diff --git a/KINGS_COUNTY_HOUSING-Updated 2.pdf b/KINGS_COUNTY_HOUSING-Updated 2.pdf
new file mode 100644
index 00000000..bc64d3db
Binary files /dev/null and b/KINGS_COUNTY_HOUSING-Updated 2.pdf differ
diff --git a/Updated Presentation.pdf b/Updated Presentation.pdf
new file mode 100644
index 00000000..f50479b8
Binary files /dev/null and b/Updated Presentation.pdf differ
diff --git a/presentation.pdf b/presentation.pdf
new file mode 100644
index 00000000..ed038166
Binary files /dev/null and b/presentation.pdf differ
diff --git a/student.ipynb b/student.ipynb
index d3bb34af..c3e0bb0e 100644
--- a/student.ipynb
+++ b/student.ipynb
@@ -14,13 +14,2030 @@
"* Blog post URL:\n"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### IMPORTING OF LIBRARIES"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd # for reading our data\n",
+ "import numpy as np # for performing calculations\n",
+ "import seaborn as sns # for visualization\n",
+ "import matplotlib.pyplot as plt # for visualization\n",
+ "%matplotlib inline\n",
+ "\n",
+ "import scipy.stats as stat # to calculate statistical operations\n",
+ "\n",
+ "from statsmodels.formula.api import ols #for creating a model\n",
+ "\n",
+ "from sklearn.model_selection import train_test_split # for performing train train_test_split on our data\n",
+ "from sklearn.linear_model import LinearRegression # making a LinearRegression model\n",
+ "from sklearn.metrics import mean_squared_error # for calculating error metrics to evaluate our model"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### LOADING DATA INTO A DATAFRAME\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " id | \n",
+ " date | \n",
+ " price | \n",
+ " bedrooms | \n",
+ " bathrooms | \n",
+ " sqft_living | \n",
+ " sqft_lot | \n",
+ " floors | \n",
+ " waterfront | \n",
+ " view | \n",
+ " ... | \n",
+ " grade | \n",
+ " sqft_above | \n",
+ " sqft_basement | \n",
+ " yr_built | \n",
+ " yr_renovated | \n",
+ " zipcode | \n",
+ " lat | \n",
+ " long | \n",
+ " sqft_living15 | \n",
+ " sqft_lot15 | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 7129300520 | \n",
+ " 10/13/2014 | \n",
+ " 221900.0 | \n",
+ " 3 | \n",
+ " 1.00 | \n",
+ " 1180 | \n",
+ " 5650 | \n",
+ " 1.0 | \n",
+ " NaN | \n",
+ " NONE | \n",
+ " ... | \n",
+ " 7 Average | \n",
+ " 1180 | \n",
+ " 0.0 | \n",
+ " 1955 | \n",
+ " 0.0 | \n",
+ " 98178 | \n",
+ " 47.5112 | \n",
+ " -122.257 | \n",
+ " 1340 | \n",
+ " 5650 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 6414100192 | \n",
+ " 12/9/2014 | \n",
+ " 538000.0 | \n",
+ " 3 | \n",
+ " 2.25 | \n",
+ " 2570 | \n",
+ " 7242 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " ... | \n",
+ " 7 Average | \n",
+ " 2170 | \n",
+ " 400.0 | \n",
+ " 1951 | \n",
+ " 1991.0 | \n",
+ " 98125 | \n",
+ " 47.7210 | \n",
+ " -122.319 | \n",
+ " 1690 | \n",
+ " 7639 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 5631500400 | \n",
+ " 2/25/2015 | \n",
+ " 180000.0 | \n",
+ " 2 | \n",
+ " 1.00 | \n",
+ " 770 | \n",
+ " 10000 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " ... | \n",
+ " 6 Low Average | \n",
+ " 770 | \n",
+ " 0.0 | \n",
+ " 1933 | \n",
+ " NaN | \n",
+ " 98028 | \n",
+ " 47.7379 | \n",
+ " -122.233 | \n",
+ " 2720 | \n",
+ " 8062 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 2487200875 | \n",
+ " 12/9/2014 | \n",
+ " 604000.0 | \n",
+ " 4 | \n",
+ " 3.00 | \n",
+ " 1960 | \n",
+ " 5000 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " ... | \n",
+ " 7 Average | \n",
+ " 1050 | \n",
+ " 910.0 | \n",
+ " 1965 | \n",
+ " 0.0 | \n",
+ " 98136 | \n",
+ " 47.5208 | \n",
