File size: 3,541 Bytes
bc0e057 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 7e00c24 98f9459 bc0e057 98f9459 7e00c24 98f9459 7e00c24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | 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'
# 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',
'total_score',
'percentage'
]
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)
return model, encoders
except Exception as e:
st.error(f"Error loading model or encoders: {e}")
return None, None
def preprocess_and_predict(model, encoders, input_data):
df_input = pd.DataFrame([input_data])
# 1. Map race/ethnicity exactly as in training
df_input['race/ethnicity'] = df_input['race/ethnicity'].map(RACE_MAP)
# 2. Apply Label Encoding for categorical inputs
for col, le in encoders.items():
df_input[col] = le.transform(df_input[col])
# 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 grade
prediction_label = model.predict(final_input_array)
return prediction_label[0]
# --- Streamlit UI ---
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")
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:", 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,
'writing score': writing
}
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}**") |