Create app.py

app.py

@@ -0,0 +1,118 @@
+import gradio as gr
+import h2o
+from h2o.estimators import H2OIsolationForestEstimator
+import pandas as pd
+import numpy as np
+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(
+    n_samples=500,
+    n_features=20,
+    n_informative=10,
+    n_redundant=5,
+    n_clusters_per_class=1,
+    random_state=42
+)
+outliers = np.random.uniform(low=-6, high=6, size=(50, 20))  # Add outliers
+X = np.vstack([X, outliers])
+
+# Convert to H2O Frame
+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
+)
+iso_forest.train(training_frame=h2o_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"})
+
+# Define SHAP explainer
+explainer = shap.Explainer(
+    lambda x: iso_forest.predict(h2o.H2OFrame(x)).as_data_frame()[["score", "predict"]],
+    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"
+
+# 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)],
+        feature_names=columns
+    ))
+    plt.savefig("shap_waterfall.png")
+    return "shap_waterfall.png"
+
+# Helper function for scatter plot
+def scatter_plot(feature1, feature2):
+    plt.figure(figsize=(8, 6))
+    plt.scatter(
+        df[feature1],
+        df[feature2],
+        c=(df["Anomaly_Label"] == "Anomaly"),
+        cmap="coolwarm",
+        edgecolor="k",
+        alpha=0.7
+    )
+    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()