Create app.py

app.py

@@ -0,0 +1,182 @@
+# app.py
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.ensemble import RandomForestRegressor
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Seed for reproducibility
+np.random.seed(42)
+
+# Function to generate student data
+def generate_student_data(n_samples=500):
+    data = {
+        'attendance_rate': np.random.uniform(0.5, 1, n_samples),
+        'study_hours_per_week': np.random.uniform(0, 40, n_samples),
+        'previous_semester_gpa': np.random.uniform(2.0, 4.0, n_samples),
+        'socioeconomic_status': np.random.choice([1, 2, 3], n_samples),
+        'extracurricular_activities': np.random.randint(0, 5, n_samples),
+        'family_support': np.random.choice([0, 1], n_samples),
+        'final_grade': None
+    }
+    
+    # Create target variable with dependencies
+    data['final_grade'] = (
+        0.3 * data['attendance_rate'] * 10 + 
+        0.25 * data['study_hours_per_week'] + 
+        0.2 * data['previous_semester_gpa'] * 2 + 
+        0.1 * (data['socioeconomic_status'] * 2) + 
+        0.05 * data['extracurricular_activities'] + 
+        0.1 * (data['family_support'] * 3) + 
+        np.random.normal(0, 1, n_samples)
+    )
+    
+    # Normalize final grade to be between 0 and 10
+    data['final_grade'] = np.clip((data['final_grade'] - np.min(data['final_grade'])) / 
+                                   (np.max(data['final_grade']) - np.min(data['final_grade'])) * 10, 0, 10)
+    
+    return pd.DataFrame(data)
+
+# Generate dataset and prepare model
+df = generate_student_data()
+X = df.drop('final_grade', axis=1)
+y = df['final_grade']
+
+# Split and scale data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+# Train Random Forest model
+rf_model = RandomForestRegressor(n_estimators=100, random_state=42)
+rf_model.fit(X_train_scaled, y_train)
+
+# Streamlit App
+st.set_page_config(page_title="Student Performance Predictor", page_icon="🎓")
+
+# App Title
+st.title("🎓 Student Performance Prediction Model")
+
+# Sidebar for Input
+st.sidebar.header("Student Information")
+
+# Input Sliders and Selectors
+attendance_rate = st.sidebar.slider(
+    "Attendance Rate", 
+    min_value=0.5, 
+    max_value=1.0, 
+    value=0.85, 
+    step=0.05
+)
+
+study_hours = st.sidebar.slider(
+    "Weekly Study Hours", 
+    min_value=0, 
+    max_value=40, 
+    value=25
+)
+
+prev_gpa = st.sidebar.slider(
+    "Previous Semester GPA", 
+    min_value=2.0, 
+    max_value=4.0, 
+    value=3.5, 
+    step=0.1
+)
+
+socioeconomic_status = st.sidebar.selectbox(
+    "Socioeconomic Status", 
+    [1, 2, 3], 
+    index=1,
+    format_func=lambda x: {1:"Low", 2:"Medium", 3:"High"}[x]
+)
+
+extracurricular_activities = st.sidebar.slider(
+    "Extracurricular Activities", 
+    min_value=0, 
+    max_value=4, 
+    value=2
+)
+
+family_support = st.sidebar.selectbox(
+    "Family Support", 
+    [0, 1], 
+    index=1,
+    format_func=lambda x: "Yes" if x == 1 else "No"
+)
+
+# Prediction Function
+def predict_student_performance(input_data):
+    input_scaled = scaler.transform(input_data)
+    prediction = rf_model.predict(input_scaled)[0]
+    return np.round(prediction, 2)
+
+# Predict Button
+if st.sidebar.button("Predict Performance"):
+    # Prepare input data
+    input_data = np.array([[
+        attendance_rate, 
+        study_hours, 
+        prev_gpa, 
+        socioeconomic_status, 
+        extracurricular_activities, 
+        family_support
+    ]])
+    
+    # Make prediction
+    predicted_grade = predict_student_performance(input_data)
+    
+    # Display prediction
+    st.subheader("Prediction Results")
+    
+    # Color-coded performance indicator
+    if predicted_grade >= 8:
+        color = "green"
+        performance = "Excellent"
+    elif predicted_grade >= 6:
+        color = "blue"
+        performance = "Good"
+    elif predicted_grade >= 4:
+        color = "orange"
+        performance = "Average"
+    else:
+        color = "red"
+        performance = "Needs Improvement"
+    
+    st.markdown(f"""
+    <div style="background-color:{color}; padding:10px; border-radius:10px;">
+    <h2 style="color:white; text-align:center;">
+    Predicted Final Grade: {predicted_grade}/10
+    <br>Performance: {performance}
+    </h2>
+    </div>
+    """, unsafe_allow_html=True)
+
+# Feature Importance Visualization
+st.subheader("Feature Importance")
+feature_importance = pd.DataFrame({
+    'feature': X.columns,
+    'importance': rf_model.feature_importances_
+}).sort_values('importance', ascending=False)
+
+fig, ax = plt.subplots(figsize=(10, 6))
+sns.barplot(x='importance', y='feature', data=feature_importance, ax=ax)
+plt.title('Factors Influencing Student Performance')
+plt.xlabel('Importance Score')
+st.pyplot(fig)
+
+# Additional Information
+st.markdown("""
+### About the Model
+This machine learning model predicts student performance based on:
+- Attendance Rate
+- Weekly Study Hours
+- Previous Semester GPA
+- Socioeconomic Status
+- Extracurricular Activities
+- Family Support
+""")