Update app.py

app.py

@@ -7,8 +7,6 @@ import os
 import warnings
 import shap
 import matplotlib.pyplot as plt
-from sklearn.metrics import roc_curve, precision_recall_curve
-from imblearn.over_sampling import SMOTE
 
 # Suppress XGBoost warnings
 warnings.filterwarnings("ignore", category=UserWarning, message=".*WARNING.*")
@@ -27,7 +25,7 @@ def load_model():
 
 model = load_model()
 
-# Prediction function with dynamic threshold and balanced data
+# Prediction function with consistent feature names
 def predict_employee_status(satisfaction_level, last_evaluation, number_project,
                             average_monthly_hours, time_spent_company, 
                             work_accident, promotion_last_5years, salary, department, threshold=0.5):
@@ -41,22 +39,22 @@ def predict_employee_status(satisfaction_level, last_evaluation, number_project,
     if department in departments:
         department_features[f"department_{department}"] = 1
 
-    # Automatically Generate Interaction Features
+    # Generate Interaction Features
     satisfaction_evaluation = satisfaction_level * last_evaluation
     work_balance = average_monthly_hours / number_project
 
-    # Prepare the input with all expected features as a DataFrame with column names
+    # Prepare the input with all expected features
     input_data = {
         "satisfaction_level": [satisfaction_level],
         "last_evaluation": [last_evaluation],
         "number_project": [number_project],
         "average_monthly_hours": [average_monthly_hours],
-        "time_spent_company": [time_spent_company],
+        "time_spent_company": [time_spent_company],  # Corrected
         "Work_accident": [work_accident],
         "promotion_last_5years": [promotion_last_5years],
         "salary": [salary],
-        "satisfaction_evaluation": [satisfaction_evaluation],
-        "work_balance": [work_balance],
+        "satisfaction_evaluation": [satisfaction_evaluation],  # Added
+        "work_balance": [work_balance],  # Added
         **department_features
     }
 
@@ -73,30 +71,11 @@ def predict_employee_status(satisfaction_level, last_evaluation, number_project,
 
         # Apply the dynamic threshold
         result = "✅ Employee is likely to quit." if prediction_prob >= threshold else "✅ Employee is likely to stay."
-        explanation = explain_prediction(input_df)
-        return f"{result} (Probability: {prediction_prob:.2%})\n\nExplanation:\n{explanation}"
+        return f"{result} (Probability: {prediction_prob:.2%})"
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-# SHAP Explainability (Directly Integrated)
-def explain_prediction(input_df):
-    try:
-        explainer = shap.TreeExplainer(model)
-        shap_values = explainer.shap_values(input_df)
-        
-        # Generate and save SHAP explanation as an image
-        shap.initjs()
-        plt.figure()
-        shap.waterfall_plot(shap.Explanation(values=shap_values[0], 
-                                             base_values=explainer.expected_value,
-                                             data=input_df.iloc[0].values,
-                                             feature_names=input_df.columns))
-        plt.savefig("shap_explanation.png")
-        return "SHAP explanation generated for this prediction."
-    except Exception as e:
-        return f"❌ Error in SHAP: {str(e)}"
-
-# Gradio interface with dynamic threshold and SHAP
+# Gradio interface with consistent feature names
 def gradio_interface():
     interface = gr.Interface(
         fn=predict_employee_status,
@@ -105,7 +84,7 @@ def gradio_interface():
             gr.Number(label="Last Evaluation (0.0 - 1.0)"),
             gr.Number(label="Number of Projects (1 - 10)"),
             gr.Number(label="Average Monthly Hours (80 - 320)"),
-            gr.Number(label="Time Spent at Company (Years)"),
+            gr.Number(label="Time Spent at Company (Years)"),  # Corrected
             gr.Radio([0, 1], label="Work Accident (0 = No, 1 = Yes)"),
             gr.Radio([0, 1], label="Promotion in Last 5 Years (0 = No, 1 = Yes)"),
             gr.Radio([0, 1, 2], label="Salary (0 = Low, 1 = Medium, 2 = High)"),
@@ -124,4 +103,3 @@ def gradio_interface():
     interface.launch()
 
 gradio_interface()
-