Update app.py

app.py

@@ -6,128 +6,97 @@ from huggingface_hub import hf_hub_download
 from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
 
 # Load the trained model and scaler objects from file
-REPO_ID = "Hemg/modelxxx"  # hugging face repo ID
-MODEL_FILENAME = "predjob.joblib"  # model file name
-SCALER_FILENAME = "scalejob.joblib"  # scaler file name
 
-model = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=MODEL_FILENAME))
-scaler = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=SCALER_FILENAME))
 
+REPO_ID = "Hemg/modelxxx" # hugging face  repo ID
+MoDEL_FILENAME = "studentpredict.joblib" # model file name
+SCALER_FILENAME ="studentscaler.joblib" # scaler file name
+
+model = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=MoDEL_FILENAME))
+
+scaler = joblib.load(hf_hub_download(repo_id=REPO_ID, filename=SCALER_FILENAME))
+ 
 def encode_categorical_columns(df):
-    # Create a copy of the DataFrame to avoid modifying the original
-    df = df.copy()
-    
-    # Define the expected categorical columns and their order
-    categorical_columns = [
-        "Location", "Course", "Faculty", "College", "Source", "Event", 
-        "Presenter", "Visited Parent", "Visited College for Inquiry", 
-        "Attended Any Event"
-    ]
-    
-    # Define the expected numeric columns
-    numeric_columns = ["College Fee", "GPA", "Year"]
-    
-    # Create label encoder dictionary
-    label_encoders = {}
-    
-    # Encode each categorical column
-    for col in categorical_columns:
-        label_encoders[col] = LabelEncoder()
-        df[col] = label_encoders[col].fit_transform(df[col].astype(str))
-    
-    # Ensure numeric columns are float type
-    for col in numeric_columns:
-        df[col] = df[col].astype(float)
-    
-    # Ensure columns are in the correct order
-    df = df[categorical_columns + numeric_columns]
-    
+    label_encoder = LabelEncoder()
+    ordinal_columns = df.select_dtypes(include=['object']).columns
+
+    for col in ordinal_columns:
+        df[col] = label_encoder.fit_transform(df[col])
+
+    nominal_columns = df.select_dtypes(include=['object']).columns.difference(ordinal_columns)
+    df = pd.get_dummies(df, columns=nominal_columns, drop_first=True)
+
     return df
 
-def predict_performance(Location, Course, Faculty, College, Source, Event, Presenter, Visited_Parent, 
-                       Visited_College_for_Inquiry, Attended_Any_Event, College_Fee, GPA, Year):
-    # Create input DataFrame with consistent column names
-    input_data = {
-        "Location": [Location],
-        "Course": [Course],
-        "Faculty": [Faculty],
-        "College": [College],
-        "Source": [Source],
-        "Event": [Event],
-        "Presenter": [Presenter],
-        "Visited Parent": [Visited_Parent],
-        "Visited College for Inquiry": [Visited_College_for_Inquiry],
-        "Attended Any Event": [Attended_Any_Event],
-        "College Fee": [float(College_Fee)],
-        "GPA": [float(GPA)],
-        "Year": [float(Year)]
-    }
+# Define the prediction function
+def predict_performance(Location, College_Fee,College, GPA, Year, Course_Interested, Faculty, Source, 
+                       Visited_College_for_Inquiry_Only, Event, Attended_Any_Events, 
+                       Presenter, Visited_Parents):
+    
+    input_data = [[Location, College_Fee,College, GPA, Year, Course_Interested, Faculty, Source,
+                 Visited_College_for_Inquiry_Only, Event, Attended_Any_Events,
+                 Presenter, Visited_Parents]]
+
+    feature_names = ["Location", "College Fee","College", "GPA", "Year", "Course Interested",
+                    "Faculty", "Source", "Visited College for Inquiry Only", "Event",
+                    "Attended Any Events", "Presenter", "Visited Parents"]
     
-    input_df = pd.DataFrame(input_data)
+    input_df = pd.DataFrame(input_data, columns=feature_names)
     
     # Debug print 2: Show DataFrame before encoding
     print("\nDataFrame before encoding:")
     print(input_df)
     
-    # Encode categorical columns
     df = encode_categorical_columns(input_df)
     
     # Debug print 3: Show DataFrame after encoding
     print("\nDataFrame after encoding:")
     print(df)
     
-    # Ensure the DataFrame columns match the order used during scaler fitting
-    expected_columns = ["Location", "Course", "Faculty", "College", "Source", "Event", 
-                        "Presenter", "Visited Parent", "Visited College for Inquiry", 
-                        "Attended Any Event", "College Fee", "GPA", "Year"]
-    df = df[expected_columns]
-    
-    # Scale input data using the loaded scaler
     scaled_input = scaler.transform(df)
     
