import numpy as np import pandas as pd import streamlit as st import joblib from pathlib import Path st.set_page_config(page_title='Spaceship Titanic - Transported Predictor', page_icon='🚀', layout='wide') BASE_DIR = Path(__file__).resolve().parent MODEL_PATH = BASE_DIR / 'spaceship_titanic_gb.pkl' HOMEPLANET_OPTIONS = ['Earth', 'Europa', 'Mars', 'Unknown'] DESTINATION_OPTIONS = ['TRAPPIST-1e', '55 Cancri e', 'PSO J318.5-22', 'Unknown'] DECK_OPTIONS = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'T', 'Unknown'] SIDE_OPTIONS = ['P', 'S', 'Unknown'] BOOL_UNKNOWN_OPTIONS = ['True', 'False', 'Unknown'] SPEND_COLS = ['RoomService', 'FoodCourt', 'ShoppingMall', 'Spa', 'VRDeck'] @st.cache_resource def load_artifact(): if not MODEL_PATH.exists(): raise FileNotFoundError( f'File not found: {MODEL_PATH.name}. Please upload it to the repo root (same folder as app.py).' ) artifact = joblib.load(MODEL_PATH) # Expected: {'model': ..., 'feature_columns': [...]} if isinstance(artifact, dict) and 'model' in artifact and 'feature_columns' in artifact: return artifact['model'], artifact['feature_columns'] # Fallback: if user saved only model return artifact, None def map_bool_unknown(val): # Map to numeric like your notebook: True->1, False->0, Unknown->-1 d = {'False': 0, 'True': 1, 'Unknown': -1, False: 0, True: 1} return d.get(val, -1) def build_features_from_row(row_dict): df = pd.DataFrame([row_dict]) # Ensure categorical values exist for c in ['HomePlanet', 'Destination', 'Deck', 'Side']: if c not in df.columns: df[c] = 'Unknown' df[c] = df[c].fillna('Unknown').astype(str) # Boolean-like with Unknown -> -1 for c in ['CryoSleep', 'VIP']: if c not in df.columns: df[c] = 'Unknown' df[c] = df[c].apply(map_bool_unknown).astype(int) # Numeric columns if 'Age' not in df.columns: df['Age'] = np.nan for c in SPEND_COLS: if c not in df.columns: df[c] = 0.0 df[c] = pd.to_numeric(df[c], errors='coerce') df['Age'] = pd.to_numeric(df['Age'], errors='coerce') # Group features if 'GroupSize' not in df.columns: df['GroupSize'] = 1 df['GroupSize'] = pd.to_numeric(df['GroupSize'], errors='coerce').fillna(1).astype(int) df['GroupSize'] = df['GroupSize'].clip(lower=1) # Feature engineering (same logic as your notebook) df['TotalSpend'] = df[SPEND_COLS].sum(axis=1) df['NotSpend'] = (df['TotalSpend'] == 0).astype(int) df['IsAlone'] = (df['GroupSize'] == 1).astype(int) # Fill remaining numeric NaNs (simple median-like fallback for single row) # For single prediction, we can fill with 0 for spends and with median-ish for Age (use 0 if missing) df['Age'] = df['Age'].fillna(df['Age'].median() if df['Age'].notna().any() else 0) return df def one_hot_and_align(df_features, feature_columns): df_encoded = pd.get_dummies(df_features, drop_first=True) if feature_columns is None: # If no feature columns are stored, we return encoded as-is (may break if columns mismatch) return df_encoded # Add missing columns missing = [c for c in feature_columns if c not in df_encoded.columns] for c in missing: df_encoded[c] = 0 # Drop extra columns extra = [c for c in df_encoded.columns if c not in feature_columns] if extra: df_encoded = df_encoded.drop(columns=extra) # Reorder df_encoded = df_encoded[feature_columns] return df_encoded st.title('🚀 Spaceship Titanic - Transported Predictor') with st.expander('What does this app do?', expanded=True): st.write( 'This app predicts whether a passenger was transported to another dimension (Transported=True/False) ' 'based on passenger features. It uses a Gradient Boosting Classifier trained on the Spaceship Titanic dataset.' ) try: model, feature_columns = load_artifact() except Exception as e: st.error(str(e)) st.stop() tab1, tab2 = st.tabs(['Single Prediction', 'Batch CSV Prediction']) with tab1: st.subheader('Single passenger prediction') colA, colB, colC = st.columns(3) with colA: homeplanet = st.selectbox('HomePlanet', HOMEPLANET_OPTIONS, index=0) destination = st.selectbox('Destination', DESTINATION_OPTIONS, index=0) age = st.number_input('Age', min_value=0.0, max_value=100.0, value=30.0, step=1.0) with colB: deck = st.selectbox('Deck', DECK_OPTIONS, index=DECK_OPTIONS.index('Unknown')) side = st.selectbox('Side', SIDE_OPTIONS, index=SIDE_OPTIONS.index('Unknown')) cryosleep = st.selectbox('CryoSleep', BOOL_UNKNOWN_OPTIONS, index=BOOL_UNKNOWN_OPTIONS.index('Unknown')) vip = st.selectbox('VIP', BOOL_UNKNOWN_OPTIONS, index=BOOL_UNKNOWN_OPTIONS.index('Unknown')) with colC: groupsize = st.number_input('GroupSize', min_value=1, max_value=20, value=1, step=1) st.markdown('### Spending') s1, s2, s3, s4, s5 = st.columns(5) with s1: roomservice = st.number_input('RoomService', min_value=0.0, value=0.0, step=10.0) with s2: foodcourt = st.number_input('FoodCourt', min_value=0.0, value=0.0, step=10.0) with s3: shoppingmall = st.number_input('ShoppingMall', min_value=0.0, value=0.0, step=10.0) with s4: spa = st.number_input('Spa', min_value=0.0, value=0.0, step=10.0) with s5: vrdeck = st.number_input('VRDeck', min_value=0.0, value=0.0, step=10.0) if st.button('Predict', type='primary'): row = { 'HomePlanet': homeplanet, 'Destination': destination, 'Deck': deck, 'Side': side, 'CryoSleep': cryosleep, 'VIP': vip, 'Age': age, 'RoomService': roomservice, 'FoodCourt': foodcourt, 'ShoppingMall': shoppingmall, 'Spa': spa, 'VRDeck': vrdeck, 'GroupSize': groupsize } df_feat = build_features_from_row(row) X = one_hot_and_align(df_feat, feature_columns) pred = model.predict(X)[0] proba = None if hasattr(model, 'predict_proba'): proba = model.predict_proba(X)[0, 1] st.success(f'Prediction: Transported = {bool(pred)}') if proba is not None: st.write(f'Probability (Transported=True): {proba:.3f}') st.caption('Note: This prediction is based on the trained ML model and engineered features.') with tab2: st.subheader('Batch prediction from CSV') st.write( 'Upload a CSV with columns like: HomePlanet, Destination, Deck, Side, CryoSleep, VIP, Age, ' 'RoomService, FoodCourt, ShoppingMall, Spa, VRDeck, GroupSize. ' 'If PassengerId exists, it will be kept in the output.' ) uploaded = st.file_uploader('Upload CSV', type=['csv']) if uploaded is not None: df_in = pd.read_csv(uploaded) # Keep PassengerId if provided passenger_ids = None if 'PassengerId' in df_in.columns: passenger_ids = df_in['PassengerId'].copy() # Prepare features # Ensure required columns exist for c in ['HomePlanet', 'Destination', 'Deck', 'Side', 'CryoSleep', 'VIP', 'Age', 'GroupSize']: if c not in df_in.columns: df_in[c] = 'Unknown' if c in ['HomePlanet', 'Destination', 'Deck', 'Side', 'CryoSleep', 'VIP'] else np.nan for c in SPEND_COLS: if c not in df_in.columns: df_in[c] = 0.0 # Build engineered features for each row df_feat = df_in.copy() for c in ['HomePlanet', 'Destination', 'Deck', 'Side']: df_feat[c] = df_feat[c].fillna('Unknown').astype(str) for c in ['CryoSleep', 'VIP']: df_feat[c] = df_feat[c].apply(map_bool_unknown).astype(int) df_feat['Age'] = pd.to_numeric(df_feat['Age'], errors='coerce') for c in SPEND_COLS: df_feat[c] = pd.to_numeric(df_feat[c], errors='coerce').fillna(0.0) df_feat['GroupSize'] = pd.to_numeric(df_feat['GroupSize'], errors='coerce').fillna(1).astype(int) df_feat['GroupSize'] = df_feat['GroupSize'].clip(lower=1) df_feat['TotalSpend'] = df_feat[SPEND_COLS].sum(axis=1) df_feat['NotSpend'] = (df_feat['TotalSpend'] == 0).astype(int) df_feat['IsAlone'] = (df_feat['GroupSize'] == 1).astype(int) # Impute Age with median from uploaded file age_med = df_feat['Age'].median() df_feat['Age'] = df_feat['Age'].fillna(age_med if pd.notna(age_med) else 0) Xb = one_hot_and_align(df_feat, feature_columns) preds = model.predict(Xb).astype(bool) out = pd.DataFrame({'Transported': preds}) if passenger_ids is not None: out.insert(0, 'PassengerId', passenger_ids) st.write('Preview:') st.dataframe(out.head(20), use_container_width=True) csv_bytes = out.to_csv(index=False).encode('utf-8') st.download_button( label='Download predictions CSV', data=csv_bytes, file_name='predictions.csv', mime='text/csv' ) st.caption('Built with Streamlit • Model: Gradient Boosting Classifier')