Update app.py

app.py

@@ -3,12 +3,11 @@ import joblib
 import numpy as np
 import pandas as pd
 from huggingface_hub import hf_hub_download
-from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
+from sklearn.preprocessing import StandardScaler, LabelEncoder
 
-# Load the trained model and scaler objects from file
-REPO_ID = "Hemg/marketpredict"  # Hugging Face repo ID
-MoDEL_FILENAME = "stx.joblib"  # Model file name
-SCALER_FILENAME = "scaler.joblib"  # Scaler file name
+REPO_ID = "Hemg/modelxxx"
+MoDEL_FILENAME = "studentpredict.joblib"
+SCALER_FILENAME = "studentscaler.joblib"
 
 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))
@@ -25,45 +24,100 @@ def encode_categorical_columns(df):
 
     return df
 
-# Define the prediction function
-def predict_performance(Year, Instagram_Advertising, Facebook_Advertising, Event_Expenses, Internet_Expenses):
-    # Prepare input data (represents independent variables for house prediction)
-    input_data = [[Year, Instagram_Advertising, Facebook_Advertising, Event_Expenses, Internet_Expenses]]
-
-    # Get the feature names from the Gradio interface inputs
-    feature_names = ["Year", "Instagram_Advertising", "Facebook_Advertising", "Event_Expenses", "Internet_Expenses"]
-
-    # Create a Pandas DataFrame with the input data and feature names
-    input_df = pd.DataFrame(input_data, columns=feature_names)
-
-    input_df = encode_categorical_columns(input_df)
-
-    # Scale the input data using the loaded scaler
-    scaled_input = scaler.transform(input_df)
-
-    # Make predictions using the loaded model
-    prediction = model.predict(scaled_input)[0]
-
-    # Return the result as HTML with custom styling (green color and larger font)
-    return f'<p style="font-size: 24px; color: green;">Forecast no of. Students admission: {prediction:,.0f}</p>'
-
-
-
-def create_demo():
-# Create the Gradio app
-    demo = gr.Interface(
-        fn=predict_performance,
-        inputs=[
-            gr.Slider(minimum=2024, maximum=2025, step=1, label="Year",info="The forecasted Year"),
-            gr.Slider(minimum=10000, maximum=45000, step=500, label="Instagram_Advertising", info="How much do you spend on Instagram ads Yearly($)?"),
-            gr.Slider(minimum=10000, maximum=75000, step=500, label="Facebook_Advertising", info="How much do you spend on Facebook ads Yearly($)?"),
-            gr.Slider(minimum=20000, maximum=100000, step=500, label="Event_Expenses", info="What’s your typical budget for events($)?"),
-            gr.Slider(minimum=5000, maximum=45000, step=500, label="Internet_Expenses", info="How much do you spend on internet Yearly($)?")
-        ],
-        outputs=gr.HTML(),  # Specify the output as HTML
-        title="Student Admission Forecast",
-        description="Forecast of chances of student admission based on marketing expenditures"
-    )
-    demo.launch(auth=("admin", "Gr@ce"),   share=True   )
-
-create_demo()
+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):
+    try:
+        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, columns=feature_names)
+        df = encode_categorical_columns(input_df)
+        df = df.reindex(columns=scaler.feature_names_in_, fill_value=0)
+        scaled_input = scaler.transform(df)
+
+        # Get probability prediction
+        probabilities = model.predict_proba(scaled_input)[0]
+        # Take the probability of positive class (usually index 1)
+        admission_probability = probabilities[1]
+        
+        # Ensure the probability is between 0 and 1
+        admission_probability = np.clip(admission_probability, 0, 1)
+        
+        # Convert to percentage
+        prediction_percentage = admission_probability * 100
+
+        # Create styled HTML output
+        # html_template = """
+        # <div style='text-align: center; padding: 20px;'>
+        #     <div style='font-family: Arial, sans-serif; font-size: 24px; margin-bottom: 15px;'>
+        #         Admission Probability: <span style='font-weight: bold;'>{:.1f}%</span>
+        #     </div>
+        #     <div style='{style}'>
+        #         {message}
+        #     </div>
+        # </div>
+        # """
+ # Create styled HTML output
+        html_template = """
+        <div style='text-align: center; padding: 20px;'>
+            <div style='{style}'>
+                {message}
+            </div>
+        </div>
+        """
+
+
+        if prediction_percentage > 50:
+            style = "font-family: Arial, sans-serif; font-size: 32px; color: #28a745; font-weight: bold;"
+            message = "High chance of admission"
+        elif prediction_percentage < 50:
+            style = "font-family: Arial, sans-serif; font-size: 32px; color: #dc3545; font-weight: bold; text-transform: uppercase;"
+            message = "Lower chance of admission"
+        else:  # exactly 50
+            style = "font-family: Arial, sans-serif; font-size: 32px; color: #ffc107; font-weight: bold;"
+            message = "Moderate chance of admission"
+
+        return html_template.format(prediction_percentage, style=style, message=message)
+
+    except Exception as e:
+        return f"<div style='color: red; font-family: Arial, sans-serif;'>Error in prediction: {str(e)}</div>"
+
+# Update the Gradio interface
+iface = gr.Interface(
+    fn=predict_performance,
+   inputs=[
+        gr.Radio(["Kathmandu", "Bhaktapur", "Lalitpur", "Kritipur"], label="Location",info="What is your current location?"),
+        gr.Slider(minimum=1000000, maximum=1700000,step=100000,label="College Fee", info="What 's the the total bachelor fee for the course you want to enroll?"),
+        gr.Radio(["Trinity", "CCRC", "KMC", "SOS", "ISMT", "St. Xavier's", "Everest", "Prime"], label="College", info="What is the name of the last college you attended?"),
+        gr.Slider(minimum=2, maximum=3, label="GPA", info="What is your GPA (Grade Point Average) of +2 ?"),
+        gr.Slider(minimum=2024, maximum=2026, step=1, label="Year", info="What is your intended year of admission?"),
+        #gr.Radio([2024, 2025, 2026], label="Year", info="What is your intended year of admission?")
+        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", info="Which course are you most interested in?"),
+        gr.Radio(["Science", "Management", "Humanities"], label="Faculty", info="what is your last stream ?"),
+        gr.Radio(["Event", "Facebook", "Instagram", "Offline", "Recommendation"], label="Source",info="How did you first hear about this college?"),
+        gr.Radio(["Yes", "No"], label="visited_college_for_inquery_only", info="Have you visited the college you're interested in for an inquiry or consultation?"),
+        gr.Radio(["Yes", "No"], label="attended_any_event", info="Have you attended any events organized by the college you're interested in?"),
+        gr.Radio(["New Year", "Dashain", "Orientation", "Fresher's Party", "Holi Festival", "Welcome Ceremony"], 
+                label="attended_event_name", info="If yes, which events did you attend?" ),
+        gr.Radio(["Ram", "Gita", "Manish", "Shyam", "Raj", "Hari", "Rina", "Shree"], label="Presenter", info="who is the counser that help you while in counseling?"),
+        gr.Radio(["Yes", "No"], label="visited_with_parents", info="Did you visit the college with your parents?")
+    ],
+
+
+    
+    outputs=gr.HTML(),  # Changed to HTML output
+    title="Student Admission Prediction",
+    description="Predict the probability of student admission",
+    css="body { font-family: Arial, sans-serif; }"
+)
+
+if __name__ == "__main__":
+    iface.launch(share=True)