https://github.com/phenomsg/binary-prediction-with-a-rainfall-dataset
Contibutor @Kaggle
https://github.com/phenomsg/binary-prediction-with-a-rainfall-dataset
dataset kaggle-competition machine-learning python3 regression-models
Last synced: 3 months ago
JSON representation
Contibutor @Kaggle
- Host: GitHub
- URL: https://github.com/phenomsg/binary-prediction-with-a-rainfall-dataset
- Owner: PhenomSG
- Created: 2025-03-02T11:12:55.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-03-02T11:22:05.000Z (3 months ago)
- Last Synced: 2025-03-02T12:24:33.472Z (3 months ago)
- Topics: dataset, kaggle-competition, machine-learning, python3, regression-models
- Language: Jupyter Notebook
- Homepage: https://www.kaggle.com/phenomsg
- Size: 3.91 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Binary Prediction with a Rainfall Dataset
## 🏆 Kaggle Competition Details
This repository contains my solution for the Kaggle competition **Playground Series - Season 5, Episode 3**: [Binary Prediction with a Rainfall Dataset](https://www.kaggle.com/competitions/playground-series-s5e3).
- **Current Rank**: 100 (as of the latest update)
- **Objective**: Predict the probability of daily rainfall using historical weather data.
- **Dataset**: Features include temperature, humidity, pressure, wind speed, and other meteorological parameters.
## 📂 Repository Structure
```
📦 Binary-Prediction-with-a-Rainfall-Dataset
├── notebooks/ # Jupyter Notebooks for data exploration and modeling
├── input/ # Scripts for data preprocessing, model training, and evaluation
├── output/ # Sample datasets (if applicable)
├── models/ # Saved models and predictions
├── results/ # Performance metrics and leaderboard submissions
├── README.md # Project documentation
```
## 📈 Results & Performance
- **Baseline Model**: Logistic Regression - Log Loss: *X.XX*
- **Best Model (so far)**: *Model Name* - Log Loss: *X.XX*, AUC-ROC: *X.XX*
## 🔥 Future Improvements
- Implement ensemble learning techniques (Stacking, Blending)
- Explore deep learning models (LSTMs, CNNs for tabular data)
- Optimize hyperparameters further
Feel free to contribute, suggest improvements, or reach out for discussions!