Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,94 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import joblib
+import pandas as pd
+import numpy as np
+
+# --- Configuration ---
+MODEL_PATH = 'src/kn_perormance_prediction.joblib' 
+ENCODERS_PATH = 'src/label_encoders.joblib' 
+
+FEATURES = [
+    'gender', 'race/ethnicity', 'parental level of education', 
+    'lunch', 'test preparation course', 'math score', 
+    'reading score', 'writing score'
+]
+
+RACE_MAP = {
+    'group A': 1, 'group B': 2, 'group C': 3, 
+    'group D': 4, 'group E': 5
+}
+
+@st.cache_resource
+def load_assets():
+    try:
+        model = joblib.load(MODEL_PATH)
+        encoders = joblib.load(ENCODERS_PATH) # Load the dict of encoders
+        return model, encoders
+    except Exception as e:
+        st.error(f"Error loading assets. Ensure model and encoders are uploaded. Error: {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)
+    df_input['race/ethnicity'] = df_input['race/ethnicity'].map(RACE_MAP)
+
+    # 3. Apply Label Encoding for other Categorical Features
+    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
+    final_input_array = df_input[FEATURES].values
+    
+    # 5. Predict the grade (O, A, B, C, D, E)
+    prediction_label = model.predict(final_input_array)
+    
+    return prediction_label[0]
+
+# --- Streamlit Interface ---
+st.set_page_config(page_title="Student Performance", layout="centered")
+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()
+
+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'])
+    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
+    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, 
+        'writing score': writing
+    }
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+    if st.button("Predict Final Grade"):
+        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.")