From fa904e8936704c8c8ecdb4c2125a2ddf9d60b534 Mon Sep 17 00:00:00 2001 From: Jeremy Waiguru Date: Thu, 25 Apr 2024 22:39:50 -0700 Subject: [PATCH 1/9] First commit --- student.ipynb | 416 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 407 insertions(+), 9 deletions(-) diff --git a/student.ipynb b/student.ipynb index d3bb34af..dcddc2f7 100644 --- a/student.ipynb +++ b/student.ipynb @@ -8,27 +8,425 @@ "\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 pace: full time\n", + "* Scheduled project review date/time: N/A\n", + "* Instructor name: Maryanne Mwikali\n", + "* Blog post URL: N/A\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Data\n", + "We have been provided with a dataset with house sale prices in King County, Washington State, USA from 2014 to 2015 to use for this project.\n", + "\n", + "A dataset has been provided and can be found in the kc_house_data.csv file in this repository.\n", + "\n", + "The column names and descriptions as provided can be found in the column_names.md file in this repository. We have explained them here for convenience.\n", + "\n", + "### Column Names and descriptions for Kings County Data Set\n", + "\n", + "id - Unique identifier for a house\n", + "date - Date house was sold\n", + "price - Sale price (prediction target)\n", + "bedrooms - Number of bedrooms\n", + "bathrooms - Number of bathrooms\n", + "sqft_living - Square footage of living space in the home\n", + "sqft_lot - Square footage of the lot\n", + "floors - Number of floors (levels) in house\n", + "waterfront - Whether the house is on a waterfront\n", + "view - Quality of view from house\n", + "condition - How good the overall condition of the house is.\n", + "grade - Overall grade of the house. Related to the construction and design of the house.\n", + "sqft_above - Square footage of house apart from basement\n", + "sqft_basement - Square footage of the basement\n", + "yr_built - Year when house was built\n", + "yr_renovated - Year when house was renovated\n", + "zipcode - ZIP Code used by the United States Postal Service\n", + "lat - Latitude coordinate\n", + "long - Longitude coordinate\n", + "sqft_living15 - The square footage of interior housing living space for the nearest 15 neighbors\n", + "sqft_lot15 - The square footage of the land lots of the nearest 15 neighbors" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "# import the necessary libraries\n", + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "import statsmodels.formula.api as sfm\n", + "import statsmodels.api as sm\n", + "import scipy.stats as stats\n", + "%matplotlib inline\n", + "\n", + "import warnings\n", + "warnings.filterwarnings('ignore')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### loading dataset" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "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_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": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# loading the data and previewing the dataframe\n", + "df = pd.read_csv('data/kc_house_data.csv')\n", + "df.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Data Preparation\n", + "In this section, we shall be preparing the data for further processing and modelling\n", + "\n", + "### Investigate data types" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, + "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" + ] + } + ], + "source": [ + "# summary of the data\n", + "df.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We conclude that ;\n", + "\n", + "date column should be changed to DateTime.\n", + "\n", + "sqft_basement column should be changed to float\n", + "\n", + "waterfront, view, condition, and grade will remain unchanged for now because they contain text\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ - "# Your code here - remember to use markdown cells for comments as well!" + "# function to change data type to datetime\n", + "def change_to_datetime(df, col):\n", + " ''' Changes column to DateTime object'''\n", + " df[col] = pd.to_datetime(df[col])\n", + " return df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "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 datetime64[ns]\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: datetime64[ns](1), float64(6), int64(9), object(5)\n", + "memory usage: 3.5+ MB\n" + ] + } + ], + "source": [ + "# changing date column type to DateTime\n", + "change_to_datetime(df, 'date')" ] } ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python (learn-env)", "language": "python", - "name": "python3" + "name": "learn-env" }, "language_info": { "codemirror_mode": { @@ -40,7 +438,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.4" + "version": "3.11.5" } }, "nbformat": 4, From cc481936fe8c6b254c4aaa5057e43de9579ac29b Mon Sep 17 00:00:00 2001 From: Jeremy Waiguru Date: Thu, 25 Apr 2024 22:45:13 -0700 Subject: [PATCH 2/9] second commit --- student.ipynb | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/student.ipynb b/student.ipynb index dcddc2f7..bcfd2947 100644 --- a/student.ipynb +++ b/student.ipynb @@ -420,6 +420,86 @@ "# changing date column type to DateTime\n", "change_to_datetime(df, 'date')" ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['id', 'date', 'price', 'bedrooms', 'bathrooms', 'sqft_living',\n", + " 'sqft_lot', 'floors', 'waterfront', 'view', 'condition', 'grade',\n", + " 'sqft_above', 'sqft_basement', 'yr_built', 'yr_renovated', 'zipcode',\n", + " 'lat', 'long', 'sqft_living15', 'sqft_lot15'],\n", + " dtype='object')" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# checking column names\n", + "df.columns" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "id 0\n", + "date 0\n", + "price 0\n", + "bedrooms 0\n", + "bathrooms 0\n", + "sqft_living 0\n", + "sqft_lot 0\n", + "floors 0\n", + "waterfront 2376\n", + "view 63\n", + "condition 0\n", + "grade 0\n", + "sqft_above 0\n", + "sqft_basement 0\n", + "yr_built 0\n", + "yr_renovated 3842\n", + "zipcode 0\n", + "lat 0\n", + "long 0\n", + "sqft_living15 0\n", + "sqft_lot15 0\n", + "dtype: int64" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# function to check null values\n", + "def check_null(df):\n", + " return df.isna().sum()\n", + "\n", + "# checking for null values in the data\n", + "check_null(df)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "There are missing values in three columns.\n", + "\n", + "Depending on the ratio of missing values, we will decide on what approach to take in dealing with them" + ] } ], "metadata": { From 7b6442c72d8a42c2d671ca0cb5c7de8818462c4d Mon Sep 17 00:00:00 2001 From: Jeremy Waiguru Date: Thu, 25 Apr 2024 22:50:00 -0700 Subject: [PATCH 3/9] 3rd commit --- student.ipynb | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/student.ipynb b/student.ipynb index bcfd2947..29fafb51 100644 --- a/student.ipynb +++ b/student.ipynb @@ -500,6 +500,33 @@ "\n", "Depending on the ratio of missing values, we will decide on what approach to take in dealing with them" ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "There is 11.00152798999861 percent of values missing in waterfront.\n", + "There is 0.29170718155299347 percent of values missing in view.\n", + "There is 17.78950780200954 percent of values missing in yr_renovated.\n" + ] + } + ], + "source": [ + "# function to calculate percentage of null values\n", + "def miss_percent(df,col):\n", + " miss = ((df[col].isna().sum()) / len(df[col])) * 100\n", + " return print(f'There is {miss} percent of values missing in {col}.')\n", + "\n", + "# checking percentage of missing values \n", + "miss_percent(df,'waterfront')\n", + "miss_percent(df, 'view')\n", + "miss_percent(df, 'yr_renovated')" + ] } ], "metadata": { From 22ad8c7bb0703589a9e98fcbb1a39bcb96b6e051 Mon Sep 17 00:00:00 2001 From: Jeremy Waiguru Date: Fri, 26 Apr 2024 10:28:11 -0700 Subject: [PATCH 4/9] 4th commit --- student.ipynb | 563 ++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 429 insertions(+), 134 deletions(-) diff --git a/student.ipynb b/student.ipynb index 29fafb51..6b2cd0b9 100644 --- a/student.ipynb +++ b/student.ipynb @@ -6,11 +6,20 @@ "source": [ "## Final Project Submission\n", "\n", - "Please fill out:\n", - "* Student name: \n", + "* Student names:\n", + "\n", + "Jeremiah Waiguru\n", + "\n", + "Olive Muloma\n", + "\n", + "Troye Gilbert\n", + "\n", + "Josephine Maro\n", + "\n", + "\n", "* Student pace: full time\n", "* Scheduled project review date/time: N/A\n", - "* Instructor name: Maryanne Mwikali\n", + "* Instructor name: Maryann Mwikali\n", "* Blog post URL: N/A\n" ] }, @@ -79,7 +88,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -103,7 +112,6 @@ " \n", " \n", " \n", - " id\n", " date\n", " price\n", " bedrooms\n", @@ -113,7 +121,7 @@ " floors\n", " waterfront\n", " view\n", - " ...\n", + " condition\n", " grade\n", " sqft_above\n", " sqft_basement\n", @@ -125,11 +133,33 @@ " sqft_living15\n", " sqft_lot15\n", " \n", + " \n", + " id\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", " \n", " \n", " \n", - " 0\n", - " 7129300520\n", + " 7129300520\n", " 10/13/2014\n", " 221900.0\n", " 3\n", @@ -139,7 +169,7 @@ " 1.0\n", " NaN\n", " NONE\n", - " ...\n", + " Average\n", " 7 Average\n", " 1180\n", " 0.0\n", @@ -152,8 +182,7 @@ " 5650\n", " \n", " \n", - " 1\n", - " 6414100192\n", + " 6414100192\n", " 12/9/2014\n", " 538000.0\n", " 3\n", @@ -163,7 +192,7 @@ " 2.0\n", " NO\n", " NONE\n", - " ...\n", + " Average\n", " 7 Average\n", " 2170\n", " 400.0\n", @@ -176,8 +205,7 @@ " 7639\n", " \n", " \n", - " 2\n", - " 5631500400\n", + " 5631500400\n", " 2/25/2015\n", " 180000.0\n", " 2\n", @@ -187,7 +215,7 @@ " 1.0\n", " NO\n", " NONE\n", - " ...\n", + " Average\n", " 6 Low Average\n", " 770\n", " 0.0\n", @@ -200,8 +228,7 @@ " 8062\n", " \n", " \n", - " 3\n", - " 2487200875\n", + " 2487200875\n", " 12/9/2014\n", " 604000.0\n", " 4\n", @@ -211,7 +238,7 @@ " 1.0\n", " NO\n", " NONE\n", - " ...\n", + " Very Good\n", " 7 Average\n", " 1050\n", " 910.0\n", @@ -224,8 +251,7 @@ " 5000\n", " \n", " \n", - " 4\n", - " 1954400510\n", + " 1954400510\n", " 2/18/2015\n", " 510000.0\n", " 3\n", @@ -235,7 +261,7 @@ " 1.0\n", " NO\n", " NONE\n", - " ...\n", + " Average\n", " 8 Good\n", " 1680\n", " 0.0\n", @@ -249,49 +275,50 @@ " \n", " \n", "\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", + " date price bedrooms bathrooms sqft_living sqft_lot \\\n", + "id \n", + "7129300520 10/13/2014 221900.0 3 1.00 1180 5650 \n", + "6414100192 12/9/2014 538000.0 3 2.25 2570 7242 \n", + "5631500400 2/25/2015 180000.0 2 1.00 770 10000 \n", + "2487200875 12/9/2014 604000.0 4 3.00 1960 5000 \n", + "1954400510 2/18/2015 510000.0 3 2.00 1680 8080 \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", + " floors waterfront view condition grade sqft_above \\\n", + "id \n", + "7129300520 1.0 NaN NONE Average 7 Average 1180 \n", + "6414100192 2.0 NO NONE Average 7 Average 2170 \n", + "5631500400 1.0 NO NONE Average 6 Low Average 770 \n", + "2487200875 1.0 NO NONE Very Good 7 Average 1050 \n", + "1954400510 1.0 NO NONE Average 8 Good 1680 \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", + " sqft_basement yr_built yr_renovated zipcode lat long \\\n", + "id \n", + "7129300520 0.0 1955 0.0 98178 47.5112 -122.257 \n", + "6414100192 400.0 1951 1991.0 98125 47.7210 -122.319 \n", + "5631500400 0.0 1933 NaN 98028 47.7379 -122.233 \n", + "2487200875 910.0 1965 0.0 98136 47.5208 -122.393 \n", + "1954400510 0.0 1987 0.0 98074 47.6168 -122.045 \n", "\n", - "[5 rows x 21 columns]" + " sqft_living15 sqft_lot15 \n", + "id \n", + "7129300520 1340 5650 \n", + "6414100192 1690 7639 \n", + "5631500400 2720 8062 \n", + "2487200875 1360 5000 \n", + "1954400510 1800 7503 " ] }, - "execution_count": 4, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# loading the data and previewing the dataframe\n", - "df = pd.read_csv('data/kc_house_data.csv')\n", + "df = pd.read_csv('data/kc_house_data.csv', index_col=0)\n", "df.head()" ] }, @@ -307,78 +334,253 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 17, "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/plain": [ + "(21597, 20)" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ - "# summary of the data\n", - "df.info()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "We conclude that ;\n", - "\n", - "date column should be changed to DateTime.\n", - "\n", - "sqft_basement column should be changed to float\n", - "\n", - "waterfront, view, condition, and grade will remain unchanged for now because they contain text\n" + "# shape of our data\n", + "df.shape" ] }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 16, "metadata": {}, - "outputs": [], + "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", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorssqft_aboveyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15
count2.159700e+0421597.00000021597.00000021597.0000002.159700e+0421597.00000021597.00000021597.00000017755.00000021597.00000021597.00000021597.00000021597.00000021597.000000
mean5.402966e+053.3732002.1158262080.3218501.509941e+041.4940961788.5968421970.99967683.63677898077.95184547.560093-122.2139821986.62031812758.283512
std3.673681e+050.9262990.768984918.1061254.141264e+040.539683827.75976129.375234399.94641453.5130720.1385520.140724685.23047227274.441950
min7.800000e+041.0000000.500000370.0000005.200000e+021.000000370.0000001900.0000000.00000098001.00000047.155900-122.519000399.000000651.000000
25%3.220000e+053.0000001.7500001430.0000005.040000e+031.0000001190.0000001951.0000000.00000098033.00000047.471100-122.3280001490.0000005100.000000
50%4.500000e+053.0000002.2500001910.0000007.618000e+031.5000001560.0000001975.0000000.00000098065.00000047.571800-122.2310001840.0000007620.000000
75%6.450000e+054.0000002.5000002550.0000001.068500e+042.0000002210.0000001997.0000000.00000098118.00000047.678000-122.1250002360.00000010083.000000
max7.700000e+0633.0000008.00000013540.0000001.651359e+063.5000009410.0000002015.0000002015.00000098199.00000047.777600-121.3150006210.000000871200.000000
