{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "5f79677e-3682-4dcf-8470-45df50331d54", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 5, "id": "03875d6c-a837-4e39-bb8f-6515c95d048f", "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", "
priceareabedroomsbathroomsstoriesmainroadguestroombasementhotwaterheatingairconditioningparkingprefareafurnishingstatus
0133000007420423yesnononoyes2yesfurnished
1122500008960444yesnononoyes3nofurnished
2122500009960322yesnoyesnono2yessemi-furnished
3122150007500422yesnoyesnoyes3yesfurnished
4114100007420412yesyesyesnoyes2nofurnished
\n", "
" ], "text/plain": [ " price area bedrooms bathrooms stories mainroad guestroom basement \\\n", "0 13300000 7420 4 2 3 yes no no \n", "1 12250000 8960 4 4 4 yes no no \n", "2 12250000 9960 3 2 2 yes no yes \n", "3 12215000 7500 4 2 2 yes no yes \n", "4 11410000 7420 4 1 2 yes yes yes \n", "\n", " hotwaterheating airconditioning parking prefarea furnishingstatus \n", "0 no yes 2 yes furnished \n", "1 no yes 3 no furnished \n", "2 no no 2 yes semi-furnished \n", "3 no yes 3 yes furnished \n", "4 no yes 2 no furnished " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Load your dataset into a DataFrame\n", "df = pd.read_csv('Housing (1).csv')\n", "# Preview the first 5 rows\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 7, "id": "f0dc4064-e064-46b7-be15-1d05558b4ed4", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "price int64\n", "area int64\n", "bedrooms int64\n", "bathrooms int64\n", "stories int64\n", "mainroad object\n", "guestroom object\n", "basement object\n", "hotwaterheating object\n", "airconditioning object\n", "parking int64\n", "prefarea object\n", "furnishingstatus object\n", "dtype: object" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.dtypes\n" ] }, { "cell_type": "code", "execution_count": 9, "id": "8c568265-3ddc-4735-9341-2c69f41fca4f", "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", "
priceareabedroomsbathroomsstoriesparking
count5.450000e+02545.000000545.000000545.000000545.000000545.000000
mean4.766729e+065150.5412842.9651381.2862391.8055050.693578
std1.870440e+062170.1410230.7380640.5024700.8674920.861586
min1.750000e+061650.0000001.0000001.0000001.0000000.000000
25%3.430000e+063600.0000002.0000001.0000001.0000000.000000
50%4.340000e+064600.0000003.0000001.0000002.0000000.000000
75%5.740000e+066360.0000003.0000002.0000002.0000001.000000
max1.330000e+0716200.0000006.0000004.0000004.0000003.000000
\n", "
" ], "text/plain": [ " price area bedrooms bathrooms stories \\\n", "count 5.450000e+02 545.000000 545.000000 545.000000 545.000000 \n", "mean 4.766729e+06 5150.541284 2.965138 1.286239 1.805505 \n", "std 1.870440e+06 2170.141023 0.738064 0.502470 0.867492 \n", "min 1.750000e+06 1650.000000 1.000000 1.000000 1.000000 \n", "25% 3.430000e+06 3600.000000 2.000000 1.000000 1.000000 \n", "50% 4.340000e+06 4600.000000 3.000000 1.000000 2.000000 \n", "75% 5.740000e+06 6360.000000 3.000000 2.000000 2.000000 \n", "max 1.330000e+07 16200.000000 6.000000 4.000000 4.000000 \n", "\n", " parking \n", "count 545.000000 \n", "mean 0.693578 \n", "std 0.861586 \n", "min 0.000000 \n", "25% 0.000000 \n", "50% 0.000000 \n", "75% 1.000000 \n", "max 3.000000 " ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.describe()\n" ] }, { "cell_type": "code", "execution_count": 11, "id": "5c1cb4b7-7613-4c20-851b-b3dce909d2a9", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "price 0\n", "area 0\n", "bedrooms 0\n", "bathrooms 0\n", "stories 0\n", "mainroad 0\n", "guestroom 0\n", "basement 0\n", "hotwaterheating 0\n", "airconditioning 0\n", "parking 0\n", "prefarea 0\n", "furnishingstatus 0\n", "dtype: int64" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 13, "id": "dc61a637-a6c8-4524-b1da-101dc511bd47", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Columns dropped: []\n", "Remaining columns: Index(['price', 'area', 'bedrooms', 'bathrooms', 'stories', 'mainroad',\n", " 'guestroom', 'basement', 'hotwaterheating', 'airconditioning',\n", " 'parking', 'prefarea', 'furnishingstatus'],\n", " dtype='object')\n" ] } ], "source": [ "missing_percentage = df.isnull().mean() * 100\n", "threshold = 30\n", "# Filter columns with more than the threshold percentage of missing values\n", "columns_to_drop = missing_percentage[missing_percentage > threshold].index\n", "# Drop the columns\n", "df = df.drop(columns=columns_to_drop)\n", "# Display the resulting dataframe after removing columns with too many missing valu\n", "print(f\"Columns dropped: {list(columns_to_drop)}\")\n", "print(f\"Remaining columns: {df.columns}\")\n" ] }, { "cell_type": "code", "execution_count": 15, "id": "91badc65-b8c6-491d-bf79-bed0ed28f6ea", "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", "
priceareabedroomsbathroomsstoriesmainroadguestroombasementhotwaterheatingairconditioningparkingprefareafurnishingstatus
013300000742042310001210
112250000896044410001300
212250000996032210100211
312215000750042210101310
411410000742041211101200
\n", "
" ], "text/plain": [ " price area bedrooms bathrooms stories mainroad guestroom \\\n", "0 13300000 7420 4 2 3 1 0 \n", "1 12250000 8960 4 4 4 1 0 \n", "2 12250000 9960 3 2 2 1 0 \n", "3 12215000 7500 4 2 2 1 0 \n", "4 11410000 7420 4 1 2 1 1 \n", "\n", " basement hotwaterheating airconditioning parking prefarea \\\n", "0 0 0 1 2 1 \n", "1 0 0 1 3 0 \n", "2 1 0 0 2 1 \n", "3 1 0 1 3 1 \n", "4 1 0 1 2 0 \n", "\n", " furnishingstatus \n", "0 0 \n", "1 0 \n", "2 1 \n", "3 0 \n", "4 0 " ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.preprocessing import LabelEncoder\n", "label_encoder = LabelEncoder()\n", "for column in df.select_dtypes(include=['object']).columns:\n", " df[column] = label_encoder.fit_transform(df[column])\n", "df.head()\n" ] }, { "cell_type": "code", "execution_count": 17, "id": "b90467a5-1edc-4fde-97dc-811f8111ddd6", "metadata": {}, "outputs": [], "source": [ "# Fill missing values in columns with mode\n", "for column in df.select_dtypes(include=['float64']).columns:\n", " mean_value = df[column].mean() # Get the mode (most frequent value)\n", " df[column] = df[column].fillna(mean_value)\n" ] }, { "cell_type": "code", "execution_count": 19, "id": "8db53775-f3bb-4faa-a67e-e3346be44924", "metadata": {}, "outputs": [], "source": [ "# Fill missing values in categorical columns with mode\n", "for column in df.select_dtypes(include=['object']).columns:\n", " mode_value = df[column].mode()[0] # Get the mode (most frequent value)\n", " df[column] = df[column].fillna(mode_value)" ] }, { "cell_type": "code", "execution_count": 21, "id": "844a7763-b627-445f-b536-00fae92a4674", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "price 0\n", "area 0\n", "bedrooms 0\n", "bathrooms 0\n", "stories 0\n", "mainroad 0\n", "guestroom 0\n", "basement 0\n", "hotwaterheating 0\n", "airconditioning 0\n", "parking 0\n", "prefarea 0\n", "furnishingstatus 0\n", "dtype: int64" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 23, "id": "05214907-1eb6-4a6b-9286-437a6a095e13", "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", "
priceareabedroomsbathroomsstoriesmainroadguestroombasementhotwaterheatingairconditioningparkingprefareafurnishingstatus
013300000742042310001210
112250000896044410001300
212250000996032210100211
312215000750042210101310
411410000742041211101200
..........................................
