Update src/streamlit_app.py

src/streamlit_app.py

@@ -4,17 +4,25 @@ import pandas as pd
 import numpy as np
 
 # --- Configuration ---
-MODEL_PATH = 'src/kn_perormance_prediction.joblib' 
-ENCODERS_PATH = 'src/label_encoders.joblib' 
+MODEL_PATH = 'src/kn_perormance_prediction.joblib'
+ENCODERS_PATH = 'src/label_encoders.joblib'
 
+# REAL features the model expects (first 10 columns of df during training)
 FEATURES = [
-    'gender', 'race/ethnicity', 'parental level of education', 
-    'lunch', 'test preparation course', 'math score', 
-    'reading score', 'writing score'
+    'gender', 
+    'race/ethnicity', 
+    'parental level of education', 
+    'lunch', 
+    'test preparation course', 
+    'math score', 
+    'reading score', 
+    'writing score',
+    'total_score',
+    'percentage'
 ]
 
 RACE_MAP = {
-    'group A': 1, 'group B': 2, 'group C': 3, 
+    'group A': 1, 'group B': 2, 'group C': 3,
     'group D': 4, 'group E': 5
 }
 
@@ -22,36 +30,45 @@ RACE_MAP = {
 def load_assets():
     try:
         model = joblib.load(MODEL_PATH)
-        encoders = joblib.load(ENCODERS_PATH) # Load the dict of encoders
+        encoders = joblib.load(ENCODERS_PATH)
         return model, encoders
     except Exception as e:
-        st.error(f"Error loading assets. Ensure model and encoders are uploaded. Error: {e}")
+        st.error(f"Error loading model or encoders: {e}")
         return None, None
 
+
 def preprocess_and_predict(model, encoders, input_data):
-    
-    # 1. Create a DataFrame for processing
+
     df_input = pd.DataFrame([input_data])
-    
-    # 2. Apply Custom Race/Ethnicity Mapping (as done in the original notebook)
+
+    # 1. Map race/ethnicity exactly as in training
     df_input['race/ethnicity'] = df_input['race/ethnicity'].map(RACE_MAP)
 
-    # 3. Apply Label Encoding for other Categorical Features
+    # 2. Apply Label Encoding for categorical inputs
     for col, le in encoders.items():
-        # Use the loaded LabelEncoder objects to transform the input strings
         df_input[col] = le.transform(df_input[col])
-        
-    # 4. Prepare the final input array
+
+    # 3. Compute total_score and percentage (missing features)
+    df_input['total_score'] = (
+        df_input['math score'] +
+        df_input['reading score'] +
+        df_input['writing score']
+    )
+
+    df_input['percentage'] = df_input['total_score'] / 3
+
+    # 4. Final array in the correct feature order
     final_input_array = df_input[FEATURES].values
-    
-    # 5. Predict the grade (O, A, B, C, D, E)
+
+    # 5. Predict grade
     prediction_label = model.predict(final_input_array)
-    
+
     return prediction_label[0]
 
-# --- Streamlit Interface ---
+
+# --- Streamlit UI ---
 st.set_page_config(page_title="Student Performance", layout="centered")
-st.title("📚 Student Final Grade Predictor (A-E)")
+st.title("📚 Student Final Grade Predictor (A–E)")
 st.markdown("Enter student characteristics and scores to predict the final letter grade.")
 
 model, encoders = load_assets()
@@ -59,36 +76,38 @@ model, encoders = load_assets()
 if model is not None and encoders is not None:
     st.sidebar.header("Student Information")
 
-    # --- INPUT WIDGETS ---
     gender = st.sidebar.selectbox("Gender:", options=['male', 'female'])
     race = st.sidebar.selectbox("Race/Ethnicity:", options=list(RACE_MAP.keys()))
-    parental_education = st.sidebar.selectbox("Parental Education:", options=['some high school', 'high school', 'some college', 'associate\'s degree', 'bachelor\'s degree', 'master\'s degree'])
+    parental_education = st.sidebar.selectbox(
+        "Parental Education:",
+        options=[
+            'some high school', 'high school', 'some college',
+            "associate's degree", "bachelor's degree", "master's degree"
+        ]
+    )
     lunch = st.sidebar.selectbox("Lunch:", options=['standard', 'free/reduced'])
     prep_course = st.sidebar.selectbox("Test Prep Course:", options=['none', 'completed'])
 
     st.sidebar.header("Scores (0-100)")
-    math = st.sidebar.slider("Math Score:", min_value=0, max_value=100, value=70)
-    reading = st.sidebar.slider("Reading Score:", min_value=0, max_value=100, value=75)
-    writing = st.sidebar.slider("Writing Score:", min_value=0, max_value=100, value=72)
-    
-    # Collect inputs
+    math = st.sidebar.slider("Math Score:", 0, 100, 70)
+    reading = st.sidebar.slider("Reading Score:", 0, 100, 75)
+    writing = st.sidebar.slider("Writing Score:", 0, 100, 72)
+
     input_data = {
-        'gender': gender, 
-        'race/ethnicity': race, 
-        'parental level of education': parental_education, 
-        'lunch': lunch, 
-        'test preparation course': prep_course, 
-        'math score': math, 
-        'reading score': reading, 
+        'gender': gender,
+        'race/ethnicity': race,
+        'parental level of education': parental_education,
+        'lunch': lunch,
+        'test preparation course': prep_course,
+        'math score': math,
+        'reading score': reading,
         'writing score': writing
     }
 
     if st.button("Predict Final Grade"):
-        with st.spinner('Calculating prediction...'):
+        with st.spinner("Calculating prediction..."):
             predicted_grade = preprocess_and_predict(model, encoders, input_data)
             
             st.success("Prediction Successful!")
             st.markdown("### Predicted Letter Grade:")
-            st.markdown(f"**{predicted_grade}**")
-            
-            st.info("The prediction is the most likely letter grade (O, A, B, C, D, E) based on the input features.")
+            st.markdown(f"**{predicted_grade}**")