File size: 4,929 Bytes
462fea8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "id": 1,
   "source": [
    "# Data Science Analysis Notebook\n",
    "\n",
    "This notebook contains some example Python code for data analysis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "id": 2,
   "source": [
    "# Import libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "# Set visualization style\n",
    "sns.set(style='whitegrid')\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "id": 3,
   "source": [
    "# Load the dataset\n",
    "df = pd.read_csv('housing_data.csv')\n",
    "\n",
    "# Display basic information\n",
    "print(f\"Dataset shape: {df.shape}\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "id": 4,
   "source": [
    "# Perform data cleaning\n",
    "# Fill missing values with median\n",
    "for column in df.columns:\n",
    "    if df[column].dtype in ['float64', 'int64']:\n",
    "        df[column].fillna(df[column].median(), inplace=True)\n",
    "    else:\n",
    "        df[column].fillna(df[column].mode()[0], inplace=True)\n",
    "\n",
    "# Check for remaining missing values\n",
    "print(\"Missing values after cleaning:\")\n",
    "print(df.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "id": 5,
   "source": [
    "# Exploratory data analysis\n",
    "# Create correlation matrix\n",
    "numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns\n",
    "correlation_matrix = df[numeric_columns].corr()\n",
    "\n",
    "# Plot heatmap\n",
    "plt.figure(figsize=(12, 10))\n",
    "sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', linewidths=0.5)\n",
    "plt.title('Correlation Matrix of Numeric Features', fontsize=18)\n",
    "plt.xticks(rotation=45, ha='right')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "id": 6,
   "source": [
    "# Feature engineering\n",
    "# Create new features\n",
    "if 'bedrooms' in df.columns and 'total_rooms' in df.columns:\n",
    "    df['bedrooms_ratio'] = df['bedrooms'] / df['total_rooms']\n",
    "\n",
    "if 'total_rooms' in df.columns and 'households' in df.columns:\n",
    "    df['rooms_per_household'] = df['total_rooms'] / df['households']\n",
    "\n",
    "# Scale numeric features\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()\n",
    "df[numeric_columns] = scaler.fit_transform(df[numeric_columns])\n",
    "\n",
    "# Display transformed data\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "id": 7,
   "source": [
    "# Build a simple prediction model\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "\n",
    "# Assume we're predicting median_house_value\n",
    "if 'median_house_value' in df.columns:\n",
    "    # Prepare features and target\n",
    "    X = df.drop('median_house_value', axis=1)\n",
    "    y = df['median_house_value']\n",
    "    \n",
    "    # Split the data\n",
    "    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "    \n",
    "    # Train the model\n",
    "    model = LinearRegression()\n",
    "    model.fit(X_train, y_train)\n",
    "    \n",
    "    # Make predictions\n",
    "    y_pred = model.predict(X_test)\n",
    "    \n",
    "    # Evaluate the model\n",
    "    mse = mean_squared_error(y_test, y_pred)\n",
    "    r2 = r2_score(y_test, y_pred)\n",
    "    \n",
    "    print(f\"Mean Squared Error: {mse:.2f}\")\n",
    "    print(f\"R² Score: {r2:.2f}\")\n",
    "    \n",
    "    # Plot actual vs predicted values\n",
    "    plt.figure(figsize=(10, 6))\n",
    "    plt.scatter(y_test, y_pred, alpha=0.5)\n",
    "    plt.plot([y.min(), y.max()], [y.min(), y.max()], 'r--')\n",
    "    plt.xlabel('Actual Values')\n",
    "    plt.ylabel('Predicted Values')\n",
    "    plt.title('Actual vs Predicted Values')\n",
    "    plt.tight_layout()\n",
    "    plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}