5401820000300021110100202
5411767150240031100000001
5421750000362021110000002
5431750000291031100000000
5441750000385031210000002
\n", "

545 rows × 13 columns

\n", "
" ], "text/plain": [ " price area bedrooms bathrooms stories mainroad guestroom \\\n", "0 13300000 7420 4 2 3 1 0 \n", "1 12250000 8960 4 4 4 1 0 \n", "2 12250000 9960 3 2 2 1 0 \n", "3 12215000 7500 4 2 2 1 0 \n", "4 11410000 7420 4 1 2 1 1 \n", ".. ... ... ... ... ... ... ... \n", "540 1820000 3000 2 1 1 1 0 \n", "541 1767150 2400 3 1 1 0 0 \n", "542 1750000 3620 2 1 1 1 0 \n", "543 1750000 2910 3 1 1 0 0 \n", "544 1750000 3850 3 1 2 1 0 \n", "\n", " basement hotwaterheating airconditioning parking prefarea \\\n", "0 0 0 1 2 1 \n", "1 0 0 1 3 0 \n", "2 1 0 0 2 1 \n", "3 1 0 1 3 1 \n", "4 1 0 1 2 0 \n", ".. ... ... ... ... ... \n", "540 1 0 0 2 0 \n", "541 0 0 0 0 0 \n", "542 0 0 0 0 0 \n", "543 0 0 0 0 0 \n", "544 0 0 0 0 0 \n", "\n", " furnishingstatus \n", "0 0 \n", "1 0 \n", "2 1 \n", "3 0 \n", "4 0 \n", ".. ... \n", "540 2 \n", "541 1 \n", "542 2 \n", "543 0 \n", "544 2 \n", "\n", "[545 rows x 13 columns]" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 25, "id": "0aa603a5-3ae7-4480-b30a-09fae3638f7c", "metadata": {}, "outputs": [], "source": [ "def replace_outliers_with_nan(column):\n", " Q1 = column.quantile(0.25)\n", " Q3 = column.quantile(0.75)\n", " IQR = Q3 - Q1\n", " lower_bound = Q1 - 1.5 * IQR\n", " upper_bound = Q3 + 1.5 * IQR\n", " # Replace outliers with NaN\n", " return column.where((column >= lower_bound) & (column <= upper_bound), np.nan)\n", "# Replace outliers with NaN for each feature\n", "for col in df.columns:\n", " df[col] = replace_outliers_with_nan(df[col])" ] }, { "cell_type": "code", "execution_count": 29, "id": "8acf5181-a191-4fce-8bfa-04fda0845ad9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Sum of null values in each column:\n", "price 15\n", "area 12\n", "bedrooms 12\n", "bathrooms 1\n", "stories 41\n", "mainroad 77\n", "guestroom 97\n", "basement 0\n", "hotwaterheating 25\n", "airconditioning 0\n", "parking 12\n", "prefarea 128\n", "furnishingstatus 0\n", "dtype: int64\n" ] } ], "source": [ "null_counts = df.isnull().sum()\n", "print(\"Sum of null values in each column:\")\n", "print(null_counts)\n" ] }, { "cell_type": "code", "execution_count": 50, "id": "7bf5aea3-ab3d-4d07-9a67-5663419126eb", "metadata": {}, "outputs": [], "source": [ "# Fill missing values in numerical columns with median\n", "for column in df.select_dtypes(include=['float64']).columns:\n", " median_value = df[column].median() # Get the median value\n", " df[column] = df[column].fillna(median_value)\n" ] }, { "cell_type": "code", "execution_count": 54, "id": "0f6ecded-d2be-44d2-b8d3-ee1bdb93b858", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index(['price', 'area', 'bedrooms', 'bathrooms', 'stories', 'mainroad',\n", " 'guestroom', 'basement', 'hotwaterheating', 'airconditioning',\n", " 'parking', 'prefarea', 'furnishingstatus'],\n", " dtype='object')\n" ] } ], "source": [ "print(df.columns)\n" ] }, { "cell_type": "code", "execution_count": 58, "id": "a6716c14-20ec-44b9-b4ea-ca88308ba6ec", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " price area bedrooms bathrooms stories mainroad guestroom \\\n", "0 4270000.0 7420.0 4.0 2.0 3.0 1.0 0.0 \n", "1 4270000.0 8960.0 4.0 1.0 2.0 1.0 0.0 \n", "2 4270000.0 9960.0 3.0 2.0 2.0 1.0 0.0 \n", "3 4270000.0 7500.0 4.0 2.0 2.0 1.0 0.0 \n", "4 4270000.0 7420.0 4.0 1.0 2.0 1.0 0.0 \n", "\n", " basement hotwaterheating airconditioning parking prefarea \\\n", "0 0 0.0 1 2.0 0.0 \n", "1 0 0.0 1 0.0 0.0 \n", "2 1 0.0 0 2.0 0.0 \n", "3 1 0.0 1 0.0 0.0 \n", "4 1 0.0 1 2.0 0.0 \n", "\n", " furnishingstatus \n", "0 0 \n", "1 0 \n", "2 1 \n", "3 0 \n", "4 0 \n" ] } ], "source": [ "print(df.head())\n" ] }, { "cell_type": "code", "execution_count": 66, "id": "8423870f-62d7-4f03-8cb7-51a3284c6ee9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "'age' column not found in the DataFrame.