Update app.py

app.py

@@ -2,6 +2,7 @@ import numpy as np
 import pandas as pd
 from sklearn.datasets import make_classification
 from sklearn.ensemble import IsolationForest
+from sklearn.metrics import roc_curve, auc
 import shap
 import matplotlib.pyplot as plt
 import gradio as gr
@@ -40,12 +41,30 @@ anomaly_labels = iso_forest.predict(df)  # -1 for anomaly, 1 for normal
 df["Anomaly_Score"] = anomaly_scores
 df["Anomaly_Label"] = np.where(anomaly_labels == -1, "Anomaly", "Normal")
 
+# Generate true labels (1 for anomaly, 0 for normal) for ROC curve
+true_labels = np.where(df["Anomaly_Label"] == "Anomaly", 1, 0)
+
 # SHAP Explainability
 explainer = shap.Explainer(iso_forest, df[columns])
 shap_values = explainer(df[columns])
 
 # Define functions for Gradio
 
+def get_roc_curve():
+    """Generates the ROC curve plot."""
+    fpr, tpr, _ = roc_curve(true_labels, -df["Anomaly_Score"])  # Use -scores as higher scores mean normal
+    roc_auc = auc(fpr, tpr)
+    plt.figure(figsize=(8, 6))
+    plt.plot(fpr, tpr, label=f"ROC Curve (AUC = {roc_auc:.2f})")
+    plt.plot([0, 1], [0, 1], "k--", label="Random Guess")
+    plt.xlabel("False Positive Rate")
+    plt.ylabel("True Positive Rate")
+    plt.title("Receiver Operating Characteristic (ROC) Curve")
+    plt.legend(loc="lower right")
+    plt.grid()
+    plt.savefig("roc_curve.png")
+    return "roc_curve.png"
+
 def get_anomaly_samples():
     """Returns formatted top, middle, and bottom 10 records based on anomaly score."""
     sorted_df = df.sort_values("Anomaly_Score", ascending=False)
@@ -63,13 +82,13 @@ with gr.Blocks() as demo:
     gr.Markdown("# Isolation Forest Anomaly Detection")
     
     with gr.Tab("Anomaly Samples"):
-        gr.Markdown("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Top 10 Records (Anomalies)</h3>", unsafe_allow_html=True)
+        gr.HTML("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Top 10 Records (Anomalies)</h3>")
         top_table = gr.Dataframe(label="Top 10 Records")
         
-        gr.Markdown("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Middle 10 Records (Mixed)</h3>", unsafe_allow_html=True)
+        gr.HTML("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Middle 10 Records (Mixed)</h3>")
         middle_table = gr.Dataframe(label="Middle 10 Records")
         
-        gr.Markdown("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Bottom 10 Records (Normal)</h3>", unsafe_allow_html=True)
+        gr.HTML("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Bottom 10 Records (Normal)</h3>")
         bottom_table = gr.Dataframe(label="Bottom 10 Records")
         
         anomaly_samples_button = gr.Button("Show Anomaly Samples")
@@ -77,6 +96,12 @@ with gr.Blocks() as demo:
             get_anomaly_samples, 
             outputs=[top_table, middle_table, bottom_table]
         )
+    
+    with gr.Tab("ROC Curve"):
+        gr.Markdown("### ROC Curve for Isolation Forest")
+        roc_button = gr.Button("Generate ROC Curve")
+        roc_image = gr.Image()
+        roc_button.click(get_roc_curve, outputs=roc_image)
 
 # Launch the Gradio app
 demo.launch()