smallUpadte

app.py

@@ -17,28 +17,53 @@ def load_and_preprocess_data(filename):
         label_encoders[col] = le
     
     X = df[["Category", "Gender", "Opening Rank", "Closing Rank", "Region"]]
-    y_college_branch = df[["College Name", "Branch"]]
+    y_college = df["College Name"]
+    y_branch = df["Branch"]
     
-    return X, y_college_branch, label_encoders, df
+    return X, y_college, y_branch, label_encoders, df
 
-filename = "AP_EAMCET_Engineering_10000 (1).csv"
-X, y_college_branch, label_encoders, df = load_and_preprocess_data(filename)
+filename = "/content/AP_EAMCET_Engineering_10000 (1).csv"
+X, y_college, y_branch, label_encoders, df = load_and_preprocess_data(filename)
 
-# Train model
-def train_model(X, y):
+# Train model and evaluate metrics
+def train_model(X, y, target_name):
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
     model = RandomForestClassifier(n_estimators=100, random_state=42)
     model.fit(X_train, y_train)
+    
+    # Predictions
+    y_pred = model.predict(X_test)
+    
+    # Evaluate model metrics
+    accuracy = accuracy_score(y_test, y_pred)
+    precision = precision_score(y_test, y_pred, average='weighted', zero_division=1)
+    recall = recall_score(y_test, y_pred, average='weighted', zero_division=1)
+    f1 = f1_score(y_test, y_pred, average='weighted', zero_division=1)
+    conf_matrix = confusion_matrix(y_test, y_pred)
+    
+    print(f"{target_name} Model Metrics:")
+    print(f"Accuracy: {accuracy:.4f}")
+    print(f"Precision: {precision:.4f}")
+    print(f"Recall: {recall:.4f}")
+    print(f"F1 Score: {f1:.4f}")
+    print(f"Confusion Matrix:\n{conf_matrix}\n")
+    
     return model
 
-college_branch_model = train_model(X, y_college_branch)
+# Train separate models
+college_model = train_model(X, y_college, "College Name")
+branch_model = train_model(X, y_branch, "Branch")
 
-joblib.dump(college_branch_model, "college_branch_model.pkl")
+# Save models and encoders
+joblib.dump(college_model, "college_model.pkl")
+joblib.dump(branch_model, "branch_model.pkl")
 joblib.dump(label_encoders, "label_encoders.pkl")
 
 # Prediction function
 def predict_colleges(category, gender, rank, region):
-    # Load label encoders
+    # Load models and label encoders
+    college_model = joblib.load("college_model.pkl")
+    branch_model = joblib.load("branch_model.pkl")
     label_encoders = joblib.load("label_encoders.pkl")
     
     # Transform input values using label encoders
@@ -49,7 +74,7 @@ def predict_colleges(category, gender, rank, region):
     except ValueError:
         return "Invalid input values. Please select valid options."
     
-    # Filter the dataset based on encoded values
+    # Filter dataset based on criteria
     filtered_df = df[
         (df["Category"] == category_enc) &
         (df["Gender"] == gender_enc) &
@@ -82,4 +107,4 @@ demo = gr.Interface(
     description="Enter your details to predict all possible colleges and branches based on your rank."
 )
 
-demo.launch()
+demo.launch()