Download src/streamlit_app.py from EnYa32/UnsupervisedCustumerPrediction: direct link, hf CLI and curl.
- Browser
- Download file 3.1 kB
-
https://huggingface.co/spaces/EnYa32/UnsupervisedCustumerPrediction/resolve/main/src/streamlit_app.py
- Command line
-
hf download hf://spaces/EnYa32/UnsupervisedCustumerPrediction/src/streamlit_app.py
-
curl -L -o streamlit_app.py https://huggingface.co/spaces/EnYa32/UnsupervisedCustumerPrediction/resolve/main/src/streamlit_app.py
3.1 kB
| import pandas as pd | |
| import numpy as np | |
| import streamlit as st | |
| import joblib | |
| from pathlib import Path | |
| st.set_page_config(page_title='Clustering Predictor (GMM)', page_icon='🧩', layout='centered') | |
| st.title('🧩 Clustering Predictor (GMM)') | |
| st.write('Single-row cluster prediction using saved preprocessing: StandardScaler → PCA → GaussianMixture.') | |
| BASE_DIR = Path(__file__).resolve().parent | |
| FEATURES_PATH = BASE_DIR / 'feature_names.pkl' | |
| SCALER_PATH = BASE_DIR / 'scaler.pkl' | |
| PCA_PATH = BASE_DIR / 'pca.pkl' | |
| GMM_PATH = BASE_DIR / 'gmm_model.pkl' | |
| def load_assets(): | |
| missing = [p.name for p in [FEATURES_PATH, SCALER_PATH, PCA_PATH, GMM_PATH] if not p.exists()] | |
| if missing: | |
| raise FileNotFoundError(f'Missing files in repo root: {missing}. Put them next to app.py.') | |
| feature_names = joblib.load(FEATURES_PATH) | |
| scaler = joblib.load(SCALER_PATH) | |
| pca = joblib.load(PCA_PATH) | |
| model = joblib.load(GMM_PATH) | |
| # Hard safety checks | |
| if hasattr(pca, 'n_features_in_') and len(feature_names) != int(pca.n_features_in_): | |
| raise ValueError( | |
| f'Feature mismatch: feature_names has {len(feature_names)} features, ' | |
| f'but PCA expects {int(pca.n_features_in_)}. ' | |
| 'Re-export feature_names.pkl and pca.pkl from the same training run.' | |
| ) | |
| return feature_names, scaler, pca, model | |
| try: | |
| feature_names, scaler, pca, model = load_assets() | |
| except Exception as e: | |
| st.error(str(e)) | |
| st.stop() | |
| def predict_cluster(values_dict: dict) -> int: | |
| df_one = pd.DataFrame([values_dict], columns=feature_names) | |
| # Convert to numeric safely | |
| for c in df_one.columns: | |
| df_one[c] = pd.to_numeric(df_one[c], errors='coerce') | |
| if df_one.isna().any().any(): | |
| bad = df_one.columns[df_one.isna().any()].tolist() | |
| raise ValueError(f'NaN values found in columns: {bad}. Please provide valid numeric values.') | |
| X_scaled = scaler.transform(df_one) # (1, 29) | |
| X_pca = pca.transform(X_scaled) # (1, 27) | |
| pred = model.predict(X_pca)[0] | |
| return int(pred) | |
| st.subheader('🧮 Single Prediction') | |
| st.caption('Tip: Use a real row from your dataset for realistic values (all zeros may be unrealistic).') | |
| with st.form('single_pred_form'): | |
| cols = st.columns(2) | |
| values = {} | |
| for i, feat in enumerate(feature_names): | |
| if i % 2 == 0: | |
| values[feat] = cols[0].number_input(feat, value=0.0) | |
| else: | |
| values[feat] = cols[1].number_input(feat, value=0.0) | |
| submitted = st.form_submit_button('Predict cluster') | |
| if submitted: | |
| try: | |
| pred = predict_cluster(values) | |
| st.success(f'✅ Predicted cluster: **{pred}**') | |
| except Exception as e: | |
| st.error(str(e)) | |
| with st.expander('Show expected feature columns'): | |
| st.write(feature_names) | |
| with st.expander('Debug shapes (advanced)'): | |
| st.write('Number of input features:', len(feature_names)) | |
| st.write('PCA expects n_features_in_:', getattr(pca, 'n_features_in_', 'NA')) | |
| st.write('PCA output components:', getattr(pca, 'n_components_', 'NA')) |