Spaces:
Runtime error
Runtime error
Download src/streamlit_app.py from EnYa32/SantanderTransactionClassifcation: direct link, hf CLI and curl.
- Browser
- Download file 4.66 kB
-
https://huggingface.co/spaces/EnYa32/SantanderTransactionClassifcation/resolve/main/src/streamlit_app.py
- Command line
-
hf download hf://spaces/EnYa32/SantanderTransactionClassifcation/src/streamlit_app.py
-
curl -L -o streamlit_app.py https://huggingface.co/spaces/EnYa32/SantanderTransactionClassifcation/resolve/main/src/streamlit_app.py
4.66 kB
| import numpy as np | |
| import pandas as pd | |
| import streamlit as st | |
| import joblib | |
| from pathlib import Path | |
| st.set_page_config( | |
| page_title="Santander Transaction Prediction (LightGBM)", | |
| page_icon="🏦", | |
| layout="wide", | |
| ) | |
| BASE_DIR = Path(__file__).resolve().parent | |
| MODEL_PATH = BASE_DIR / "lightgbm_santander_model.pkl" # <- ggf. anpassen | |
| def load_model(path: Path): | |
| if not path.exists(): | |
| raise FileNotFoundError( | |
| f"Model file not found: {path.name}. Put it in the repo root (same folder as app.py)." | |
| ) | |
| obj = joblib.load(path) | |
| # supports either plain model or dict artifact {"model":..., "features":[...], "threshold":...} | |
| if isinstance(obj, dict) and "model" in obj: | |
| model = obj["model"] | |
| features = obj.get("features", None) | |
| default_threshold = float(obj.get("threshold", 0.5)) | |
| return model, features, default_threshold | |
| return obj, None, 0.5 | |
| def ensure_feature_order(df: pd.DataFrame, feature_list): | |
| """Return X with correct feature order.""" | |
| if feature_list is not None: | |
| missing = [c for c in feature_list if c not in df.columns] | |
| extra = [c for c in df.columns if c not in feature_list] | |
| return df[feature_list], missing, extra | |
| # If no stored feature list: assume Santander var_0..var_199 | |
| expected = [f"var_{i}" for i in range(200)] | |
| missing = [c for c in expected if c not in df.columns] | |
| extra = [c for c in df.columns if c not in expected] | |
| # If expected columns exist, use them; else fallback to current columns | |
| if len(missing) == 0: | |
| return df[expected], [], extra | |
| return df, missing, extra | |
| st.title("🏦 Santander Customer Transaction Prediction") | |
| st.write( | |
| "This app predicts the probability that a customer will make a specific transaction " | |
| "using a trained **LightGBM** model." | |
| ) | |
| # Load model | |
| try: | |
| model, saved_features, saved_default_threshold = load_model(MODEL_PATH) | |
| except Exception as e: | |
| st.error(str(e)) | |
| st.stop() | |
| with st.sidebar: | |
| st.header("Settings") | |
| threshold = st.slider( | |
| "Classification threshold (for label only)", | |
| min_value=0.0, | |
| max_value=1.0, | |
| value=float(saved_default_threshold), | |
| step=0.01, | |
| ) | |
| st.caption("Note: Kaggle uses probabilities (ROC-AUC). Threshold is for label display only.") | |
| st.subheader("1) Upload test data (CSV)") | |
| st.write( | |
| "Upload a CSV with columns **ID_code** and **var_0 ... var_199**. " | |
| "You can upload the original Kaggle `test.csv`." | |
| ) | |
| uploaded = st.file_uploader("Choose a CSV file", type=["csv"]) | |
| if uploaded is None: | |
| st.info("Upload a CSV to get predictions. (Tip: use Kaggle `test.csv`.)") | |
| st.stop() | |
| df = pd.read_csv(uploaded) | |
| if "ID_code" in df.columns: | |
| ids = df["ID_code"].astype(str) | |
| X = df.drop(columns=["ID_code"]) | |
| else: | |
| ids = pd.Series([f"row_{i}" for i in range(len(df))]) | |
| X = df.copy() | |
| X, missing_cols, extra_cols = ensure_feature_order(X, saved_features) | |
| if missing_cols: | |
| st.error( | |
| "Missing required columns. Please upload a file with the correct feature columns.\n\n" | |
| f"Missing (showing up to 15): {missing_cols[:15]}" | |
| ) | |
| st.stop() | |
| if extra_cols: | |
| st.warning( | |
| "Your file contains extra columns that are not used by the model. " | |
| f"(showing up to 15): {extra_cols[:15]}" | |
| ) | |
| # Predict probabilities | |
| proba = model.predict_proba(X)[:, 1] | |
| pred_label = (proba >= threshold).astype(int) | |
| st.subheader("2) Results") | |
| col1, col2, col3 = st.columns(3) | |
| col1.metric("Rows", f"{len(df):,}") | |
| col2.metric("Mean probability", f"{np.mean(proba):.4f}") | |
| col3.metric("Predicted positives", f"{int(pred_label.sum()):,}") | |
| result = pd.DataFrame( | |
| { | |
| "ID_code": ids.values, | |
| "probability": proba, | |
| "prediction": pred_label, | |
| } | |
| ) | |
| st.dataframe(result.head(20), use_container_width=True) | |
| st.subheader("3) Download predictions") | |
| csv_out = result.to_csv(index=False).encode("utf-8") | |
| st.download_button( | |
| label="Download predictions as CSV", | |
| data=csv_out, | |
| file_name="predictions_lightgbm.csv", | |
| mime="text/csv", | |
| ) | |
| st.caption( | |
| "For Kaggle submission: rename columns to **ID_code** and **target** " | |
| "and submit probabilities (no threshold)." | |
| ) | |
| # Kaggle submission helper | |
| st.subheader("4) Kaggle submission format (optional)") | |
| sub = pd.DataFrame({"ID_code": ids.values, "target": proba}) | |
| st.dataframe(sub.head(10), use_container_width=True) | |
| sub_csv = sub.to_csv(index=False).encode("utf-8") | |
| st.download_button( | |
| label="Download Kaggle submission CSV", | |
| data=sub_csv, | |
| file_name="submission_lightgbm.csv", | |
| mime="text/csv", | |
| ) |