW1VTU2N2tp6Tuki/txu7yr6qqpMud1SUZGVBUrR5woahqniYk/AqFhpqVuFhR7ZHaHdssXaIpupU9uVkdFzcVUnUxkZpqZNa9fo0W794hetEdsbhqlnntmtL7+Urruub0cwhw3zWGqXzDmdVhec2dH1tV5b65I7+eJ4AEAULI+s+kZNZ86cqWXLlmns2LH+37355pt6+OGHY987hBWsvFRhoUemGaykU++CVCn4qJgvgLBaw7Q7KwFZdrZ02WVteuihbPX8O7x9uvzyNmVnd7a//PI2PfBA6PazZrXp5JOjX7DUm52Z0iWnM5pNJUJhgwEASF+2R1bXrVunU045JeC24447Tn//+99j1ilEFqq8lG+K37fPvU9hYe8Dn+6jYjU1mSopydekSXlqbg6XgxmalYCspiZTzz+ftff4gY+RkaGgi7VuvrlNs2e3KaPbKzxUezt8f3d5eZ5mzuyn8vI8lZTkWyoLJkUu0RVs9DpZRVv+qqtYlGMDACQv25/y+++/v9auXaszzzzTf1tVVZW++c1vxrRjCM1KiarcXOnZZ3dr82ZDTU2GtmwxdO+94fIkA/kWwSxb1qItW3qOigXuUBSNwDJRoYR+HO8NDz7YoiFDTFVVZfbo4803t+mnP23TY49l6bPPMnTQQR5NndruH4GNRqj++AInK1Pc5HRaF205NoTWm1kBAEgE28HqnDlzdPXVV+vJJ59UUVGRvvjiC/3zn/8kDaAPWSlR1dhoaN06l554Iqtb28jpAL6A6dZbgwdMbW3SvHnBAwhrrJWJCheo+OqrzpqVK4+n83fdp4a9KQTtUfTRXn/sBk6hSnQVFZlMbXdhtRxbsi5G62ukUwBIRraD1bFjx2rNmjX6wx/+oC+//FJjxozR3XffrQMOOCAe/UMQVhfedO5v312wPM7AgKm8vF033dTzS628vF2rVmWpqclOBkng8YuLrQVkkQIVyZCn21qlUCOcwUaTMm2++mMdOMUypzNVscFA7MRiVgAAEiGqZK9hw4ZRbzWB7C28CbfjU2CbggKPZsxo1yGHeDR9es8vtYYGY++iJRuPvneUdt68Vg0b5gkakIWalowmAAk2whlqNOn221t18cXWjx2PwClZC//3lXRZjBZvpFMASGaWg9Xx48frd7/7nU499dSA7Va7+tOf/hSzjsErWCDX1BRpi1HfSGaooCn4jk87dhhatChbhYVm2Kl3O1P/kaa1w01LRhuA+EY4ly/P0hdfGHrkkZ4BdmOjoUsuydU++0gnnRT8ON2f+8GDCZz6GhsMxAbpFACSmeVgdcaMGZK8O1iFClYRW8ECuaIij1pafD+FClSt6jnCIpnati381HtkpgoKvJUDjj8+9LR2pGnJX/6yJWygEsmNN+aG7uHev/Xqq6V331WPqgGhnvv8fE+YygemCgtNud0KuuAL9rEYLTZIpwCQzAzTjH49tyR98skn6t+/v4YMGRKrPsXEli07ba9UNwxp8OABUd031gIDudjWS40v7+KprvlvvhHKxkZvZYJBg0ztt5+pK6/MDbPtqLdawK23tmr6dG/QGU3AasX117fq2ms7S1mFf+59gvfZMAL7yeKV2IjFwiAnvb/7Wm2tS+XleRHbVVfvTomR1XQ+1+mI852cfOfNUlu7wepf/vIX3XrrrXruuee0atUq3XLLLcrMzNQvfvELnXbaaVF1OB6SOVh1u6WSkvy9q8SjC9D69/do167o7x+tQYM8Wry4NaAWa/cgw47q6t3ats3ocYyMDHPv4qpwaRBWmVq50htcx+K578o3+sfild7rbcklp7y/E8H3uo6UTlFf35wSo9TpfK7TEec7OdkJVm0vsFqyZIlOPvlkmaapRx55RHfeeacKCgq0ZMkSRwWrySzyKvjIdu3KkN3tT3vHm9P5f//X7K9j2vtarN6UgEmTeq6ab2oy9o64dt+pS4omyPQtLonFc98Vi1dih8Vo0SOdAkAys/2t/Omnn+rqq6/Wp59+qi1btuiHP/yhTj75ZH3xxRfx6F9aSr68Me+X3Z13tvoD1fA1Uq3zLibruRPShAkd+uUvW2KyM5dkqKEhwx8Mx5p38Yr3+ECi+Gr7FhUFvme670wHAE5je2TV5XKpublZr7/+ur7//e8rOztbGzduVP/+/ePRv7RkfTV5pOluq1UDest7jJtuylFGhvdLMVYjlIMGBX8uamoyNW9eToTFYPb4Rm3jJfkuQpBqqO0LIBnZDlZPO+00XXDBBdq4caMqKir073//W7Nnz1ZZWVk8+peWRo50a9Agz95RxeBB5oABUn6+qU2bIgVAwctUBf4uNroWF29ri9zeiu6jQJI3UL3kklAr/cMF5+H5vrh7U4Eg0vGBRCOdAkCysT0sdeONN+rCCy/UwoULddZZZykzM1Pnnnuurrvuunj0L+3U1GTq2GPz9+4QFbpO6s6dhgxDGj/eWlRYUBD/QMkX3FVU5GjffXv7eKaKiz096me63dINN+Ts/SnY89M1OA88XqgcXsPofCxfbl/wY4Tvbyhdjw8AAOyxHay6XC5NnDhRo0eP1gcffKADDzxQP/nJT+RiHqnXfAuSuu4VH86mTYZ+97ssS20feaRFgwZ5FO9FV778zI4O74r93jxesAUf3hJY4QJ5KfiGCL7bgven62P5cvtCpSD0FC6dwrvBAotXAACIju1gtbm5Wddee61GjRqlCy64QJ999plOP/10ffrpp/HoX9qIZkGSd6V5+KDQN6qXmakIo7Wx9fjjWfJ4oi//NH16W9AFH/bzPsMHnC6XNGtWm8aN61BtrUtVVZmqrXVp3LgOvf9+c4QA30rKgaEf/aidxSsAAETJdrC6aNEi7d69W2vXrlVWVpYOOOAAnXLKKbr99tvj0b+00bkgyV4wZprG3qCwswRNl9/6R/VefNF2enKvrF1rbcQ3lAMP7Pxb3G75A0n7wWr4PF2PR3rggWwddli+ysvzNHNmP5WX56mkJF8vvZSpxYtbZRg9n9uez3VoL72UqTfecMlNFgAAALbZDlZfffVV3XnnnfrWt74lwzCUlZWlBQsW6G9/+1s8+pc2ertSPD9fysvrHkAZys2VHnggS48+2rvg0brYpBn4puBrajJVUtIZSN58c+gtVKPhqwG7bVvg8+9bLCYpZLmf+fOt5Qvv3p2hs8/O09FH56umpm8vGgAASHa2vzk9Ho+y9xbT9G1+1fU2RKe3K8Wbm6XOnMzOwKulxVB9fV8GSLFJMygqMmOyqYA1PfvctZh/fX1z0HI/kvToo1navt3aNV9jo6FLLsn175YFAAAisz2yWlpaqltvvVV79uyRYXi/5H/xi1/o2GOPjXnn0omvZFL0I5NGt/8mr0GDPBo50h2TTQV6w7dYrLbWFbQupcslzZjRbuOI3r/j2mtzSAkAAMAi28HqT3/6U33yyScaOXKkdu7cqREjRmj9+vW6/vrr49G/tOFySeXldgKfYJI/UJWk733Po8cey4oqhzceLr00t0c+q286f86cNhUW2rnIMLRtmzcA9umak1tbS24rAABdGaZpb5J1+/bt+sY3vqG//e1v2rhxo4YOHapDDjlE99xzj2688cZ49dO2LVt22p4+Ngxp8OABUd23twKnvBMfoKGrwNQK3+Iq3xaVgZsUWDt348e3acWKVtXUZKqiIidgt6/iYo8qK1tJFYixRL6/0bc41+mF852cfOfNCssjqx9++KHGjh2r4447Tueee66++c1vaty4ccrLy9PkyZO1Zs2aqDucToKNokVTtgqxFK40Vc8aql03P3C7vXVZV67suQgrnN/9LksLF2YHravrW9zFYiwAAGwEq7fffrsOOeQQPfTQQ+rfv78efvhh1dXV6bzzztOAAQNUXV0dz36mhO4r231TykuXZlue8u5tof105HJZec6C7XgVuk6sL5+1rs47nV9W1qH772+x1a8HH8wOeoHSPRjuDVIMkAi87gDEkuWhmw8//FAvv/yyBg4cqEMPPVQXXHCBnn32WV1wwQW65pprlJFhO/01rYRa2d7YaGjRIuuVFLw1VYOP+CE4tzvS82Ro0CCPmpo62xUUmNq+PfLz+8YbnQuv7JUfM8JOV3mDYUO1tS65XOqxuMsKUgyQCLzuAMSa5ZzVESNG6L333vP/fMQRR2ju3Lm65JJL4ta53nBSzqrbLZWU5O+d7g0W0NgNPJMtUE1Uf00ZRudIZThTp7Zp2DCPBg0yVVRkyuORzj47z9ajeQPe2F60FRR4AkpjWf3SD5UD3T3fNp2Q1xZ/Tnndca7TC+c7OcUlZ9VXpsonKytLU6ZMsdezNBV5dyrf7dZXlCeXWPTX3ieQ78vRSqAqSY89lq0bb8xVZWWOtm0zdPzx3lJioXeq6pla4B2Zje0nZffRXSv5rOFyoGOZYpCOmN4OjdcdgHiJehgoKytLWVl9tStScrMzPWxnG0+ENnSoabMGqpcvGFy7NlOVla2Sgm9j6xV+K9fYsP+lH+niqHu+LawJlXPOQjgvXncA4sXyp2xHR4eee+45/8/t7e0BP0vSj370oxh1K7VY350q9iNzqcNeIHj//S3KyJAefdTezmrdd65asaJlb/5d18cP15f4j3r78lnr6lwaPbpnxGr14qi3W/ymk3A559Om5aZlWkV3vO4AxIvlYHXw4MFatmyZ/+fCwsKAnw3DIFgNwbc7VWOjEXFamnyb2PjqK0NnndVh+XnvyhcMvvWWS4WFpioqWtXUZGjDhgw99VSmmpudsZgw1Je+1Yuj3m7xmy4iTW/7Lm7GjeuwvPgtFfG6AxAvloPVV155JZ79SGkul1RZ2app03JlGGaEwIlRh1gYONDU8uVZ+u533WpoyFQ0i7ymTcsNWNwUm1Hv2C02C/WlH+niyDC8i8hKS0ketKJzeju4SCPd6YLXHYB4ccYQURooK+vQihX2CscjGqby8z0699x+uvHGXP3pT1mKNjgMXroqumMZhqnCQo8MI1wOrPVjFRd7Qn7p+y6OfG2731fy/j6dRwHtYHrbGl53AOKFYLUPlZV1qL6+WXPntia6KynK+4XY3GzI4+n+u2gCiVgtoDJlmtKSJa0hLljsL8CL9KUf6uKoqMi0nV/pWwG/enWmHnkkS6tXp9dKeKa3rYvl6w4AfCzXWU02Tqqz2l1trUvl5fZqeCKyggKPduwwguYWJpapgQNN/f3vzXK5pLY26bHHsvSnP2XqtdfsrSS3W1zd7fZOY0ezqYAUvMB7tH1JtGjf3746yZGmt+vrmxk13Ku3r7veou5meuF8Jyc7dVapuZIAdhZcwZof/7hNhx/u0S235Ca6K0EY2rrVm9O4bZsRMvgLzVuGa9y4Dttf+i6Xos6jDLUC3qehIT1WwofLOWd6O7jevO4AoDvSABLk/PPb9wYBwfIXuTS0a/XqLL32mrOjhRdecGnatNxuZbCkcOc7I8PU8uUtqqxs1ejRfTc6FW4FfCfvKHY6FHpnehsAEoeR1T5WU5Opa6/N0bZtXCfEkmkatqfU+9rq1Vkhgj9ffd2ut3uDokcfbdGECfENhIJN2UZaAd8pfVbCl5V1aNy4joRObwNAOnL2t3uKWbMmU5deGmmamrSA6HXdtjbY8xhq56n4MgxT/fubamoKF/wF71NGnK9pguWkFhd7bI8UpstKeKa3AaDvMbzXR9asydSMGbnyBiXp8cWeWMHLQ82c2abq6t16+OE9evbZ3dp//2BtY9sP05R27rR7zg0ZRnyn2H05qd3TEhobDT36qL2tlFkJDwCIF4LVPlBT4x1R9XgIUvtGqPqohtasyVJTk3cKd8sWQzNm+H4fn2Brn32kgoLojh3PvdQj7cokefNle9aE7dHLsDVfAQDoLdIA4sjtlt56y6W5c3MS3ZU0FDwloKHB2JuK0XlbYaGptjZDzc2x78XXX/d+JD0eU+yRc1J9tWp9C/5Cp1WwEh6RJLqUFYDkxshqnNTUZKqkJF9nn523d8tORlUTI3Jh/+3bvYHqOee09U2XbIrHFLvVAPiyy9pUXBzq8Q0VFjL9j/B8n4Xl5XmaObOfysvzVFKSr5oaxkoAWEOwGgehcgHhFD2nvQ1DeuONTBUVecJMffdtWbFI26r2htUA+BvfkOrrmzV/fquC/f3bt3trrRJ4IJhwedG8bgBYRbAaY9bqU8JpTNNQY2OGpkxpl9Rzb3NfkDZvXqxHX00FCwLjXWzetzFF+JxUU4sXZ+v3v8/UE0/4FlwFz29Nh1qrsMdKXjSvGwBWEKzGWGcuIIFqMho2zBO0+Htxsbc4/zHHuPcGeL0fYTUMU4YhzZ7dc6o93sXmfbsyBd+Ywt9DSdL11+eEfU3HcyEY4svt9m7/XFWVqdpaV0wDx0ifhbxuAFjFHEyMpUu9yVQ1ZIip0aPdPYq/NzUZuukmu9ukhldUZKqyslVlZR2qqGjr8wUoZWUdmj+/TYsWhV4AaJqGmpqsvaZ57SeXUDV2fa/J3rL6euB1AyASgtUYo95ksjKVkSGNHOkdWupa/L2mJlPTp+fuHYWMjmGYGjrU1P33t+irr3oGpIkqNj9smCdmx+K1nzx8uaTdX9O+XNJYjOpbfT3wugEQCWkAMWYtFxDOY8jjMbR+feBwZixykH2vhdtvb9WJJ7o1cWKHRo92Rukeq4HCoEGhX9PxXAiG2OurXNJIn4W8bgBYRbAaY75cQCnYIh04XfcpSfs5yKYyMvo2/7Q3rAYUd90V/DUd74VgiL2+yiUN91nI6waAHQSrcVBW1hF0kQ6c79NPO98Sbre0YoX1bUd9C6YefbTFv6VrdfVu1dc3OzJQlawHFBMmBH9NOzkQR3B9mUsa6rOQ1w0AOwzT7E0mnnNt2bLTdo6hYUiDBw+I6r7B+HZtef75TD3+eHbvD4g4M1VcbKq+vllr12bq2mtztG2b9eu5aBenOGF3H6uLbZzQ12jF+v2drGprXSovz4vYrrp6d8zyqPv6dcO5Ti+c7+TkO29WsMAqjnyLZj74gAHs5GCoocHQkiXZuvtuqxcXpgoKvKNExx9v/ws4mhXZ8fjiLyvr6FEBIZkCUVjnS/1obDT8OapdGYapoiIzprmkiVpACCA1EKz2gUGDuNRLJt5A1foU6IwZ7VEHqpFWZFspoRWrckORAop4lzpC3/ClfkyblivDMAMCVnJJATgRaQBd2J1KsDrC9frrLk2aFHnaDckrVNAW6jXidkslJfl7t6EMPrpVWGgqJ0dqbOw6Mu97YfYMMOKZAxgYWHftr/ex589v05w5bY4OcJgqDJTKFx+c6/TC+U5OdtIACFa7sPOCt5Pjd801Ofrtb8lZdb6egaDd+3YN2sK9RgoLTUt5g97jdg8OQ0/d1tc3xzxgjBRY+xQVeXT77d7XvxNzW/lC68mJ5ykWONfphfOdnAhWFd9gNdQoU/cRrpoa+4t0EGvBgzurQWA0ioo8mjixXQ8+mB3yNTJ9ersefTT2FzCxXBTjY3VBjuSthjBrVpuqq7McN2LHF1r64FynF853cmKBVRxFKqhtGKYqKnLk8UiXXpqbkD6iOyuBaOy2fGxsNPTAA75ANPhr5Nln4/PWi8fWldaPacg0zS5/e6dY7owEAEgvDPnZZLWg9jXX+PZbZ9/rxAo3dW3qmmukuXNb4/SYoV8jTU0ZYXeFilY8tq60d8zgf3ssd0YCAKQXRwarTU1NmjVrlo455hiNGjVKt99+uzo6nDEaY3WUadcuO7seoe95z82zzyph2z1OmtTu7UmPgDWagNPUwIHx2boyVlsIx2pnJABAenFksHrNNdcoLy9Pb7zxhlavXq23335bjz/+eKK7JSk+I1dIFEP//a80c2Zi0jX+539MzZjRpoEDA19TxcWmCgvDBYfBb9+61dDatZlyu715plVVmaqtdfV6JLPrLlfRBdKB4pGqAABIXY5bYPX555/rjDPO0Ouvv64hQ4ZIkv7whz9o8eLFevXVVy0fZ8vnmxX0T3O5pNwuwUlzs/9/eyRpZ2RI/foFtPV4pNGj87VpkyGzy8ipRxlqUT/58iP7abeMEF/spgztUeeCFTttc7VHGfKE/Lt3Kz+qtjlqkUuhoxp7bfPkG7nMVqsyFXpU3E7bPeonc+/1VZbalKX2mLRtUY48e9O3g7ftzHltUa48e4+bqQ5lqy3kcVuVI/fe42aqvUtbUxmG5OlS37L/wCz9aJI0blyHSo9p1cs1bl1+ee7e1oELwdqUrQ5580Jd6lCO9m6XuneDgpwcadNmbx/blK39il3exU3jWqWWlpD9VVaW3K5s1dW59GWjR0WFe3TssW5l7L2kfeGFTN1yS442bc5Qu7LUvrcPhjzqpz0hD9u97fNPN4UeAc7MlHL2ptCYprR7d+j+2mnrcsnol9v5/t7VHLZtqM+IHoJ8Rlhuu3u3Qq4GMQwpLy+6tnv2SJ7Q73vl50fXtqVFYa987LTNy/P2W5JaW6VwM2d22vbrJ2VkeD/L98nRlsatoRfc7G0rSWprk9pDf0YoN1f+Mgl22ra3e9uHkpPjfR3bbdvR4X0uQsnOlrKy7Ld1uyN+Rig7235bj8f7WotF2yDv+5ALrGx+Rlh+3/MZEbytzc8Iw+PR4G8OCd2+K9NhXn75ZfPYY48NuO2jjz4yDznkEHPHjh3WDzRggGl6T13Av9bTzjC/+upr/z9PXl7QdqZkth1/QkBb96BBIdu+o2NMw/CYkseUTPM/+mbIth/osICbPtBhIdv+R98MuOkdHROy7ZcaHHDTqxoTsu0u5QXcVKMfhmxrSgE//q8mhW2bp13+Hx/TRWHbDtaX/h/v16ywbb+p//h/XKTrwrY9TB/4f7xZN4dte4ze8f94nRaFbTtGr5oDB7rNggK3OUv3h237Q9X4f7xIj4Vt+2P91jQMj/nYY7vNHct/FbbtRXrM/+MPVRO27SzdbxqGxzQMj7n2+hfCtn3nnNvN4mK3KZnmMXonbNubdZPpe60fpg/Ctl2k6/b+r8c86hufhG27e+ql/vfblg8/Ddt2z+TzO9+fnzWGbdsy/kfmli1fm6Zpev8bpm28PiPavj8ioG3HAQeGbNs+/NCAtu3DDw3ZtuOAAwPatn1/RMi27kGDAtsef0LItp68vIC2raedEfZ569q2ZfyPwrf9rNHfds/k88O23fLhp/62u6deGrZtU/3fvK+dLV+b5nXhPyO2vrHOf9zmeQvCtt320qv+trtuvi1s2+3P/d7fduedd4dv++T/+tt+veyhsG13LP+Vv22kz4ivlz3kb7v9yf8N23bnnXd3tn3u92Hb7rr5Nn/bbS+9GrZt87wF/rZb31gXvu3sq/xtm+r/FrZtPD8jur6Gw7XlM8L7r9efEQMGWA7pHFcNoLm5Wf26XllI/p93796tffbZp1fHz87OtFwqISvLFdjWCD99uf/+ho44Qnrhhd70EE52xWxpwj0ZcrmkFydI+kNsjmvuXZR00039NGVxv4jtbR3bNGQY0sqVOfpBmHbP/G+WGixmBk0+x9CKtwx98YWdnhjaviP88fv1y1Y/33vODDNqIyk3N0u5vrb9wh83JydTOYO8bQcNCv/+j9dnRFZmt7YZodtmujIC27pC/32uDCOwbWbonOAMo1vbrNBtDXUrK5Md/usioG2Ohba+UZbcrLBtBw3qL/nPc/hybwMHdmkbQWFhfmfbvJywbQsKurTND9/2G9/I62zbP3yKUUDbAeHb7rNPv862+4T/jBgwIFcDfG2/Eb7sXP/+uepvsW1+fo7yfW0L8sO2zcvLUZ6vbWGEtv2yO9vu6h+2bVw/Iyy+dviM8IrnZ0SPxzJN07R1jzh7+eWXVVFRoXXr1vlv+/jjjzVhwgS9++67GjDA2gukaUN0aQCDBg1QU1PoNICu3G5p/XqXvvzS0KefZWrl0/v4dxsiDSCZ0gBy5ZEraNtpl7TqD3/IUuOmDH/bfQoMXXZZu+Zc0azbb5ZWrAz+5RU6DSB82+ef/VrHl/Scrqqrc2nyuXl70wC8X/Bd0wCC6do2Q249v2prwBS8ryj87Nm5+nJ7ttqV42+bK+8XgSHvhgNvvul9/a9f79KmpmwNHOo97pYvTRUX7tbIkd7jlpTka9v2zooAXdMAMuTWsKLdevPNEJsXxDkNwP/+Jg3AftskSwMYNCBHTZtIA0iXNICA7+4wbUMiDaBTH6YBDDrQWhqA40ZWDz74YG3fvl1btmzR4MGDJUmffPKJhg4dajlQlSQzLy/0h1TX2/O6PHmGpPx8mXs8nfcN1Vbe1WmjTvVuEnDH0sA93rsGmJHYaevNi41921ZZX2Rkp22bctSm8CMR0bRtV7Y/AIpn2/tW+s5N5xXu9u3SXXfl6MEHs3XZZW3abaHPHcryB42RNH6VJTOv50jEMWOkguJ+amw0/K9LtzK12+Lb2COX/ru1v0bleb/sg+2w1bVt1wuUfzdK9zySrSeeCF7sf9Sp3tdEba1LG7eHfj175NK/Gwfo7b+6Qm9e4H8fGT3ec7Foa5oK+vwGP65s9MFm234R3vfRts2N8L6Ptm1OhPe9nbZd22fneP/FvG22zLz80N8DXdtmZXv/WTmunbaZWd5/sW7rypTyIrzvo2mb4bL+GrbT1siIT1vf+z7Yd3eotpaOK2e0TfXPCBtrbR1XDeCggw5SSUmJ7rjjDu3atUv//e9/9eCDD2rSpEmJ7lpQ4TYJQCoIXS91505Dd9+drfx8jwLfhb0TquJE11X50Za7uvHGHNXUZPp3YfNuoWrNokXZPdr7iv3X1Hi/DK2u9KciAADAKscFq5K0bNkydXR0aOzYsTrnnHN04oknatasWYnuVlCRNglA6mtujt25z8vzyOMJPZNSVtahFStaVFQUGJwWFJjq3z9y0Lx1qze4vPbaaC+wwhf7t1rajRJwAACrHJezGivR7BEczf7CVVWZmjkztgtikIxMxfKCxTe9HmprUrdbWro0W48+mqXt27tec/rn0sIc3W5frbWvrt6t0lK3Skry1dho+APZrgzDm/9aXx8iZzWO2D88fXCuk5Mvh37zZkNDhpgqLXVb+pzgfCcn33mzwnE5q8mGESJ49TZQDQwIfdPr8+a16aCDPGpqMjRokDfQKy11a+3aTC1enB3lB7P1vhqGafkxNm82/KkK06bl7r1v52P5UhcqK1v7PFBNZ9EGAEBfCpZDH+miHemDYLWXfFtRhhpJAiLrOXLpfS2ZWrSo52KSoiKPWloUYhrfUCzzZ4uKTF1wQXvQfnTnu3DzpSp4v3g6+1dUZPLF08cIAJAMfDn03S+MfRftK1a08HpNc6QBdBHtVILvjSaJgBV9IFYpB6GO490Ja8WKFh1/fGc5KrtT+04b0Uu3qcLAAKDnCHcqBwDpdq6Tmdvt/XzxXthGlzrE+U5OdtIAHLnAKtmEWvQCBGdKMnXqqdEGClYD1eCvR8MwNXCgx///3X9nGNI997TqxBO9wWXXKgTdj8nUfvy53d6SYFVVmaqtdYUtY9j1PqGqlHRfFAckUqRFyqZpqKEhQ3V1fMCkM4LVGCkr61B9fbOqq3drxow2+QISoLuCAlPz57dp1qwwBcBjJFgwKkl3392qlSt7XmAVFZkhR9wKCnqOxBYWBm9fU5OpkpJ8lZfnaebMfiovz1NJSb6/xBWsifZ5JABAsqDcHazgmyOGXC5p9Gi3Ro92q7TUrblzc7R9O2+w1GBllb0127dnaNGiHBUVeZSf79lb+ip2rxPftNmtt7bqppvC542OG9cRcao+VD6ZZGrr1p79Jv8sNnrzPBIAIFlQ7g5WkLPaRazzXl5/3aVJk6zvTgWn6v5iiOYLPliw2/W40QYNgaOd3fMRe5s3ajefLBb5Z/GSTHltvX0ea2tdKi+P/NlTXb079E5iSSyZznW6873We1PujvPde4lYY0DOqkOMHu3WoEFh9tRF0rj88jYVFlr9FAy1u1SwlfvRjqqaKiz0RJzG9432T5zYodGjg3/4hMuJtDudzPRzbPT2efRVKem505mXYZgqLvaotDT1AlUkl3A785ET3zeSIW2LYDWOXC7prrtaRf5qclu2rEVnnOHWtm1WdyoLFZTGive1NH16u9av9+ZJP/zwHlVX71Z9fbOtKfZIH1J2p5OZfo6N3j6PBABIJqEWKYfLoUdshNp6u/tW2olGsBpnEyZ0aPbs+C+kQfwsXJijtWuje8NOmhSPc+8NfhctytGxx+Zr2zYj7MhpKFY+pOzmk1ltP3iwaXuFezqJRR4fAQCSSddFytFefMOeZKoaQs5