\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot \\\n", + "count 2.159700e+04 21597.000000 21597.000000 21597.000000 2.159700e+04 \n", + "mean 5.402966e+05 3.373200 2.115826 2080.321850 1.509941e+04 \n", + "std 3.673681e+05 0.926299 0.768984 918.106125 4.141264e+04 \n", + "min 7.800000e+04 1.000000 0.500000 370.000000 5.200000e+02 \n", + "25% 3.220000e+05 3.000000 1.750000 1430.000000 5.040000e+03 \n", + "50% 4.500000e+05 3.000000 2.250000 1910.000000 7.618000e+03 \n", + "75% 6.450000e+05 4.000000 2.500000 2550.000000 1.068500e+04 \n", + "max 7.700000e+06 33.000000 8.000000 13540.000000 1.651359e+06 \n", + "\n", + " floors sqft_above yr_built yr_renovated zipcode \\\n", + "count 21597.000000 21597.000000 21597.000000 17755.000000 21597.000000 \n", + "mean 1.494096 1788.596842 1970.999676 83.636778 98077.951845 \n", + "std 0.539683 827.759761 29.375234 399.946414 53.513072 \n", + "min 1.000000 370.000000 1900.000000 0.000000 98001.000000 \n", + "25% 1.000000 1190.000000 1951.000000 0.000000 98033.000000 \n", + "50% 1.500000 1560.000000 1975.000000 0.000000 98065.000000 \n", + "75% 2.000000 2210.000000 1997.000000 0.000000 98118.000000 \n", + "max 3.500000 9410.000000 2015.000000 2015.000000 98199.000000 \n", + "\n", + " lat long sqft_living15 sqft_lot15 \n", + "count 21597.000000 21597.000000 21597.000000 21597.000000 \n", + "mean 47.560093 -122.213982 1986.620318 12758.283512 \n", + "std 0.138552 0.140724 685.230472 27274.441950 \n", + "min 47.155900 -122.519000 399.000000 651.000000 \n", + "25% 47.471100 -122.328000 1490.000000 5100.000000 \n", + "50% 47.571800 -122.231000 1840.000000 7620.000000 \n", + "75% 47.678000 -122.125000 2360.000000 10083.000000 \n", + "max 47.777600 -121.315000 6210.000000 871200.000000 " + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# function to change data type to datetime\n", - "def change_to_datetime(df, col):\n", - " ''' Changes column to DateTime object'''\n", - " df[col] = pd.to_datetime(df[col])\n", - " return df.info()" + "# Describing the data\n", + "df.describe()" ] }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 15, "metadata": {}, "outputs": [ { @@ -386,39 +588,47 @@ "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 datetime64[ns]\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: datetime64[ns](1), float64(6), int64(9), object(5)\n", + "Index: 21597 entries, 7129300520 to 1523300157\n", + "Data columns (total 20 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 date 21597 non-null object \n", + " 1 price 21597 non-null float64\n", + " 2 bedrooms 21597 non-null int64 \n", + " 3 bathrooms 21597 non-null float64\n", + " 4 sqft_living 21597 non-null int64 \n", + " 5 sqft_lot 21597 non-null int64 \n", + " 6 floors 21597 non-null float64\n", + " 7 waterfront 19221 non-null object \n", + " 8 view 21534 non-null object \n", + " 9 condition 21597 non-null object \n", + " 10 grade 21597 non-null object \n", + " 11 sqft_above 21597 non-null int64 \n", + " 12 sqft_basement 21597 non-null object \n", + " 13 yr_built 21597 non-null int64 \n", + " 14 yr_renovated 17755 non-null float64\n", + " 15 zipcode 21597 non-null int64 \n", + " 16 lat 21597 non-null float64\n", + " 17 long 21597 non-null float64\n", + " 18 sqft_living15 21597 non-null int64 \n", + " 19 sqft_lot15 21597 non-null int64 \n", + "dtypes: float64(6), int64(8), object(6)\n", "memory usage: 3.5+ MB\n" ] } ], "source": [ - "# changing date column type to DateTime\n", - "change_to_datetime(df, 'date')" + "# summary of the data\n", + "df.info()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The dataset contains 21,597 entries and 20 columns\n", + "\n", + "Some columns like 'waterfront', 'view', 'yr_renovated' have missing values\n" ] }, { @@ -501,6 +711,13 @@ "Depending on the ratio of missing values, we will decide on what approach to take in dealing with them" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Dealing with missing values\n" + ] + }, { "cell_type": "code", "execution_count": 10, @@ -527,6 +744,84 @@ "miss_percent(df, 'view')\n", "miss_percent(df, 'yr_renovated')" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "The threshold on how to deal with missing values commonly used is 50% and also depends on the specific column. The percentages of missing values are very low for the specific columns so we can replace.\n", + "\n", + "Checking the year renovated column we may assume the missing value is because the house was never renovated, maybe the house did not have a view or a waterfront also for the other two columns hence we can Fill them with zeros.\n", + "\n", + "Since the missing values in the 3 columns are categorical and are a small percentage of the columns, replacing them with mode won`t skew the data nor give false conclusions" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "There is 0.00% of values missing in waterfront.\n", + "There is 0.00% of values missing in view.\n", + "There is 0.00% of values missing in yr_renovated.\n" + ] + } + ], + "source": [ + "def miss_percent(df, col, fill_value=None):\n", + " miss = ((df[col].isna().sum()) / len(df[col])) * 100\n", + " if fill_value is not None:\n", + " df[col].fillna(fill_value, inplace=True)\n", + " return miss\n", + "\n", + "# checking percentage of missing values and filling missing values with the mode\n", + "fill_values = {'waterfront': df['waterfront'].mode()[0], \n", + " 'view': df['view'].mode()[0], \n", + " 'yr_renovated': df['yr_renovated'].mode()[0]}\n", + "\n", + "for col in fill_values:\n", + " missing_percent = miss_percent(df, col, fill_value=fill_values[col])\n", + " print(f'There is {missing_percent:.2f}% of values missing in {col}.')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### check duplicates" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "duplicates = df.duplicated().sum()\n", + "duplicates" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Choosing predictors to be used in modelling" + ] } ], "metadata": { From cf3e679811fa76d9a4e4b8860183606308791552 Mon Sep 17 00:00:00 2001 From: Jeremy Waiguru Date: Fri, 26 Apr 2024 11:44:26 -0700 Subject: [PATCH 5/9] 5th commit --- student.ipynb | 306 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 268 insertions(+), 38 deletions(-) diff --git a/student.ipynb b/student.ipynb index 6b2cd0b9..11c05982 100644 --- a/student.ipynb +++ b/student.ipynb @@ -32,31 +32,8 @@ "\n", "A dataset has been provided and can be found in the kc_house_data.csv file in this repository.\n", "\n", - "The column names and descriptions as provided can be found in the column_names.md file in this repository. We have explained them here for convenience.\n", - "\n", - "### Column Names and descriptions for Kings County Data Set\n", - "\n", - "id - Unique identifier for a house\n", - "date - Date house was sold\n", - "price - Sale price (prediction target)\n", - "bedrooms - Number of bedrooms\n", - "bathrooms - Number of bathrooms\n", - "sqft_living - Square footage of living space in the home\n", - "sqft_lot - Square footage of the lot\n", - "floors - Number of floors (levels) in house\n", - "waterfront - Whether the house is on a waterfront\n", - "view - Quality of view from house\n", - "condition - How good the overall condition of the house is.\n", - "grade - Overall grade of the house. Related to the construction and design of the house.\n", - "sqft_above - Square footage of house apart from basement\n", - "sqft_basement - Square footage of the basement\n", - "yr_built - Year when house was built\n", - "yr_renovated - Year when house was renovated\n", - "zipcode - ZIP Code used by the United States Postal Service\n", - "lat - Latitude coordinate\n", - "long - Longitude coordinate\n", - "sqft_living15 - The square footage of interior housing living space for the nearest 15 neighbors\n", - "sqft_lot15 - The square footage of the land lots of the nearest 15 neighbors" + "The column names and descriptions as provided can be found in the column_names.md file in this repository.\n", + "\n" ] }, { @@ -631,22 +608,282 @@ "Some columns like 'waterfront', 'view', 'yr_renovated' have missing values\n" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### loading the column.md dataset" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [], + "source": [ + "with open('data/column_names.md', 'r') as file:\n", + " md_lines = file.readlines()\n", + "\n", + "df1 = pd.DataFrame({'Text': md_lines})\n", + "\n", + "pd.set_option('display.max_colwidth',None)\n", + "\n", + "# df1" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### cleaning the column_md dataset" + ] + }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 30, + "metadata": {}, + "outputs": [], + "source": [ + "df1[['Column name', 'Descriptions']] = df1['Text'].str.split('-', n=1,expand=True)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### drop the original 'text' column" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": {}, + "outputs": [], + "source": [ + "df1.drop(columns=['Text'], inplace=True)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### remove rows where 'descriptions' columns contains 'None'" + ] + }, + { + "cell_type": "code", + "execution_count": 32, "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 nameDescriptions
1* `id`Unique identifier for a house\\n
2* `date`Date house was sold\\n
3* `price`Sale price (prediction target)\\n
4* `bedrooms`Number of bedrooms\\n
5* `bathrooms`Number of bathrooms\\n
6* `sqft_living`Square footage of living space in the home\\n
7* `sqft_lot`Square footage of the lot\\n
8* `floors`Number of floors (levels) in house\\n
9* `waterfront`Whether the house is on a waterfront\\n
11* `view`Quality of view from house\\n
13* `condition`How good the overall condition of the house is. Related to maintenance of house.\\n
15* `grade`Overall grade of the house. Related to the construction and design of the house.\\n
17* `sqft_above`Square footage of house apart from basement\\n
18* `sqft_basement`Square footage of the basement\\n
19* `yr_built`Year when house was built\\n
20* `yr_renovated`Year when house was renovated\\n
21* `zipcode`ZIP Code used by the United States Postal Service\\n
22* `lat`Latitude coordinate\\n
23* `long`Longitude coordinate\\n
24* `sqft_living15`The square footage of interior housing living space for the nearest 15 neighbors\\n
25* `sqft_lot15`The square footage of the land lots of the nearest 15 neighbors\\n
\n", + "
" + ], "text/plain": [ - "Index(['id', 'date', 'price', 'bedrooms', 'bathrooms', 'sqft_living',\n", - " 'sqft_lot', 'floors', 'waterfront', 'view', 'condition', 'grade',\n", - " 'sqft_above', 'sqft_basement', 'yr_built', 'yr_renovated', 'zipcode',\n", - " 'lat', 'long', 'sqft_living15', 'sqft_lot15'],\n", + " Column name \\\n", + "1 * `id` \n", + "2 * `date` \n", + "3 * `price` \n", + "4 * `bedrooms` \n", + "5 * `bathrooms` \n", + "6 * `sqft_living` \n", + "7 * `sqft_lot` \n", + "8 * `floors` \n", + "9 * `waterfront` \n", + "11 * `view` \n", + "13 * `condition` \n", + "15 * `grade` \n", + "17 * `sqft_above` \n", + "18 * `sqft_basement` \n", + "19 * `yr_built` \n", + "20 * `yr_renovated` \n", + "21 * `zipcode` \n", + "22 * `lat` \n", + "23 * `long` \n", + "24 * `sqft_living15` \n", + "25 * `sqft_lot15` \n", + "\n", + " Descriptions \n", + "1 Unique identifier for a house\\n \n", + "2 Date house was sold\\n \n", + "3 Sale price (prediction target)\\n \n", + "4 Number of bedrooms\\n \n", + "5 Number of bathrooms\\n \n", + "6 Square footage of living space in the home\\n \n", + "7 Square footage of the lot\\n \n", + "8 Number of floors (levels) in house\\n \n", + "9 Whether the house is on a waterfront\\n \n", + "11 Quality of view from house\\n \n", + "13 How good the overall condition of the house is. Related to maintenance of house.\\n \n", + "15 Overall grade of the house. Related to the construction and design of the house.\\n \n", + "17 Square footage of house apart from basement\\n \n", + "18 Square footage of the basement\\n \n", + "19 Year when house was built\\n \n", + "20 Year when house was renovated\\n \n", + "21 ZIP Code used by the United States Postal Service\\n \n", + "22 Latitude coordinate\\n \n", + "23 Longitude coordinate\\n \n", + "24 The square footage of interior housing living space for the nearest 15 neighbors\\n \n", + "25 The square footage of the land lots of the nearest 15 neighbors\\n " + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1 = df1[df1['Descriptions'].notna()]\n", + "df1" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['date', 'price', 'bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot',\n", + " 'floors', 'waterfront', 'view', 'condition', 'grade', 'sqft_above',\n", + " 'sqft_basement', 'yr_built', 'yr_renovated', 'zipcode', 'lat', 'long',\n", + " 'sqft_living15', 'sqft_lot15'],\n", " dtype='object')" ] }, - "execution_count": 8, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" } @@ -815,13 +1052,6 @@ "duplicates = df.duplicated().sum()\n", "duplicates" ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Choosing predictors to be used in modelling" - ] } ], "metadata": { From a8a1b09cc32d79cee9b5659a6ff1893860db197d Mon Sep 17 00:00:00 2001 From: Olive Mideva <67095878+olivemideva@users.noreply.github.com> Date: Fri, 26 Apr 2024 13:30:08 +0300 Subject: [PATCH 6/9] EDA( Visualization before modelling) --- student.ipynb | 194 +++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 167 insertions(+), 27 deletions(-) diff --git a/student.ipynb b/student.ipynb index 11c05982..a062b729 100644 --- a/student.ipynb +++ b/student.ipynb @@ -38,13 +38,14 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# import the necessary libraries\n", "import pandas as pd\n", "import numpy as np\n", + "import matplotlib as plt\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "import statsmodels.formula.api as sfm\n", @@ -65,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 2, "metadata": {}, "outputs": [ { @@ -288,7 +289,7 @@ "1954400510 1800 7503 " ] }, - "execution_count": 13, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -311,7 +312,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -320,7 +321,7 @@ "(21597, 20)" ] }, - "execution_count": 17, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -332,7 +333,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -545,7 +546,7 @@ "max 47.777600 -121.315000 6210.000000 871200.000000 " ] }, - "execution_count": 16, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -557,7 +558,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -565,7 +566,7 @@ "output_type": "stream", "text": [ "\n", - "Index: 21597 entries, 7129300520 to 1523300157\n", + "Int64Index: 21597 entries, 7129300520 to 1523300157\n", "Data columns (total 20 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", @@ -617,7 +618,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -640,7 +641,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -656,7 +657,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -672,7 +673,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -858,7 +859,7 @@ "25 The square footage of the land lots of the nearest 15 neighbors\\n " ] }, - "execution_count": 32, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -870,7 +871,7 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -883,7 +884,7 @@ " dtype='object')" ] }, - "execution_count": 33, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -895,13 +896,12 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "id 0\n", "date 0\n", "price 0\n", "bedrooms 0\n", @@ -925,7 +925,7 @@ "dtype: int64" ] }, - "execution_count": 9, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -957,7 +957,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -995,16 +995,16 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "There is 0.00% of values missing in waterfront.