evaluate_model.py

import pandas as pd
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix, roc_curve, auc, precision_recall_curve
import matplotlib.pyplot as plt
import joblib

# Load the test dataset
test_file_path = 'data/test_dataset.csv'
test_data = pd.read_csv(test_file_path)

# Load the trained model
model_file_path = 'models/diabetes_model.pkl'
model = joblib.load(model_file_path)

# Separate features and labels from the test set
X_test = test_data.drop('diabetes', axis=1)
y_test = test_data['diabetes']

# Make predictions
y_pred = model.predict(X_test)
y_prob = model.predict_proba(X_test)[:, 1]

# Calculate evaluation metrics
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
conf_matrix = confusion_matrix(y_test, y_pred)
specificity = conf_matrix[0,0] / (conf_matrix[0,0] + conf_matrix[0,1])

# Print evaluation metrics
print(f'Accuracy: {accuracy:.2f}')
print(f'Precision: {precision:.2f}')
print(f'Recall (Sensitivity): {recall:.2f}')
print(f'Specificity: {specificity:.2f}')
print(f'F1-Score: {f1:.2f}')
print(f'Confusion Matrix:\n{conf_matrix}')

# Plot ROC Curve
fpr, tpr, _ = roc_curve(y_test, y_prob)
roc_auc = auc(fpr, tpr)
plt.figure()
plt.plot(fpr, tpr, color='darkorange', lw=2, label=f'ROC curve (area = {roc_auc:.2f})')
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver Operating Characteristic (ROC) Curve')
plt.legend(loc='lower right')
plt.show()

# Plot Precision-Recall Curve
precision_vals, recall_vals, _ = precision_recall_curve(y_test, y_prob)
plt.figure()
plt.plot(recall_vals, precision_vals, color='blue', lw=2)
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Precision-Recall Curve')
plt.show()