qF/HMe1mzJlPXX5+jpiauD5JP9IurfvzjNj3zTHavHv0b3/DoiCPcqq31Bcy9r5lpNSfynXeadeyx1vPJrOSfFRSYys2VGhv7tlB9MuW1xSKPr+uxnFTvti8k07lG73G+o5Po3HZyVh1owoQOffBBs+bPJy0g+XiDhYwM++cscqDqfS2Eyi2UpB07jKCBqhT91a/VnMj16122ppMjTT+bprRtm6HGRmdPOSVaLKfxreQtJ1o0tWQB9E4ypW0RrPYhl0u67ro2rVzZouJigtXkYsjjsfOGDXZBEvzn00/v0MCB4V4P4RdiRbNoyc6HlN3p5FDthw41uyxSc/aUkxOkyzR+MizuAFJRMpUNIw2gi76cSvBNzb3wgkuPPOIbfUv81QtiwVraQEaGaTMADu/hh/do4kRrAUw00z92p5O7t/d4pLPPTvyUU7JNFabyNH68toRN1nON6HC+oxPLdKNo2EkD4NI1QbpuIDBqlEfXXpujbdsIVuMpFgX4Bw707C2EH+4YVo7vDd5iyc7Vr6+0UaQPqa6ljXyvWau6t6+qsvZx44QpJyex+7wni0iLOwzDVEVFjsaN60iZ4BxwEl+60bRpuXvTtHpeMDqlaghpAA5QVtahf/zDm89aUEBd1ngZP943QhP9pfcll7THpjOSYjWSHk3NzESUNkqmKSfEHzV5gcRLlnQjglWH8OWzfviht3THjBltbCgQY6tWZauw0FT//tEHQ9/5jkczZsQiYI1doGqa0gUXtOv55+0tTunrDykK1aOrZFrcAaSyZCgbRs5qF07Le2lrk446Kl9NTbEuKp++fMFdbq7U0iLZfV6rq3dbzr3sC/n5HhmGtGtX9GWg+ion0u2Wli7N1qJFPXO0e5ujaIXT3t/pLp5lczjX6YXznZzIWU0R69e7qMsaY76cHG+gauueKioy1d4u/fa3vXnbmOr9hUfnAq7m5p6vD18ZKKuBX1/kRNbUZKqiImfvtG9PRUVm3OuswlmiyZsGkJ6IhByM6S9n+fprQ+eck6dnn7Va5D94qarCwtBT4daPGfq1YZqGTFOaOzdHb7yR+JqVoXbK8pX3mj+/1XFTTog/toQFYBXBqoOx0MQpvOehudnevfr3D/y5uNjUypUtWrKkde9UVTzPr6Ht2zN09tmJrVkZbsW3ZMgwpCeeyEpAz+AEybK4A0BikQbgYFanyZYta9GmTYbmz8/V7t2MxsZW1y9Rq8+td6p/1y5v+4IC76KsOXPa5HIpqsAxL8+j3btDr5wOJ1JaQDxzVjtXfAfnXfFtqK7O5cjyTKlc49Qpyso6NG5cB88zgJAIVh3Mag20k07yfsnn5rbo0ktzfS36urspyu7z2HO0dMcOQ4sXZ+vQQz0aN65DFRU5No7tPV5vLkLC1awMlktqd4FWOMm84jvezw06pWotWQCxQRqAw9mZJpswoUOzZ7f1dRcdLhGpFKG3Eq2tDV9bMuAoRjSjusEFq1kZKpfUNxIbi9SBZK2t2hfPDQDAGkpXdeHk8hd2piPXrMnU9dfnUElAUmxW38fOnDmtWro0J3JDSYMHe7RlS2zPoW9LVt82e95gzN42e3Zei4nezi/wsay9v3vz3MAZnPxZjtjjfCcnO6WriGaShG+abOLEDo0eHT6fa8KEDn3wgbfA7zXXtPZdJx3JOYGq5H1zWnHbbS269dbYnzvfCGa0uwfV1GSqpCRf5eV5mjmzn8rLwy/gSsYV3+ysBADOQrCaonzB7fXXt4XdNchXPgh9Y/RotwoLPQr1nPt2cbr00vYeqR/hmcrJCX0uu+8OFU0uabRT48m24juZ82wBIBWReJXiIi3S6pwycdZ0eXDJ20ff1PG2bYa2bQv1N3jPh2+kMVI1CJ9Bgzy6665WZWRI06bl7j1O8MV4vhFMu7mk4UpQhVvA5ZNMK76TNc8WAFIVI6tpINzI1sqVLVq5sufvnMnpgaoUKlCVpFtvbdVNN4WvBDBwoKlx47wjjeGm0LsW1P/gg2ZNmNBhawTTFwiHGnH3jcS63VJVVaaWL8/q9dS4nVSWRLL63LCzEgD0DRZYdZHqSdrhFsZ0/d2++5rq6JAuuaTf3kL4yRAkRpK4UVlfuaPCQjOqvdDDlVAKNlopWVsA5ZvWlxR0xL2w0NS2bfauZ30LuJzIzvs73HMjqdfpC9Rvja9U/yxHIM53crKzwIo0gDQSrpZhsN/dd1+LLrkkN2j75BMsUI1fAHvbbS3ad18zIBCpqrL2duueCxlqCn3t2sy9q9Y7A8qiIo+mTGnXsGGesBckQ4Z4R3BXrGjZGwh3PmZhoamtW8OlK4SWKlPjvlHq7s9NUZHZ6zqr1G8FAHsYWe2Cq7Oe1qzJ1IwZufJ4UmF0NZTuQWuoINZK3VNTxcXByxrV1rqiGlkNNgq3dq135K9nDmlg331BkCRLo7P77mvqiity1dgYvGxTpJxcJ5dziub9HesRUN+IbffzFs2ILaOzofFZnl4438nJzsgqwWoXvOCDW7MmM8LOWGaY34XSF9Py0T5GqL/H1A9+0KEXXsgM+XtJWrky9LamdmuOBhuFKyryqKVFe0c+w/99gYvoAvscLECyGlB3f4zux3GiRL+/Y1m/ldHZ8BJ9rtG3ON/JiTqriKkJEzq0cmWLiouDfwoUFvpuD74IKPjtdvXFJ5C3r5df3tbjbx082KPly1v06197F6R1/s2dBg40Qwaqkv2ao+FKRXlzSSMH4oFBceidtdx7B3KjKcfk1BJUThOr+q3srgUg3fCpBku65k02NhpqajI0aJB3JKipydC8eTk9FuMUFpo6//x2VVdndftijWa008p9TA0ebOqWW1p18805amqy+zjeEkzPP5+ld95p1vr1wadYfc9Fba1LtbUuGYY33/f44yNPw1rNhQxXKsr+8xe6vTdAMlRX59Lo0W7LOafBcnIRXizqt/a2hBgAJCOCVVgWbBFWTU2mpk/PDTL1Ymr7dkMlJR5VVDT7c+v++c8M3XOPte1G7TFlGNKiRd5V99FuNesL3tavd4VcjCZ5n4uTTnLrpJPsly+yUnO0cxSub/gCpEi1XX1T1Zde2k4wZNO++/a+fmuk10X3iw8ASAWkASBqVkb/Kiq8gamvvuaJJ/buC3ThwhZddlmrBg3yBNxeXNw5FR2LnYXivTtRqJqjbrc3b7Svp3J9AVIybo+aDGpqMnXFFeEra1ip38ruWgDSEcEqohZNDl6kguuRclMffjhbo0Z59MEHzaqu3q2HH96j6urdqq9v9k+hx6J8UiJKMNXUeEtRlZfnacWKbIv3stLPcFvqmiosDAyQkm17VKfz5Zh6KywEZ/VCgN21AKQj0gAQtWhGecJt/9oZUIVexb9pk3cRSbigyRcQh1p1Ha56gW+au7TU3aelgQJLGnXva/B+FhSYys1VtyAosH3PagA9GUGeomTaHtXJws8+dLJav9Vqmga7awFIJYysImrRjvKEGrkrLjY1e3Zb2K1fg61g787lksrL23336H4E//+Fm+b2FdwvL8/TzJn9VF6ep5KS/LhMz0dOpwjezyVLWvWXv3SOMM+f39rjuRs0yBe8hgqUDG3dGnwFerJsjxotX8pFVVWmamtdIV9PvRFp9sFn2TJrI9akaQBIR4ysImq9GeUJN3J3yiluTZoUutZnpEUkbrf01FNZvl5075UkUwMHmsrJCRyV9I1uSQo6yukrDRTrrTY9HkVYTBX4N3Qfhev6HMyZ0xZw7MZGQ7Nm9YvYp1TOcfQ9319+aeiQQ6Tvflf6wx/6pk6p1ed1yxbrz388d9cCACciWEXUwk3pWxnlCbX9q9Uv7lCBwNKl2RH2tDe0dauhZ5/drYED8/TPf+7Rfvt1BtUlJfm2SwNZTRkIVsy9oMDTs2EQ06a1qaysI+x0fPfntLbW2hBbquY4Bnu+Cwvzg24lG6uLka7ilWNKmgaAdEKwil6JxyhPb77g3W7p0UezgrTuacsWQxMnSkcc0eEfRa2ttV8ayOpuQqHyUrdvtxacl5V12C5HlM45jqGe785ANf51SuP5/Ie62AOAVEPOKnqtrKxD9fWhV+fbFaliQLgSP3V1Lm3fbu1lHSzYtbtozOpuQtbyUu3/vZGka45j5Oe7d7tIWZWuzz8AxBLBKmIilotxevMFbzXY7F6uycfOqG6k3YSkzoVgkRfa+AKo2AY0brd3J7EZM9o0cGD6lKKyurAplFjm8FIKDAB6hzQAOFK06QVWg83p04PvwGRn2tbObkJWg5+CAjMgLaA36RTB0hMGDfLo7LO9+Y6pnOPY22Az1jm85JgCQPQIVuFY0XzBRwo2vUXwTc2Z0xb0/nYWjdlJGbAa/Cxf3uI/dm8CmlD5mlu3GvrlL7NSPlCKNtiMRw5v98V3Z50Vm3xYAEgXBKtwNLuLSLoGm6EK6p9/fvh97a2O6trZ693qiG0s6plGSk+I9SIiJ7Jy0eJlr4KFXVYX3wEAQiNnFSmnrKxDs2YFHzmVpAcfzI5Y3D/SojG7e7335UKbaLbBTTVWnu/CwvjmkFpdfAcACI9gFSnH7Zaqq0OVr4q8A5ZPqEVj0e713lcLbaLZBjcVhdspbeXKFv3jH7GrYNGdncV3AIDwuLRHyrGz8Omss+wdu7d7vffFQpt4FaJPRl2fb+8OVv303e82K2PvyyNedUrtvAaplQoA4RGsIuXEc2QxUhDis2xZi046KXgQEu9i7um8EUAwvufbMKTBg6UtW9Rj4VmsMboNALFDGgBSTjxHFuOx13usUYg+8RjdBoDYIVhFyunNDliRJEsQQiH6xIrnaxAA0g3BKlJOPEcWkykIifU2uLCO0W0AiB2CVaSkeI0sJlsQEu02uG63VFvrUlVVpmprXaxajwKj2wAQG4ZpxnupQWJs2bLT9iIK7wKMAVHdF87Uffegrivve3O+U7nYe6r+bYl6f4d7DSI++CxPL5zv5OQ7b5baEqx24gWfXnp7vlMxCAncprXn7k7JPCLI+zt9cK7TC+c7OdkJVildBUQp3iWo+hrbtCIdpeJFJ5BqCFYBSKKQPdJPqqa8AKmGBVYAJFHIHunFl/LS0BD4em5sNDRtWq5qahjLAZyCYBWApOSpIQv0VqSUF8n7e6pgAM5AsApAUnLVkAV6ozPlJfgsgTflJUN1dSSvAk5AsApAUvLVkAWiRcoLkFwIVgH4Ucge6YCUFyC5kEEOIEBZWYfGjevoVTmfeJQDosQQYsWX8tLYaPhzVLsyDFNFRSYpL4BDEKwC6KE3NWTjUQ6IEkOIJV/Ky7RpuTIMMyBgJeUFcB7SAADETDzKAVFiCPFAyguQPNhutQu2bEsvnO/YcrulkpL8vUFl6KnV+vpmyyNWsTwm5zt92DnXpJckP97byYntVoEUkGxfovHYAYtdtRBvqbZtMpCKCFYBB0rGHM14lAOixBAAgJxVwGGSNUczHuWAKDEEACBYBRwkmbeBjMcOWOyqBQAgWAUcJJm3gYzHDljsqgUAIFgFHCTZczTjUQ6IEkMAkN6cmfwGpKlUyNGMxQ5YfXFMAEByIFgFHCRVtoGMRzkgSgwBQHoiDQBwEHI0AQAIRLAKOAw5moiW2y3V1rpUVZWp2lqXI6tGAIBdpAEADkSOJuxKxo0kAMAKglXAocjRhFW+jSS674vu20iCEXkAyYw0AABIYsm8kQQAWEGwCgBJLJk3kgAAKwhWASCJJftGEgAQCcEqACSxVNhIAgDCIVgFgCTm20iie11eH8MwVVzscfxGEgAQCsEqACQxNpIAkOoIVgEgybGRBOKNDSeQSNRZBYAUwEYSiBc2nECiEawCQIpgIwnEGhtOwAlIAwAAAD2w4QScgmAVAAD0wIYTcAqCVQAA0AMbTsApHBus7tmzR5MnT1ZVVVWiuwIAQNphwwk4hSOD1X/961/6yU9+ov/7v/9LdFcAAEhLbDgBp3BcsPr222/roosuUnl5uYqLixPdHQAA0hIbTsAp+rx0VUtLizZv3hz0d/vuu68OPfRQvfrqq8rJydFjjz0W9eMYUaTQ+O4TzX2RfDjf6YXznT4417EzfnyHVq5s0Q035KihofMJLS42HVNnlfOdnOycrz4PVt9//31deOGFQX/3wAMP6LTTTovJ4wwaNCAh90Xy4XynF853+uBcx8bFF0tTpkhvvCE1NkpFRdKJJ2bI5eqX6K4F4Hynrj4PVkeNGqWPP/447o/T1LSzRxHjSAzD+2KP5r5IPpzv9ML5Th+c6/g44gjvP0nati2xfemK852cfOfNipTdwco0FfWLtjf3RfLhfKcXznf64FynF8536krZYBUA7HK7vYXQN282NGSIqdJSN4tHACDBCFYBQN490Csqcvbu2ONVXOxxzCKSVMeFAoBQHB2svvLKK4nuAoA0UFOTqWnTcntMITY2Gpo2LVcrVrQQsMYRFwoAwnFcnVUA6Etut1RRkbM3UA2spWKa3p8rKnLkpu55XPguFLqWRZI6LxRqahw9pgKgDxCsAkhrdXWuvSN6wYv+maahhoYM1dUxJx1rXCgAsIJgFUBa27zZWmVqq+1gHRcKAKwgWAWQ1oYMsVbrxmo7WMeFAgArCFYBpLXSUreKiz099j73MQxTxcUelZYyFx1rXCgAsIJgFUBac7mkyspWSeoRsPp+rqxspYxSHHChgHTkdku1tS5VVWWqttZFTrYFBKsA0l5ZWYdWrGhRUVFg0FRUZFK2Ko64UEC6qanJVElJvsrL8zRzZj+Vl+eppCSfqhcRGKaZmpuTbdlif49gw5AGDx4Q1X2RfDjf6cXK+aYwfWLEus4q7+30kiznO7Cec2cetu/CLN0ujH3nzVJbgtVOyfKCR2xwvtML59vZYnmhwLlOL8lwvt1uqaQkf2894Z4LBg3DVFGRqfr65rS5QLYTrDLuDABIOJdLGj2a5D2kps4ybcF5y7QZqqtz8T4IgpxVAACAOKJMW+8QrAIAAMQRZdp6h2AVAAAgjijT1jsEqwAAAHFEmbbeIVgFAACIM+o5R49qAAAAAH2grKxD48Z1UM/ZJoJVAACAPkKZNvtIAwAAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsglUAAAA4FsEqAAAAHItgFQAAAI5FsAoAAADHIlgFAACAYxGsAgAAwLEIVgEAAOBYBKsAAABwLIJVAAAAOBbBKgAAAByLYBUAAACOlZnoDgAAkEhut1RX59LmzYaGDDFVWuqWy5XoXgHwIVgFAKStmppMVVTkqKGhc6KxuNijyspWlZV1JLBnAHxIAwAApKWamkxNm5arhgYj4PbGRkPTpuWqpobxHMAJCFYBAGnH7ZYqKnJkmpIUGKyapvfnioocud193zcAgQhWAQBpp67OtXfq3wj6e9M01NCQobo6kleBRCNYBQCknc2bgwep0bYDED8EqwCAtDNkiBnTdgDih2AVAJB2SkvdKi72yDCCB6OGYaq42KPSUpJWgUQjWAUApB2XS6qsbJWkHgGr7+fKylbqrQIOQLAKAEhLZWUdWrGiRUVFgcFqUZGpFStaqLMKOARF5AAAaausrEPjxnWwgxXgYASrAIC05nJJo0eTmwo4FWkAAAAAcCyCVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsglUAAAA4FsEqAAAAHItgFQAAAI5FsAoAAADHykx0B+LFMKK/TzT3RfLhfKcXznf64FynF853crJzvgzTNM34dQUAAACIHmkAAAAAcCyCVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsgtW9mpqaNGvWLB1zzDEaNWqUbr/9dnV0dCS6W4izrVu36vTTT9e6desS3RXEyUcffaSpU6fq2GOP1ejRozV//nxt3bo10d1CnLz99tv68Y9/rKOPPlqjR4/WbbfdppaWlkR3C3Hkdrs1ZcoULViwINFdQZwQrO51zTXXKC8vT2+88YZWr16tt99+W48//niiu4U4qq+v1+TJk7Vhw4ZEdwVx0tLSoksvvVQjRozQm2++qZqaGm3fvl0/+9nPEt01xMHWrVt12WWX6bzzztO7776r6upqvfPOO3r00UcT3TXE0f33369333030d1AHBGsSvr888/1zjvvaN68eerXr58OOOAAzZo