Python Linear Regression Script 🐍
Below is the Python script used to build the linear regression model on the California Housing dataset. It uses Pandas, Scikit-learn, and Matplotlib to preprocess data, train the model, and generate visualizations.
# Import libraries
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import StandardScaler
# Load the dataset
california = fetch_california_housing()
df = pd.DataFrame(california.data, columns=california.feature_names)
df['MedHouseVal'] = california.target
# Preprocessing
X = df[['MedInc', 'HouseAge', 'AveRooms']]
y = df['MedHouseVal']
# Normalize features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
# Split data
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
# Build model
model = LinearRegression()
model.fit(X_train, y_train)
# Predictions
y_pred = model.predict(X_test)
# Evaluation
mse = mean_squared_error(y_test, y_pred)
print(f"Mean Squared Error: {mse:.2f}")
# Visualization
plt.scatter(y_test, y_pred)
plt.xlabel('Actual Prices')
plt.ylabel('Predicted Prices')
plt.title('Actual vs Predicted House Prices')
plt.savefig('images/predictions.png')
plt.close()
print("Linear Regression model completed.")