Untitled

# ============================================
# Step 1: Import Libraries
# ============================================
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.datasets import load_diabetes
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression, Lasso, Ridge
from sklearn.metrics import mean_squared_error, r2_score


# ============================================
# Step 2: Load the Dataset
# ============================================
diabetes = load_diabetes()

X = pd.DataFrame(diabetes.data, columns=diabetes.feature_names)
y = pd.Series(diabetes.target, name="target")

print("Shape of X:", X.shape)
print("Shape of y:", y.shape)

print("\nFirst 5 rows of dataset:")
print(X.head())


# ============================================
# Step 3: Exploratory Data Analysis (EDA)
# ============================================
print("\nSummary Statistics:")
print(X.describe())

# Correlation Heatmap
plt.figure(figsize=(10, 8))
sns.heatmap(X.corr(), annot=True, cmap='coolwarm')
plt.title("Correlation Heatmap of Diabetes Features")
plt.show()

# Scatter plots for selected features
plt.figure(figsize=(12, 5))
features = ['bmi', 'bp', 's5']

for i, col in enumerate(features):
    plt.subplot(1, 3, i + 1)
        plt.scatter(X[col], y, alpha=0.6)
            plt.xlabel(col)
                plt.ylabel("Target")
                    plt.title(f"{col} vs Target")

                    plt.tight_layout()
                    plt.show()


                    # ============================================
                    # Step 4: Correlation Analysis & Feature Dropping
                    # ============================================
                    corr_matrix = X.corr().abs()

                    upper = corr_matrix.where(
                            np.triu(np.ones(corr_matrix.shape), k=1).astype(bool)
                    )

                    to_drop = [col for col in upper.columns if any(upper[col] >= 0.8)]

                    print("\nHighly correlated columns to drop:", to_drop)

                    X_reduced = X.drop(columns=to_drop)

                    print("Shape after feature reduction:", X_reduced.shape)


                    # ============================================
                    # Step 5: Train-Test Split
                    # ============================================
                    X_train, X_test, y_train, y_test = train_test_split(
                            X_reduced, y, test_size=0.2, random_state=42
                    )


                    # ============================================
                    # Step 6: Model Training
                    # ============================================
                    models = {
                            "Linear Regression": LinearRegression(),
                                "Lasso": Lasso(alpha=0.1),
                                    "Ridge": Ridge(alpha=1.0)
                    }

                    results = {}

                    for name, model in models.items():
                        model.fit(X_train, y_train)
                            y_pred = model.predict(X_test)

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

                                        results[name] = {"MSE": mse, "R2": r2}

                                            print(f"\n{name}")
                                                print("MSE:", mse)
                                                    print("R2 Score:", r2)


                                                    # ============================================
                                                    # Step 7: Result Comparison
                                                    # ============================================
                                                    results_df = pd.DataFrame(results).T

                                                    print("\nModel Comparison:")
                                                    print(results_df)


                                                    # Optional: Plot comparison
                                                    results_df.plot(kind='bar', figsize=(8,5))
                                                    plt.title("Model Performance Comparison")
                                                    plt.ylabel("Score")
                                                    plt.xticks(rotation=0)
                                                    plt.grid(axis='y')
                                                    plt.show()
                    }
                    )
                    )