\n", - "There is 0.00% of values missing in view.\n", - "There is 0.00% of values missing in yr_renovated.\n" + "There is 11.00% of values missing in waterfront.\n", + "There is 0.29% of values missing in view.\n", + "There is 17.79% of values missing in yr_renovated.\n" ] } ], @@ -1034,7 +1034,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 14, "metadata": {}, "outputs": [ { @@ -1043,7 +1043,7 @@ "0" ] }, - "execution_count": 23, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -1052,6 +1052,146 @@ "duplicates = df.duplicated().sum()\n", "duplicates" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### EDA 1\n", + "\n", + "Exploratory data analysis, including visualizations like scatter plots, bar plots, and heatmaps, is essential before creating regression models. These analyses help understand variable relationships, identify influential predictors, validate model assumptions, and guide feature selection. Visual exploration ensures that subsequent regression models are well-informed, optimized, and interpretable. It also aids in interpreting results and effectively communicating insights, enhancing the overall quality and utility of regression analysis. Conducting thorough exploratory analysis before modeling is crucial for building reliable and actionable regression models." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "***1. Heatmap***\n", + "\n", + "The heatmap of correlations between price and features (bedrooms, bathrooms, sqft_living, sqft_lot) is essential for both linear and multilinear regression. It identifies influential predictors based on their relationships with the target variable (price). This helps prioritize predictors in linear models and detect multicollinearity in multilinear models, ensuring stable and interpretable models. Overall, the heatmap guides feature selection and model interpretation in regression analysis." + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(10, 6))\n", + "sns.heatmap(df[['price', 'bedrooms', 'bathrooms', 'sqft_living', 'sqft_lot']].corr(), annot=True, cmap='coolwarm')\n", + "plt.title('Correlation Heatmap')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "***2. Bar Graph***\n", + "\n", + "The bar plot of price by condition is essential for developing regression models. It identifies influential condition categories for predictor selection and aids in understanding price variations. This visualization guides preprocessing of categorical variables and validates predictor-target relationships. Overall, it informs feature selection, interpretation, and validation in regression modeling." + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(10, 6))\n", + "sns.barplot(x='condition', y='price', data=df, color='blue')\n", + "plt.title('Price Distribution by Condition')\n", + "plt.xlabel('Condition')\n", + "plt.ylabel('Price')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "***3. Scatter plot***\n", + "\n", + "The scatter plots of price against square footage of living space (`sqft_living`) and lot size (`sqft_lot`) provide insights for linear and multilinear regression models. They show how price relates to these predictors, helping assess linearity and identify outliers. Clear trends in these plots guide decisions on model complexity and feature engineering, essential for accurate regression analysis." + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(figsize=(12, 6))\n", + "plt.subplot(1, 2, 1)\n", + "sns.scatterplot(x='sqft_living', y='price', data=df)\n", + "plt.title('Price vs Sqft Living')\n", + "plt.subplot(1, 2, 2)\n", + "sns.scatterplot(x='sqft_lot', y='price', data=df)\n", + "plt.title('Price vs Sqft Lot')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### MODELLING" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "***1. Linear Regression model***\n", + "\n", + "We will pick **`sqft_living` - Square footage of living space in the home** to be used to create our linear regression model because it has the most correlation with the price and it has the most linear scatter plor hence a good candidate." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -1070,7 +1210,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.5" + "version": "3.8.5" } }, "nbformat": 4, From dae029ec0f12c4fe3e54f9ac6c6a8614c2f48ba8 Mon Sep 17 00:00:00 2001 From: Jeremy Waiguru Date: Sun, 28 Apr 2024 11:25:56 -0700 Subject: [PATCH 7/9] new commit --- student.ipynb | 212 +++++++++++++++++--------------------------------- 1 file changed, 71 insertions(+), 141 deletions(-) diff --git a/student.ipynb b/student.ipynb index a062b729..17d6f965 100644 --- a/student.ipynb +++ b/student.ipynb @@ -17,9 +17,9 @@ "Josephine Maro\n", "\n", "\n", - "* Student pace: full time\n", + "* Student pace: FULL TIME HYBRID\n", "* Scheduled project review date/time: N/A\n", - "* Instructor name: Maryann Mwikali\n", + "* Instructor name: MARYANN MWIKALI\n", "* Blog post URL: N/A\n" ] }, @@ -38,7 +38,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -66,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -256,40 +256,18 @@ "" ], "text/plain": [ - " date price bedrooms bathrooms sqft_living sqft_lot \\\n", - "id \n", - "7129300520 10/13/2014 221900.0 3 1.00 1180 5650 \n", - "6414100192 12/9/2014 538000.0 3 2.25 2570 7242 \n", - "5631500400 2/25/2015 180000.0 2 1.00 770 10000 \n", - "2487200875 12/9/2014 604000.0 4 3.00 1960 5000 \n", - "1954400510 2/18/2015 510000.0 3 2.00 1680 8080 \n", - "\n", - " floors waterfront view condition grade sqft_above \\\n", - "id \n", - "7129300520 1.0 NaN NONE Average 7 Average 1180 \n", - "6414100192 2.0 NO NONE Average 7 Average 2170 \n", - "5631500400 1.0 NO NONE Average 6 Low Average 770 \n", - "2487200875 1.0 NO NONE Very Good 7 Average 1050 \n", - "1954400510 1.0 NO NONE Average 8 Good 1680 \n", + " date price bedrooms ... long sqft_living15 sqft_lot15\n", + "id ... \n", + "7129300520 10/13/2014 221900.0 3 ... -122.257 1340 5650\n", + "6414100192 12/9/2014 538000.0 3 ... -122.319 1690 7639\n", + "5631500400 2/25/2015 180000.0 2 ... -122.233 2720 8062\n", + "2487200875 12/9/2014 604000.0 4 ... -122.393 1360 5000\n", + "1954400510 2/18/2015 510000.0 3 ... -122.045 1800 7503\n", "\n", - " sqft_basement yr_built yr_renovated zipcode lat long \\\n", - "id \n", - "7129300520 0.0 1955 0.0 98178 47.5112 -122.257 \n", - "6414100192 400.0 1951 1991.0 98125 47.7210 -122.319 \n", - "5631500400 0.0 1933 NaN 98028 47.7379 -122.233 \n", - "2487200875 910.0 1965 0.0 98136 47.5208 -122.393 \n", - "1954400510 0.0 1987 0.0 98074 47.6168 -122.045 \n", - "\n", - " sqft_living15 sqft_lot15 \n", - "id \n", - "7129300520 1340 5650 \n", - "6414100192 1690 7639 \n", - "5631500400 2720 8062 \n", - "2487200875 1360 5000 \n", - "1954400510 1800 7503 " + "[5 rows x 20 columns]" ] }, - "execution_count": 2, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -312,7 +290,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -321,7 +299,7 @@ "(21597, 20)" ] }, - "execution_count": 3, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -333,7 +311,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -515,38 +493,20 @@ "" ], "text/plain": [ - " price bedrooms bathrooms sqft_living sqft_lot \\\n", - "count 2.159700e+04 21597.000000 21597.000000 21597.000000 2.159700e+04 \n", - "mean 5.402966e+05 3.373200 2.115826 2080.321850 1.509941e+04 \n", - "std 3.673681e+05 0.926299 0.768984 918.106125 4.141264e+04 \n", - "min 7.800000e+04 1.000000 0.500000 370.000000 5.200000e+02 \n", - "25% 3.220000e+05 3.000000 1.750000 1430.000000 5.040000e+03 \n", - "50% 4.500000e+05 3.000000 2.250000 1910.000000 7.618000e+03 \n", - "75% 6.450000e+05 4.000000 2.500000 2550.000000 1.068500e+04 \n", - "max 7.700000e+06 33.000000 8.000000 13540.000000 1.651359e+06 \n", - "\n", - " floors sqft_above yr_built yr_renovated zipcode \\\n", - "count 21597.000000 21597.000000 21597.000000 17755.000000 21597.000000 \n", - "mean 1.494096 1788.596842 1970.999676 83.636778 98077.951845 \n", - "std 0.539683 827.759761 29.375234 399.946414 53.513072 \n", - "min 1.000000 370.000000 1900.000000 0.000000 98001.000000 \n", - "25% 1.000000 1190.000000 1951.000000 0.000000 98033.000000 \n", - "50% 1.500000 1560.000000 1975.000000 0.000000 98065.000000 \n", - "75% 2.000000 2210.000000 1997.000000 0.000000 98118.000000 \n", - "max 3.500000 9410.000000 2015.000000 2015.000000 98199.000000 \n", + " price bedrooms ... sqft_living15 sqft_lot15\n", + "count 2.159700e+04 21597.000000 ... 21597.000000 21597.000000\n", + "mean 5.402966e+05 3.373200 ... 1986.620318 12758.283512\n", + "std 3.673681e+05 0.926299 ... 685.230472 27274.441950\n", + "min 7.800000e+04 1.000000 ... 399.000000 651.000000\n", + "25% 3.220000e+05 3.000000 ... 1490.000000 5100.000000\n", + "50% 4.500000e+05 3.000000 ... 1840.000000 7620.000000\n", + "75% 6.450000e+05 4.000000 ... 2360.000000 10083.000000\n", + "max 7.700000e+06 33.000000 ... 6210.000000 871200.000000\n", "\n", - " lat long sqft_living15 sqft_lot15 \n", - "count 21597.000000 21597.000000 21597.000000 21597.000000 \n", - "mean 47.560093 -122.213982 1986.620318 12758.283512 \n", - "std 0.138552 0.140724 685.230472 27274.441950 \n", - "min 47.155900 -122.519000 399.000000 651.000000 \n", - "25% 47.471100 -122.328000 1490.000000 5100.000000 \n", - "50% 47.571800 -122.231000 1840.000000 7620.000000 \n", - "75% 47.678000 -122.125000 2360.000000 10083.000000 \n", - "max 47.777600 -121.315000 6210.000000 871200.000000 " + "[8 rows x 14 columns]" ] }, - "execution_count": 4, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -558,7 +518,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -566,7 +526,7 @@ "output_type": "stream", "text": [ "\n", - "Int64Index: 21597 entries, 7129300520 to 1523300157\n", + "Index: 21597 entries, 7129300520 to 1523300157\n", "Data columns (total 20 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", @@ -618,7 +578,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -641,7 +601,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -657,7 +617,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 10, "metadata": {}, "outputs": [], "source": [ @@ -673,7 +633,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -812,54 +772,31 @@ "" ], "text/plain": [ - " Column name \\\n", - "1 * `id` \n", - "2 * `date` \n", - "3 * `price` \n", - "4 * `bedrooms` \n", - "5 * `bathrooms` \n", - "6 * `sqft_living` \n", - "7 * `sqft_lot` \n", - "8 * `floors` \n", - "9 * `waterfront` \n", - "11 * `view` \n", - "13 * `condition` \n", - "15 * `grade` \n", - "17 * `sqft_above` \n", - "18 * `sqft_basement` \n", - "19 * `yr_built` \n", - "20 * `yr_renovated` \n", - "21 * `zipcode` \n", - "22 * `lat` \n", - "23 * `long` \n", - "24 * `sqft_living15` \n", - "25 * `sqft_lot15` \n", - "\n", - " Descriptions \n", - "1 Unique identifier for a house\\n \n", - "2 Date house was sold\\n \n", - "3 Sale price (prediction target)\\n \n", - "4 Number of bedrooms\\n \n", - "5 Number of bathrooms\\n \n", - "6 Square footage of living space in the home\\n \n", - "7 Square footage of the lot\\n \n", - "8 Number of floors (levels) in house\\n \n", - "9 Whether the house is on a waterfront\\n \n", - "11 Quality of view from house\\n \n", - "13 How good the overall condition of the house is. Related to maintenance of house.\\n \n", - "15 Overall grade of the house. Related to the construction and design of the house.\\n \n", - "17 Square footage of house apart from basement\\n \n", - "18 Square footage of the basement\\n \n", - "19 Year when house was built\\n \n", - "20 Year when house was renovated\\n \n", - "21 ZIP Code used by the United States Postal Service\\n \n", - "22 Latitude coordinate\\n \n", - "23 Longitude coordinate\\n \n", - "24 The square footage of interior housing living space for the nearest 15 neighbors\\n \n", - "25 The square footage of the land lots of the nearest 15 neighbors\\n " + " Column name Descriptions\n", + "1 * `id` Unique identifier for a house\\n\n", + "2 * `date` Date house was sold\\n\n", + "3 * `price` Sale price (prediction target)\\n\n", + "4 * `bedrooms` Number of bedrooms\\n\n", + "5 * `bathrooms` Number of bathrooms\\n\n", + "6 * `sqft_living` Square footage of living space in the home\\n\n", + "7 * `sqft_lot` Square footage of the lot\\n\n", + "8 * `floors` Number of floors (levels) in house\\n\n", + "9 * `waterfront` Whether the house is on a waterfront\\n\n", + "11 * `view` Quality of view from house\\n\n", + "13 * `condition` How good the overall condition of the house is. Related to maintenance of house.\\n\n", + "15 * `grade` Overall grade of the house. Related to the construction and design of the house.\\n\n", + "17 * `sqft_above` Square footage of house apart from basement\\n\n", + "18 * `sqft_basement` Square footage of the basement\\n\n", + "19 * `yr_built` Year when house was built\\n\n", + "20 * `yr_renovated` Year when house was renovated\\n\n", + "21 * `zipcode` ZIP Code used by the United States Postal Service\\n\n", + "22 * `lat` Latitude coordinate\\n\n", + "23 * `long` Longitude coordinate\\n\n", + "24 * `sqft_living15` The square footage of interior housing living space for the nearest 15 neighbors\\n\n", + "25 * `sqft_lot15` The square footage of the land lots of the nearest 15 neighbors\\n" ] }, - "execution_count": 9, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -871,7 +808,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -884,7 +821,7 @@ " dtype='object')" ] }, - "execution_count": 10, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -896,7 +833,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -925,7 +862,7 @@ "dtype: int64" ] }, - "execution_count": 11, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -957,7 +894,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 14, "metadata": {}, "outputs": [ { @@ -995,16 +932,16 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "There is 11.00% of values missing in waterfront.\n", - "There is 0.29% of values missing in view.\n", - "There is 17.79% of values missing in yr_renovated.\n" + "There is 0.00% of values missing in waterfront.\n", + "There is 0.00% of values missing in view.\n", + "There is 0.00% of values missing in yr_renovated.\n" ] } ], @@ -1034,7 +971,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 16, "metadata": {}, "outputs": [ { @@ -1043,7 +980,7 @@ "0" ] }, - "execution_count": 14, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" } @@ -1078,7 +1015,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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", "text/plain": [ "
" ] @@ -1112,7 +1049,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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", "text/plain": [ "
