🎮 League of Legends Match Predictor

---

🧩 Project Overview

The League of Legends Match Predictor is a machine learning project developed as part of the IBM Skills Network Labs final assessment.
It predicts whether a team wins or loses based on in-game statistics such as kills, gold earned, objectives taken, and vision control.

This project demonstrates a full data science pipeline — from data preprocessing and EDA to model training and evaluation — all implemented in Python using Jupyter Notebook.

---

⚙️ Tech Stack

Category	Tools / Libraries
Language	Python 3.8+
IDE	Jupyter Notebook
Libraries	Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn
Environment	IBM Skills Network Labs (SN Labs)
Version Control	Git & GitHub

---

🧠 Skills Demonstrated

• Data preprocessing & feature engineering
• Exploratory Data Analysis (EDA)
• Building and training ML models
• Hyperparameter tuning and model evaluation
• Visualization & interpretation of results
• Working in cloud-based lab environments (SN Labs)

---

📂 Project Structure

League_of_Legends_Match_Predictor/
│
├── League_of_Legends_Match_Predictor.ipynb   # Main Jupyter Notebook
├── data/                                     # Dataset (if provided)
├── README.md                                 # Documentation
└── requirements.txt                          # Dependencies list

Follow these steps to run the notebook locally or on IBM SN Labs.

1. Clone this Repository
git clone https://github.com/<your-username>/League-of-Legends-Match-Predictor.git
cd League-of-Legends-Match-Predictor

2. Install Dependencies

Create a virtual environment and install required libraries:

pip install -r requirements.txt


If no requirements.txt is available, install manually:

pip install pandas numpy matplotlib seaborn scikit-learn

3. Launch Jupyter Notebook
jupyter notebook


Then open League_of_Legends_Match_Predictor.ipynb and run each cell sequentially.

🧾 Steps in the Notebook

Data Loading & Cleaning
Import the dataset, remove null values, and engineer key features.

Exploratory Data Analysis (EDA)
Visualize correlations, win rate trends, and impact of objectives.

Model Building
Train models such as Logistic Regression, Random Forest, and XGBoost.

Evaluation
Assess model performance using accuracy, F1-score, and confusion matrix.

Prediction
Use the trained model to predict match outcomes based on given stats.