+ " -122.393 | \n",
+ " 1360 | \n",
+ " 5000 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1954400510 | \n",
+ " 2/18/2015 | \n",
+ " 510000.0 | \n",
+ " 3 | \n",
+ " 2.00 | \n",
+ " 1680 | \n",
+ " 8080 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " ... | \n",
+ " 8 Good | \n",
+ " 1680 | \n",
+ " 0.0 | \n",
+ " 1987 | \n",
+ " 0.0 | \n",
+ " 98074 | \n",
+ " 47.6168 | \n",
+ " -122.045 | \n",
+ " 1800 | \n",
+ " 7503 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
5 rows × 21 columns
\n",
+ "
"
+ ]
+ },
+ "metadata": {
+ "needs_background": "light"
+ },
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "\n",
+ "# Plotting box plots to visualize our outliers\n",
+ "# Creating a list of column names excluding non-numeric columns (if any)\n",
+ "numeric_columns = kc_data_df.select_dtypes(include=['number']).columns\n",
+ "\n",
+ "# Seting up the figure and axes\n",
+ "fig, axes = plt.subplots(nrows=len(numeric_columns), figsize=(10, 6 * len(numeric_columns)))\n",
+ "\n",
+ "# Iterating over each numeric column and create a boxplot\n",
+ "for i, column in enumerate(numeric_columns):\n",
+ " ax = axes[i] if len(numeric_columns) > 1 else axes # If there's only one numeric column, axes is not a list\n",
+ " \n",
+ " # Creating the boxplots\n",
+ " sns.boxplot(x=kc_data_df[column], ax=ax)\n",
+ " \n",
+ " # Seting titles and labels\n",
+ " ax.set_title(f'Boxplot of {column}')\n",
+ " ax.set_xlabel(column)\n",
+ " \n",
+ "\n",
+ "plt.tight_layout(pad=3.0) # Adjusting the spacing between subplots\n",
+ "plt.subplots_adjust(top=0.95) # Adjusting the top margin to accommodate titles \n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "There is a significant amount of outliers in a number of our columns let remove them"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 73,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Removing the outliers \n",
+ "# outliers_df_iqr = kc_data_df[~((kc_data_df < (Q1 - 1.5 * IQR)) |(kc_data_df > (Q3 + 1.5 * IQR))).any(axis=1)]\n",
+ "\n",
+ "#print(outliers_df_iqr.shape) # The number of rows and columns in the new dataframe"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "After we began modelling we chose to undo the removing of outlier since the removal of outliers really affected the performance of our models"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "#### Conversion of the bedroom ,zip code and floors feature into a Categorical Feature\n",
+ "\n",
+ "Analysing the `bedroom`,'zipcode' and floors features in our dataset we observe that although they are stored in numerical form, they are actually a categorical features."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 74,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# creating a function to change the data type of values of a specific column\n",
+ "def change_dtype(df, column_name):\n",
+ " df[column_name] = df[column_name].astype('category')\n",
+ " new_dtype = df[column_name].dtype\n",
+ " return new_dtype\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 75,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "CategoricalDtype(categories=[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 33], ordered=False)"
+ ]
+ },
+ "execution_count": 75,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "change_dtype(kc_data_df, 'bedrooms') # changing the bedroom feature into categorical data type"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 76,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "CategoricalDtype(categories=[1.0, 1.5, 2.0, 2.5, 3.0, 3.5], ordered=False)"
+ ]