" ] @@ -1148,7 +1085,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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", "text/plain": [ "
" ] @@ -1185,13 +1122,6 @@ "\n", "We will pick **`sqft_living` - Square footage of living space in the home** to be used to create our linear regression model because it has the most correlation with the price and it has the most linear scatter plor hence a good candidate." ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] } ], "metadata": { @@ -1210,7 +1140,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.5" + "version": "3.11.5" } }, "nbformat": 4, From 6a29e9c22c6a87245a058481e58ea3d2f01edeba Mon Sep 17 00:00:00 2001 From: troye Date: Mon, 29 Apr 2024 13:08:39 +0300 Subject: [PATCH 8/9] completed pre-processing of the data --- student.ipynb | 4228 ++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 4155 insertions(+), 73 deletions(-) diff --git a/student.ipynb b/student.ipynb index 17d6f965..f8cc5c88 100644 --- a/student.ipynb +++ b/student.ipynb @@ -38,7 +38,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -66,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [ { @@ -256,18 +256,40 @@ "" ], "text/plain": [ - " date price bedrooms ... long sqft_living15 sqft_lot15\n", - "id ... \n", - "7129300520 10/13/2014 221900.0 3 ... -122.257 1340 5650\n", - "6414100192 12/9/2014 538000.0 3 ... -122.319 1690 7639\n", - "5631500400 2/25/2015 180000.0 2 ... -122.233 2720 8062\n", - "2487200875 12/9/2014 604000.0 4 ... -122.393 1360 5000\n", - "1954400510 2/18/2015 510000.0 3 ... -122.045 1800 7503\n", - "\n", - "[5 rows x 20 columns]" + " date price bedrooms bathrooms sqft_living sqft_lot \\\n", + "id \n", + "7129300520 10/13/2014 221900.0 3 1.00 1180 5650 \n", + "6414100192 12/9/2014 538000.0 3 2.25 2570 7242 \n", + "5631500400 2/25/2015 180000.0 2 1.00 770 10000 \n", + "2487200875 12/9/2014 604000.0 4 3.00 1960 5000 \n", + "1954400510 2/18/2015 510000.0 3 2.00 1680 8080 \n", + "\n", + " floors waterfront view condition grade sqft_above \\\n", + "id \n", + "7129300520 1.0 NaN NONE Average 7 Average 1180 \n", + "6414100192 2.0 NO NONE Average 7 Average 2170 \n", + "5631500400 1.0 NO NONE Average 6 Low Average 770 \n", + "2487200875 1.0 NO NONE Very Good 7 Average 1050 \n", + "1954400510 1.0 NO NONE Average 8 Good 1680 \n", + "\n", + " sqft_basement yr_built yr_renovated zipcode lat long \\\n", + "id \n", + "7129300520 0.0 1955 0.0 98178 47.5112 -122.257 \n", + "6414100192 400.0 1951 1991.0 98125 47.7210 -122.319 \n", + "5631500400 0.0 1933 NaN 98028 47.7379 -122.233 \n", + "2487200875 910.0 1965 0.0 98136 47.5208 -122.393 \n", + "1954400510 0.0 1987 0.0 98074 47.6168 -122.045 \n", + "\n", + " sqft_living15 sqft_lot15 \n", + "id \n", + "7129300520 1340 5650 \n", + "6414100192 1690 7639 \n", + "5631500400 2720 8062 \n", + "2487200875 1360 5000 \n", + "1954400510 1800 7503 " ] }, - "execution_count": 4, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -290,7 +312,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -299,7 +321,7 @@ "(21597, 20)" ] }, - "execution_count": 5, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -311,7 +333,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -493,20 +515,38 @@ "" ], "text/plain": [ - " price bedrooms ... sqft_living15 sqft_lot15\n", - "count 2.159700e+04 21597.000000 ... 21597.000000 21597.000000\n", - "mean 5.402966e+05 3.373200 ... 1986.620318 12758.283512\n", - "std 3.673681e+05 0.926299 ... 685.230472 27274.441950\n", - "min 7.800000e+04 1.000000 ... 399.000000 651.000000\n", - "25% 3.220000e+05 3.000000 ... 1490.000000 5100.000000\n", - "50% 4.500000e+05 3.000000 ... 1840.000000 7620.000000\n", - "75% 6.450000e+05 4.000000 ... 2360.000000 10083.000000\n", - "max 7.700000e+06 33.000000 ... 6210.000000 871200.000000\n", - "\n", - "[8 rows x 14 columns]" + " price bedrooms bathrooms sqft_living sqft_lot \\\n", + "count 2.159700e+04 21597.000000 21597.000000 21597.000000 2.159700e+04 \n", + "mean 5.402966e+05 3.373200 2.115826 2080.321850 1.509941e+04 \n", + "std 3.673681e+05 0.926299 0.768984 918.106125 4.141264e+04 \n", + "min 7.800000e+04 1.000000 0.500000 370.000000 5.200000e+02 \n", + "25% 3.220000e+05 3.000000 1.750000 1430.000000 5.040000e+03 \n", + "50% 4.500000e+05 3.000000 2.250000 1910.000000 7.618000e+03 \n", + "75% 6.450000e+05 4.000000 2.500000 2550.000000 1.068500e+04 \n", + "max 7.700000e+06 33.000000 8.000000 13540.000000 1.651359e+06 \n", + "\n", + " floors sqft_above yr_built yr_renovated zipcode \\\n", + "count 21597.000000 21597.000000 21597.000000 17755.000000 21597.000000 \n", + "mean 1.494096 1788.596842 1970.999676 83.636778 98077.951845 \n", + "std 0.539683 827.759761 29.375234 399.946414 53.513072 \n", + "min 1.000000 370.000000 1900.000000 0.000000 98001.000000 \n", + "25% 1.000000 1190.000000 1951.000000 0.000000 98033.000000 \n", + "50% 1.500000 1560.000000 1975.000000 0.000000 98065.000000 \n", + "75% 2.000000 2210.000000 1997.000000 0.000000 98118.000000 \n", + "max 3.500000 9410.000000 2015.000000 2015.000000 98199.000000 \n", + "\n", + " lat long sqft_living15 sqft_lot15 \n", + "count 21597.000000 21597.000000 21597.000000 21597.000000 \n", + "mean 47.560093 -122.213982 1986.620318 12758.283512 \n", + "std 0.138552 0.140724 685.230472 27274.441950 \n", + "min 47.155900 -122.519000 399.000000 651.000000 \n", + "25% 47.471100 -122.328000 1490.000000 5100.000000 \n", + "50% 47.571800 -122.231000 1840.000000 7620.000000 \n", + "75% 47.678000 -122.125000 2360.000000 10083.000000 \n", + "max 47.777600 -121.315000 6210.000000 871200.000000 " ] }, - "execution_count": 6, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } @@ -518,7 +558,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -526,7 +566,7 @@ "output_type": "stream", "text": [ "\n", - "Index: 21597 entries, 7129300520 to 1523300157\n", + "Int64Index: 21597 entries, 7129300520 to 1523300157\n", "Data columns (total 20 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", @@ -578,7 +618,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -601,7 +641,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -617,7 +657,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -633,7 +673,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -772,31 +812,54 @@ "" ], "text/plain": [ - " Column name Descriptions\n", - "1 * `id` Unique identifier for a house\\n\n", - "2 * `date` Date house was sold\\n\n", - "3 * `price` Sale price (prediction target)\\n\n", - "4 * `bedrooms` Number of bedrooms\\n\n", - "5 * `bathrooms` Number of bathrooms\\n\n", - "6 * `sqft_living` Square footage of living space in the home\\n\n", - "7 * `sqft_lot` Square footage of the lot\\n\n", - "8 * `floors` Number of floors (levels) in house\\n\n", - "9 * `waterfront` Whether the house is on a waterfront\\n\n", - "11 * `view` Quality of view from house\\n\n", - "13 * `condition` How good the overall condition of the house is. Related to maintenance of house.\\n\n", - "15 * `grade` Overall grade of the house. Related to the construction and design of the house.\\n\n", - "17 * `sqft_above` Square footage of house apart from basement\\n\n", - "18 * `sqft_basement` Square footage of the basement\\n\n", - "19 * `yr_built` Year when house was built\\n\n", - "20 * `yr_renovated` Year when house was renovated\\n\n", - "21 * `zipcode` ZIP Code used by the United States Postal Service\\n\n", - "22 * `lat` Latitude coordinate\\n\n", - "23 * `long` Longitude coordinate\\n\n", - "24 * `sqft_living15` The square footage of interior housing living space for the nearest 15 neighbors\\n\n", - "25 * `sqft_lot15` The square footage of the land lots of the nearest 15 neighbors\\n" + " Column name \\\n", + "1 * `id` \n", + "2 * `date` \n", + "3 * `price` \n", + "4 * `bedrooms` \n", + "5 * `bathrooms` \n", + "6 * `sqft_living` \n", + "7 * `sqft_lot` \n", + "8 * `floors` \n", + "9 * `waterfront` \n", + "11 * `view` \n", + "13 * `condition` \n", + "15 * `grade` \n", + "17 * `sqft_above` \n", + "18 * `sqft_basement` \n", + "19 * `yr_built` \n", + "20 * `yr_renovated` \n", + "21 * `zipcode` \n", + "22 * `lat` \n", + "23 * `long` \n", + "24 * `sqft_living15` \n", + "25 * `sqft_lot15` \n", + "\n", + " Descriptions \n", + "1 Unique identifier for a house\\n \n", + "2 Date house was sold\\n \n", + "3 Sale price (prediction target)\\n \n", + "4 Number of bedrooms\\n \n", + "5 Number of bathrooms\\n \n", + "6 Square footage of living space in the home\\n \n", + "7 Square footage of the lot\\n \n", + "8 Number of floors (levels) in house\\n \n", + "9 Whether the house is on a waterfront\\n \n", + "11 Quality of view from house\\n \n", + "13 How good the overall condition of the house is. Related to maintenance of house.\\n \n", + "15 Overall grade of the house. Related to the construction and design of the house.\\n \n", + "17 Square footage of house apart from basement\\n \n", + "18 Square footage of the basement\\n \n", + "19 Year when house was built\\n \n", + "20 Year when house was renovated\\n \n", + "21 ZIP Code used by the United States Postal Service\\n \n", + "22 Latitude coordinate\\n \n", + "23 Longitude coordinate\\n \n", + "24 The square footage of interior housing living space for the nearest 15 neighbors\\n \n", + "25 The square footage of the land lots of the nearest 15 neighbors\\n " ] }, - "execution_count": 11, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -808,7 +871,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -821,7 +884,7 @@ " dtype='object')" ] }, - "execution_count": 12, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -833,7 +896,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -862,7 +925,7 @@ "dtype: int64" ] }, - "execution_count": 13, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -894,7 +957,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -932,16 +995,16 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "There is 0.00% of values missing in waterfront.\n", - "There is 0.00% of values missing in view.\n", - "There is 0.00% of values missing in yr_renovated.\n" + "There is 11.00% of values missing in waterfront.\n", + "There is 0.29% of values missing in view.\n", + "There is 17.79% of values missing in yr_renovated.\n" ] } ], @@ -971,7 +1034,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 14, "metadata": {}, "outputs": [ { @@ -980,7 +1043,7 @@ "0" ] }, - "execution_count": 16, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -1044,12 +1107,12 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 16, "metadata": {}, "outputs": [ { "data": { - "image/png": "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", + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAncAAAGDCAYAAABJITbwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAAAoSklEQVR4nO3dfZheVX3v//dHIg+KIA8RMEGDQmsRlQoirRyrxQK2teA58DO01qj8yiWHtvanlgNVi0JphVat1oqHSiTgA1BsBa2I+UGpckqBoCCgUlKDEGAgGkBEQYPf88deA3fGmcnk4c5Mdt6v67qve99r77X22rMh85m197p3qgpJkiT1w5OmuwOSJEnacAx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJU5Lkh0meMw37/ViSd2+gtp7VjmOL9vnKJP/vhmi7tXdpkgUbqr2Bds9J8hcbut1hS/KeJJ9sy6v97CfYflr+G5P6xnAnbaaS3J7kx+0X6r1JPpFk24m2r6ptq+o7Q+rDQ0keSPLvSd6S5PF/m6rqLVV16hTbetVk21TVHe04HtsAfX88uAy0/+qqWrS+bQ9TOn+c5OYkDydZnuQfk7xgmPsd+7MfL1gP478xaXNkuJM2b6+pqm2BFwMvAd41doMkszZCH54GPBt4H/C/gLM39E42wnFsKj4EvBX4Y2BH4BeAzwG/NY19krQBGe4kUVV3AZcC+wAkqSTHJ7kNuG2gbM+2vE2S9yf5bpIHk1yVZJu27sA2AvdAkhuTvGKKfXiwqi4BXgcsSDLal8cvSSbZOckXWtsrk3w1yZOSnAc8C/h8G4k8Icm81udjktwBXDFQNhj0npvk2nYcFyfZse3rFUmWD/ZxdHQwyWHAnwGva/u7sa1/fDSq9etd7Wd0X5Jzk2zf1o32Y0GSO5J8L8k71/Aj2jnJ4jbK+W9Jnt3a+vsk7x/Tz88n+ZOxDSTZCzgeOLqqrqiqR6vqR1X1qap6X9tm+9bXFa3v7xodSU3yxnau/ybJ/UmWJXn1QPt7tL49lGQxsPPAusd/9klOA/4b8JH28/tI22bwv7F17oe0uTPcSSLJ7sBvAl8fKD4CeCmw9zhV/gbYD/hVutGfE4CfJZkD/AvwF638HcBnk8yeal+q6lpgOd0v/7He3tbNBnahC1hVVb8P3EEbiayqMwbq/BrwS8ChE+zyDcCbgWcCq4APT6GPXwL+Erig7e9F42z2xvZ6JfAcYFvgI2O2OQj4ReBg4M+T/NIku/094FS6wHQD8KlWvgg4eiD47Nza+8w4bRwMLG8/44n8HbB96/Ov0f183jSw/qXAra0fZwBnJ0lb92ng+rbuVGDc+w+r6p3AV4E/bD+/P9zA/ZA2a4Y7afP2uSQPAFcB/0YXWEb9VVWtrKofD1ZoIeLNwFur6q6qeqyq/r2qHgVeD3yxqr5YVT+rqsXAErrguDbupguHY/0U2A14dlX9tKq+Wmt+QPZ7qurhsccx4LyqurmqHgbeDfw/meSm/7Xwe8AHquo7VfVD4CRg/phRw/dW1Y+r6kbgRmC8kDjqX6rqK+3n/E7gV5Ls3oLag3TBDWA+cGVV3TtOGzsB90y0g3bcrwNOqqqHqup24P3A7w9s9t2q+od279wiuvOxS5Jn0V3af3cbEfwK8PlJjmdC69OPddmf1DeGO2nzdkRVPb2qnl1V/3NMALpzgjo7A1sD/zXOumcDR7XLpg+04HgQ3S/etTEHWDlO+V8DS4EvJ/lOkhOn0NZExzHe+u8CT2bgcuJ6eGZrb7DtWaweQEYGln9EN7o3kcf72cLiyrYP6MLN69vy64HzJmjj+0x+LnYGthyn33PG63NV/agtbtv6cn8LyYN118X69EPa7BnuJE1kohGx7wGPAM8dZ92ddCNhTx94PXX0fq6pSPISul/iV/1ch7pRnLdX1XOA1wBvSzI6YjVRf9c0srf7wPKz6EYHvwc8DDxloF9b0F0Onmq7d9OF3cG2VwHjjahNxeP9TDerece2D4BPAocneRHdJejPTdDG5cDcJPtPsP57dMc/tt93TaF/9wA7JHnqmLoTmezntz79kDZ7hjtJa6WqfgYsBD6Q5JlJtkjyK0m2ogsZr0lyaCvfuk1MmLumdpNsl+S3gfOBT1bVTeNs89tJ9mz3Vv0AeKy9oAtN6/Idaa9PsneSpwCnABe1S33/CWyd5LeSPJluJvFWA/XuBeZl4GtbxvgM8P+1SQbb8sQ9eqvWoY8Av5nkoCRb0t3Pdk1V3QlQVcuB6+hG7D470SXoqroN+CjwmXZetmznaH6SE9txXwicluRpbdLG2+jO66Sq6rt0l+Df29o9iC6AT2TC87U+/ZBkuJO0bt4B3EQXKFYCpwNPamHjcLqJDivoRvL+lMn/rfl8kofatu8EPsDqN84P2gv4/4EfAlcDH62qK9u6vwLe1S4Hv2MtjuU84By6y3xb031FCFX1IPA/gY/TjRg9TDeZY9Q/tvfvJ/naOO0ubG1/BVhGN9r5R2vRr7E+DZxM9/Pej+6evkGLgBcw8SXZUX9MN7Hj74EH6C6vv5Yn7o/7I7pj/Q7d6Omn27FMxe/STXRY2fp67iTbfgg4ss12HW8Sy/r0Q9qsZc33IkuSZrokL6cb2ZrXRlclbaYcuZOkTVy7bPxW4OMGO0mGO0nahLXvxnuAbhbs305rZyTNCF6WlSRJ6hFH7iRJknrEcCdJktQjs9a8yeZh5513rnnz5k13NyRJktbo+uuv/15VjfvcbsNdM2/ePJYsWTLd3ZAkSVqjJBM+3s/LspIkST1iuJMkSeoRw50kSVKPGO4kSZJ6xHAnSZLUI4Y7SZKkHjHcSZIk9YjhTpIkqUcMd5IkST1iuJMkSeoRw50kSVKPGO4kSZJ6ZNZ0d0DS5E444QRGRkbYddddOeOMM6a7O5KkGc5wJ81wIyMj3HXXXdPdDUnSJsLLspIkST1iuJMkSeoRw50kSVKPGO4kSZJ6xHAnSZLUI4Y7SZKkHjHcSZIk9YjhTpIkqUcMd5IkST1iuJMkSeoRHz+mzc4ee9w+3V1YK3PnrmLLLWHZslWbTN+XLZs33V2QpM2WI3eSJEk9MtRwl+TpSS5K8u0k30ryK0l2TLI4yW3tfYeB7U9KsjTJrUkOHSjfL8lNbd2Hk6SVb5XkglZ+TZJ5A3UWtH3clmTBMI9TkiRpphj2yN2HgC9V1fOAFwHfAk4ELq+qvYDL22eS7A3MB54PHAZ8NMkWrZ0zgWOBvdrrsFZ+DHB/Ve0JfBA4vbW1I3Ay8FLgAODkwRApSZLUV0MLd0m2A14OnA1QVT+pqgeAw4FFbbNFwBFt+XDg/Kp6tKqWAUuBA5LsBmxXVVdXVQHnjqkz2tZFwMFtVO9QYHFVrayq+4HFPBEIJUmSemuYI3fPAVYAn0jy9SQfT/JUYJequgegvT+jbT8HuHOg/vJWNqctjy1frU5VrQIeBHaapC1JkqReG2a4mwW8GDizqn4ZeJh2CXYCGaesJilf1zpP7DA5NsmSJEtWrFgxSdckSZI2DcMMd8uB5VV1Tft8EV3Yu7ddaqW93zew/e4D9ecCd7fyueOUr1YnySxge2DlJG2tpqrOqqr9q2r/2bNnr+NhSpIkzRxDC3dVNQLcmeQXW9HBwDeBS4DR2asLgIvb8iXA/DYDdg+6iRPXtku3DyU5sN1P94YxdUbbOhK4ot2XdxlwSJId2kSKQ1qZJElSrw37S4z/CPhUki2B7wBvoguUFyY5BrgDOAqgqm5JciFdAFwFHF9Vj7V2jgPOAbYBLm0v6CZrnJdkKd2I3fzW1sokpwLXte1OqaqVwzxQSZKkmWCo4a6qbgD2H2fVwRNsfxpw2jjlS4B9xil/hBYOx1m3EFi4Ft2VZqRVq3Za7V2SpMn4+DFphhsZeft0d0GStAnx8WOSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqkVnT3QEN3wknnMDIyAi77rorZ5xxxnR3R5IkDZHhbjMwMjLCXXfdNd3dkCRJG4GXZSVJknrEcCdJktQjXpZdR3vscft0d2HK5s5dxZZbwrJlqzapfi9bNm+6uyBJ0ibHkTtJkqQeMdxJkiT1iOFOkiSpR7znbjOwatVOq71L2jj8jklJ08FwtxkYGXn7dHdB2iz5HZOSpoOXZSVJknrEcCdJktQjhjtJkqQeMdxJkiT1iBMqJG1SNqWnrPh0GEnTwZE7SZKkHjHcSZIk9YjhTpIkqUcMd5IkST1iuJMkSeoRZ8tK0pD4XGdJ02GoI3dJbk9yU5IbkixpZTsmWZzktva+w8D2JyVZmuTWJIcOlO/X2lma5MNJ0sq3SnJBK78mybyBOgvaPm5LsmCYxylJ4xkZeTvLl/+lz3eWtFFtjMuyr6yqfatq//b5RODyqtoLuLx9JsnewHzg+cBhwEeTbNHqnAkcC+zVXoe18mOA+6tqT+CDwOmtrR2Bk4GXAgcAJw+GSEmSpL6ajnvuDgcWteVFwBED5edX1aNVtQxYChyQZDdgu6q6uqoKOHdMndG2LgIObqN6hwKLq2plVd0PLOaJQChJktRbww53BXw5yfVJjm1lu1TVPQDt/RmtfA5w50Dd5a1sTlseW75anapaBTwI7DRJW5IkSb027AkVL6uqu5M8A1ic5NuTbJtxymqS8nWt88QOu8B5LMCznvWsSbomSZK0aRjqyF1V3d3e7wP+me7+t3vbpVba+31t8+XA7gPV5wJ3t/K545SvVifJLGB7YOUkbY3t31lVtX9V7T979ux1P1BJkqQZYmjhLslTkzxtdBk4BLgZuAQYnb26ALi4LV8CzG8zYPegmzhxbbt0+1CSA9v9dG8YU2e0rSOBK9p9eZcBhyTZoU2kOKSVSZIk9dowL8vuAvxz+9aSWcCnq+pLSa4DLkxyDHAHcBRAVd2S5ELgm8Aq4Piqeqy1dRxwDrANcGl7AZwNnJdkKd2I3fzW1sokpwLXte1OqaqVQzxWSZKkGWFo4a6qvgO8aJzy7wMHT1DnNOC0ccqXAPuMU/4ILRyOs24hsHDtei1JkrRp8/FjkiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6pFZ090BSZJmohNOOIGRkRF23XVXzjjjjOnujjRlhjtJksYxMjLCXXfdNd3dkNaal2UlSZJ6xHAnSZLUI4Y7SZKkHjHcSZIk9YjhTpIkqUcMd5IkST1iuJMkSeoRw50kSVKPGO4kSZJ6xHAnSZLUI4Y7SZKkHjHcSZIk9YjhTpIkqUcMd5IkST1iuJMkSeoRw50kSVKPGO4kSZJ6xHAnSZLUI4Y7SZKkHjHcSZIk9cjQw12SLZJ8PckX2ucdkyxOclt732Fg25OSLE1ya5JDB8r3S3JTW/fhJGnlWyW5oJVfk2TeQJ0FbR+3JVkw7OOUJEmaCTbGyN1bgW8NfD4RuLyq9gIub59JsjcwH3g+cBjw0SRbtDpnAscCe7XXYa38GOD+qtoT+CBwemtrR+Bk4KXAAcDJgyFSkiSpr4Ya7pLMBX4L+PhA8eHAora8CDhioPz8qnq0qpYBS4EDkuwGbFdVV1dVAeeOqTPa1kXAwW1U71BgcVWtrKr7gcU8EQglSZJ6a9gjd38LnAD8bKBsl6q6B6C9P6OVzwHuHNhueSub05bHlq9Wp6pWAQ8CO03SliRJUq8NLdwl+W3gvqq6fqpVximrScrXtc5gH49NsiTJkhUrVkyxm5IkSTPXMEfuXgb8TpLbgfOBX0/ySeDedqmV9n5f2345sPtA/bnA3a187jjlq9VJMgvYHlg5SVurqaqzqmr/qtp/9uzZ636kkiRJM8TQwl1VnVRVc6tqHt1EiSuq6vXAJcDo7NUFwMVt+RJgfpsBuwfdxIlr26Xbh5Ic2O6ne8OYOqNtHdn2UcBlwCFJdmgTKQ5pZZIkSb02axr2+T7gwiTHAHcARwFU1S1JLgS+CawCjq+qx1qd44BzgG2AS9sL4GzgvCRL6Ubs5re2ViY5FbiubXdKVa0c9oFJkiRNt40S7qrqSuDKtvx94OAJtjsNOG2c8iXAPuOUP0ILh+OsWwgsXNc+S5IkbYp8QoUkSVKPGO4kSZJ6xHAnSZLUI4Y7SZKkHjHcSZIk9YjhTpIkqUcMd5IkST1iuJMkSeoRw50kSVKPGO4kSZJ6ZDqeLStJkjRUJ5xwAiMjI+y6666cccYZ092djcpwJ0mSemdkZIS77rprursxLbwsK0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSj0wp3CX5hSSXJ7m5fX5hkncNt2uSJElaW1MdufsH4CTgpwBV9Q1g/rA6JUmSpHUz1XD3lKq6dkzZqg3dGUmSJK2fqYa77yV5LlAASY4E7hlaryRJkrROpvps2eOBs4DnJbkLWAa8fmi9kiRJ0jqZUrirqu8Ar0ryVOBJVfXQcLslSeqbPfa4fbq7sFbmzl3FllvCsmWrNqm+L1s2b7q7oGk21dmyf5nk6VX1cFU9lGSHJH8x7M5JkiRp7Uz1nrtXV9UDox+q6n7gN4fSI0mSJK2zqYa7LZJsNfohyTbAVpNsL0mSpGkw1QkVnwQuT/IJuhmzbwYWDa1XkiRJWidTnVBxRpKbgIOBAKdW1WVD7ZkkSZLW2lRH7qiqS4FLh9gXSZI0Q21KM4Zh05ztvKFmOk8a7pJcVVUHJXmI9gXGo6uAqqrtNkgvJEmStEFMGu6q6qD2/rSN0x1JkiStjzXOlk3ypCQ3b4zOSJIkaf2sMdxV1c+AG5M8ayP0R5IkSethqhMqdgNuSXIt8PBoYVX9zlB6JUmSpHUy1XD33qH2QpIkSRvEmmbLbg28BdgTuAk4u6pWbYyOSZIkae2t6Z67RcD+dMHu1cD7h94jSZIkrbM1XZbdu6peAJDkbODa4XdJkiRJ62pNI3c/HV1Y28uxSbZOcm2SG5PckuS9rXzHJIuT3Nbedxioc1KSpUluTXLoQPl+SW5q6z6cJK18qyQXtPJrkswbqLOg7eO2JAvWpu+SJEmbqjWFuxcl+UF7PQS8cHQ5yQ/WUPdR4Ner6kXAvsBhSQ4ETgQur6q9gMvbZ5LsDcwHng8cBnw0yRatrTOBY4G92uuwVn4McH9V7Ql8EDi9tbUjcDLwUuAA4OTBEClJktRXk4a7qtqiqrZrr6dV1ayB5UkfPVadH7aPT26vAg6nu5eP9n5EWz4cOL+qHq2qZcBS4IAkuwHbVdXVVVXAuWPqjLZ1EXBwG9U7FFhcVSur6n5gMU8EQkmSpN5a45cYr48kWyS5AbiPLmxdA+xSVfcAtPdntM3nAHcOVF/eyua05bHlq9Vpl40fBHaapC1JkqReG2q4q6rHqmpfYC7dKNw+k2ye8ZqYpHxd6zyxw+TYJEuSLFmxYsUkXZMkSdo0DDXcjaqqB4Ar6S6N3tsutdLe72ubLQd2H6g2F7i7lc8dp3y1OklmAdsDKydpa2y/zqqq/atq/9mzZ6/7AUqSJM0QQwt3SWYneXpb3gZ4FfBt4BJgdPbqAuDitnwJML/NgN2DbuLEte3S7UNJDmz3071hTJ3Rto4Ermj35V0GHJJkhzaR4pBWJkmS1GtTffzYutgNWNRmvD4JuLCqvpDkauDCJMcAdwBHAVTVLUkuBL4JrAKOr6rHWlvHAecA2wCXthfA2cB5SZbSjdjNb22tTHIqcF3b7pSqWjnEY5UkSTPIqlU7rfa+ORlauKuqbwC/PE7594GDJ6hzGnDaOOVLgJ+7X6+qHqGFw3HWLQQWrl2vJUlSH4yMvH26uzBtNso9d5IkSdo4DHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHZk13ByRJmolWrdpptXdpU2G4kyRpHCMjb5/uLkjrxMuykiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjQwt3SXZP8q9JvpXkliRvbeU7Jlmc5Lb2vsNAnZOSLE1ya5JDB8r3S3JTW/fhJGnlWyW5oJVfk2TeQJ0FbR+3JVkwrOOUJEmaSYY5crcKeHtV/RJwIHB8kr2BE4HLq2ov4PL2mbZuPvB84DDgo0m2aG2dCRwL7NVeh7XyY4D7q2pP4IPA6a2tHYGTgZcCBwAnD4ZISZKkvhpauKuqe6rqa235IeBbwBzgcGBR22wRcERbPhw4v6oeraplwFLggCS7AdtV1dVVVcC5Y+qMtnURcHAb1TsUWFxVK6vqfmAxTwRCSZKk3too99y1y6W/DFwD7FJV90AXAIFntM3mAHcOVFveyua05bHlq9WpqlXAg8BOk7QlSZLUa0MPd0m2BT4L/ElV/WCyTccpq0nK17XOYN+OTbIkyZIVK1ZM0jVJkqRNw1DDXZIn0wW7T1XVP7Xie9ulVtr7fa18ObD7QPW5wN2tfO445avVSTIL2B5YOUlbq6mqs6pq/6raf/bs2et6mJIkSTPGMGfLBjgb+FZVfWBg1SXA6OzVBcDFA+Xz2wzYPegmTlzbLt0+lOTA1uYbxtQZbetI4Ip2X95lwCFJdmgTKQ5pZZIkSb02a4htvwz4feCmJDe0sj8D3gdcmOQY4A7gKICquiXJhcA36WbaHl9Vj7V6xwHnANsAl7YXdOHxvCRL6Ubs5re2ViY5FbiubXdKVa0c0nFKkiTNGEMLd1V1FePf+wZw8AR1TgNOG6d8CbDPOOWP0MLhOOsWAgun2l9JkqQ+8AkVkiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpRwx3kiRJPWK4kyRJ6hHDnSRJUo8Y7iRJknrEcCdJktQjhjtJkqQeMdxJkiT1iOFOkiSpR4YW7pIsTHJfkpsHynZMsjjJbe19h4F1JyVZmuTWJIcOlO+X5Ka27sNJ0sq3SnJBK78mybyBOgvaPm5LsmBYxyhJkjTTDHPk7hzgsDFlJwKXV9VewOXtM0n2BuYDz291Pppki1bnTOBYYK/2Gm3zGOD+qtoT+CBwemtrR+Bk4KXAAcDJgyFSkiSpz4YW7qrqK8DKMcWHA4va8iLgiIHy86vq0apaBiwFDkiyG7BdVV1dVQWcO6bOaFsXAQe3Ub1DgcVVtbKq7gcW8/MhU5IkqZc29j13u1TVPQDt/RmtfA5w58B2y1vZnLY8tny1OlW1CngQ2GmStiRJknpvpkyoyDhlNUn5utZZfafJsUmWJFmyYsWKKXVUkiRpJtvY4e7edqmV9n5fK18O7D6w3Vzg7lY+d5zy1eokmQVsT3cZeKK2fk5VnVVV+1fV/rNnz16Pw5IkSZoZNna4uwQYnb26ALh4oHx+mwG7B93EiWvbpduHkhzY7qd7w5g6o20dCVzR7su7DDgkyQ5tIsUhrUySJKn3Zg2r4SSfAV4B7JxkOd0M1vcBFyY5BrgDOAqgqm5JciHwTWAVcHxVPdaaOo5u5u02wKXtBXA2cF6SpXQjdvNbWyuTnApc17Y7parGTuyQJEnqpaGFu6o6eoJVB0+w/WnAaeOULwH2Gaf8EVo4HGfdQmDhlDsrSZLUEzNlQoUkSZI2AMOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB4x3EmSJPWI4U6SJKlHDHeSJEk90utwl+SwJLcmWZrkxOnujyRJ0rD1Ntwl2QL4e+DVwN7A0Un2nt5eSZIkDVdvwx1wALC0qr5TVT8BzgcOn+Y+SZIkDVWfw90c4M6Bz8tbmSRJUm/Nmu4ODFHGKavVNkiOBY5tH3+Y5Nah92r67Ax8b7o7sTYy3hncfG1S589zt5pN6tyB528Mz9+mbZM6f2t57p490Yo+h7vlwO4Dn+cCdw9uUFVnAWdtzE5NlyRLqmr/6e6H1o3nb9Pludu0ef42bZvr+evzZdnrgL2S7JFkS2A+cMk090mSJGmoejtyV1WrkvwhcBmwBbCwqm6Z5m5JkiQNVW/DHUBVfRH44nT3Y4bYLC4/95jnb9Pludu0ef42bZvl+UtVrXkrSZIkbRL6fM+dJEnSZsdwN8MleW2SSvK86e6Lfl6SK5McOqbsT5J8dAj7eluSbye5KcmNST6Q5MkboN03JvnIhujj5iLJLkk+neQ7Sa5PcnWS126Adq9MstnN7JsOSR5LckOSm5P8Y5KnTHeftPYGzuPoa94k2/77RuzatDLczXxHA1fRzfZdL+2RbNqwPsPPn5v5rXyNpnpOkrwFOAQ4sKpeALwEuA/YZupd1YaQJMDngK9U1XOqaj+6cz53WjumtfXjqtq3qvYBfgK8ZX0aS9Lre9hnsNHzOPq6faINq+pXx5b19fei4W4GS7It8DLgGGB+klcnuXBg/SuSfL4tH9JGD77W/grdtpXfnuTPk1wFHJXkD5Jc10Z+Pjv612qS5yb5j7bulCQ/HNjPn7bybyR578b8GWwCLgJ+O8lWAO2vxmcCV03xnJyY5GujjSXZK8n14+znncBxVfUAQFX9pKreV1U/aPWObiN6Nyc5faC9icrflOQ/k/wb3X9jmrpfB35SVR8bLaiq71bV3yXZOskn2s/860leCTBJ+TZJzm//b12AYX26fBXYM8mOST7Xzsd/JHkhwCTl70lyVpIvA+dO5wGok2TbJJe3f3dvSnL4wLoftvdXJPnXJJ8Gbpq2zg6R4W5mOwL4UlX9J7AS+D5wYJKntvWvAy5IsjPwLuBVVfViYAnwtoF2Hqmqg6rqfOCfquolVfUi4Ft0wRHgQ8CHquolDHzZc5JDgL3ontW7L7BfkpcP5Wg3QVX1feBa4LBWNB+4ANiJqZ2T04AHk+zbyt8EnDO4jyRPA7atqmXj9SHJM4HT6ULHvsBLkhwxSfluwHvpQt1vAHuv6/Fvpp4PfG2CdccDtNHVo4FFSbaepPw44EdV9ULgNGC/IfddY7QRt1fT/ZJ/L/D1dj7+jCcC20Tl0J2zw6vqdzderzVgm4FLsv8MPAK8tv27+0rg/W20fawDgHdWVS///XMYeWY7Gvjbtnw+cBTwJeA1SS4Cfgs4Afg1ul/Q/6f9N7wlcPVAOxcMLO+T5C+ApwPb0n0PIMCv0IVJgE8Df9OWD2mvr7fP29KFva+s57H1yeil2Yvb+5uBA5n6Ofk48KYkb6ML7AeMaT8MPDov3T1+p9Odw98FZgNXVtWKtv5TwMtbnfHKGVN+AfAL63z0m7kkfw8cRHdpbznwdwBV9e0k36X72R40QfnLgQ+38m8k+cbGP4LN1jZJbmjLXwXOBq4B/gdAVV2RZKck29Odv/HKAS6pqh9v3K5rwI+rat/RD+nuQ/7LNgjxM7pnyu8CjIypd+1EfzD3geFuhkqyE92Iyz5Jiu6LmItuZOd4upG866rqofZXyeKqOnqC5h4eWD4HOKKqbkzyRuAVa+oK8FdV9b/X9Vg2A58DPpDkxcA2VfW1JHOY+jn5LHAycAVwfRsNfFxV/SDJw0n2qKplVXUZcFmSL9CFxomeRjjZUwr9DqR1dwvtFz1AVR3fRs+XAHdNUMdzMfOsFgrg8fspxyomf1b5w+Os0/T5Pbo/ePerqp8muR3Yepzten3evCw7cx0JnFtVz66qeVW1O7AMWAW8GPgDnhj9+Q/gZUn2BEjylCQTjcQ8Dbin/XXzewPl/8ETv7AGJwhcBrx54H6xOUmesf6H1x9V9UPgSmAhT0ykmPI5qapH6H7OZwKfmGA3fwWcmeTprb3wxD9Y1wC/lmTndDcHHw382xrKX9FGH55MNyKsqbsC2DrJcQNlozMtv0L7/6qd72cBt06xfB/ghRuh/5rY4Pl4BfC9dl/rROWaebYH7mvB7pXAs6e7Q9PBkbuZ62jgfWPKPksXvL4AvBFYAFBVK9oo3GfSbuynu9/rP8dp9910v9y/S3ePydNa+Z8An0zyduBfgAdb219O8kvA1e2P2h8Cr6ebqaknfAb4J1owXstzAvAp4L8DX55g/Zl0AeKaJI/SnYf/Q3cf0INJTgL+lW6E4YtVdTHAJOXvobtMfA/d/WO9nDE2DFVVSY4APpjkBGAF3SjA/6K7NP+xJDfR/SH2xqp6NN1X44xXfibwiXY59ga6+zc1fd7DE+fjR7R/Yycp18zzKeDzSZbQ/T/17entzvTwCRUCupElussUlWQ+cHRVHb6metowkrwD2L6q3j3dfZEkbdocudOo/YCPtMt9D9BNCtBG0GZ4PZfuHktJktaLI3eSJEk94oQKSZKkHjHcSZIk9YjhTpIkqUcMd5IEJNk13XNe/yvJN5N8cZLvi5xqm69oXzZNkt9JcmJbPiLJ3gPbnZLkVet3BJLUcbaspM1emyX+z8Ciqprfyvale2zRRN9NuFaq6hLgkvbxCLrvq/xmW/fnG2IfkgSO3EkSdA8Y/2lVfWy0oKpuAK5K8tdJbk5yU5LXweMjclcmuSjJt5N8avTRVUkOa2VX0X0xNa38jUk+kuRXgd8B/ro97Py5Sc5JcmTb7uAkX2/7Wzj6JdhJbk/y3iRfa+uet7F+OJI2LYY7SYJ9gOvHKf/vwL7Ai4BX0QWy3dq6X6Z7ssvewHPoHje3NfAPwGuA/wbsOrbBqvp3uhG8P62qfavqv0bXtfrnAK+rqhfQXV0ZfMzZ96rqxXRPLHnHOh6rpJ4z3EnSxA4CPlNVj1XVvXTP5n1JW3dtVS2vqp/RPeZoHvA8YFlV3Vbdl4h+ci3394ut/uil4EXAywfW/1N7v77tT5J+juFOkuAWuqe0jJVJ6jw6sPwYT9zDvD7fDD/Z/gb3Obg/SVqN4U6S4ApgqyR/MFqQ5CXA/cDrkmyRZDbdKNq1k7TzbWCPJM9tn4+eYLuHgKdNUH9ekj3b59+nGy2UpCkz3Ena7LVLqK8FfqN9FcotwHuATwPfAG6kC4AnVNXIJO08AhwL/EubUPHdCTY9H/jTNnHiuWPqvwn4xyQ3AT8DPjZBG5I0Lp8tK0mS1COO3EmSJPWI4U6SJKlHDHeSJEk9YriTJEnqEcOdJElSjxjuJEmSesRwJ0mS1COGO0mSpB75v7UPDGHtVzP+AAAAAElFTkSuQmCC", "text/plain": [ "
" ] @@ -1080,7 +1143,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 17, "metadata": {}, "outputs": [ { @@ -1107,6 +1170,4025 @@ "plt.show()" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### PRE-PROCESSING" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Int64Index: 21597 entries, 7129300520 to 1523300157\n", + "Data columns (total 20 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 date 21597 non-null object \n", + " 1 price 21597 non-null float64\n", + " 2 bedrooms 21597 non-null int64 \n", + " 3 bathrooms 21597 non-null float64\n", + " 4 sqft_living 21597 non-null int64 \n", + " 5 sqft_lot 21597 non-null int64 \n", + " 6 floors 21597 non-null float64\n", + " 7 waterfront 21597 non-null object \n", + " 8 view 21597 non-null object \n", + " 9 condition 21597 non-null object \n", + " 10 grade 21597 non-null object \n", + " 11 sqft_above 21597 non-null int64 \n", + " 12 sqft_basement 21597 non-null object \n", + " 13 yr_built 21597 non-null int64 \n", + " 14 yr_renovated 21597 non-null float64\n", + " 15 zipcode 21597 non-null int64 \n", + " 16 lat 21597 non-null float64\n", + " 17 long 21597 non-null float64\n", + " 18 sqft_living15 21597 non-null int64 \n", + " 19 sqft_lot15 21597 non-null int64 \n", + "dtypes: float64(6), int64(8), object(6)\n", + "memory usage: 4.1+ MB\n" + ] + } + ], + "source": [ + "df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongradesqft_abovesqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15
id
71293005202014-10-13221900.031.00118056501.0NONONEAverage7 Average11800.019550.09817847.5112-122.25713405650
64141001922014-12-09538000.032.25257072422.0NONONEAverage7 Average2170400.019511991.09812547.7210-122.31916907639
56315004002015-02-25180000.021.00770100001.0NONONEAverage6 Low Average7700.019330.09802847.7379-122.23327208062
24872008752014-12-09604000.043.00196050001.0NONONEVery Good7 Average1050910.019650.09813647.5208-122.39313605000
19544005102015-02-18510000.032.00168080801.0NONONEAverage8 Good16800.019870.09807447.6168-122.04518007503
...............................................................
2630000182014-05-21360000.032.50153011313.0NONONEAverage8 Good15300.020090.09810347.6993-122.34615301509
66000601202015-02-23400000.042.50231058132.0NONONEAverage8 Good23100.020140.09814647.5107-122.36218307200
15233001412014-06-23402101.020.75102013502.0NONONEAverage7 Average10200.020090.09814447.5944-122.29910202007
2913101002015-01-16400000.032.50160023882.0NONONEAverage8 Good16000.020040.09802747.5345-122.06914101287
15233001572014-10-15325000.020.75102010762.0NONONEAverage7 Average10200.020080.09814447.5941-122.29910201357
\n", + "

21597 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " date price bedrooms bathrooms sqft_living sqft_lot \\\n", + "id \n", + "7129300520 2014-10-13 221900.0 3 1.00 1180 5650 \n", + "6414100192 2014-12-09 538000.0 3 2.25 2570 7242 \n", + "5631500400 2015-02-25 180000.0 2 1.00 770 10000 \n", + "2487200875 2014-12-09 604000.0 4 3.00 1960 5000 \n", + "1954400510 2015-02-18 510000.0 3 2.00 1680 8080 \n", + "... ... ... ... ... ... ... \n", + "263000018 2014-05-21 360000.0 3 2.50 1530 1131 \n", + "6600060120 2015-02-23 400000.0 4 2.50 2310 5813 \n", + "1523300141 2014-06-23 402101.0 2 0.75 1020 1350 \n", + "291310100 2015-01-16 400000.0 3 2.50 1600 2388 \n", + "1523300157 2014-10-15 325000.0 2 0.75 1020 1076 \n", + "\n", + " floors waterfront view condition grade sqft_above \\\n", + "id \n", + "7129300520 1.0 NO NONE Average 7 Average 1180 \n", + "6414100192 2.0 NO NONE Average 7 Average 2170 \n", + "5631500400 1.0 NO NONE Average 6 Low Average 770 \n", + "2487200875 1.0 NO NONE Very Good 7 Average 1050 \n", + "1954400510 1.0 NO NONE Average 8 Good 1680 \n", + "... ... ... ... ... ... ... \n", + "263000018 3.0 NO NONE Average 8 Good 1530 \n", + "6600060120 2.0 NO NONE Average 8 Good 2310 \n", + "1523300141 2.0 NO NONE Average 7 Average 1020 \n", + "291310100 2.0 NO NONE Average 8 Good 1600 \n", + "1523300157 2.0 NO NONE Average 7 Average 1020 \n", + "\n", + " sqft_basement yr_built yr_renovated zipcode lat long \\\n", + "id \n", + "7129300520 0.0 1955 0.0 98178 47.5112 -122.257 \n", + "6414100192 400.0 1951 1991.0 98125 47.7210 -122.319 \n", + "5631500400 0.0 1933 0.0 98028 47.7379 -122.233 \n", + "2487200875 910.0 1965 0.0 98136 47.5208 -122.393 \n", + "1954400510 0.0 1987 0.0 98074 47.6168 -122.045 \n", + "... ... ... ... ... ... ... \n", + "263000018 0.0 2009 0.0 98103 47.6993 -122.346 \n", + "6600060120 0.0 2014 0.0 98146 47.5107 -122.362 \n", + "1523300141 0.0 2009 0.0 98144 47.5944 -122.299 \n", + "291310100 0.0 2004 0.0 98027 47.5345 -122.069 \n", + "1523300157 0.0 2008 0.0 98144 47.5941 -122.299 \n", + "\n", + " sqft_living15 sqft_lot15 \n", + "id \n", + "7129300520 1340 5650 \n", + "6414100192 1690 7639 \n", + "5631500400 2720 8062 \n", + "2487200875 1360 5000 \n", + "1954400510 1800 7503 \n", + "... ... ... \n", + "263000018 1530 1509 \n", + "6600060120 1830 7200 \n", + "1523300141 1020 2007 \n", + "291310100 1410 1287 \n", + "1523300157 1020 1357 \n", + "\n", + "[21597 rows x 20 columns]" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Converting date to datetime format \n", + "df['date'] = pd.to_datetime(df['date'])\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongradesqft_abovesqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15
id
71293005202014-10-13221900.031.00118056501.0NONONEAverage7 Average11800.019550.09817847.5112-122.25713405650
64141001922014-12-09538000.032.25257072422.0NONONEAverage7 Average2170400.019511.09812547.7210-122.31916907639
56315004002015-02-25180000.021.00770100001.0NONONEAverage6 Low Average7700.019330.09802847.7379-122.23327208062
24872008752014-12-09604000.043.00196050001.0NONONEVery Good7 Average1050910.019650.09813647.5208-122.39313605000
19544005102015-02-18510000.032.00168080801.0NONONEAverage8 Good16800.019870.09807447.6168-122.04518007503
...............................................................