1S08++WSiu4Y4qa6u1nXXXac5c+YkuiuIo4aGBh166KGaPXu2srOzVVhYqMmTJ2v9+vWJ7hriYODAgXrrrbc0ceJEGYah7du3q7W1VQMHDkx01xAnb7/9tl566SWdccYZie4K4ohgVdK//vUvFRQUaMiQIf7bvv3tb6uhoUFff/11AnuGeDnhhBP08ssv64c//GGiu4I4GjZsmJYvXy6Xy+W/7cUXX9Thhx+ewF4hnvr37y9JGjNmjMaPH699991XEydOTHCvEA9NTU264YYbtGTJEvXr1y/R3UEcEaxKam5u7vFC9/28e/fuRHQJcbbvvvsqMzMz0d1AHzJNU0uXLtWrr76qG264IdHdQZy99NJLev3115WRkaGrrroq0d1BjHk8Hs2bN09Tp07VoYcemujuIM4IViXl5eVpz549Abf5fs7Pz09ElwDE0K5du3TVVVfpd7/7nZ544gkNHz480V1CnOXm5mrIkCGaN2+e3njjDe3YsSPRXUIMPfLII8rOztaUKVMS3RX0AYaWJB188MHavn27tmzZosGDB0uSPvnkEw0dOlQDBgxIcO8A9MaGDRs0ffp0FRcXa/Xq1eQvprC//OUv+tnPfqY1a9YoOztbktTW1qasrCymiVPM888/ry+//FLHHHOMJPkrPvzxj39ksVUKYmRV0kEHHaSSkhLdcccd2rVrl/773//qwQcf1KRJkxLdNQC9sGPHDl100UU6+uijtWLFCgLVFDd8+HC1tLRoyZIlamtr08aNG3XXXXdp0qRJ/uAVqeGFF17QX/7yF7377rt69913VVZWprKyMgLVFMXI6l7Lli3TrbfeqrFjxyojI0M/+tGPNGvWrER3C0AvVFVVqaGhQWvXrtULL7wQ8Lv33nsvQb1CvOTn52v58uW64447NHr0aA0YMEDjx4/X7NmzE901AL1gmKZpJroTAAAAQDCkAQAAAMCxCFYBAADgWASrAAAAcCyCVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAgIi2bt2q008/XevWrbN8nxdffFFlZWX6/ve/r9NPP12rV6+2/bgEqwCQIJ999lmiuwAAltTX12vy5MnasGGD5fvU1dVpwYIFmjdvnt577z3ddtttWrhwof7617/aemyCVQAp69RTT9WRRx6pESNGaMSIEfr+97+vE044QXfddZc8Hk/MHmfKlCm67777JEk33XSTbrrppoj3eeWVVzRt2rSoH7Oqqkqnnnpqj9v37NmjY489Vr/+9a+D3u/aa6+NuDtfqGMDSE/V1dW67rrrNGfOnB6/e+uttzRp0iQdc8wxOvPMM7VmzRr/7x5//HFdeOGFGjNmjAzDUGlpqZ599lkdeOCBth6f7VYBpLSFCxdq4sSJ/p8//vhjXXzxxerXr5+uuuqqmD/erbfeaqnd9u3bFY8NBPv166ezzz5bzzzzjC688MKA323dulUvvviili9fHvPHBZC6TjjhBI0fP16ZmZkBAetHH32kyy+/XIsXL9bYsWP1/vvva9asWSosLNSJJ56ov/71rxo1apRmzJih999/X0OHDtWVV16pQw45xNbjM7IKIK0MHz5cI0eO1D/+8Q9J3lHRBQsW6JRTTtHJJ5+sXbt2acOGDZo5c6ZGjRqlU045RUuXLlVbW5v/GM8884zGjh2rESNG6Prrr9eePXv8v1uwYIEWLFjg//lXv/qVTj/9dI0YMUITJ07U22+/rXXr1unmm29WQ0ODRowYoc2bN6utrU333nuvxo4dq2OPPVbTp0/X559/7j/OJ598oilTpmjEiBEaP368v//BnH/++fr3v/+t//u//wu4ffXq1frWt76l0tJSvfLKKzr33HN13HHH6aijjtIFF1wQNC1h3bp1Gj58eMBt3f/G3//+9xo/frxKSko0ceJEvfnmm/7frV+/XhMnTtQxxxyj008/Xbfffrs6OjpC9h2A8+y7777KzOw5vrlq1SqNHTtWZ5xxhlwul44++midc845evLJJyVJO3bs0IoVK3T55ZertrZWs2fP1pw5c/T+++/benyCVQBpo729XevWrVNdXZ1Gjx7tv/2tt97SqlWrtGbNGmVkZOjiiy/WwQcfrNdff11PPfWU3nrrLf80/9tvv61bb71VlZWVWr9+vY466ij97W9/C/p4VVVVevDBB7Vo0SLV19frvPPO0+WXX67hw4dr4cKFKi4u1nvvvachQ4Zo6dKleu211/T444/rjTfe0FFHHaVLLrlEra2tam9v12WXXaaDDz5YdXV1uueee/THP/4x5N95wAEHaMyYMfrf//1f/20ej0e//e1vdeGFF2rTpk26+uqrNWPGDL399tt67bXXZJqmHnjgAdvP6Z///GfdfPPNuummm/TOO+/oyiuv1JVXXql//etfkqT58+drypQpevfdd/XYY4/phRde0J/+9CfbjwPAeTZu3KiXX35ZxxxzjP/fb37zGzU2NkqSsrOzdfbZZ2vEiBHKzMzUGWecoeOOO04vvviircchWAWQ0hYuXOj/ED3uuON02223aerUqbrgggv8bU466SQNGTJE++yzj1577TW1tbVp7ty5ysnJUVFRka6++mr/SMGaNWv8H7iZmZk6//zzddhhhwV97Orqak2ePFkjRoxQRkaGfvzjH2vlypXKzc0NaGeaplatWqW5c+fqgAMOUE5OjmbPnq329na99tpreu+999TY2Kj58+crJydHBx98sKZOnRr2777wwgu1du1a7dq1S5L0xhtvaNeuXRo/frwGDhyo3//+9zr11FO1a9cubdq0SYWFhdq8ebPt5/eJJ57Qeeedp5EjR8rlcumUU07RqaeeqlWrVkmScnJytHbtWr366qsqKCjQn//8Z/2///f/bD8OAOcZOnSoysvL9e677/r/vfjii3r00UclSd/+9rcDZqUkye12206BImcVQEq7+eabA3JWg9lvv/38/79x40Zt3bpVI0eO9N9mmqba29vV1NSkzZs36/DDDw+4/wEHHBD0uF999ZWKi4sDbjv66KN7tNu6dat2796tq6++WhkZnWMI7e3t2rhxo9ra2lRYWBgQ5EZaoHD88cerqKhINTU1Ovfcc/XUU09p8uTJys3NlWmaqqmp0apVq2QYhg455BDt2rUr6DRfJBs3btQ777yjp59+2n+b2+1WaWmpJG8axH333aeFCxfqq6++0oknnqhbbrlFQ4cOtf1YAJxl0qRJmjp1qs444wwdf/zx2rBhg2bMmKFTTjlFP/3pT3Xeeefptttu04knnqjS0lK9/PLLWrdunebOnWvrcQhWAaQ9wzD8/z906FAdeOCBeuGFF/y37dq1S01NTRo4cKCGDh2q//73vwH337Rpkw4++OAexy0qKvJPh/ksXbpUEyZMCLitsLBQOTk5Wrlypb7//e/7b//00081ZMgQffjhh9q6dauam5uVn5/vf8xIfvKTn+iZZ57RmDFjVFtbq4ULF0qS1q5dqyeeeEJPP/20vvnNb0qSbrvtNv3zn//scQyXyyVJamtrU3Z2tiRp27ZtKiws9D9fP/rRjzRjxgz/fRoaGpSbm6vW1lb9+9//1i233KLMzEz95z//UUVFhe644w4tW7YsYv8BONtRRx2le+65R/fcc4+uvvpq9evXT2VlZf5g9Oyzz1ZGRoZ+/vOf64svvtD++++vpUuX9rjgj4Q0AADo4pRTTlFzc7OWL1+utrY2ff3117r++us1Z84cGYahs88+W3/84x/16quvqqOjQ9XV1SEXC0ycOFG//e1v9de//lUej0fPPvusnnzySX9wumfPHnV0dCgjI0OTJk3SkiVLtGnTJnk8HlVXV6usrEyff/65RowYoW9961uqrKzUnj179Pnnn2vlypUR/5by8nJ9/vnn+sUvfqHTTjvNP5q5c+dOZWRk+EdZX3/9dT333HNqb2/vcYwDDzxQmZmZ+v3vfy/Jm99bV1fn//0555yjX//61/66iX/72980ceJE1dTUyDAMzZ07VytXrlRHR4d/kYYv0AWQfD7++GONGjXK//PJJ5+sqqoq1dfX680339SCBQv8F7aS93Pod7/7nd577z3V1NTo9NNPt/2YjKwCQBf9+/fX448/rjvvvFPLly+Xx+PRqFGj9NBDD0mSSkpKtGjRIt15552aM2eOSktLAxZrdTV+/Hh9/fXXmjdvnr766it95zvf0S9/+UsNHDhQI0eO1KBBgzRy5EitWrVK119/ve677z6df/752r59uw444AAtW7bMnw/76KOP6qabbtLxxx+vwYMHa+zYsXrppZfC/i15eXmaOHGifvWrX+mpp57y315eXq76+nqdeeaZcrlcGjZsmC666CI9+eSTPfLL9ttvP/3sZz/Tgw8+qNtuu02lpaWaOHGivwLCD37wA+3evVs/+9nP1NDQoIKCAl188cWaMmWKDMPQQw89pLvuukuPPPKIXC6XTjrpJF133XVRnx8A6ccw41HoDwAAAIgB0gAAAADgWASrAAAAcCyCVQAAADgWwSoAAAAci2AVAAAAjkWwCgAAAMciWAUAAIBjEawCAADAsQhWAQAA4FgEqwAAAHAsglUAAAA41v8HCQyeehfOsEQAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Calculate