linear regression.py

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

# Load your dataset
file_path = "C:/Users/wilso/OneDrive/Desktop/uk_renewable_energy.csv"
df = pd.read_csv(file_path)


X = df[['Energy from renewable & waste sources']].values
y = df['Total energy consumption of primary fuels and equivalents'].values

# 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)

# Create a linear regression model
model = LinearRegression()

# Train the model on the training set
model.fit(X_train, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test)

# Evaluate the model
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')

# Plot the training data and the regression line
plt.scatter(X_train, y_train, color='blue', label='Training Data')
plt.scatter(X_test, y_test, color='green', label='Test Data')
plt.plot(X_test, y_pred, color='red', linewidth=3, label='Regression Line')
plt.xlabel('Energy from renewable & waste sources')
plt.ylabel('Total energy consumption of primary fuels and equivalents')
plt.legend()
plt.show()