2630000182014-05-21360000.032.50153011313.0NONONEAverage8 Good15300.020090.09810347.6993-122.34615301509
66000601202015-02-23400000.042.50231058132.0NONONEAverage8 Good23100.020140.09814647.5107-122.36218307200
15233001412014-06-23402101.020.75102013502.0NONONEAverage7 Average10200.020090.09814447.5944-122.29910202007
2913101002015-01-16400000.032.50160023882.0NONONEAverage8 Good16000.020040.09802747.5345-122.06914101287
15233001572014-10-15325000.020.75102010762.0NONONEAverage7 Average10200.020080.09814447.5941-122.29910201357
\n", + "

21597 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " date price bedrooms bathrooms sqft_living sqft_lot \\\n", + "id \n", + "7129300520 2014-10-13 221900.0 3 1.00 1180 5650 \n", + "6414100192 2014-12-09 538000.0 3 2.25 2570 7242 \n", + "5631500400 2015-02-25 180000.0 2 1.00 770 10000 \n", + "2487200875 2014-12-09 604000.0 4 3.00 1960 5000 \n", + "1954400510 2015-02-18 510000.0 3 2.00 1680 8080 \n", + "... ... ... ... ... ... ... \n", + "263000018 2014-05-21 360000.0 3 2.50 1530 1131 \n", + "6600060120 2015-02-23 400000.0 4 2.50 2310 5813 \n", + "1523300141 2014-06-23 402101.0 2 0.75 1020 1350 \n", + "291310100 2015-01-16 400000.0 3 2.50 1600 2388 \n", + "1523300157 2014-10-15 325000.0 2 0.75 1020 1076 \n", + "\n", + " floors waterfront view condition grade sqft_above \\\n", + "id \n", + "7129300520 1.0 NO NONE Average 7 Average 1180 \n", + "6414100192 2.0 NO NONE Average 7 Average 2170 \n", + "5631500400 1.0 NO NONE Average 6 Low Average 770 \n", + "2487200875 1.0 NO NONE Very Good 7 Average 1050 \n", + "1954400510 1.0 NO NONE Average 8 Good 1680 \n", + "... ... ... ... ... ... ... \n", + "263000018 3.0 NO NONE Average 8 Good 1530 \n", + "6600060120 2.0 NO NONE Average 8 Good 2310 \n", + "1523300141 2.0 NO NONE Average 7 Average 1020 \n", + "291310100 2.0 NO NONE Average 8 Good 1600 \n", + "1523300157 2.0 NO NONE Average 7 Average 1020 \n", + "\n", + " sqft_basement yr_built yr_renovated zipcode lat long \\\n", + "id \n", + "7129300520 0.0 1955 0.0 98178 47.5112 -122.257 \n", + "6414100192 400.0 1951 1.0 98125 47.7210 -122.319 \n", + "5631500400 0.0 1933 0.0 98028 47.7379 -122.233 \n", + "2487200875 910.0 1965 0.0 98136 47.5208 -122.393 \n", + "1954400510 0.0 1987 0.0 98074 47.6168 -122.045 \n", + "... ... ... ... ... ... ... \n", + "263000018 0.0 2009 0.0 98103 47.6993 -122.346 \n", + "6600060120 0.0 2014 0.0 98146 47.5107 -122.362 \n", + "1523300141 0.0 2009 0.0 98144 47.5944 -122.299 \n", + "291310100 0.0 2004 0.0 98027 47.5345 -122.069 \n", + "1523300157 0.0 2008 0.0 98144 47.5941 -122.299 \n", + "\n", + " sqft_living15 sqft_lot15 \n", + "id \n", + "7129300520 1340 5650 \n", + "6414100192 1690 7639 \n", + "5631500400 2720 8062 \n", + "2487200875 1360 5000 \n", + "1954400510 1800 7503 \n", + "... ... ... \n", + "263000018 1530 1509 \n", + "6600060120 1830 7200 \n", + "1523300141 1020 2007 \n", + "291310100 1410 1287 \n", + "1523300157 1020 1357 \n", + "\n", + "[21597 rows x 20 columns]" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Convert any houses that have been renovated to '1' to indicate true and any houses that have not been renovated to '0' to indicate false.\n", + "df['yr_renovated'] = df['yr_renovated'].apply(lambda x: 1 if x > 0 else x)\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Int64Index: 21597 entries, 7129300520 to 1523300157\n", + "Data columns (total 20 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 date 21597 non-null datetime64[ns]\n", + " 1 price 21597 non-null float64 \n", + " 2 bedrooms 21597 non-null int64 \n", + " 3 bathrooms 21597 non-null float64 \n", + " 4 sqft_living 21597 non-null int64 \n", + " 5 sqft_lot 21597 non-null int64 \n", + " 6 floors 21597 non-null float64 \n", + " 7 waterfront 21597 non-null object \n", + " 8 view 21597 non-null object \n", + " 9 condition 21597 non-null object \n", + " 10 grade 21597 non-null object \n", + " 11 sqft_above 21597 non-null int64 \n", + " 12 sqft_basement 21597 non-null object \n", + " 13 yr_built 21597 non-null int64 \n", + " 14 yr_renovated 21597 non-null float64 \n", + " 15 zipcode 21597 non-null int64 \n", + " 16 lat 21597 non-null float64 \n", + " 17 long 21597 non-null float64 \n", + " 18 sqft_living15 21597 non-null int64 \n", + " 19 sqft_lot15 21597 non-null int64 \n", + "dtypes: datetime64[ns](1), float64(6), int64(8), object(5)\n", + "memory usage: 4.1+ MB\n" + ] + } + ], + "source": [ + "df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['0.0', '400.0', '910.0', '1530.0', '?', '730.0', '1700.0', '300.0',\n", + " '970.0', '760.0', '720.0', '700.0', '820.0', '780.0', '790.0',\n", + " '330.0', '1620.0', '360.0', '588.0', '1510.0', '410.0', '990.0',\n", + " '600.0', '560.0', '550.0', '1000.0', '1600.0', '500.0', '1040.0',\n", + " '880.0', '1010.0', '240.0', '265.0', '290.0', '800.0', '540.0',\n", + " '710.0', '840.0', '380.0', '770.0', '480.0', '570.0', '1490.0',\n", + " '620.0', '1250.0', '1270.0', '120.0', '650.0', '180.0', '1130.0',\n", + " '450.0', '1640.0', '1460.0', '1020.0', '1030.0', '750.0', '640.0',\n", + " '1070.0', '490.0', '1310.0', '630.0', '2000.0', '390.0', '430.0',\n", + " '850.0', '210.0', '1430.0', '1950.0', '440.0', '220.0', '1160.0',\n", + " '860.0', '580.0', '2060.0', '1820.0', '1180.0', '200.0', '1150.0',\n", + " '1200.0', '680.0', '530.0', '1450.0', '1170.0', '1080.0', '960.0',\n", + " '280.0', '870.0', '1100.0', '460.0', '1400.0', '660.0', '1220.0',\n", + " '900.0', '420.0', '1580.0', '1380.0', '475.0', '690.0', '270.0',\n", + " '350.0', '935.0', '1370.0', '980.0', '1470.0', '160.0', '950.0',\n", + " '50.0', '740.0', '1780.0', '1900.0', '340.0', '470.0', '370.0',\n", + " '140.0', '1760.0', '130.0', '520.0', '890.0', '1110.0', '150.0',\n", + " '1720.0', '810.0', '190.0', '1290.0', '670.0', '1800.0', '1120.0',\n", + " '1810.0', '60.0', '1050.0', '940.0', '310.0', '930.0', '1390.0',\n", + " '610.0', '1830.0', '1300.0', '510.0', '1330.0', '1590.0', '920.0',\n", + " '1320.0', '1420.0', '1240.0', '1960.0', '1560.0', '2020.0',\n", + " '1190.0', '2110.0', '1280.0', '250.0', '2390.0', '1230.0', '170.0',\n", + " '830.0', '1260.0', '1410.0', '1340.0', '590.0', '1500.0', '1140.0',\n", + " '260.0', '100.0', '320.0', '1480.0', '1060.0', '1284.0', '1670.0',\n", + " '1350.0', '2570.0', '1090.0', '110.0', '2500.0', '90.0', '1940.0',\n", + " '1550.0', '2350.0', '2490.0', '1481.0', '1360.0', '1135.0',\n", + " '1520.0', '1850.0', '1660.0', '2130.0', '2600.0', '1690.0',\n", + " '243.0', '1210.0', '1024.0', '1798.0', '1610.0', '1440.0',\n", + " '1570.0', '1650.0', '704.0', '1910.0', '1630.0', '2360.0',\n", + " '1852.0', '2090.0', '2400.0', '1790.0', '2150.0', '230.0', '70.0',\n", + " '1680.0', '2100.0', '3000.0', '1870.0', '1710.0', '2030.0',\n", + " '875.0', '1540.0', '2850.0', '2170.0', '506.0', '906.0', '145.0',\n", + " '2040.0', '784.0', '1750.0', '374.0', '518.0', '2720.0', '2730.0',\n", + " '1840.0', '3480.0', '2160.0', '1920.0', '2330.0', '1860.0',\n", + " '2050.0', '4820.0', '1913.0', '80.0', '2010.0', '3260.0', '2200.0',\n", + " '415.0', '1730.0', '652.0', '2196.0', '1930.0', '515.0', '40.0',\n", + " '2080.0', '2580.0', '1548.0', '1740.0', '235.0', '861.0', '1890.0',\n", + " '2220.0', '792.0', '2070.0', '4130.0', '2250.0', '2240.0',\n", + " '1990.0', '768.0', '2550.0', '435.0', '1008.0', '2300.0', '2610.0',\n", + " '666.0', '3500.0', '172.0', '1816.0', '2190.0', '1245.0', '1525.0',\n", + " '1880.0', '862.0', '946.0', '1281.0', '414.0', '2180.0', '276.0',\n", + " '1248.0', '602.0', '516.0', '176.0', '225.0', '1275.0', '266.0',\n", + " '283.0', '65.0', '2310.0', '10.0', '1770.0', '2120.0', '295.0',\n", + " '207.0', '915.0', '556.0', '417.0', '143.0', '508.0', '2810.0',\n", + " '20.0', '274.0', '248.0'], dtype=object)" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df['sqft_basement'].unique()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "sqft_basement has a '?' value, let's replace it with a 0" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongradesqft_abovesqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15
id
71293005202014-10-13221900.031.00118056501.0NONONEAverage7 Average11800.019550.09817847.5112-122.25713405650
64141001922014-12-09538000.032.25257072422.0NONONEAverage7 Average2170400.019511.09812547.7210-122.31916907639
56315004002015-02-25180000.021.00770100001.0NONONEAverage6 Low Average7700.019330.09802847.7379-122.23327208062
24872008752014-12-09604000.043.00196050001.0NONONEVery Good7 Average1050910.019650.09813647.5208-122.39313605000
19544005102015-02-18510000.032.00168080801.0NONONEAverage8 Good16800.019870.09807447.6168-122.04518007503
...............................................................
2630000182014-05-21360000.032.50153011313.0NONONEAverage8 Good15300.020090.09810347.6993-122.34615301509
66000601202015-02-23400000.042.50231058132.0NONONEAverage8 Good23100.020140.09814647.5107-122.36218307200
15233001412014-06-23402101.020.75102013502.0NONONEAverage7 Average10200.020090.09814447.5944-122.29910202007
2913101002015-01-16400000.032.50160023882.0NONONEAverage8 Good16000.020040.09802747.5345-122.06914101287
15233001572014-10-15325000.020.75102010762.0NONONEAverage7 Average10200.020080.09814447.5941-122.29910201357
\n", + "

21597 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " date price bedrooms bathrooms sqft_living sqft_lot \\\n", + "id \n", + "7129300520 2014-10-13 221900.0 3 1.00 1180 5650 \n", + "6414100192 2014-12-09 538000.0 3 2.25 2570 7242 \n", + "5631500400 2015-02-25 180000.0 2 1.00 770 10000 \n", + "2487200875 2014-12-09 604000.0 4 3.00 1960 5000 \n", + "1954400510 2015-02-18 510000.0 3 2.00 1680 8080 \n", + "... ... ... ... ... ... ... \n", + "263000018 2014-05-21 360000.0 3 2.50 1530 1131 \n", + "6600060120 2015-02-23 400000.0 4 2.50 2310 5813 \n", + "1523300141 2014-06-23 402101.0 2 0.75 1020 1350 \n", + "291310100 2015-01-16 400000.0 3 2.50 1600 2388 \n", + "1523300157 2014-10-15 325000.0 2 0.75 1020 1076 \n", + "\n", + " floors waterfront view condition grade sqft_above \\\n", + "id \n", + "7129300520 1.0 NO NONE Average 7 Average 1180 \n", + "6414100192 2.0 NO NONE Average 7 Average 2170 \n", + "5631500400 1.0 NO NONE Average 6 Low Average 770 \n", + "2487200875 1.0 NO NONE Very Good 7 Average 1050 \n", + "1954400510 1.0 NO NONE Average 8 Good 1680 \n", + "... ... ... ... ... ... ... \n", + "263000018 3.0 NO NONE Average 8 Good 1530 \n", + "6600060120 2.0 NO NONE Average 8 Good 2310 \n", + "1523300141 2.0 NO NONE Average 7 Average 1020 \n", + "291310100 2.0 NO NONE Average 8 Good 1600 \n", + "1523300157 2.0 NO NONE Average 7 Average 1020 \n", + "\n", + " sqft_basement yr_built yr_renovated zipcode lat long \\\n", + "id \n", + "7129300520 0.0 1955 0.0 98178 47.5112 -122.257 \n", + "6414100192 400.0 1951 1.0 98125 47.7210 -122.319 \n", + "5631500400 0.0 1933 0.0 98028 47.7379 -122.233 \n", + "2487200875 910.0 1965 0.0 98136 47.5208 -122.393 \n", + "1954400510 0.0 1987 0.0 98074 47.6168 -122.045 \n", + "... ... ... ... ... ... ... \n", + "263000018 0.0 2009 0.0 98103 47.6993 -122.346 \n", + "6600060120 0.0 2014 0.0 98146 47.5107 -122.362 \n", + "1523300141 0.0 2009 0.0 98144 47.5944 -122.299 \n", + "291310100 0.0 2004 0.0 98027 47.5345 -122.069 \n", + "1523300157 0.0 2008 0.0 98144 47.5941 -122.299 \n", + "\n", + " sqft_living15 sqft_lot15 \n", + "id \n", + "7129300520 1340 5650 \n", + "6414100192 1690 7639 \n", + "5631500400 2720 8062 \n", + "2487200875 1360 5000 \n", + "1954400510 1800 7503 \n", + "... ... ... \n", + "263000018 1530 1509 \n", + "6600060120 1830 7200 \n", + "1523300141 1020 2007 \n", + "291310100 1410 1287 \n", + "1523300157 1020 1357 \n", + "\n", + "[21597 rows x 20 columns]" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Convert sqft_basement to int and replace ? with 0\n", + "df['sqft_basement'] = df['sqft_basement'].replace({'?':np.nan}).astype(float)\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
datepricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewcondition...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
id
71293005202014-10-13221900.031.00118056501.0NONONEAverage...0.019550.09817847.5112-122.25713405650102014
64141001922014-12-09538000.032.25257072422.0NONONEAverage...400.019511.09812547.7210-122.31916907639122014
56315004002015-02-25180000.021.00770100001.0NONONEAverage...0.019330.09802847.7379-122.2332720806222015
24872008752014-12-09604000.043.00196050001.0NONONEVery Good...910.019650.09813647.5208-122.39313605000122014
19544005102015-02-18510000.032.00168080801.0NONONEAverage...0.019870.09807447.6168-122.0451800750322015
..................................................................
