IPL prediction 2018

by kuharan

GitHub Readme.md

Indian Premier League Predictions - 2018

made-with-python Website shields.io GitHub forks GitHub license Twitter

The Indian Premier League, officially Vivo Indian Premier League (for sponsorship reasons), is a professional Twenty20 cricket league in India contested during April and May of every year by teams representing Indian cities and some states.

This project is an attempt to predict the winner of T20 cricket matches. The objective is to predict the result (winner) of every IPL match. The project also predicts the ultimate winner of the tournament. It does not impose a specific development philosophy or framework, so you're free to clone, modify and architect your code in the way that you want and add your contribution to this repository.

We are Live on Heroku!

Download for Android

If you’re greeted with, "Install blocked. For security, your phone is set to block installation of applications not obtained from Play Store" message as you try to install, follow this steps:

Navigate to Setting > Security. Check the option "Unknown sources". Tap OK on the prompt message. Allow installation of apps from unknown sources.

Android App Link

Features

Minimum OS version - Jelly Bean 4.1, 4.1.1 Target OS version - Marshmallow 6.0 Size - 4.69 MB

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

  • PyCharm
  • Any Web Browser

PyCharm Packages Used

Pandas, sklearn, sklearn.tree, model_selection, DecisionTreeClassifier, csv, Flask, BeautifulSoup, requests, json 

List of all the packages that have been used in this project is frozen into requirements.txt file.

Dataset

The dataset that we use in this project is IPL (Indian Premier League) Dataset posted on Kaggle Datasets sourced from cricsheet. And calculated Team data based on player EF scores.

EFscore:

The eigenfactor score, a metric used for ranking teams in different formats of the game. This is an alternative way of ranking teams in international Cricket, by taking into account the relative strengths of the teams. A victory against a relatively stronger team will lead to a higher EFscore as compared to a victory against a relatively weaker team.

The advantage of this method is that it is a non-parametric way of ranking teams, that is we do not give any additional parameters to the algorithm for computing the team rankings.

forthebadge made-with-python

Deployment

Click on this button to set up a live system on Heroku Cloud!

Deploy

Contributing Open Source Love

Please submit a pull request to this repo or open an issue.

Authors

License

This project is licensed under the GNU Affero General Public License v3.0 - see the LICENSE.md file for details.