add shap

pages/Anchors.py

@@ -86,7 +86,7 @@ def explain_example(anchors_threshold, example_idx):
         class_names,
         feature_names,
         X_train.values,
-        categorical_names)
+        categorical_names, seed=42)
     
     # Explain the selected sample
     exp = explainer.explain_instance(X_test.values[example_idx], global_model.predict, threshold=anchors_threshold)

pages/LIME.py

@@ -1,7 +1,4 @@
 # Import Libraries
-import numpy as np
-import pandas as pd
-import matplotlib.pyplot as plt
 import streamlit as st
 import src.prompt_config as prompt_params
 import streamlit.components.v1 as components
@@ -12,8 +9,6 @@ from sklearn.model_selection import train_test_split
 # XAI (Explainability)
 import shap
 import lime
-# from anchor import anchor_tabular
-from sklearn.inspection import PartialDependenceDisplay
 
 # Global Variables to Store Model & Data
 global_model = None

pages/SHAP.py

@@ -0,0 +1,106 @@
+# Import Libraries
+import matplotlib.pyplot as plt
+import streamlit as st
+import src.prompt_config as prompt_params
+# Models
+import xgboost
+from sklearn.model_selection import train_test_split
+
+# XAI (Explainability)
+import shap
+
+# Global Variables to Store Model & Data
+global_model = None
+X_train, X_test, y_train, y_test = None, None, None, None
+
+
+def train_model():
+    """ Train the XGBoost model only once and store it globally. """
+    global global_model, X_train, X_test, y_train, y_test
+    
+    if global_model is None:
+        # Load Data from SHAP library
+        X, y = shap.datasets.adult()
+        
+        # Split data
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=42)
+        
+        # Train XGBoost model
+        global_model = xgboost.XGBClassifier()
+        global_model.fit(X_train, y_train)
+        
+        print("XGBoost Model training completed!")
+
+
+
+def explain_example(kernel_width, example_idx):
+    """ Explain a given sample without retraining the model. """
+    global global_model, X_train, X_test, y_train, y_test
+    
+    if global_model is None:
+        train_model()
+    
+    X, y = shap.datasets.adult()
+    X100 = shap.utils.sample(X, 100)
+    explainer = shap.TreeExplainer(global_model, X100)  # Use the TreeExplainer algorithm with background distribution
+    shap_values = explainer.shap_values(X_test)  # Get shap values
+    shap_values_exp = explainer(X_test)  # Get explainer for X_test
+
+    # SHAP Summary Plot (BeeSwarm)
+    st.write("### 📊 SHAP Summary Plot")
+    fig, ax = plt.subplots(figsize=(10, 5))
+    shap.summary_plot(shap_values, X_test, show=False)
+    st.pyplot(fig)
+
+    # SHAP Summary Bar Plot
+    st.write("### 📊 SHAP Feature Importance (Bar Plot)")
+    fig, ax = plt.subplots(figsize=(10, 5))
+    shap.summary_plot(shap_values, X_test, plot_type="bar", show=False)
+    st.pyplot(fig)
+
+    # SHAP Dependence Plot
+    st.write("### 🔍 SHAP Dependence Plot for 'Age'")
+    fig, ax = plt.subplots(figsize=(10, 5))
+    shap.dependence_plot('Age', shap_values, X_test, ax=ax, show=False)
+    st.pyplot(fig)
+
+    # SHAP Waterfall Plot
+    st.write(f"### 🌊 SHAP Waterfall Plot for Example {example_idx}")
+    fig, ax = plt.subplots(figsize=(10, 5))
+    shap.plots.waterfall(shap_values_exp[example_idx], show=False)
+    st.pyplot(fig)
+
+
+def main():
+    global global_model
+    
+    # Ensure the model is trained only once
+    if global_model is None:
+        train_model()
+    
+    # Streamlit UI Controls
+    lime_kernel_width = st.sidebar.slider(
+        label="Set the `kernel` value:",
+        min_value=0.0,
+        max_value=100.0,
+        value=3.0,  # Default value
+        step=0.1,  # Step size
+        help=prompt_params.LIME_KERNEL_WIDTH_HELP,
+    )
+    
+    example_idx = st.sidebar.number_input(
+        label="Select the sample index to explain:",
+        min_value=0,
+        max_value=len(X_test) - 1,  # Ensures the index is within range
+        value=1,  # Default value
+        step=1,  # Step size
+        help=prompt_params.EXAMPLE_BE_EXPLAINED_IDX,
+    )
+    
+    # Explain the selected sample
+    if st.button("Explain Sample"):
+        explain_example(lime_kernel_width, example_idx)
+
+
+if __name__ == '__main__':
+    main()