Scribd
Upload
8 views

Ridge Regression

Uploaded by

22eg105n47
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
8 views

Ridge Regression

Uploaded by

22eg105n47
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

RIDGE REGRESSION

# Import necessary libraries


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.datasets import fetch_california_housing

# Load the California Housing Dataset


california = fetch_california_housing()
X = california.data # Features
y = california.target # Target (Median house value)

# Convert to DataFrame for better readability (optional)


df = pd.DataFrame(X, columns=california.feature_names)
df['Target'] = y
print("Sample Data:")
print(df.head())

# Split the data into training and testing sets


X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)

# Initialize Ridge Regression model


ridge_reg = Ridge(alpha=1.0) # Regularization strength

# Train the model


ridge_reg.fit(X_train, y_train)

# Predict on the test set


y_pred = ridge_reg.predict(X_test)

# Evaluate the model


mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

# Display performance metrics


print(f"Ridge Regression - MSE: {mse:.2f}, R-squared: {r2:.2f}")

# Visualize actual vs predicted values


plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, color='blue', alpha=0.6)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()],
color='red', linestyle='--')
plt.title("Ridge Regression: Actual vs Predicted (California Housing
Dataset)")
plt.xlabel("Actual Median House Value")
plt.ylabel("Predicted Median House Value")
plt.show()

*********************LASSO REGRESSION**********************************

# Import necessary libraries


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import Lasso # Change from Ridge to Lasso
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.datasets import fetch_california_housing

# Load the California Housing Dataset


california = fetch_california_housing()
X = california.data # Features
y = california.target # Target (Median house value)

# Convert to DataFrame for better readability (optional)


df = pd.DataFrame(X, columns=california.feature_names)
df['Target'] = y
print("Sample Data:")
print(df.head())

# Split the data into training and testing sets


X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)

# Initialize Lasso Regression model (Change here from Ridge to Lasso)


lasso_reg = Lasso(alpha=1.0) # Regularization strength, you can tune
alpha

# Train the model


lasso_reg.fit(X_train, y_train)

# Predict on the test set


y_pred = lasso_reg.predict(X_test)

# Evaluate the model


mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

# Display performance metrics


print(f"Lasso Regression - MSE: {mse:.2f}, R-squared: {r2:.2f}")

# Visualize actual vs predicted values


plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, color='blue', alpha=0.6)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()],
color='red', linestyle='--')
plt.title("Lasso Regression: Actual vs Predicted (California Housing
Dataset)")
plt.xlabel("Actual Median House Value")
plt.ylabel("Predicted Median House Value")
plt.show()

You might also like