roc curve

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_curve, auc, confusion_matrix, classification_report

# Generate a synthetic dataset
X, y = make_classification(n_samples=1000, n_features=20, n_classes=2, random_state=42)

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Train the logistic regression classifier
lr = LogisticRegression()
lr.fit(X_train_scaled, y_train)

# Calculate the predicted probabilities
y_pred_proba = lr.predict_proba(X_test_scaled)[:, 1]

# Compute the ROC curve
fpr, tpr, thresholds = roc_curve(y_test, y_pred_proba)
roc_auc = auc(fpr, tpr)

# Find the optimal threshold
optimal_idx = np.argmax(tpr - fpr)
optimal_threshold = thresholds[optimal_idx]

# Apply the optimal threshold to the predicted probabilities
y_pred_optimal = (y_pred_proba >= optimal_threshold).astype(int)

# Evaluate the classifier's performance with the optimal threshold
conf_matrix = confusion_matrix(y_test, y_pred_optimal)
print("Confusion Matrix:nn", conf_matrix)

class_report = classification_report(y_test, y_pred_optimal)
print("nnClassification Report:nn", class_report)