app.py

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 itertools import combinations

# 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 DataFrame
columns = [f"Feature{i+1}" for i in range(20)]
df = pd.DataFrame(X, columns=columns)

# Fit Isolation Forest
iso_forest = IsolationForest(
    n_estimators=100,
    max_samples=256,
    contamination=0.1,
    random_state=42
)
iso_forest.fit(df)

# Predict anomaly scores
anomaly_scores = iso_forest.decision_function(df)  # Negative values indicate anomalies
anomaly_labels = iso_forest.predict(df)  # -1 for anomaly, 1 for normal

# 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])

# SHAP Summary Plot (Global Explainability)
shap.summary_plot(shap_values, df[columns], feature_names=columns)

# 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
    )
)

# 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],
        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.show()