2630000182014-05-21360000.032.50153011313.0NONONEAverage...0.020090.09810347.6993-122.3461530150952014
66000601202015-02-23400000.042.50231058132.0NONONEAverage...0.020140.09814647.5107-122.3621830720022015
15233001412014-06-23402101.020.75102013502.0NONONEAverage...0.020090.09814447.5944-122.2991020200762014
2913101002015-01-16400000.032.50160023882.0NONONEAverage...0.020040.09802747.5345-122.0691410128712015
15233001572014-10-15325000.020.75102010762.0NONONEAverage...0.020080.09814447.5941-122.29910201357102014
\n", + "

21597 rows × 22 columns

\n", + "
" + ], + "text/plain": [ + " date price bedrooms bathrooms sqft_living sqft_lot \\\n", + "id \n", + "7129300520 2014-10-13 221900.0 3 1.00 1180 5650 \n", + "6414100192 2014-12-09 538000.0 3 2.25 2570 7242 \n", + "5631500400 2015-02-25 180000.0 2 1.00 770 10000 \n", + "2487200875 2014-12-09 604000.0 4 3.00 1960 5000 \n", + "1954400510 2015-02-18 510000.0 3 2.00 1680 8080 \n", + "... ... ... ... ... ... ... \n", + "263000018 2014-05-21 360000.0 3 2.50 1530 1131 \n", + "6600060120 2015-02-23 400000.0 4 2.50 2310 5813 \n", + "1523300141 2014-06-23 402101.0 2 0.75 1020 1350 \n", + "291310100 2015-01-16 400000.0 3 2.50 1600 2388 \n", + "1523300157 2014-10-15 325000.0 2 0.75 1020 1076 \n", + "\n", + " floors waterfront view condition ... sqft_basement yr_built \\\n", + "id ... \n", + "7129300520 1.0 NO NONE Average ... 0.0 1955 \n", + "6414100192 2.0 NO NONE Average ... 400.0 1951 \n", + "5631500400 1.0 NO NONE Average ... 0.0 1933 \n", + "2487200875 1.0 NO NONE Very Good ... 910.0 1965 \n", + "1954400510 1.0 NO NONE Average ... 0.0 1987 \n", + "... ... ... ... ... ... ... ... \n", + "263000018 3.0 NO NONE Average ... 0.0 2009 \n", + "6600060120 2.0 NO NONE Average ... 0.0 2014 \n", + "1523300141 2.0 NO NONE Average ... 0.0 2009 \n", + "291310100 2.0 NO NONE Average ... 0.0 2004 \n", + "1523300157 2.0 NO NONE Average ... 0.0 2008 \n", + "\n", + " yr_renovated zipcode lat long sqft_living15 \\\n", + "id \n", + "7129300520 0.0 98178 47.5112 -122.257 1340 \n", + "6414100192 1.0 98125 47.7210 -122.319 1690 \n", + "5631500400 0.0 98028 47.7379 -122.233 2720 \n", + "2487200875 0.0 98136 47.5208 -122.393 1360 \n", + "1954400510 0.0 98074 47.6168 -122.045 1800 \n", + "... ... ... ... ... ... \n", + "263000018 0.0 98103 47.6993 -122.346 1530 \n", + "6600060120 0.0 98146 47.5107 -122.362 1830 \n", + "1523300141 0.0 98144 47.5944 -122.299 1020 \n", + "291310100 0.0 98027 47.5345 -122.069 1410 \n", + "1523300157 0.0 98144 47.5941 -122.299 1020 \n", + "\n", + " sqft_lot15 month_of_date year_of_date \n", + "id \n", + "7129300520 5650 10 2014 \n", + "6414100192 7639 12 2014 \n", + "5631500400 8062 2 2015 \n", + "2487200875 5000 12 2014 \n", + "1954400510 7503 2 2015 \n", + "... ... ... ... \n", + "263000018 1509 5 2014 \n", + "6600060120 7200 2 2015 \n", + "1523300141 2007 6 2014 \n", + "291310100 1287 1 2015 \n", + "1523300157 1357 10 2014 \n", + "\n", + "[21597 rows x 22 columns]" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Retrieve the month and year from the date column.\n", + "df['month_of_date'] = pd.DatetimeIndex(df['date']).month\n", + "df['year_of_date'] = pd.DatetimeIndex(df['date']).year\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongrade...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
id
7129300520221900.031.00118056501.0NONONEAverage7 Average...0.019550.09817847.5112-122.25713405650102014
6414100192538000.032.25257072422.0NONONEAverage7 Average...400.019511.09812547.7210-122.31916907639122014
5631500400180000.021.00770100001.0NONONEAverage6 Low Average...0.019330.09802847.7379-122.2332720806222015
2487200875604000.043.00196050001.0NONONEVery Good7 Average...910.019650.09813647.5208-122.39313605000122014
1954400510510000.032.00168080801.0NONONEAverage8 Good...0.019870.09807447.6168-122.0451800750322015
..................................................................
263000018360000.032.50153011313.0NONONEAverage8 Good...0.020090.09810347.6993-122.3461530150952014
6600060120400000.042.50231058132.0NONONEAverage8 Good...0.020140.09814647.5107-122.3621830720022015
1523300141402101.020.75102013502.0NONONEAverage7 Average...0.020090.09814447.5944-122.2991020200762014
291310100400000.032.50160023882.0NONONEAverage8 Good...0.020040.09802747.5345-122.0691410128712015
1523300157325000.020.75102010762.0NONONEAverage7 Average...0.020080.09814447.5941-122.29910201357102014
\n", + "

21597 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "id \n", + "7129300520 221900.0 3 1.00 1180 5650 1.0 \n", + "6414100192 538000.0 3 2.25 2570 7242 2.0 \n", + "5631500400 180000.0 2 1.00 770 10000 1.0 \n", + "2487200875 604000.0 4 3.00 1960 5000 1.0 \n", + "1954400510 510000.0 3 2.00 1680 8080 1.0 \n", + "... ... ... ... ... ... ... \n", + "263000018 360000.0 3 2.50 1530 1131 3.0 \n", + "6600060120 400000.0 4 2.50 2310 5813 2.0 \n", + "1523300141 402101.0 2 0.75 1020 1350 2.0 \n", + "291310100 400000.0 3 2.50 1600 2388 2.0 \n", + "1523300157 325000.0 2 0.75 1020 1076 2.0 \n", + "\n", + " waterfront view condition grade ... sqft_basement \\\n", + "id ... \n", + "7129300520 NO NONE Average 7 Average ... 0.0 \n", + "6414100192 NO NONE Average 7 Average ... 400.0 \n", + "5631500400 NO NONE Average 6 Low Average ... 0.0 \n", + "2487200875 NO NONE Very Good 7 Average ... 910.0 \n", + "1954400510 NO NONE Average 8 Good ... 0.0 \n", + "... ... ... ... ... ... ... \n", + "263000018 NO NONE Average 8 Good ... 0.0 \n", + "6600060120 NO NONE Average 8 Good ... 0.0 \n", + "1523300141 NO NONE Average 7 Average ... 0.0 \n", + "291310100 NO NONE Average 8 Good ... 0.0 \n", + "1523300157 NO NONE Average 7 Average ... 0.0 \n", + "\n", + " yr_built yr_renovated zipcode lat long sqft_living15 \\\n", + "id \n", + "7129300520 1955 0.0 98178 47.5112 -122.257 1340 \n", + "6414100192 1951 1.0 98125 47.7210 -122.319 1690 \n", + "5631500400 1933 0.0 98028 47.7379 -122.233 2720 \n", + "2487200875 1965 0.0 98136 47.5208 -122.393 1360 \n", + "1954400510 1987 0.0 98074 47.6168 -122.045 1800 \n", + "... ... ... ... ... ... ... \n", + "263000018 2009 0.0 98103 47.6993 -122.346 1530 \n", + "6600060120 2014 0.0 98146 47.5107 -122.362 1830 \n", + "1523300141 2009 0.0 98144 47.5944 -122.299 1020 \n", + "291310100 2004 0.0 98027 47.5345 -122.069 1410 \n", + "1523300157 2008 0.0 98144 47.5941 -122.299 1020 \n", + "\n", + " sqft_lot15 month_of_date year_of_date \n", + "id \n", + "7129300520 5650 10 2014 \n", + "6414100192 7639 12 2014 \n", + "5631500400 8062 2 2015 \n", + "2487200875 5000 12 2014 \n", + "1954400510 7503 2 2015 \n", + "... ... ... ... \n", + "263000018 1509 5 2014 \n", + "6600060120 7200 2 2015 \n", + "1523300141 2007 6 2014 \n", + "291310100 1287 1 2015 \n", + "1523300157 1357 10 2014 \n", + "\n", + "[21597 rows x 21 columns]" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Drop the date column.\n", + "df.drop(columns=['date'], inplace=True)\n", + "df\n" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['Average', 'Very Good', 'Good', 'Poor', 'Fair'], dtype=object)" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Inspecting the condition column\n", + "df['condition'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "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", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongrade...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
id
7129300520221900.031.00118056501.0NONONE37 Average...0.019550.09817847.5112-122.25713405650102014
6414100192538000.032.25257072422.0NONONE37 Average...400.019511.09812547.7210-122.31916907639122014
5631500400180000.021.00770100001.0NONONE36 Low Average...0.019330.09802847.7379-122.2332720806222015
2487200875604000.043.00196050001.0NONONE17 Average...910.019650.09813647.5208-122.39313605000122014
1954400510510000.032.00168080801.0NONONE38 Good...0.019870.09807447.6168-122.0451800750322015
\n", + "

5 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "id \n", + "7129300520 221900.0 3 1.00 1180 5650 1.0 \n", + "6414100192 538000.0 3 2.25 2570 7242 2.0 \n", + "5631500400 180000.0 2 1.00 770 10000 1.0 \n", + "2487200875 604000.0 4 3.00 1960 5000 1.0 \n", + "1954400510 510000.0 3 2.00 1680 8080 1.0 \n", + "\n", + " waterfront view condition grade ... sqft_basement \\\n", + "id ... \n", + "7129300520 NO NONE 3 7 Average ... 0.0 \n", + "6414100192 NO NONE 3 7 Average ... 400.0 \n", + "5631500400 NO NONE 3 6 Low Average ... 0.0 \n", + "2487200875 NO NONE 1 7 Average ... 910.0 \n", + "1954400510 NO NONE 3 8 Good ... 0.0 \n", + "\n", + " yr_built yr_renovated zipcode lat long sqft_living15 \\\n", + "id \n", + "7129300520 1955 0.0 98178 47.5112 -122.257 1340 \n", + "6414100192 1951 1.0 98125 47.7210 -122.319 1690 \n", + "5631500400 1933 0.0 98028 47.7379 -122.233 2720 \n", + "2487200875 1965 0.0 98136 47.5208 -122.393 1360 \n", + "1954400510 1987 0.0 98074 47.6168 -122.045 1800 \n", + "\n", + " sqft_lot15 month_of_date year_of_date \n", + "id \n", + "7129300520 5650 10 2014 \n", + "6414100192 7639 12 2014 \n", + "5631500400 8062 2 2015 \n", + "2487200875 5000 12 2014 \n", + "1954400510 7503 2 2015 \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Mapping conditions with the respective number\n", + "# Ratings mapping\n", + "ratings_mapping = {\n", + " 'Average': 3,\n", + " 'Very Good': 1,\n", + " 'Good': 2,\n", + " 'Poor': 4,\n", + " 'Fair': 5\n", + "}\n", + "\n", + "# Replace categorical values with numerical values\n", + "df['condition'] = df['condition'].replace(ratings_mapping)\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['NO', 'YES'], dtype=object)" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Inspecting the waterfront column\n", + "df['waterfront'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "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", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongrade...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
id
7129300520221900.031.00118056501.00NONE37 Average...0.019550.09817847.5112-122.25713405650102014
6414100192538000.032.25257072422.00NONE37 Average...400.019511.09812547.7210-122.31916907639122014
5631500400180000.021.00770100001.00NONE36 Low Average...0.019330.09802847.7379-122.2332720806222015
2487200875604000.043.00196050001.00NONE17 Average...910.019650.09813647.5208-122.39313605000122014
1954400510510000.032.00168080801.00NONE38 Good...0.019870.09807447.6168-122.0451800750322015
\n", + "

5 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "id \n", + "7129300520 221900.0 3 1.00 1180 5650 1.0 \n", + "6414100192 538000.0 3 2.25 2570 7242 2.0 \n", + "5631500400 180000.0 2 1.00 770 10000 1.0 \n", + "2487200875 604000.0 4 3.00 1960 5000 1.0 \n", + "1954400510 510000.0 3 2.00 1680 8080 1.0 \n", + "\n", + " waterfront view condition grade ... sqft_basement \\\n", + "id ... \n", + "7129300520 0 NONE 3 7 Average ... 0.0 \n", + "6414100192 0 NONE 3 7 Average ... 400.0 \n", + "5631500400 0 NONE 3 6 Low Average ... 0.0 \n", + "2487200875 0 NONE 1 7 Average ... 910.0 \n", + "1954400510 0 NONE 3 8 Good ... 0.0 \n", + "\n", + " yr_built yr_renovated zipcode lat long sqft_living15 \\\n", + "id \n", + "7129300520 1955 0.0 98178 47.5112 -122.257 1340 \n", + "6414100192 1951 1.0 98125 47.7210 -122.319 1690 \n", + "5631500400 1933 0.0 98028 47.7379 -122.233 2720 \n", + "2487200875 1965 0.0 98136 47.5208 -122.393 1360 \n", + "1954400510 1987 0.0 98074 47.6168 -122.045 1800 \n", + "\n", + " sqft_lot15 month_of_date year_of_date \n", + "id \n", + "7129300520 5650 10 2014 \n", + "6414100192 7639 12 2014 \n", + "5631500400 8062 2 2015 \n", + "2487200875 5000 12 2014 \n", + "1954400510 7503 2 2015 \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Mapping waterfront with the respective number \n", + "# Replacing YES with 1 and NO with 0\n", + "df['waterfront'] = df['waterfront'].astype(str).replace({'YES': 1, 'NO': 0})\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['NONE', 'GOOD', 'EXCELLENT', 'AVERAGE', 'FAIR'], dtype=object)" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Inspecting the view column\n", + "df['view'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "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", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongrade...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
id
7129300520221900.031.00118056501.00037 Average...0.019550.09817847.5112-122.25713405650102014
6414100192538000.032.25257072422.00037 Average...400.019511.09812547.7210-122.31916907639122014
5631500400180000.021.00770100001.00036 Low Average...0.019330.09802847.7379-122.2332720806222015
2487200875604000.043.00196050001.00017 Average...910.019650.09813647.5208-122.39313605000122014
1954400510510000.032.00168080801.00038 Good...0.019870.09807447.6168-122.0451800750322015
\n", + "

5 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "id \n", + "7129300520 221900.0 3 1.00 1180 5650 1.0 \n", + "6414100192 538000.0 3 2.25 2570 7242 2.0 \n", + "5631500400 180000.0 2 1.00 770 10000 1.0 \n", + "2487200875 604000.0 4 3.00 1960 5000 1.0 \n", + "1954400510 510000.0 3 2.00 1680 8080 1.0 \n", + "\n", + " waterfront view condition grade ... sqft_basement \\\n", + "id ... \n", + "7129300520 0 0 3 7 Average ... 0.0 \n", + "6414100192 0 0 3 7 Average ... 400.0 \n", + "5631500400 0 0 3 6 Low Average ... 0.0 \n", + "2487200875 0 0 1 7 Average ... 910.0 \n", + "1954400510 0 0 3 8 Good ... 0.0 \n", + "\n", + " yr_built yr_renovated zipcode lat long sqft_living15 \\\n", + "id \n", + "7129300520 1955 0.0 98178 47.5112 -122.257 1340 \n", + "6414100192 1951 1.0 98125 47.7210 -122.319 1690 \n", + "5631500400 1933 0.0 98028 47.7379 -122.233 2720 \n", + "2487200875 1965 0.0 98136 47.5208 -122.393 1360 \n", + "1954400510 1987 0.0 98074 47.6168 -122.045 1800 \n", + "\n", + " sqft_lot15 month_of_date year_of_date \n", + "id \n", + "7129300520 5650 10 2014 \n", + "6414100192 7639 12 2014 \n", + "5631500400 8062 2 2015 \n", + "2487200875 5000 12 2014 \n", + "1954400510 7503 2 2015 \n", + "\n", + "[5 rows x 21 columns]" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Define the mappings\n", + "quality_mapping = {\n", + " 'NONE': 0,\n", + " 'GOOD': 1,\n", + " 'EXCELLENT': 2,\n", + " 'AVERAGE': 3,\n", + " 'FAIR': 4\n", + "}\n", + "\n", + "# Replace the values using the mapping\n", + "df['view'] = df['view'].replace(quality_mapping)\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array(['7 Average', '6 Low Average', '8 Good', '11 Excellent', '9 Better',\n", + " '5 Fair', '10 Very Good', '12 Luxury', '4 Low', '3 Poor',\n", + " '13 Mansion'], dtype=object)" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Inspecting the grade column\n", + "df['grade'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongrade...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
id
7129300520221900.031.00118056501.00037...0.019550.09817847.5112-122.25713405650102014
6414100192538000.032.25257072422.00037...400.019511.09812547.7210-122.31916907639122014
5631500400180000.021.00770100001.00036...0.019330.09802847.7379-122.2332720806222015
2487200875604000.043.00196050001.00017...910.019650.09813647.5208-122.39313605000122014
1954400510510000.032.00168080801.00038...0.019870.09807447.6168-122.0451800750322015
..................................................................
