Update app.py

app.py

@@ -4,26 +4,20 @@ import pandas as pd
 import joblib
 import os
 import warnings
-import zipfile
+from huggingface_hub import hf_hub_download
 
+# Suppress warnings
 warnings.filterwarnings("ignore")
 
+# Load ensemble model from Hugging Face Hub
 def load_model():
-    zip_path = "final_ensemble_model.zip"
-    pkl_path = "final_ensemble_model.pkl"
-
-    if not os.path.exists(pkl_path):
-        print("📦 Extracting model from zip...")
-        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-            zip_ref.extractall(".")
-    
-    try:
-        model = joblib.load(pkl_path)
-        print("✅ Ensemble model loaded.")
-        return model
-    except Exception as e:
-        print(f"❌ Failed to load model: {e}")
-        return None
+    model_path = hf_hub_download(
+        repo_id="Zeyadd-Mostaffa/final_ensemble_model",
+        filename="final_ensemble_model.pkl"
+    )
+    model = joblib.load(model_path)
+    print("✅ Ensemble model loaded successfully.")
+    return model
 
 model = load_model()
 
@@ -32,19 +26,15 @@ def predict_employee_status(satisfaction_level, last_evaluation, number_project,
                             average_monthly_hours, time_spend_company,
                             work_accident, promotion_last_5years, salary, department, threshold=0.5):
 
-    departments = [
-        'RandD', 'accounting', 'hr', 'management', 'marketing',
-        'product_mng', 'sales', 'support', 'technical'
-    ]
+    departments = ['RandD', 'accounting', 'hr', 'management', 'marketing',
+                   'product_mng', 'sales', 'support', 'technical']
     department_features = {f"department_{dept}": 0 for dept in departments}
     if department in departments:
         department_features[f"department_{department}"] = 1
 
-    # Feature engineering
     satisfaction_evaluation = satisfaction_level * last_evaluation
     work_balance = average_monthly_hours / number_project
 
-    # Construct DataFrame
     input_data = {
         "satisfaction_level": [satisfaction_level],
         "last_evaluation": [last_evaluation],
@@ -60,36 +50,33 @@ def predict_employee_status(satisfaction_level, last_evaluation, number_project,
     }
 
     input_df = pd.DataFrame(input_data)
+    prediction_prob = model.predict_proba(input_df)[0][1]
+    result = "✅ Employee is likely to quit." if prediction_prob >= threshold else "✅ Employee is likely to stay."
+    return f"{result} (Probability: {prediction_prob:.2%})"
 
-    # Prediction
-    if model is None:
-        return "❌ No model loaded."
+# Launch Gradio UI
+def gradio_interface():
+    gr.Interface(
+        fn=predict_employee_status,
+        inputs=[
+            gr.Number(label="Satisfaction Level (0.0 - 1.0)"),
+            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 Spend at Company (Years)"),
+            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)"),
+            gr.Dropdown(['RandD', 'accounting', 'hr', 'management', 'marketing',
+                         'product_mng', 'sales', 'support', 'technical'], label="Department"),
+            gr.Slider(0.1, 0.9, value=0.5, step=0.05, label="Prediction Threshold")
+        ],
+        outputs="text",
+        title="Employee Retention Prediction System (Ensemble from Hugging Face Hub)",
+        description="Predict whether an employee is likely to stay or quit based on their profile. Adjust the threshold for accurate predictions.",
+        theme="dark"
+    ).launch()
 
-    try:
-        prob = model.predict_proba(input_df)[0][1]
-        label = "✅ Employee is likely to quit." if prob >= threshold else "✅ Employee is likely to stay."
-        return f"{label} (Probability: {prob:.2%})"
-    except Exception as e:
-        return f"❌ Error during prediction: {str(e)}"
+gradio_interface()
 
-# Launch Gradio Interface
-gr.Interface(
-    fn=predict_employee_status,
-    inputs=[
-        gr.Number(label="Satisfaction Level (0.0 - 1.0)"),
-        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 Spend at Company (Years)"),
-        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)"),
-        gr.Dropdown(departments, label="Department"),
-        gr.Slider(0.1, 0.9, value=0.5, step=0.05, label="Prediction Threshold")
-    ],
-    outputs="text",
-    title="Employee Retention Prediction System (Voting Ensemble)",
-    description="Predict whether an employee will stay or quit. Adjust threshold for sensitivity.",
-    theme="dark"
-).launch()