7_Roc_Curve.py

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_curve, auc

# Generate synthetic data for demonstration
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=0.2, random_state=42)

# print(X_train.shape)

# Train two different models
logistic_model = LogisticRegression(random_state=42)
logistic_model.fit(X_train, y_train)

random_forest_model = RandomForestClassifier(n_estimators=100, random_state=42)
random_forest_model.fit(X_train, y_train)


# Generate predictions
y_pred_logistic = logistic_model.predict_proba(X_test)[:, 1]
y_pred_rf = random_forest_model.predict_proba(X_test)[:, 1]



# Create a DataFrame
test_df = pd.DataFrame(
    {'True': y_test, 'Logistic': y_pred_logistic, 'RandomForest': y_pred_rf})


# print(test_df.head())
# output: 
#    True  Logistic  RandomForest
# 0     1  0.648888          0.75
# 1     1  0.867905          0.79
# 2     1  0.475407          0.25
# 3     1  0.852635          0.89
# 4     1  0.955500          0.99


# Plot ROC curve for each model
plt.figure(figsize=(7, 5))

for model in ['Logistic', 'RandomForest']:
    fpr, tpr, _ = roc_curve(test_df['True'], test_df[model])
    roc_auc = auc(fpr, tpr)
    plt.plot(fpr, tpr, label=f'{model} (AUC = {roc_auc:.2f})')

# Plot random guess line
plt.plot([0, 1], [0, 1], 'r--', label='Random Guess')

# Set labels and title
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curves for Two Models')
plt.legend()
plt.show()