residuals\n", + "residuals = y_test_original - y_pred\n", + "\n", + "# Plot residuals vs predicted values\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_pred, residuals, color='blue')\n", + "plt.title('Residuals Plot')\n", + "plt.xlabel('Predicted Values')\n", + "plt.ylabel('Residuals')\n", + "plt.axhline(y=0, color='red', linestyle='--')\n", + "plt.grid(True)\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# REGRESSION RESULTS" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "From all the models observed,We can see the positive correlation between the house prices and all other features except the year built which indicates a negative correlation.\n", + "\n", + "Polynomial Regression is the preferred model beacuse from the evaluation it has the highest R-squared value of 0.73\n", + "\n", + "The features below impact price such that an increase will cause an increase in the price of the property. 'bedrooms','bathrooms', 'sqft_living','floors', 'waterfront','view''condition', 'grade', 'sqft_above','sqft_basement', 'yr_renovated', 'sqft_living15','renovated', 'basement'." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Assumptions\n", + "\n", + "Linearity: The relationship between the independent variables (predictors) and the dependent variable (response) is linear. This means that a change in the independent variable corresponds to a proportional change in the dependent variable.\n", + "\n", + "Independence of errors: The errors (residuals) from the regression model should be independent of each other. In other words, the residual for one observation should not predict the residual for another observation.\n", + "\n", + "Normality of errors: The errors are normally distributed. This implies that the residuals should follow a normal distribution with a mean of zero.\n", + "\n", + "No perfect multicollinearity: There should be no perfect linear relationship between the independent variables. In other words, no independent variable should be a perfect linear combination of other independent variables." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Limitations\n", + "Despite its effectiveness in predicting property prices, the model has several limitations that need to be addressed:\n", + "\n", + "Limited Property Characteristics: The dataset may lack comprehensive property-based characteristics, potentially limiting the model's ability to capture the full range of factors influencing housing prices.\n", + "\n", + "\n", + "Multicollinearity Concerns: The presence of correlated predictors, such as square footage and number of bedrooms, can introduce multicollinearity issues. This makes it difficult to discern the individual impact of each feature accurately, potentially affecting the model's reliability.\n", + "\n", + "Assumption Violations: Polynomial regression relies on the assumption of linearity between predictors and the target variable. However, in reality, this assumption may not always hold true, leading to biased estimates and less dependable predictions.Also heteroscedasticity was present.\n", + "\n", + "Overfitting Risk: Polynomial regression models, especially those with high degrees, are prone to overfitting. This occurs when the model fits the training data too closely, capturing noise rather than underlying patterns. As a result, the model may struggle to generalize well to unseen data, impacting its predictive performance." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Recommedations\n", + "# Statistical recommedations.