+ },
+ "execution_count": 76,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "change_dtype(kc_data_df, 'floors') # changing the floors feature into categorical data type"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 77,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "CategoricalDtype(categories=[98001, 98002, 98003, 98004, 98005, 98006, 98007, 98008,\n",
+ " 98010, 98011, 98014, 98019, 98022, 98023, 98024, 98027,\n",
+ " 98028, 98029, 98030, 98031, 98032, 98033, 98034, 98038,\n",
+ " 98039, 98040, 98042, 98045, 98052, 98053, 98055, 98056,\n",
+ " 98058, 98059, 98065, 98070, 98072, 98074, 98075, 98077,\n",
+ " 98092, 98102, 98103, 98105, 98106, 98107, 98108, 98109,\n",
+ " 98112, 98115, 98116, 98117, 98118, 98119, 98122, 98125,\n",
+ " 98126, 98133, 98136, 98144, 98146, 98148, 98155, 98166,\n",
+ " 98168, 98177, 98178, 98188, 98198, 98199],\n",
+ " ordered=False)"
+ ]
+ },
+ "execution_count": 77,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "change_dtype(kc_data_df, 'zipcode') # changing the zipcode feature into categorical data type"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### FEATURE ENGINEERING"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Lets create additional columns to determine the age of a house by getting the differnce between 2015 (that's when the data was last recorded) the reference year and yr_built, and another column age of the house after renovation by also getting the difference between 2015 and yr_renovated \n",
+ "\n",
+ "These new columns will help to determine whether the age of built or renovation has an impact on the price of the house"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 78,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# creating a new column 'age_built' showing the age of house since its was built upto 2015\n",
+ "kc_data_df['age_built'] = 2015 - kc_data_df['yr_built']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 79,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#creating a new column 'age_renovated'showing the age of a house after renovation\n",
+ "kc_data_df['age_renovated'] = (2015 - kc_data_df['yr_renovated']).apply(lambda x: 0 if x == 2015 else x)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 80,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Index(['id', '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', 'month_sold', 'year_sold', 'age_built',\n",
+ " 'age_renovated'],\n",
+ " dtype='object')"
+ ]
+ },
+ "execution_count": 80,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "kc_data_df.columns # checking to see if the two columns have been added"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 81,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " id | \n",
+ " price | \n",
+ " bedrooms | \n",
+ " bathrooms | \n",
+ " sqft_living | \n",
+ " sqft_lot | \n",
+ " floors | \n",
+ " waterfront | \n",
+ " view | \n",
+ " condition | \n",
+ " ... | \n",
+ " yr_renovated | \n",
+ " zipcode | \n",
+ " lat | \n",
+ " long | \n",
+ " sqft_living15 | \n",
+ " sqft_lot15 | \n",
+ " month_sold | \n",
+ " year_sold | \n",
+ " age_built | \n",
+ " age_renovated | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 7129300520 | \n",
+ " 221900.0 | \n",
+ " 3 | \n",
+ " 1.00 | \n",
+ " 1180 | \n",
+ " 5650 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98178 | \n",
+ " 47.5112 | \n",
+ " -122.257 | \n",
+ " 1340 | \n",
+ " 5650 | \n",
+ " 10 | \n",
+ " 2014 | \n",
+ " 60 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 6414100192 | \n",
+ " 538000.0 | \n",
+ " 3 | \n",
+ " 2.25 | \n",
