gsdfgsdaga

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


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)
display(x.head())
print("\nSummary Statistics:")
display(x.describe())


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



plt.figure(figsize=(12,5))
for i , col in enumerate(['bmi','bp','s5']):
    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()