A Machine Learning & Deep Learning project that predicts poker hand rankings from 5-card combinations. The model classifies hands such as High Card, Pair, Two Pair, Three of a Kind, Straight, Flush, Full House, Four of a Kind, Straight Flush, and Royal Flush.
[Project for Social Winter of Code (SWOC 2025)]

• Each row represents a single 5-card poker hand.
• Columns encode the rank and suit for each card.
• A target column stores the integer label for the hand category.
• Source: Noah Boggs – Poker Hand Dataset.

1. Data Loading – Import training and testing files from /Dataset.
2. Preprocessing – Validate schema, handle encoding and normalizate the data.
3. Feature Engineering – Represent ranks/suits and derive hand features where useful.
4. Model Training – Train models (MLP, Random Forest, Gradient Boosting).
5. Evaluation – Accuracy, precision, recall, F1-score, and confusion matrix on the test set.

• Multi-Layer Perceptron Classifier (MLP)
• Random Forest Classifier
• Gradient Boosting Classifier
• Stacking Classifier (all above 3 models)

Install the core dependencies:

pip install pandas numpy scikit-learn imbalanced-learn matplotlib seaborn 

Poker Hand Prediction
├── Dataset
│   ├── poker-hand-training.data   
│   └── poker-hand-testing.data  
├── Poker_Hand_Prediction_Model
├── LICENSE 
├── NOTICE 
└── README.md