+ " 2570 | \n",
+ " 7242 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 1991.0 | \n",
+ " 98125 | \n",
+ " 47.7210 | \n",
+ " -122.319 | \n",
+ " 1690 | \n",
+ " 7639 | \n",
+ " 12 | \n",
+ " 2014 | \n",
+ " 64 | \n",
+ " 24.0 | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 5631500400 | \n",
+ " 180000.0 | \n",
+ " 2 | \n",
+ " 1.00 | \n",
+ " 770 | \n",
+ " 10000 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98028 | \n",
+ " 47.7379 | \n",
+ " -122.233 | \n",
+ " 2720 | \n",
+ " 8062 | \n",
+ " 2 | \n",
+ " 2015 | \n",
+ " 82 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 2487200875 | \n",
+ " 604000.0 | \n",
+ " 4 | \n",
+ " 3.00 | \n",
+ " 1960 | \n",
+ " 5000 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Very Good | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98136 | \n",
+ " 47.5208 | \n",
+ " -122.393 | \n",
+ " 1360 | \n",
+ " 5000 | \n",
+ " 12 | \n",
+ " 2014 | \n",
+ " 50 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1954400510 | \n",
+ " 510000.0 | \n",
+ " 3 | \n",
+ " 2.00 | \n",
+ " 1680 | \n",
+ " 8080 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98074 | \n",
+ " 47.6168 | \n",
+ " -122.045 | \n",
+ " 1800 | \n",
+ " 7503 | \n",
+ " 2 | \n",
+ " 2015 | \n",
+ " 28 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " 7237550310 | \n",
+ " 1230000.0 | \n",
+ " 4 | \n",
+ " 4.50 | \n",
+ " 5420 | \n",
+ " 101930 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98053 | \n",
+ " 47.6561 | \n",
+ " -122.005 | \n",
+ " 4760 | \n",
+ " 101930 | \n",
+ " 5 | \n",
+ " 2014 | \n",
+ " 14 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 6 | \n",
+ " 1321400060 | \n",
+ " 257500.0 | \n",
+ " 3 | \n",
+ " 2.25 | \n",
+ " 1715 | \n",
+ " 6819 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98003 | \n",
+ " 47.3097 | \n",
+ " -122.327 | \n",
+ " 2238 | \n",
+ " 6819 | \n",
+ " 6 | \n",
+ " 2014 | \n",
+ " 20 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 7 | \n",
+ " 2008000270 | \n",
+ " 291850.0 | \n",
+ " 3 | \n",
+ " 1.50 | \n",
+ " 1060 | \n",
+ " 9711 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98198 | \n",
+ " 47.4095 | \n",
+ " -122.315 | \n",
+ " 1650 | \n",
+ " 9711 | \n",
+ " 1 | \n",
+ " 2015 | \n",
+ " 52 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 8 | \n",
+ " 2414600126 | \n",
+ " 229500.0 | \n",
+ " 3 | \n",
+ " 1.00 | \n",
+ " 1780 | \n",
+ " 7470 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98146 | \n",
+ " 47.5123 | \n",
+ " -122.337 | \n",
+ " 1780 | \n",
+ " 8113 | \n",
+ " 4 | \n",
+ " 2015 | \n",
+ " 55 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ " | 9 | \n",
+ " 3793500160 | \n",
+ " 323000.0 | \n",
+ " 3 | \n",
+ " 2.50 | \n",
+ " 1890 | \n",
+ " 6560 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 0.0 | \n",
+ " 98038 | \n",
+ " 47.3684 | \n",
+ " -122.031 | \n",
+ " 2390 | \n",
+ " 7570 | \n",
+ " 3 | \n",
+ " 2015 | \n",
+ " 12 | \n",
+ " 0.0 | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
10 rows × 24 columns
\n",
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " id | \n",
+ " price | \n",
+ " bedrooms | \n",
+ " bathrooms | \n",
+ " sqft_living | \n",
+ " sqft_lot | \n",
+ " floors | \n",
+ " waterfront | \n",
+ " view | \n",
+ " condition | \n",
+ " ... | \n",
+ " zipcode | \n",
+ " lat | \n",
+ " long | \n",
+ " sqft_living15 | \n",
+ " sqft_lot15 | \n",
+ " month_sold | \n",
+ " year_sold | \n",
+ " age_built | \n",
+ " age_renovated | \n",
+ " season_sold | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " 7129300520 | \n",
+ " 221900.0 | \n",
+ " 3 | \n",