-    # Make the prediction
-    prediction = model.predict(scaled_input)[0]
+    # Debug print 4: Show scaled input
+    print("\nScaled input:")
+    print(scaled_input)
     
-    # Clip the prediction to be between 0 and 1
-    prediction = np.clip(prediction, 0, 1)
+    prediction = model.predict(scaled_input)[0]
     
-    # Debug print
+    # Debug print 5: Show prediction details
     print("\nPrediction details:")
     print(f"Raw prediction: {prediction}")
+    prediction_probability = 1 / (1 + np.exp(-prediction))
+    print(f"Probability: {prediction_probability}")
+    prediction_percentage = prediction_probability * 100
+    print(f"Percentage: {prediction_percentage}")
     
-    return f"Chance of Admission: {prediction:.1f}"
-
-# Create Gradio interface
+    return f"Chance of Admission: {prediction_percentage:.1f}%"
+ 
 iface = gr.Interface(
     fn=predict_performance,
     inputs=[
         gr.Radio(["Kathmandu", "Bhaktapur", "Lalitpur", "Kritipur"], label="Location"),
-        gr.Radio(["MSc IT & Applied Security", "BSc (Hons) Computing", 
-                 "BSc (Hons) Computing with Artificial Intelligence", 
-                 "BSc (Hons) Computer Networking & IT Security", 
-                 "BSc (Hons) Multimedia Technologies", "MBA", 
-                 "BA (Hons) Accounting & Finance", 
-                 "BA (Hons) Business Administration"], label="Course"),
+        gr.Slider(minimum=1000000, maximum=1700000, label="College Fee"),
+        gr.Slider(minimum=2, maximum=3, label="GPA"),  # Fixed GPA input
+        gr.Slider(minimum=2019, maximum=2025, step=1, label="Year"),
+        gr.Radio(["MSc IT & Applied Security", "BSc (Hons) Computing", "BSc (Hons) Computing with Artificial Intelligence", 
+                 "BSc (Hons) Computer Networking & IT Security", "BSc (Hons) Multimedia Technologies", "MBA", 
+                 "BA (Hons) Accounting &  Finance", "BA (Hons) Business Administration"], label="Course_Interested"),
         gr.Radio(["Science", "Management", "Humanities"], label="Faculty"),
-        gr.Radio(["Trinity", "CCRC", "KMC", "SOS", "ISMT", "St. Xavier's", "Everest", "Prime"], label="College"),
         gr.Radio(["Event", "Facebook", "Instagram", "Offline", "Recommendation"], label="Source"),
-        gr.Radio(["New Year", "Dashain", "Orientation", "Fresher's Party", 
-                 "Holi Festival", "Welcome Ceremony"], label="Event"),
-        gr.Radio(["Ram", "Gita", "Manish", "Shyam", "Raj", "Hari", "Rina", "Shree"], 
-                label="Presenter"),
-        gr.Radio(["Yes", "No"], label="Visited Parent"),
-        # gr.Radio(["Trinity", "CCRC", "KMC", "SOS", "ISMT", "St. Xavier's", "Everest", "Prime"], label="College"),
-        gr.Radio(["Yes", "No"], label="Visited College for Inquiry"),
-        gr.Radio(["Yes", "No"], label="Attended Any Event"),
-        gr.Number(label="College Fee"),
-        gr.Number(label="GPA"),
-        gr.Number(label="Year")
+        gr.Radio(["Yes", "No"], label="visited_college_for_inquery_only"),
+        gr.Radio(["New Year", "Dashain", "Orientation", "Fresher's Party", "Holi Festival", "Welcome Ceremony"], 
+                label="attended_event_name"),  # Changed from Slider to Radio
+        gr.Radio(["Yes", "No"], label="attended_any_event"), 
+        gr.Radio(["Trinity", "CCRC", "KMC", "SOS", "ISMT", "St. Xavier's", "Everest", "Prime"], label="College"),
+        gr.Radio(["Ram", "Gita", "Manish", "Shyam", "Raj", "Hari", "Rina", "Shree"], label="Presenter"),
+        gr.Radio(["Yes", "No"], label="visited_with_parents") ["Trinity", "CCRC", "KMC", "SOS", "ISMT", "St. Xavier's", "Everest", "Prime"]
+
     ],
     outputs="text",
-    title="Chance of Student Admission",
-    description="Predict the chances of a student's admission based on various inputs."
+    title="chances of student admission",
+    description="chances of student admission"
 )
 
 # Run the app
 if __name__ == "__main__":
-    iface.launch(share=True)
+    iface.launch(share=True)