| --- |
| title: RainfallPredictionClassification |
| emoji: 🌧️ |
| colorFrom: blue |
| colorTo: indigo |
| sdk: docker |
| app_port: 8501 |
| tags: |
| - streamlit |
| pinned: false |
| short_description: App that predicts rainfall probability (0–1) |
| license: mit |
| --- |
| |
| # 🌧️ Rainfall Probability Predictor (LogReg) |
|
|
| This Streamlit app predicts the **probability of rainfall (0–1)** from daily weather features using a trained **Logistic Regression** model. |
|
|
| ## What the app does |
| - Takes weather inputs (temperature, humidity, wind, pressure, cloud cover, sunshine, day of year) |
| - Creates a few engineered features (e.g., temperature range, humidity gap, seasonal sin/cos) |
| - Outputs a rainfall probability for **ROC-AUC style** prediction tasks |
|
|
| ## Files required |
| Place these files in the repo root (same folder as `app.py`): |
| - `logistic_regression_model.pkl` |
| - `feature_names.pkl` |
| - `app.py` |
| - `requirements.txt` |
|
|
| ## How to run locally |
| ```bash |
| pip install -r requirements.txt |
| streamlit run app.py |
| Notes |
| The model expects the same feature order used in training. |
| |
| feature_names.pkl is used to enforce the correct column order. |
| |
| The app outputs probabilities, not hard class labels. |
