Update app.py

app.py

@@ -1,16 +1,11 @@
-import gradio as gr
-import h2o
-from h2o.estimators import H2OIsolationForestEstimator
-import pandas as pd
 import numpy as np
+import pandas as pd
+from sklearn.datasets import make_classification
+from sklearn.ensemble import IsolationForest
 import shap
 import matplotlib.pyplot as plt
-from sklearn.datasets import make_classification
 from itertools import combinations
 
-# Initialize H2O
-h2o.init()
-
 # Generate synthetic data with 20 features
 np.random.seed(42)
 X, _ = make_classification(
@@ -24,56 +19,49 @@ X, _ = make_classification(
 outliers = np.random.uniform(low=-6, high=6, size=(50, 20))  # Add outliers
 X = np.vstack([X, outliers])
 
-# Convert to H2O Frame
+# Convert to DataFrame
 columns = [f"Feature{i+1}" for i in range(20)]
 df = pd.DataFrame(X, columns=columns)
-h2o_df = h2o.H2OFrame(df)
 
-# Fit H2O Isolation Forest
-iso_forest = H2OIsolationForestEstimator(
-    ntrees=100,
-    max_depth=8,
-    sample_size=256,
-    seed=42,
-    contamination=0.1
+# Fit Isolation Forest
+iso_forest = IsolationForest(
+    n_estimators=100,
+    max_samples=256,
+    contamination=0.1,
+    random_state=42
 )
-iso_forest.train(training_frame=h2o_df)
+iso_forest.fit(df)
 
 # Predict anomaly scores
-predictions = iso_forest.predict(h2o_df)
-pred_df = predictions.as_data_frame()
-df["Anomaly_Score"] = pred_df["score"]
-df["Anomaly_Label"] = pred_df["predict"].map({0: "Normal", 1: "Anomaly"})
+anomaly_scores = iso_forest.decision_function(df)  # Negative values indicate anomalies
+anomaly_labels = iso_forest.predict(df)  # -1 for anomaly, 1 for normal
 
-# Define SHAP explainer
-explainer = shap.Explainer(
-    lambda x: iso_forest.predict(h2o.H2OFrame(x)).as_data_frame()[["score", "predict"]],
-    df[columns]
-)
+# Add results to DataFrame
+df["Anomaly_Score"] = anomaly_scores
+df["Anomaly_Label"] = np.where(anomaly_labels == -1, "Anomaly", "Normal")
+
+# SHAP Explainability
+explainer = shap.Explainer(iso_forest, df[columns])
+shap_values = explainer(df[columns])
 
-# Helper function for SHAP summary plot
-def shap_summary():
-    shap_values = explainer(df[columns])
-    plt.figure()
-    shap.summary_plot(shap_values, df[columns], feature_names=columns, show=False)
-    plt.savefig("shap_summary.png")
-    return "shap_summary.png"
+# SHAP Summary Plot (Global Explainability)
+shap.summary_plot(shap_values, df[columns], feature_names=columns)
 
-# Helper function for SHAP waterfall plot
-def shap_waterfall(index):
-    shap_values = explainer(df[columns])
-    plt.figure()
-    shap.waterfall_plot(shap.Explanation(
-        values=shap_values.values[int(index)],
-        base_values=shap_values.base_values[int(index)],
-        data=df.iloc[int(index)],
+# SHAP Waterfall Plot for a Specific Data Point (Local Explainability)
+specific_index = df[df["Anomaly_Label"] == "Anomaly"].index[0]  # Select first anomaly
+shap.waterfall_plot(
+    shap.Explanation(
+        values=shap_values.values[specific_index],
+        base_values=shap_values.base_values[specific_index],
+        data=df.iloc[specific_index],
         feature_names=columns
-    ))
-    plt.savefig("shap_waterfall.png")
-    return "shap_waterfall.png"
+    )
+)
 
-# Helper function for scatter plot
-def scatter_plot(feature1, feature2):
+# Scatter plots for pairwise combinations of features
+feature_combinations = list(combinations(columns[:5], 2))  # Use first 5 features for simplicity
+
+for feature1, feature2 in feature_combinations:
     plt.figure(figsize=(8, 6))
     plt.scatter(
         df[feature1],
@@ -86,33 +74,4 @@ def scatter_plot(feature1, feature2):
     plt.title(f"Isolation Forest - {feature1} vs {feature2}")
     plt.xlabel(feature1)
     plt.ylabel(feature2)
-    plt.savefig("scatter_plot.png")
-    return "scatter_plot.png"
-
-# Gradio app
-with gr.Blocks() as app:
-    gr.Markdown("# Anomaly Detection with Isolation Forest")
-    
-    with gr.Tab("SHAP Summary Plot"):
-        gr.Markdown("Global explainability using SHAP summary plot.")
-        shap_summary_button = gr.Button("Generate SHAP Summary")
-        shap_summary_image = gr.Image()
-        shap_summary_button.click(fn=shap_summary, outputs=shap_summary_image)
-
-    with gr.Tab("SHAP Waterfall Plot"):
-        gr.Markdown("Local explainability for a specific data point.")
-        index_input = gr.Number(label="Data Point Index", value=0)
-        shap_waterfall_button = gr.Button("Generate SHAP Waterfall")
-        shap_waterfall_image = gr.Image()
-        shap_waterfall_button.click(fn=shap_waterfall, inputs=index_input, outputs=shap_waterfall_image)
-
-    with gr.Tab("Scatter Plot"):
-        gr.Markdown("Visualize pairwise feature interactions.")
-        feature1_dropdown = gr.Dropdown(choices=columns, label="Feature 1")
-        feature2_dropdown = gr.Dropdown(choices=columns, label="Feature 2")
-        scatter_plot_button = gr.Button("Generate Scatter Plot")
-        scatter_plot_image = gr.Image()
-        scatter_plot_button.click(fn=scatter_plot, inputs=[feature1_dropdown, feature2_dropdown], outputs=scatter_plot_image)
-
-# Launch the app
-app.launch()
+    plt.show()