Update app.py

app.py

@@ -1,60 +1,73 @@
-# Import necessary libraries
-import pandas as pd
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import accuracy_score
-from sklearn.pipeline import Pipeline
-from sklearn.preprocessing import StandardScaler
 import gradio as gr
+import numpy as np
+import pandas as pd
+import joblib
+
+# Load the trained models
+rf_fullstk = joblib.load('rf_hacathon_fullstk.pkl')
+rf_prodengg = joblib.load('rf_hacathon_prodengg.pkl')
+rf_mkt = joblib.load('rf_hacathon_mkt.pkl')
+
+# Define prediction functions for each model
+def predict_fullstk(degree_p, internship, DSA, java):
+    new_data = pd.DataFrame({
+        'degree_p': degree_p,
+        'internship': internship,
+        'DSA': DSA,
+        'java': java,
+    }, index=[0])
+    prediction = rf_fullstk.predict(new_data)[0]
+    probability = rf_fullstk.predict_proba(new_data)[0][1]
+    return 'Placed' if prediction == 1 else 'Not Placed', probability
+
+def predict_prodengg(degree_p, internship, management, leadership):
+    new_data = pd.DataFrame({
+        'degree_p': degree_p,
+        'internship': internship,
+        'management': management,
+        'leadership': leadership,
+    }, index=[0])
+    prediction = rf_prodengg.predict(new_data)[0]
+    probability = rf_prodengg.predict_proba(new_data)[0][1]
+    return 'Placed' if prediction == 1 else 'Not Placed', probability
+
+def predict_mkt(degree_p, internship, communication, sales):
+    new_data = pd.DataFrame({
+        'degree_p': degree_p,
+        'internship': internship,
+        'communication': communication,
+        'sales': sales,
+    }, index=[0])
+    prediction = rf_mkt.predict(new_data)[0]
+    probability = rf_mkt.predict_proba(new_data)[0][1]
+    return 'Placed' if prediction == 1 else 'Not Placed', probability
+
+# Create input and output components for each model
+fullstk_inputs = [
+    gr.inputs.Number(label='Degree Percentage', min_value=0, max_value=100),
+    gr.inputs.Radio(label='Internship', choices=[0, 1]),
+    gr.inputs.Radio(label='DSA', choices=[0, 1]),
+    gr.inputs.Radio(label='Java', choices=[0, 1])
+]
+fullstk_output = gr.outputs.Label(num_top_classes=2, label='Placement Status')
+
+prodengg_inputs = [
+    gr.inputs.Number(label='Degree Percentage', min_value=0, max_value=100),
+    gr.inputs.Radio(label='Internship', choices=[0, 1]),
+    gr.inputs.Radio(label='Management Skills', choices=[0, 1]),
+    gr.inputs.Radio(label='Leadership Skills', choices=[0, 1])
+]
+prodengg_output = gr.outputs.Label(num_top_classes=2, label='Placement Status')
+
+mkt_inputs = [
+    gr.inputs.Number(label='Degree Percentage', min_value=0, max_value=100),
+    gr.inputs.Radio(label='Internship', choices=[0, 1]),
+    gr.inputs.Radio(label='Communication Skills', choices=[0, 1]),
+    gr.inputs.Radio(label='Sales Skills', choices=[0, 1])
+]
+mkt_output = gr.outputs.Label(num_top_classes=2, label='Placement Status')
 
-# Load the CSV data into a pandas DataFrame
-data = pd.read_csv('dataset.csv')
-
-# Split the data into features (X) and labels (y)
-X = data.iloc[:, :-1]  # All columns except the last one
-y = data.iloc[:, -1]  # Last column (placed or not)
-
-# Split the data into training and testing sets
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-# Create a pipeline with a Random Forest Classifier
-pipeline = Pipeline([
-    ('scaler', StandardScaler()),  # Standardize features
-    ('classifier', RandomForestClassifier())  # Random Forest Classifier
-])
-
-# Fit the pipeline to the training data
-pipeline.fit(X_train, y_train)
-
-# Make predictions on the testing data
-y_pred = pipeline.predict(X_test)
-
-# Calculate accuracy of the model
-accuracy = accuracy_score(y_test, y_pred)
-print('Accuracy:', accuracy)
-
-# Define the input and output types for Gradio
-input_type = 'csv'
-output_type = 'label'
-
-# Define the function to make predictions using the trained model
-def predict_placement(Internships, CGPA, HistoryOfBacklogs):
-    # Create a DataFrame from the input data
-    input_df = pd.DataFrame({'Internships': [Internships], 'CGPA': [CGPA], 'HistoryOfBacklogs': [HistoryOfBacklogs]})
-    
-    # Make a prediction using the trained model
-    prediction = pipeline.predict(input_df)[0]
-    
-    # Return the predicted label
-    return 'Placed' if prediction else 'Not Placed'
-
-interface = gr.Interface(
-    fn=predict_placement,
-    inputs=["number", "number", "number"],
-    outputs="text",
-    title="Student Placement Prediction",
-    description="Predict whether a student will be placed in a job based on their internships, CGPA, and history of backlogs."
-)
-
-# Launch the Gradio interface
-interface.launch()
+# Create the Gradio app
+fullstk_interface = gr.Interface(
+    fn=predict_fullstk,
+    inputs=fullstk