\n" ] } ], "source": [ "# Check if 'age' column exists\n", "if 'age' in df.columns:\n", " plt.figure(figsize=(8, 6))\n", " sns.histplot(df['age'], bins=15, kde=True, color='blue')\n", " plt.title('Age Distribution')\n", " plt.xlabel('Age')\n", " plt.ylabel('Frequency')\n", " plt.show()\n", "else:\n", " print(\"'age' column not found in the DataFrame.\")\n" ] }, { "cell_type": "code", "execution_count": 68, "id": "4bb77117-dab9-4ee8-a859-919c7fa5bd2a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: matplotlib in c:\\users\\hp\\anaconda3\\lib\\site-packages (3.8.4)\n", "Requirement already satisfied: seaborn in c:\\users\\hp\\anaconda3\\lib\\site-packages (0.13.2)\n", "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (1.2.0)\n", "Requirement already satisfied: cycler>=0.10 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (0.11.0)\n", "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (4.51.0)\n", "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (1.4.4)\n", "Requirement already satisfied: numpy>=1.21 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (1.26.4)\n", "Requirement already satisfied: packaging>=20.0 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (23.2)\n", "Requirement already satisfied: pillow>=8 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (10.3.0)\n", "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (3.0.9)\n", "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from matplotlib) (2.9.0.post0)\n", "Requirement already satisfied: pandas>=1.2 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from seaborn) (2.2.2)\n", "Requirement already satisfied: pytz>=2020.1 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas>=1.2->seaborn) (2024.1)\n", "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from pandas>=1.2->seaborn) (2023.3)\n", "Requirement already satisfied: six>=1.5 in c:\\users\\hp\\anaconda3\\lib\\site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n", "Note: you may need to restart the kernel to use updated packages.\n" ] } ], "source": [ "pip install matplotlib seaborn" ] }, { "cell_type": "code", "execution_count": 73, "id": "5bde8611-7f57-4018-a1a5-fabfa1df9693", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index(['price', 'area', 'bedrooms', 'bathrooms', 'stories', 'mainroad',\n", " 'guestroom', 'basement', 'hotwaterheating', 'airconditioning',\n", " 'parking', 'prefarea', 'furnishingstatus'],\n", " dtype='object')\n" ] } ], "source": [ "print(df.columns)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "63701e24-8397-47b4-9986-4d0c5ed87527", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 76, "id": "821ac923-ac36-4647-b443-b6ae60a574c6", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " price area bedrooms bathrooms stories mainroad guestroom \\\n", "0 4270000.0 7420.0 4.0 2.0 3.0 1.0 0.0 \n", "1 4270000.0 8960.0 4.0 1.0 2.0 1.0 0.0 \n", "2 4270000.0 9960.0 3.0 2.0 2.0 1.0 0.0 \n", "3 4270000.0 7500.0 4.0 2.0 2.0 1.0 0.0 \n", "4 4270000.0 7420.0 4.0 1.0 2.0 1.0 0.0 \n", "\n", " basement hotwaterheating airconditioning parking prefarea \\\n", "0 0 0.0 1 2.0 0.0 \n", "1 0 0.0 1 0.0 0.0 \n", "2 1 0.0 0 2.0 0.0 \n", "3 1 0.0 1 0.0 0.0 \n", "4 1 0.0 1 2.0 0.0 \n", "\n", " furnishingstatus \n", "0 0 \n", "1 0 \n", "2 1 \n", "3 0 \n", "4 0 \n" ] } ], "source": [ "print(df.head())\n" ] }, { "cell_type": "code", "execution_count": 78, "id": "ba459c23-468a-422e-b1af-fea195b96b09", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "'age' column not found in the DataFrame.\n" ] } ], "source": [ "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "# Check if 'age' column exists\n", "if 'age' in df.columns:\n", " plt.figure(figsize=(8, 6))\n", " sns.histplot(df['age'], bins=15, kde=True, color='blue')\n", " plt.title('Age Distribution')\n", " plt.xlabel('Age')\n", " plt.ylabel('Frequency')\n", " plt.show()\n", "else:\n", " print(\"'age' column not found in the DataFrame.