Lab_ML(10/03/25)

# %%
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.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix, roc_curve, auc

# %%
diabetes = load_diabetes()
X,y = diabetes.data, diabetes.target

# %%
y_binary = (y>np.median(y)).astype(int)

# %%
X_train, X_test, y_train, y_test = train_test_split(X,y_binary, test_size=0.2,random_state=42)

# %%
scalar = StandardScaler()
X_train = scalar.fit_transform(X_train)
X_test = scalar.transform(X_test)

# %%
model = LogisticRegression()
model.fit(X_train,y_train)

# %%
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test,y_pred)
print("Accuracy: {:.2f}%".format(accuracy*100))

# %%
print("Confusion Matrix: \n",confusion_matrix(y_test,y_pred))
print("\n Classification Report: \n", classification_report(y_test,y_pred))

# %%
plt.figure(figsize=(8,6))
sns.scatterplot(x=X_test[:,2], y=X_test[:,8], hue=y_test, palette={0: 'blue', 1: 'red'}, marker='o')
plt.xlabel("BMI")
plt.ylabel("Age")
plt.title("Logistic Regression Decision Boundary\n Accuracy: {:.2f}%".format(accuracy * 100))
plt.legend(title="Diabetes", loc="upper right")
plt.show()

# %%
y_prob = model.predict_proba(X_test)[:, 1]
fpr, tpr, thresholds = roc_curve(y_test, y_prob)
roc_auc = auc(fpr, tpr)

plt.figure(figsize=(8, 6))
plt.plot(fpr, tpr, color='darkorange', lw=2, label=f'ROC Curve (AUC = {roc_auc:.2f})')
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--', label='Random')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title(f'Receiver Operating Characteristic (ROC) Curve\nAccuracy: {accuracy * 100:.2f}%')
plt.legend(loc='lower right')
plt.show()