Download src/streamlit_app.py from EnYa32/RainfallPredictionClassification: direct link, hf CLI and curl.
- Browser
- Download file 4.62 kB
-
https://huggingface.co/spaces/EnYa32/RainfallPredictionClassification/resolve/main/src/streamlit_app.py
- Command line
-
hf download hf://spaces/EnYa32/RainfallPredictionClassification/src/streamlit_app.py
-
curl -L -o streamlit_app.py https://huggingface.co/spaces/EnYa32/RainfallPredictionClassification/resolve/main/src/streamlit_app.py
4.62 kB
| import numpy as np | |
| import pandas as pd | |
| import streamlit as st | |
| import joblib | |
| from pathlib import Path | |
| # ------------------------------- | |
| # Page config | |
| # ------------------------------- | |
| st.set_page_config( | |
| page_title='Rainfall Probability Predictor (LogReg)', | |
| page_icon='🌧️', | |
| layout='centered' | |
| ) | |
| st.title('🌧️ Rainfall Probability Predictor') | |
| st.write('Predicts the probability of rainfall (0–1) using a Logistic Regression model trained on weather features.') | |
| BASE_DIR = Path(__file__).resolve().parent | |
| MODEL_PATH = BASE_DIR / 'lr_final_model.pkl' | |
| FEATURE_NAMES_PATH = BASE_DIR / 'feature_names.pkl' | |
| def load_artifacts(): | |
| if not MODEL_PATH.exists(): | |
| raise FileNotFoundError( | |
| f'Model not found: {MODEL_PATH.name}. Put it in the repo root (same folder as app.py).' | |
| ) | |
| if not FEATURE_NAMES_PATH.exists(): | |
| raise FileNotFoundError( | |
| f'Feature names not found: {FEATURE_NAMES_PATH.name}. Put it in the repo root (same folder as app.py).' | |
| ) | |
| model = joblib.load(MODEL_PATH) | |
| feature_names = joblib.load(FEATURE_NAMES_PATH) | |
| if not isinstance(feature_names, list) or len(feature_names) == 0: | |
| raise ValueError('feature_names.pkl must contain a non-empty list of column names.') | |
| return model, feature_names | |
| def add_features(df: pd.DataFrame) -> pd.DataFrame: | |
| df = df.copy() | |
| # Temperature variability | |
| df['temp_range'] = df['maxtemp'] - df['mintemp'] | |
| # Air saturation level | |
| df['humidity_gap'] = df['humidity'] - df['dewpoint'] | |
| # Sunshine vs clouds | |
| df['sunshine_ratio'] = df['sunshine'] / (df['cloud'] + 1) | |
| # Wind intensity (simple interaction) | |
| df['wind_energy'] = df['windspeed'] * df['winddirection'] | |
| # Seasonal pattern | |
| df['sin_day'] = np.sin(2 * np.pi * df['day'] / 365) | |
| df['cos_day'] = np.cos(2 * np.pi * df['day'] / 365) | |
| return df | |
| model, feature_names = load_artifacts() | |
| st.subheader('Input features') | |
| # Note: ranges are generic. If you want, you can set them based on df1.describe(). | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| day = st.number_input('day (1–365)', min_value=1, max_value=365, value=100, step=1) | |
| pressure = st.number_input('pressure', value=1013.0, step=0.1) | |
| maxtemp = st.number_input('maxtemp', value=20.0, step=0.1) | |
| temperature = st.number_input('temperature', value=15.0, step=0.1) | |
| mintemp = st.number_input('mintemp', value=10.0, step=0.1) | |
| with col2: | |
| dewpoint = st.number_input('dewpoint', value=8.0, step=0.1) | |
| humidity = st.number_input('humidity', value=70.0, step=0.1) | |
| cloud = st.number_input('cloud', value=50.0, step=1.0) | |
| sunshine = st.number_input('sunshine', value=5.0, step=0.1) | |
| windspeed = st.number_input('windspeed', value=10.0, step=0.1) | |
| winddirection = st.number_input('winddirection', value=180.0, step=1.0) | |
| # Build one-row dataframe with the ORIGINAL base features | |
| input_df = pd.DataFrame([{ | |
| 'day': float(day), | |
| 'pressure': float(pressure), | |
| 'maxtemp': float(maxtemp), | |
| 'temparature': float(temperature), | |
| 'mintemp': float(mintemp), | |
| 'dewpoint': float(dewpoint), | |
| 'humidity': float(humidity), | |
| 'cloud': float(cloud), | |
| 'sunshine': float(sunshine), | |
| 'windspeed': float(windspeed), | |
| 'winddirection': float(winddirection) | |
| }]) | |
| # Add engineered features (must match training) | |
| input_df = add_features(input_df) | |
| # Ensure correct feature order and missing columns safety | |
| missing_cols = [c for c in feature_names if c not in input_df.columns] | |
| extra_cols = [c for c in input_df.columns if c not in feature_names] | |
| if missing_cols: | |
| st.error(f'Missing required feature columns: {missing_cols}') | |
| st.stop() | |
| # Keep only the expected columns in the correct order | |
| X = input_df[feature_names].copy() | |
| st.divider() | |
| if st.button('Predict rainfall probability'): | |
| try: | |
| proba = float(model.predict_proba(X)[:, 1][0]) | |
| st.metric('Rainfall probability', f'{proba:.3f}', delta=None) | |
| st.progress(min(max(proba, 0.0), 1.0)) | |
| if proba >= 0.7: | |
| st.success('High chance of rainfall.') | |
| elif proba >= 0.4: | |
| st.warning('Medium chance of rainfall.') | |
| else: | |
| st.info('Low chance of rainfall.') | |
| with st.expander('Show model input (debug)'): | |
| st.write('Used feature columns (ordered):') | |
| st.write(feature_names) | |
| st.dataframe(X) | |
| if extra_cols: | |
| st.caption(f'Note: These columns were ignored (not in feature_names): {extra_cols}') | |
| except Exception as e: | |
| st.error(f'Prediction failed: {e}') |