update

app.py

@@ -6,6 +6,7 @@ from sklearn.preprocessing import LabelEncoder
 from sklearn.ensemble import RandomForestClassifier
 import joblib
 
+#
 # Load and preprocess data
 def load_and_preprocess_data(filename):
     df = pd.read_csv(filename)
@@ -17,53 +18,28 @@ def load_and_preprocess_data(filename):
         label_encoders[col] = le
     
     X = df[["Category", "Gender", "Opening Rank", "Closing Rank", "Region"]]
-    y_college = df["College Name"]
-    y_branch = df["Branch"]
+    y_college_branch = df[["College Name", "Branch"]]
     
-    return X, y_college, y_branch, label_encoders, df
+    return X, y_college_branch, label_encoders, df
 
 filename = "AP_EAMCET_Engineering_10000 (1).csv"
-X, y_college, y_branch, label_encoders, df = load_and_preprocess_data(filename)
+X, y_college_branch, label_encoders, df = load_and_preprocess_data(filename)
 
-# Train model and evaluate metrics
-def train_model(X, y, target_name):
+# Train model
+def train_model(X, y):
     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
 
-# Train separate models
-college_model = train_model(X, y_college, "College Name")
-branch_model = train_model(X, y_branch, "Branch")
+college_branch_model = train_model(X, y_college_branch)
 
-# Save models and encoders
-joblib.dump(college_model, "college_model.pkl")
-joblib.dump(branch_model, "branch_model.pkl")
+joblib.dump(college_branch_model, "college_branch_model.pkl")
 joblib.dump(label_encoders, "label_encoders.pkl")
 
 # Prediction function
 def predict_colleges(category, gender, rank, region):
-    # Load models and label encoders
-    college_model = joblib.load("college_model.pkl")
-    branch_model = joblib.load("branch_model.pkl")
+    # Load label encoders
     label_encoders = joblib.load("label_encoders.pkl")
     
     # Transform input values using label encoders
@@ -74,7 +50,7 @@ def predict_colleges(category, gender, rank, region):
     except ValueError:
         return "Invalid input values. Please select valid options."
     
-    # Filter dataset based on criteria
+    # Filter the dataset based on encoded values
     filtered_df = df[
         (df["Category"] == category_enc) &
         (df["Gender"] == gender_enc) &
@@ -107,4 +83,4 @@ demo = gr.Interface(
     description="Enter your details to predict all possible colleges and branches based on your rank."
 )
 
-demo.launch()
+demo.launch()

college predictor.py

@@ -1,85 +0,0 @@
-import pandas as pd
-import numpy as np
-import gradio as gr
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import LabelEncoder
-from sklearn.ensemble import RandomForestClassifier
-import joblib
-
-# Load and preprocess data
-def load_and_preprocess_data(filename):
-    df = pd.read_csv(filename)
-    
-    label_encoders = {}
-    for col in ["College Name", "Category", "Gender", "Branch", "Region"]:
-        le = LabelEncoder()
-        df[col] = le.fit_transform(df[col])
-        label_encoders[col] = le
-    
-    X = df[["Category", "Gender", "Opening Rank", "Closing Rank", "Region"]]
-    y_college_branch = df[["College Name", "Branch"]]
-    
-    return X, y_college_branch, label_encoders, df
-
-filename = "AP_EAMCET_Engineering_10000 (1).csv"
-X, y_college_branch, label_encoders, df = load_and_preprocess_data(filename)
-
-# Train model
-def train_model(X, y):
-    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)
-    return model
-
-college_branch_model = train_model(X, y_college_branch)
-
-joblib.dump(college_branch_model, "college_branch_model.pkl")
-joblib.dump(label_encoders, "label_encoders.pkl")
-
-# Prediction function
-def predict_colleges(category, gender, rank, region):
-    # Load label encoders
-    label_encoders = joblib.load("label_encoders.pkl")
-    
-    # Transform input values using label encoders
-    try:
-        category_enc = label_encoders["Category"].transform([category])[0]
-        gender_enc = label_encoders["Gender"].transform([gender])[0]
-        region_enc = label_encoders["Region"].transform([region])[0]
-    except ValueError:
-        return "Invalid input values. Please select valid options."
-    
-    # Filter the dataset based on encoded values
-    filtered_df = df[
-        (df["Category"] == category_enc) &
-        (df["Gender"] == gender_enc) &
-        (df["Opening Rank"] <= rank) &
-        (df["Closing Rank"] >= rank) &
-        (df["Region"] == region_enc)
-    ]
-    
-    if filtered_df.empty:
-        return "No matching colleges found."
-    
-    # Decode college names and branches
-    filtered_df["College Name"] = label_encoders["College Name"].inverse_transform(filtered_df["College Name"].values)
-    filtered_df["Branch"] = label_encoders["Branch"].inverse_transform(filtered_df["Branch"].values)
-    
-    result = filtered_df[["College Name", "Branch"]].drop_duplicates().to_string(index=False)
-    return result
-
-# Gradio Interface
-demo = gr.Interface(
-    fn=predict_colleges,
-    inputs=[
-        gr.Dropdown(choices=["OC", "BC", "SC", "ST"], label="Category"),
-        gr.Radio(choices=["Male", "Female"], label="Gender"),
-        gr.Number(label="Rank"),
-        gr.Dropdown(choices=["AU", "SV"], label="Region")
-    ],
-    outputs="text",
-    title="AP EAMCET College Predictor",
-    description="Enter your details to predict all possible colleges and branches based on your rank."
-)
-
-demo.launch()