import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import roc_curve, roc_auc_score
import matplotlib.pyplot as plt

# Set a random seed for reproducibility
np.random.seed(42)

# Generate random data
num_samples = 1000
num_features = 10

# Generate features (X)
X = np.random.randn(num_samples, num_features)

# Generate labels (y)
y = np.random.randint(2, size=num_samples)

# Standardize the features
X = (X - np.mean(X, axis=0)) / np.std(X, axis=0)

# Split the data into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Fit the train set using random forest classifier
rf_clf = RandomForestClassifier()
rf_clf.fit(X_train, y_train)

# Fit the train set using K-nearest neighbors (KNN) classifier
knn_clf = KNeighborsClassifier()
knn_clf.fit(X_train, y_train)

# Predict probabilities for the positive class (class 1)
y_train_rf_probs = rf_clf.predict_proba(X_train)[:, 1]
y_train_knn_probs = knn_clf.predict_proba(X_train)[:, 1]

# Calculate the false positive rate (FPR), true positive rate (TPR), and thresholds for the ROC curve
rf_fpr, rf_tpr, rf_thresholds = roc_curve(y_train, y_train_rf_probs)
knn_fpr, knn_tpr, knn_thresholds = roc_curve(y_train, y_train_knn_probs)

# Calculate the AUC score for the ROC curve
rf_auc = roc_auc_score(y_train, y_train_rf_probs)
knn_auc = roc_auc_score(y_train, y_train_knn_probs)

# Plot the ROC curve
plt.plot(rf_fpr, rf_tpr, label=f"Random Forest (AUC = {rf_auc:.2f})")
plt.plot(knn_fpr, knn_tpr, label=f"KNN (AUC = {knn_auc:.2f})")
plt.plot([0, 1], [0, 1], 'k--')  # Diagonal line for random classifier
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curve - Train Set')
plt.legend(loc='lower right')
plt.show()