Update app.py

app.py

@@ -6,63 +6,112 @@ from sklearn.preprocessing import LabelEncoder
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.metrics import accuracy_score, classification_report
 
-def load_data(uploaded_file):
-    df = pd.read_csv(uploaded_file)
-    df.drop(columns=['id', 'City', 'Profession', 'Degree'], inplace=True, errors='ignore')
+# Step 1: Load dataset
+def load_data():
+    df = pd.read_csv(r"C:\Users\pavilion\Desktop\INNOMATICS_PROJECTS(SL)\Student_Depresion_Prediction(Machine_Learning)\student_depression_dataset.csv")
+    
+    # Drop unnecessary columns
+    df.drop(columns=['id', 'City', 'Work Pressure', 'Job Satisfaction'], inplace=True, errors='ignore')
+
+    # Keep only 'Student' in Profession and then drop the column
+    if 'Profession' in df.columns:
+        df = df[df['Profession'].str.lower() == 'student']
+        df.drop(columns=['Profession'], inplace=True, errors='ignore')
+
     return df
 
+# Step 2: Preprocess data (Convert categorical features to numerical)
 def preprocess_data(df):
     label_encoders = {}
-    categorical_cols = ['Gender', 'Sleep Duration', 'Dietary Habits', 
-                        'Have you ever had suicidal thoughts ?', 'Financial Stress', 
-                        'Family History of Mental Illness']
+    
+    # Identify categorical columns
+    categorical_cols = df.select_dtypes(include=['object']).columns.tolist()
+    
     for col in categorical_cols:
-        if col in df.columns:
-            le = LabelEncoder()
-            df[col] = le.fit_transform(df[col])
-            label_encoders[col] = le
+        le = LabelEncoder()
+        df[col] = le.fit_transform(df[col])  # Convert to numeric values
+        label_encoders[col] = le  # Store the encoder for later use
+
     return df, label_encoders
 
+# Step 3: Train the Random Forest model
 def train_model(X_train, y_train):
     model = RandomForestClassifier(n_estimators=100, random_state=42)
-    model.fit(X_train, y_train)
+    model.fit(X_train, y_train)  # Train the model
     return model
 
+# Step 4: Streamlit App
 def main():
-    st.title("Student Depression Prediction")
-    st.write("Upload your dataset to train and evaluate the Random Forest model.")
-    
-    uploaded_file = st.file_uploader("Upload CSV", type=["csv"])
+    st.set_page_config(page_title="Student Depression Prediction", layout="wide")
     
-    if uploaded_file:
-        df = load_data(uploaded_file)
-        df, _ = preprocess_data(df)
-        
-        X = df.drop(columns=['Depression'])
-        y = df['Depression']
-        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
-        
-        model = train_model(X_train, y_train)
-        y_pred = model.predict(X_test)
-        
-        accuracy = accuracy_score(y_test, y_pred)
-        classification_rep = classification_report(y_test, y_pred)
-        
-        feature_importances = model.feature_importances_
-        feature_importance_df = pd.DataFrame({
-            'Feature': X.columns,
-            'Importance': feature_importances
-        }).sort_values(by='Importance', ascending=False)
-        
-        st.subheader("Model Evaluation")
+    st.markdown("<h1 style='text-align: center;'>🎓 Student Depression Prediction App</h1>", unsafe_allow_html=True)
+    st.write("This app predicts whether a student is likely to experience depression based on various factors.")
+
+    # Load dataset
+    df = load_data()
+
+    # Preprocess data
+    df, label_encoders = preprocess_data(df)
+
+    # Split features (X) and target variable (y)
+    X = df.drop(columns=['Depression'])  # Features
+    y = df['Depression']  # Target (Depression)
+
+    # Train/Test split
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+
+    # Train model
+    model = train_model(X_train, y_train)
+    y_pred = model.predict(X_test)
+
+    # Model evaluation
+    accuracy = accuracy_score(y_test, y_pred)
+    classification_rep = classification_report(y_test, y_pred)
+
+    # Train Model Button
+    if st.button("🚀 Train Model"):
+        st.subheader("✅ Model Trained Successfully!")
         st.write(f"**Accuracy:** {accuracy:.2f}")
         st.text("Classification Report:")
         st.text(classification_rep)
+
+    # Feature Importance
+    feature_importances = model.feature_importances_
+    feature_importance_df = pd.DataFrame({
+        'Feature': X.columns,
+        'Importance': feature_importances
+    }).sort_values(by='Importance', ascending=False)
+
+    st.subheader("🔍 Feature Importance")
+    fig, ax = plt.subplots()
+    ax.barh(feature_importance_df['Feature'], feature_importance_df['Importance'], color='skyblue')
+    ax.set_xlabel("Importance")
+    ax.set_ylabel("Feature")
+    ax.set_title("Feature Importance in Random Forest")
+    st.pyplot(fig)
+
+    # User Input for Prediction
+    st.subheader("📊 Predict Depression Risk")
+
+    input_data = {}
+    
+    for col in X.columns:
+        if col in label_encoders:  # Categorical columns
+            input_data[col] = st.selectbox(f"Select {col}", label_encoders[col].classes_)
+            input_data[col] = label_encoders[col].transform([input_data[col]])[0]
+        else:  # Numeric columns
+            input_data[col] = st.number_input(f"Enter {col}", min_value=int(X[col].min()), max_value=int(X[col].max()), value=int(X[col].mean()))
+
+    # Prediction Button
+    if st.button("🔮 Predict"):
+        input_df = pd.DataFrame([input_data])
+        prediction = model.predict(input_df)[0]
         
-        st.subheader("Feature Importance")
-        fig, ax = plt.subplots()
-        ax.barh(feature_importance_df['Feature'], feature_importance_df['Importance'], color='skyblue')
-        ax.set_xlabel("Importance")
-        ax.set_ylabel("Feature")
-        ax.set_title("Feature Importance in Random Forest")
-        st.pyplot(fig)
+        if prediction == 1:
+            st.success("😨 The student is **at risk of depression**.")
+        else:
+            st.info("🥳 The student is **not at risk of depression**.")
+
+# Run the Streamlit app
+if __name__ == '__main__':
+    main()