IPL Ball-by-Ball Dataset
~72400 cleaned ball by ball labelled dataset
@kaggle.karandej_ipl_ball_by_ball_score_dataset
About this Dataset
IPL Ball-by-Ball Dataset
IPL is one of the most-attended cricket league. We have collected data of almost every match from 2008 to 2019. The collected data is well processed and cleaned using Python tool. With the help of this dataset we can analyze the status of each team whether it is going to win or lose. We can apply various machine learning and deep learning algorithms to predict the probability of win. We have chosen very real features which are used for predicting the probability of win based on current score, balls left, current run rate, wickets left etc.
| 👉 Feature Name👈 | 👉 Meaning👈 |
|---|---|
| batting team | (current) team for batting in 2nd inning |
| bowling team | (previous) team for bowling in 2nd inning |
| runs left | for every ball (out of ~120 balls) runs left for win |
| balls left | balls left (out of ~120) |
| wicktes | wickets left |
| target runs | target runs (score by 1st team which is bowling team now) |
| cur run rate | represent current run rate of batting team |
| req run rate | represent required run rate fot batting team to win the match |
| result | 1 if team 2 (currently batting team) won otherwise 0 |