\n", + "To mitigate multicollinearity, strategies such as feature selection, principal component analysis (PCA), or regularization methods like ridge regression or Lasso regression can be employed. These techniques prioritize essential predictors and enhance the model's interpretability while stabilizing it against multicollinearity.\n", + "\n", + "\n", + "\n", + "Before opting for polynomial regression, it's essential to validate the assumption of linearity between predictors and the target variable. If this assumption doesn't hold, alternative regression techniques such as generalized additive models (GAMs) or spline regression should be considered to better capture intricate relationships.\n", + "\n", + "\n", + "Preventing heteroscedasticity, or addressing it if it's present, is crucial for ensuring the reliability of linear regression analysis\n", + "# Recommedation to real estate clients:Home owners and investors.\n", + "\n", + "\n", + "1.Invest in Larger Properties: Investors seeking maximum returns should focus on larger houses, as there's a positive correlation between total square footage and price. Such properties have the potential for higher profits upon resale or rental.\n", + "\n", + "\n", + "2.Upgrade Existing Properties: Homeowners can increase their property's value by investing in upgrades that increase square footage, such as adding extra rooms or expanding living spaces.\n", + "\n", + "\n", + "3.Optimize Bedroom and Bathroom Ratios: It's essential to find the right balance between bedrooms and bathrooms to maximize property value. Consulting with real estate professionals can help determine the optimal ratio based on market trends and buyer preferences.\n", + "\n", + "\n", + "4.Focus on Quality Over Quantity: Prioritize quality improvements that enhance functionality and aesthetics, such as renovating bathrooms with modern fixtures or upgrading kitchen appliances, to add perceived value to the property.\n", + "\n", + "\n", + "5.Highlight Features in Listings: Emphasize the number of bedrooms and bathrooms in property listings to attract buyers who prioritize space and convenience. Highlight unique features that add versatility to the property.\n", + "\n", + "\n", + "6.Differentiate Marketing Strategies: Tailor marketing strategies based on property condition and grade ratings. Highlight the benefits of higher-grade properties to attract premium buyers, while emphasizing renovation potential for properties with lower condition ratings.\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# CONCLUSION\n", + "\n", + "Property Size Matters: There is a clear positive correlation between the size of a property, indicated by total square footage, and its price. Investing in larger properties can potentially yield higher returns for investors and increase market value for homeowners.\n", + "\n", + "\n", + "Strategic Upgrades Add Value: Upgrading existing properties with strategic renovations and expansions, particularly those that increase square footage, can enhance their market value. Quality improvements that improve functionality and aesthetics are key to maximizing property value.\n", + "\n", + "\n", + "Balance is Key: While adding extra bedrooms and bathrooms can increase a property's price, there's a point of diminishing returns. It's important to strike a balance between quantity and quality, optimizing the bedroom-to-bathroom ratio to align with market trends and buyer preferences.\n", + "\n", + "\n", + "Marketing Differentiation is Essential: Tailoring marketing strategies based on property condition and grade ratings is crucial. Highlighting the unique features and benefits of higher-grade properties can attract premium buyers, while emphasizing renovation potential for properties with lower ratings can appeal to savvy investors.\n" ] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -40,9 +5179,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.4" + "version": "3.11.7" } }, "nbformat": 4, - "nbformat_minor": 2 + "nbformat_minor": 4 }