+ " 1.00 | \n",
+ " 1180 | \n",
+ " 5650 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98178 | \n",
+ " 47.5112 | \n",
+ " -122.257 | \n",
+ " 1340 | \n",
+ " 5650 | \n",
+ " 10 | \n",
+ " 2014 | \n",
+ " 60 | \n",
+ " 0.0 | \n",
+ " Fall | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " 6414100192 | \n",
+ " 538000.0 | \n",
+ " 3 | \n",
+ " 2.25 | \n",
+ " 2570 | \n",
+ " 7242 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98125 | \n",
+ " 47.7210 | \n",
+ " -122.319 | \n",
+ " 1690 | \n",
+ " 7639 | \n",
+ " 12 | \n",
+ " 2014 | \n",
+ " 64 | \n",
+ " 24.0 | \n",
+ " Winter | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " 5631500400 | \n",
+ " 180000.0 | \n",
+ " 2 | \n",
+ " 1.00 | \n",
+ " 770 | \n",
+ " 10000 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98028 | \n",
+ " 47.7379 | \n",
+ " -122.233 | \n",
+ " 2720 | \n",
+ " 8062 | \n",
+ " 2 | \n",
+ " 2015 | \n",
+ " 82 | \n",
+ " 0.0 | \n",
+ " Winter | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " 2487200875 | \n",
+ " 604000.0 | \n",
+ " 4 | \n",
+ " 3.00 | \n",
+ " 1960 | \n",
+ " 5000 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Very Good | \n",
+ " ... | \n",
+ " 98136 | \n",
+ " 47.5208 | \n",
+ " -122.393 | \n",
+ " 1360 | \n",
+ " 5000 | \n",
+ " 12 | \n",
+ " 2014 | \n",
+ " 50 | \n",
+ " 0.0 | \n",
+ " Winter | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " 1954400510 | \n",
+ " 510000.0 | \n",
+ " 3 | \n",
+ " 2.00 | \n",
+ " 1680 | \n",
+ " 8080 | \n",
+ " 1.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98074 | \n",
+ " 47.6168 | \n",
+ " -122.045 | \n",
+ " 1800 | \n",
+ " 7503 | \n",
+ " 2 | \n",
+ " 2015 | \n",
+ " 28 | \n",
+ " 0.0 | \n",
+ " Winter | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 21592 | \n",
+ " 263000018 | \n",
+ " 360000.0 | \n",
+ " 3 | \n",
+ " 2.50 | \n",
+ " 1530 | \n",
+ " 1131 | \n",
+ " 3.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98103 | \n",
+ " 47.6993 | \n",
+ " -122.346 | \n",
+ " 1530 | \n",
+ " 1509 | \n",
+ " 5 | \n",
+ " 2014 | \n",
+ " 6 | \n",
+ " 0.0 | \n",
+ " Spring | \n",
+ "
\n",
+ " \n",
+ " | 21593 | \n",
+ " 6600060120 | \n",
+ " 400000.0 | \n",
+ " 4 | \n",
+ " 2.50 | \n",
+ " 2310 | \n",
+ " 5813 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98146 | \n",
+ " 47.5107 | \n",
+ " -122.362 | \n",
+ " 1830 | \n",
+ " 7200 | \n",
+ " 2 | \n",
+ " 2015 | \n",
+ " 1 | \n",
+ " 0.0 | \n",
+ " Winter | \n",
+ "
\n",
+ " \n",
+ " | 21594 | \n",
+ " 1523300141 | \n",
+ " 402101.0 | \n",
+ " 2 | \n",
+ " 0.75 | \n",
+ " 1020 | \n",
+ " 1350 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98144 | \n",
+ " 47.5944 | \n",
+ " -122.299 | \n",
+ " 1020 | \n",
+ " 2007 | \n",
+ " 6 | \n",
+ " 2014 | \n",
+ " 6 | \n",
+ " 0.0 | \n",
+ " Summer | \n",
+ "
\n",
+ " \n",
+ " | 21595 | \n",
+ " 291310100 | \n",
+ " 400000.0 | \n",
+ " 3 | \n",
+ " 2.50 | \n",
+ " 1600 | \n",
+ " 2388 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98027 | \n",
+ " 47.5345 | \n",
+ " -122.069 | \n",
+ " 1410 | \n",
+ " 1287 | \n",
+ " 1 | \n",
+ " 2015 | \n",
+ " 11 | \n",
+ " 0.0 | \n",
+ " Winter | \n",
+ "
\n",
+ " \n",
+ " | 21596 | \n",
+ " 1523300157 | \n",
+ " 325000.0 | \n",
+ " 2 | \n",
+ " 0.75 | \n",
+ " 1020 | \n",
+ " 1076 | \n",
+ " 2.0 | \n",
+ " NO | \n",
+ " NONE | \n",
+ " Average | \n",
+ " ... | \n",
+ " 98144 | \n",
+ " 47.5941 | \n",
+ " -122.299 | \n",
+ " 1020 | \n",
+ " 1357 | \n",
+ " 10 | \n",
+ " 2014 | \n",
+ " 7 | \n",
+ " 0.0 | \n",
+ " Fall | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
21597 rows × 25 columns
\n",
+ "