7. Develop a program to demonstrate the working of Linear Regression and Polynomial Regression.
Use
Boston Housing Dataset for Linear Regression and Auto MPG Dataset (for vehicle fuel efficiency
prediction) for Polynomial Regression.
import numpy as np
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.preprocessing import PolynomialFeatures, StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.metrics import mean_squared_error, r2_score
def linear_regression_california():
# Fetching California Housing dataset
housing = fetch_california_housing(as_frame=True)
X = housing.data[["AveRooms"]]
y = housing.target
# Train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Linear Regression model
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
# Plotting
plt.scatter(X_test, y_test, color="blue", label="Actual")
plt.plot(X_test, y_pred, color="red", label="Predicted")
plt.xlabel("Average number of rooms (AveRooms)")
plt.ylabel("Median value of homes ($100,000)")
plt.title("Linear Regression - California Housing Dataset")
plt.legend()
plt.show()
# Model performance
print("Linear Regression - California Housing Dataset")
print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
print("R^2 Score:", r2_score(y_test, y_pred))
def polynomial_regression_auto_mpg():
# URL of Auto MPG dataset
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data"
column_names = ["mpg", "cylinders", "displacement", "horsepower", "weight", "acceleration",
"model_year", "origin"]
# Loading and cleaning the dataset
data = pd.read_csv(url, sep='\s+', names=column_names, na_values="?")
data = data.dropna()
# Feature and target variables
X = data["displacement"].values.reshape(-1, 1)
y = data["mpg"].values
# Train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Polynomial Regression model
poly_model = make_pipeline(PolynomialFeatures(degree=2), StandardScaler(), LinearRegression())
poly_model.fit(X_train, y_train)
y_pred = poly_model.predict(X_test)
# Plotting
plt.scatter(X_test, y_test, color="blue", label="Actual")
plt.scatter(X_test, y_pred, color="red", label="Predicted")
plt.xlabel("Displacement")
plt.ylabel("Miles per gallon (mpg)")
plt.title("Polynomial Regression - Auto MPG Dataset")
plt.legend()
plt.show()
# Model performance
print("Polynomial Regression - Auto MPG Dataset")
print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
print("R^2 Score:", r2_score(y_test, y_pred))
if __name__ == "__main__":
print("Demonstrating Linear Regression and Polynomial Regression\n")
linear_regression_california()
polynomial_regression_auto_mpg()