263000018360000.032.50153011313.00038...0.020090.09810347.6993-122.3461530150952014
6600060120400000.042.50231058132.00038...0.020140.09814647.5107-122.3621830720022015
1523300141402101.020.75102013502.00037...0.020090.09814447.5944-122.2991020200762014
291310100400000.032.50160023882.00038...0.020040.09802747.5345-122.0691410128712015
1523300157325000.020.75102010762.00037...0.020080.09814447.5941-122.29910201357102014
\n", + "

21597 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "id \n", + "7129300520 221900.0 3 1.00 1180 5650 1.0 \n", + "6414100192 538000.0 3 2.25 2570 7242 2.0 \n", + "5631500400 180000.0 2 1.00 770 10000 1.0 \n", + "2487200875 604000.0 4 3.00 1960 5000 1.0 \n", + "1954400510 510000.0 3 2.00 1680 8080 1.0 \n", + "... ... ... ... ... ... ... \n", + "263000018 360000.0 3 2.50 1530 1131 3.0 \n", + "6600060120 400000.0 4 2.50 2310 5813 2.0 \n", + "1523300141 402101.0 2 0.75 1020 1350 2.0 \n", + "291310100 400000.0 3 2.50 1600 2388 2.0 \n", + "1523300157 325000.0 2 0.75 1020 1076 2.0 \n", + "\n", + " waterfront view condition grade ... sqft_basement yr_built \\\n", + "id ... \n", + "7129300520 0 0 3 7 ... 0.0 1955 \n", + "6414100192 0 0 3 7 ... 400.0 1951 \n", + "5631500400 0 0 3 6 ... 0.0 1933 \n", + "2487200875 0 0 1 7 ... 910.0 1965 \n", + "1954400510 0 0 3 8 ... 0.0 1987 \n", + "... ... ... ... ... ... ... ... \n", + "263000018 0 0 3 8 ... 0.0 2009 \n", + "6600060120 0 0 3 8 ... 0.0 2014 \n", + "1523300141 0 0 3 7 ... 0.0 2009 \n", + "291310100 0 0 3 8 ... 0.0 2004 \n", + "1523300157 0 0 3 7 ... 0.0 2008 \n", + "\n", + " yr_renovated zipcode lat long sqft_living15 \\\n", + "id \n", + "7129300520 0.0 98178 47.5112 -122.257 1340 \n", + "6414100192 1.0 98125 47.7210 -122.319 1690 \n", + "5631500400 0.0 98028 47.7379 -122.233 2720 \n", + "2487200875 0.0 98136 47.5208 -122.393 1360 \n", + "1954400510 0.0 98074 47.6168 -122.045 1800 \n", + "... ... ... ... ... ... \n", + "263000018 0.0 98103 47.6993 -122.346 1530 \n", + "6600060120 0.0 98146 47.5107 -122.362 1830 \n", + "1523300141 0.0 98144 47.5944 -122.299 1020 \n", + "291310100 0.0 98027 47.5345 -122.069 1410 \n", + "1523300157 0.0 98144 47.5941 -122.299 1020 \n", + "\n", + " sqft_lot15 month_of_date year_of_date \n", + "id \n", + "7129300520 5650 10 2014 \n", + "6414100192 7639 12 2014 \n", + "5631500400 8062 2 2015 \n", + "2487200875 5000 12 2014 \n", + "1954400510 7503 2 2015 \n", + "... ... ... ... \n", + "263000018 1509 5 2014 \n", + "6600060120 7200 2 2015 \n", + "1523300141 2007 6 2014 \n", + "291310100 1287 1 2015 \n", + "1523300157 1357 10 2014 \n", + "\n", + "[21597 rows x 21 columns]" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Define the mappings\n", + "rating_mapping = {\n", + " 'Average': 7,\n", + " 'Low Average': 6,\n", + " 'Good': 8,\n", + " 'Excellent': 11,\n", + " 'Better': 9,\n", + " 'Fair': 5,\n", + " 'Very Good': 10,\n", + " 'Luxury': 12,\n", + " 'Low': 4,\n", + " 'Poor': 3,\n", + " 'Mansion': 13\n", + "}\n", + "\n", + "# Extract the rating string and replace with the corresponding numerical value\n", + "df['grade'] = df['grade'].str.extract('(\\d+)').astype(int)\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Int64Index: 21597 entries, 7129300520 to 1523300157\n", + "Data columns (total 21 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 price 21597 non-null float64\n", + " 1 bedrooms 21597 non-null int64 \n", + " 2 bathrooms 21597 non-null float64\n", + " 3 sqft_living 21597 non-null int64 \n", + " 4 sqft_lot 21597 non-null int64 \n", + " 5 floors 21597 non-null float64\n", + " 6 waterfront 21597 non-null int64 \n", + " 7 view 21597 non-null int64 \n", + " 8 condition 21597 non-null int64 \n", + " 9 grade 21597 non-null int64 \n", + " 10 sqft_above 21597 non-null int64 \n", + " 11 sqft_basement 21143 non-null float64\n", + " 12 yr_built 21597 non-null int64 \n", + " 13 yr_renovated 21597 non-null float64\n", + " 14 zipcode 21597 non-null int64 \n", + " 15 lat 21597 non-null float64\n", + " 16 long 21597 non-null float64\n", + " 17 sqft_living15 21597 non-null int64 \n", + " 18 sqft_lot15 21597 non-null int64 \n", + " 19 month_of_date 21597 non-null int64 \n", + " 20 year_of_date 21597 non-null int64 \n", + "dtypes: float64(7), int64(14)\n", + "memory usage: 4.2 MB\n" + ] + } + ], + "source": [ + "df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "sqft_living 0.701917\n", + "grade 0.667951\n", + "sqft_above 0.605368\n", + "sqft_living15 0.585241\n", + "bathrooms 0.525906\n", + "sqft_basement 0.325008\n", + "bedrooms 0.308787\n", + "lat 0.306692\n", + "view 0.290620\n", + "waterfront 0.264306\n", + "floors 0.256804\n", + "yr_renovated 0.117543\n", + "sqft_lot 0.089876\n", + "sqft_lot15 0.082845\n", + "yr_built 0.053953\n", + "zipcode 0.053402\n", + "condition 0.040742\n", + "long 0.022036\n", + "month_of_date 0.009928\n", + "year_of_date 0.003727\n", + "Name: price, dtype: float64" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Checking the correlation between price (target) and predictors\n", + "df.corr()['price'].drop(['price']).map(abs).sort_values(ascending=False)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "sqft_living, grade, sqft_above have the highest correlation with the target while year_of_date, month_of_date and long have the lowest correlation with the target." + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": {}, + "outputs": [], + "source": [ + "# Identfying Numeric and categorical columns\n", + "numeric = ['bedrooms', \n", + " 'bathrooms', \n", + " 'sqft_living', \n", + " 'sqft_lot', \n", + " 'sqft_above', \n", + " 'sqft_basement',\n", + " 'lat', \n", + " 'long',\n", + " 'sqft_living15', \n", + " 'sqft_lot15']\n", + "\n", + "categorical = ['floors',\n", + " 'waterfront', \n", + " 'view', \n", + " 'condition', \n", + " 'grade',\n", + " 'yr_renovated',\n", + " 'zipcode',\n", + " 'month_of_date']" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongrade...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
0221900.031.00118056501.00037...0.019550.09817847.5112-122.25713405650102014
1538000.032.25257072422.00037...400.019511.09812547.7210-122.31916907639122014
2180000.021.00770100001.00036...0.019330.09802847.7379-122.2332720806222015
3604000.043.00196050001.00017...910.019650.09813647.5208-122.39313605000122014
4510000.032.00168080801.00038...0.019870.09807447.6168-122.0451800750322015
..................................................................
21592360000.032.50153011313.00038...0.020090.09810347.6993-122.3461530150952014
21593400000.042.50231058132.00038...0.020140.09814647.5107-122.3621830720022015
21594402101.020.75102013502.00037...0.020090.09814447.5944-122.2991020200762014
21595400000.032.50160023882.00038...0.020040.09802747.5345-122.0691410128712015
21596325000.020.75102010762.00037...0.020080.09814447.5941-122.29910201357102014
\n", + "

21597 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot floors \\\n", + "0 221900.0 3 1.00 1180 5650 1.0 \n", + "1 538000.0 3 2.25 2570 7242 2.0 \n", + "2 180000.0 2 1.00 770 10000 1.0 \n", + "3 604000.0 4 3.00 1960 5000 1.0 \n", + "4 510000.0 3 2.00 1680 8080 1.0 \n", + "... ... ... ... ... ... ... \n", + "21592 360000.0 3 2.50 1530 1131 3.0 \n", + "21593 400000.0 4 2.50 2310 5813 2.0 \n", + "21594 402101.0 2 0.75 1020 1350 2.0 \n", + "21595 400000.0 3 2.50 1600 2388 2.0 \n", + "21596 325000.0 2 0.75 1020 1076 2.0 \n", + "\n", + " waterfront view condition grade ... sqft_basement yr_built \\\n", + "0 0 0 3 7 ... 0.0 1955 \n", + "1 0 0 3 7 ... 400.0 1951 \n", + "2 0 0 3 6 ... 0.0 1933 \n", + "3 0 0 1 7 ... 910.0 1965 \n", + "4 0 0 3 8 ... 0.0 1987 \n", + "... ... ... ... ... ... ... ... \n", + "21592 0 0 3 8 ... 0.0 2009 \n", + "21593 0 0 3 8 ... 0.0 2014 \n", + "21594 0 0 3 7 ... 0.0 2009 \n", + "21595 0 0 3 8 ... 0.0 2004 \n", + "21596 0 0 3 7 ... 0.0 2008 \n", + "\n", + " yr_renovated zipcode lat long sqft_living15 sqft_lot15 \\\n", + "0 0.0 98178 47.5112 -122.257 1340 5650 \n", + "1 1.0 98125 47.7210 -122.319 1690 7639 \n", + "2 0.0 98028 47.7379 -122.233 2720 8062 \n", + "3 0.0 98136 47.5208 -122.393 1360 5000 \n", + "4 0.0 98074 47.6168 -122.045 1800 7503 \n", + "... ... ... ... ... ... ... \n", + "21592 0.0 98103 47.6993 -122.346 1530 1509 \n", + "21593 0.0 98146 47.5107 -122.362 1830 7200 \n", + "21594 0.0 98144 47.5944 -122.299 1020 2007 \n", + "21595 0.0 98027 47.5345 -122.069 1410 1287 \n", + "21596 0.0 98144 47.5941 -122.299 1020 1357 \n", + "\n", + " month_of_date year_of_date \n", + "0 10 2014 \n", + "1 12 2014 \n", + "2 2 2015 \n", + "3 12 2014 \n", + "4 2 2015 \n", + "... ... ... \n", + "21592 5 2014 \n", + "21593 2 2015 \n", + "21594 6 2014 \n", + "21595 1 2015 \n", + "21596 10 2014 \n", + "\n", + "[21597 rows x 21 columns]" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#reset index and dropping the id column\n", + "df.reset_index(inplace=True, drop=True)\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "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 price 21597 non-null float64\n", + " 1 bedrooms 21597 non-null int64 \n", + " 2 bathrooms 21597 non-null float64\n", + " 3 sqft_living 21597 non-null int64 \n", + " 4 sqft_lot 21597 non-null int64 \n", + " 5 floors 21597 non-null float64\n", + " 6 waterfront 21597 non-null int64 \n", + " 7 view 21597 non-null int64 \n", + " 8 condition 21597 non-null int64 \n", + " 9 grade 21597 non-null int64 \n", + " 10 sqft_above 21597 non-null int64 \n", + " 11 sqft_basement 21143 non-null float64\n", + " 12 yr_built 21597 non-null int64 \n", + " 13 yr_renovated 21597 non-null float64\n", + " 14 zipcode 21597 non-null int64 \n", + " 15 lat 21597 non-null float64\n", + " 16 long 21597 non-null float64\n", + " 17 sqft_living15 21597 non-null int64 \n", + " 18 sqft_lot15 21597 non-null int64 \n", + " 19 month_of_date 21597 non-null int64 \n", + " 20 year_of_date 21597 non-null int64 \n", + "dtypes: float64(7), int64(14)\n", + "memory usage: 3.5 MB\n" + ] + } + ], + "source": [ + "df.info()" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -1126,9 +5208,9 @@ ], "metadata": { "kernelspec": { - "display_name": "Python (learn-env)", + "display_name": "learn-env", "language": "python", - "name": "learn-env" + "name": "python3" }, "language_info": { "codemirror_mode": { @@ -1140,7 +5222,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.5" + "version": "3.8.5" } }, "nbformat": 4, From 35274322edea6984280f1912c27751b13c06d396 Mon Sep 17 00:00:00 2001 From: troye Date: Mon, 29 Apr 2024 13:23:35 +0300 Subject: [PATCH 9/9] pre-processing --- student.ipynb | 310 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 310 insertions(+) diff --git a/student.ipynb b/student.ipynb index f8cc5c88..ff16a400 100644 --- a/student.ipynb +++ b/student.ipynb @@ -5189,6 +5189,316 @@ "df.info()" ] }, + { + "cell_type": "code", + "execution_count": 45, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
pricebedroomsbathroomssqft_livingsqft_lotfloorswaterfrontviewconditiongrade...sqft_basementyr_builtyr_renovatedzipcodelatlongsqft_living15sqft_lot15month_of_dateyear_of_date
count2.159700e+0421597.00000021597.00000021597.0000002.159700e+0421597.00000021597.00000021597.00000021597.00000021597.000000...21143.00000021597.00000021597.00000021597.00000021597.00000021597.00000021597.00000021597.00000021597.00000021597.000000
mean5.402966e+053.3732002.1158262080.3218501.509941e+041.4940960.0067600.2469322.5967037.657915...291.8517241970.9996760.03444998077.95184547.560093-122.2139821986.62031812758.2835126.5739692014.322962
std3.673681e+050.9262990.768984918.1061254.141264e+040.5396830.0819440.8152130.6694071.173200...442.49833729.3752340.18238453.5130720.1385520.140724685.23047227274.4419503.1150610.467619
min7.800000e+041.0000000.500000370.0000005.200000e+021.0000000.0000000.0000001.0000003.000000...0.0000001900.0000000.00000098001.00000047.155900-122.519000399.000000651.0000001.0000002014.000000
25%3.220000e+053.0000001.7500001430.0000005.040000e+031.0000000.0000000.0000002.0000007.000000...0.0000001951.0000000.00000098033.00000047.471100-122.3280001490.0000005100.0000004.0000002014.000000
50%4.500000e+053.0000002.2500001910.0000007.618000e+031.5000000.0000000.0000003.0000007.000000...0.0000001975.0000000.00000098065.00000047.571800-122.2310001840.0000007620.0000006.0000002014.000000
75%6.450000e+054.0000002.5000002550.0000001.068500e+042.0000000.0000000.0000003.0000008.000000...560.0000001997.0000000.00000098118.00000047.678000-122.1250002360.00000010083.0000009.0000002015.000000
max7.700000e+0633.0000008.00000013540.0000001.651359e+063.5000001.0000004.0000005.00000013.000000...4820.0000002015.0000001.00000098199.00000047.777600-121.3150006210.000000871200.00000012.0000002015.000000
\n", + "

8 rows × 21 columns

\n", + "
" + ], + "text/plain": [ + " price bedrooms bathrooms sqft_living sqft_lot \\\n", + "count 2.159700e+04 21597.000000 21597.000000 21597.000000 2.159700e+04 \n", + "mean 5.402966e+05 3.373200 2.115826 2080.321850 1.509941e+04 \n", + "std 3.673681e+05 0.926299 0.768984 918.106125 4.141264e+04 \n", + "min 7.800000e+04 1.000000 0.500000 370.000000 5.200000e+02 \n", + "25% 3.220000e+05 3.000000 1.750000 1430.000000 5.040000e+03 \n", + "50% 4.500000e+05 3.000000 2.250000 1910.000000 7.618000e+03 \n", + "75% 6.450000e+05 4.000000 2.500000 2550.000000 1.068500e+04 \n", + "max 7.700000e+06 33.000000 8.000000 13540.000000 1.651359e+06 \n", + "\n", + " floors waterfront view condition grade \\\n", + "count 21597.000000 21597.000000 21597.000000 21597.000000 21597.000000 \n", + "mean 1.494096 0.006760 0.246932 2.596703 7.657915 \n", + "std 0.539683 0.081944 0.815213 0.669407 1.173200 \n", + "min 1.000000 0.000000 0.000000 1.000000 3.000000 \n", + "25% 1.000000 0.000000 0.000000 2.000000 7.000000 \n", + "50% 1.500000 0.000000 0.000000 3.000000 7.000000 \n", + "75% 2.000000 0.000000 0.000000 3.000000 8.000000 \n", + "max 3.500000 1.000000 4.000000 5.000000 13.000000 \n", + "\n", + " ... sqft_basement yr_built yr_renovated zipcode \\\n", + "count ... 21143.000000 21597.000000 21597.000000 21597.000000 \n", + "mean ... 291.851724 1970.999676 0.034449 98077.951845 \n", + "std ... 442.498337 29.375234 0.182384 53.513072 \n", + "min ... 0.000000 1900.000000 0.000000 98001.000000 \n", + "25% ... 0.000000 1951.000000 0.000000 98033.000000 \n", + "50% ... 0.000000 1975.000000 0.000000 98065.000000 \n", + "75% ... 560.000000 1997.000000 0.000000 98118.000000 \n", + "max ... 4820.000000 2015.000000 1.000000 98199.000000 \n", + "\n", + " lat long sqft_living15 sqft_lot15 \\\n", + "count 21597.000000 21597.000000 21597.000000 21597.000000 \n", + "mean 47.560093 -122.213982 1986.620318 12758.283512 \n", + "std 0.138552 0.140724 685.230472 27274.441950 \n", + "min 47.155900 -122.519000 399.000000 651.000000 \n", + "25% 47.471100 -122.328000 1490.000000 5100.000000 \n", + "50% 47.571800 -122.231000 1840.000000 7620.000000 \n", + "75% 47.678000 -122.125000 2360.000000 10083.000000 \n", + "max 47.777600 -121.315000 6210.000000 871200.000000 \n", + "\n", + " month_of_date year_of_date \n", + "count 21597.000000 21597.000000 \n", + "mean 6.573969 2014.322962 \n", + "std 3.115061 0.467619 \n", + "min 1.000000 2014.000000 \n", + "25% 4.000000 2014.000000 \n", + "50% 6.000000 2014.000000 \n", + "75% 9.000000 2015.000000 \n", + "max 12.000000 2015.000000 \n", + "\n", + "[8 rows x 21 columns]" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.describe()" + ] + }, { "cell_type": "markdown", "metadata": {},