Untitled

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

# Load the Diabetes dataset
diabetes = load_diabetes()
X = diabetes.data[:, np.newaxis, 2]  # using only one feature for simplicity
y = diabetes.target

# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train the linear regression model
model = LinearRegression()
model.fit(X_train, y_train)

# Make predictions
y_pred = model.predict(X_test)

# RMSE
rmse = np.sqrt(mean_squared_error(y_test, y_pred))
print(f"RMSE: {rmse:.2f}")

# R-squared score
r2 = r2_score(y_test, y_pred)
print(f"R-squared: {r2:.2f}")

# Visualize the model
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=2, label='Regression line')
plt.xlabel('Feature')
plt.ylabel('Disease Progression')
plt.legend()
plt.title('Simple Linear Regression')
plt.show()