Indian Premier League (IPL) Analysis and Match Prediction in Python

By Nihal Chandra

Exploratory Data Analysis of IPL Matches to extract useful information and match prediction using the Decision Tree Classifier.

The Indian Premier League (IPL) is one of the most popular Twenty20 cricket leagues in the world, founded by the Board of Control for Cricket in India (BCCI) in 2008. There have been 12 seasons conducted since, then where 14 teams with cricketers from all over the world have participated in this cash-rich tournament. Currently, its an 8-team format with two stages - the League Stage and the Playoffs. The 13th season is scheduled to start from 19th September 2020.

Behind the scenes, there are numerous analysts and experts working on finding critical patterns and statistics about different players, their playing style, venues, and how different team combinations perform in various scenarios. Such data becomes invaluable to the captain, coaches, and support staff of the team, helping them make better decisions on the field. 

In this project, I've tried to extract potentially useful inferences from the dataset and also applied the Decision Tree Classifier for predicting the winning team.

The dataset used in this project is obtained from Kaggle. It contains two .csv files:

- matches.csv - Match by match data
- deliveries.csv - Ball by ball data

This project has been implemented in Python 3.6 environment using Jupyter Notebook by making use of the following libraries:

- Numpy                   v1.19.1

- Pandas                   v1.1.1

- Matplotlib               v3.3.1

- Plotly                     v4.9.0

- Sci-kit learn           v0.23.2

Implementation:

Open the IPL Analysis and Match Prediction.ipynb file using Jupyter Notebook and click on the Run button |>>|