\")\n" ] }, { "cell_type": "code", "execution_count": 88, "id": "357e2ab6-5d63-440e-9716-a06beeada6ea", "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "import seaborn as sns" ] }, { "cell_type": "code", "execution_count": 90, "id": "4d62edfb-a2e6-4cef-a063-2446314ba561", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns" ] }, { "cell_type": "code", "execution_count": 92, "id": "5b978dbd-5e73-403b-96b9-b3b6203d5925", "metadata": {}, "outputs": [], "source": [ "# Load your dataset\n", "df = pd.read_csv('Housing (1).csv')" ] }, { "cell_type": "code", "execution_count": 94, "id": "2c8d87f7-0162-4743-a9e4-38aa01cb6e2f", "metadata": {}, "outputs": [ { "ename": "KeyError", "evalue": "'age'", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\indexes\\base.py:3805\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 3804\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 3805\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine\u001b[38;5;241m.\u001b[39mget_loc(casted_key)\n\u001b[0;32m 3806\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n", "File \u001b[1;32mindex.pyx:167\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", "File \u001b[1;32mindex.pyx:196\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", "File \u001b[1;32mpandas\\\\_libs\\\\hashtable_class_helper.pxi:7081\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", "File \u001b[1;32mpandas\\\\_libs\\\\hashtable_class_helper.pxi:7089\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", "\u001b[1;31mKeyError\u001b[0m: 'age'", "\nThe above exception was the direct cause of the following exception:\n", "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[94], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m# Check and handle NaN values in 'age' column if needed\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mage\u001b[39m\u001b[38;5;124m'\u001b[39m] \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mto_numeric(df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mage\u001b[39m\u001b[38;5;124m'\u001b[39m], errors\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcoerce\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\frame.py:4102\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 4100\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\u001b[38;5;241m.\u001b[39mnlevels \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m 4101\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_getitem_multilevel(key)\n\u001b[1;32m-> 4102\u001b[0m indexer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\u001b[38;5;241m.\u001b[39mget_loc(key)\n\u001b[0;32m 4103\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_integer(indexer):\n\u001b[0;32m 4104\u001b[0m indexer \u001b[38;5;241m=\u001b[39m [indexer]\n", "File \u001b[1;32m~\\anaconda3\\Lib\\site-packages\\pandas\\core\\indexes\\base.py:3812\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 3807\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(casted_key, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m (\n\u001b[0;32m 3808\u001b[0m \u001b[38;5;28misinstance\u001b[39m(casted_key, abc\u001b[38;5;241m.\u001b[39mIterable)\n\u001b[0;32m 3809\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m casted_key)\n\u001b[0;32m 3810\u001b[0m ):\n\u001b[0;32m 3811\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m InvalidIndexError(key)\n\u001b[1;32m-> 3812\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n\u001b[0;32m 3813\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[0;32m 3814\u001b[0m \u001b[38;5;66;03m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[0;32m 3815\u001b[0m \u001b[38;5;66;03m# InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[0;32m 3816\u001b[0m \u001b[38;5;66;03m# the TypeError.\u001b[39;00m\n\u001b[0;32m 3817\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_indexing_error(key)\n", "\u001b[1;31mKeyError\u001b[0m: 'age'" ] } ], "source": [ "# Check and handle NaN values in 'age' column if needed\n", "df['age'] = pd.to_numeric(df['age'], errors='coerce') # Ensure age is numeric" ] }, { "cell_type": "code", "execution_count": null, "id": "f47b6c43-6ba6-4c2d-8a66-f26751f9c402", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.4" } }, "nbformat": 4, "nbformat_minor": 5 }