Context

This file consists of data from over 500+ cricket matches! Detailed Bowling Statistics (30columns in Bowl.csv )like runs conceded, mainden, economy, wickets, match date, player name, etc) Detailed Batting Statistics (28 Columns in bat.csv) like runs scored, #4's, #6's, balls faced, strike rate, how he got out, match id, etc) Detailed Match Statistics like date, match number, series, format, year are present here

It so so so excited that SO MANY THINGS can be done with this data :) A few things done are listed below.

1. Vizualizae a players Performance over the years
2. Predict fantasy points for a player
3. Find teams performance from over the years
4. Segregate test, ODi, and t20 Performance for a player
5. Find interesting statistics
6. Optimize fantasy teams
7. Predict Best performers and players for a specific series like IPL 2020.

Content

Go through all the data and you will get ALL THE CRICKET STATS YOU WILL EVER NEED. In total 60+ Columns of data

Acknowledgements

We wouldn't be here without the help of others. If you owe any attributions or thanks, include them here along with any citations of past research.

Inspiration

I have co-authored a Research paper using the same data called PrOBML: A machine learning approach to Predict, Optimise & Build fantasy Cricket teams using evolutionary algorithm I would like to see what the Kaggle community can do with this data. Do share and Upvote so that maximum people can make use of this data!

Cricket Dataset V1

## Overview

Cricket Dataset V1 is a dataset for object detection tasks - it contains Game States annotations for 1,920 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Cricket Players Statistics Dataset

https://cdn-icons-png.flaticon.com/512/5971/5971593.png" alt="">

Overview

This dataset contains comprehensive cricket statistics for international players across all formats (Test, ODI, and T20I) for both men's and women's cricket. The dataset includes 31,393 unique player records spanning multiple decades of international cricket.

Data Structure

The CSV file contains the following columns: - Player Information: No., Name, First (match date), Last (match date) - Batting Statistics: Mat (Matches), Runs, HS (Highest Score), Avg (Average), 50s, 100s - Bowling Statistics: Balls, Wkt (Wickets), BBI (Best Bowling in an Innings), Ave (Average), 5WI (5 Wickets in an Innings) - Fielding Statistics: Ca (Catches), St (Stumpings) - Categorical Information: Format (ODI/T20I/Test), Gender (Male/Female), Team

Coverage

• Time Span: Records from the first international cricket match to present
• Teams: Includes data from all ICC member nations
  • Men's cricket: 210 teams (maximum in T20I format)
  • Women's cricket: 180 teams (maximum in T20I format)

Format Distribution

1. T20 International
   • Men: 8,688 players
   • Women: 5,540 players
2. One Day International (ODI)
   • Men: 6,234 players
   • Women: 2,931 players
3. Test Cricket
   • Men: 6,502 players
   • Women: 1,498 players

Usage Notes

• All statistics are updated to the latest available international matches
• Player names are standardized across formats
• Performance metrics follow ICC's official statistical guidelines
• The dataset is suitable for historical analysis, player comparisons, and cricket analytics research

A collection of cricket videos, which are already publicly available, with about 2 overs of a cricket game. Annotations provide the action type "is bowling" or "bowl release" in the "event" key. The bounding boxes of players and their role are also provided under the key "person". This dataset has been curated and provided by Sportradar.

Flat Cricket

## Overview

Flat Cricket is a dataset for object detection tasks - it contains Ball annotations for 663 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This dataset contains detailed ball-by-ball information from various cricket matches. It provides an in-depth view of match events, such as player performance, wickets, and scoring patterns, enabling analysis of team strategies, individual contributions, and overall match outcomes.

Dataset Features:

• Match ID: A unique identifier for each match.
• Date: The date on which the match was played.
• Venue: The stadium or location where the match took place.
• Bat First: The team that batted first in the match.
• Bat Second: The team that batted second in the match.
• Innings: The innings number (1 or 2) during the match.
• Over: The over in which the ball was bowled.
• Ball: The specific ball in the over.
• Batter: The player on strike facing the delivery.
• Non-Striker: The player at the non-striker's end.
• Bowler: The bowler delivers the ball.
• Batter Runs: The runs scored by the batter from a specific ball.
• Extra Runs: Additional runs awarded due to extras (integer value.).
• Runs From Ball: Total runs scored off the delivery, including extras.
• Ball Rebowled: Indicates whether the ball was re-bowled (Yes - 1/No - 0).
• Wicket: Indicates whether a wicket was taken (Yes - 1/No - 0).
• Method: Describes how the batter got out (e.g., bowled, caught, LBW).
• Player Out: The name of the player dismissed.
• Innings Runs: Total runs scored in the respective innings.
• Innings Wickets: Total wickets lost in the innings.
• Target Score: The score the batting team is chasing (if applicable).
• Runs to Get: Runs needed to win at that point in the match.
• Balls Remaining: Number of balls left in the innings.
• Winner: The team that won the match.
• Chased Successfully: Indicates whether the target was successfully chased (1 for Yes, 0 for No).

Usage:

This dataset is ideal for cricket analytics and machine learning tasks, including: - Analysing player and team performance trends. - Training predictive models for match outcomes. - Developing simulation tools for cricket strategy optimisation. - Identifying key moments and contributors in matches.

Coverage:

The dataset encompasses critical match and ball-level details, capturing the intricacies of cricket gameplay. It is suitable for exploring various analytical dimensions, such as player efficiency, bowling performance, and team tactics.

License:

CC0 (Public Domain)

Who can use it:

This dataset is designed for data scientists, sports analysts, machine learning practitioners, and cricket enthusiasts interested in leveraging data for sports analytics.

How to use it:

• Build predictive models for match outcomes and player performances.
• Analyse player contributions in different match contexts.
• Conduct exploratory data analysis on cricket match events.
• Simulate match scenarios to evaluate team strategies.

Cricket Bat Detection

## Overview

Cricket Bat Detection is a dataset for object detection tasks - it contains Bat annotations for 1,179 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [Public Domain license](https://creativecommons.org/licenses/Public Domain).

Dataset Card for "llama-cricket-dataset"

More Information needed

Cricket Analysis Software Market Outlook

In 2023, the global cricket analysis software market size was valued at approximately USD 1.2 billion and is projected to grow to around USD 3.5 billion by 2032, registering a compound annual growth rate (CAGR) of approximately 12.5% during the forecast period. The primary growth factor driving this market is the increasing demand for data-driven decision-making in sports to enhance player and team performance.

The significant growth in the cricket analysis software market is largely driven by the increasing adoption of advanced technologies in sports. Cricket teams worldwide are increasingly relying on data analytics to gain a competitive edge. The inclusion of detailed performance metrics and real-time analysis helps coaches and players make informed decisions, thus improving their game strategies and overall performance. This growing reliance on data-driven insights is a crucial factor contributing to the market's expansion.

Another critical growth factor is the rising popularity of cricket globally. Cricket is no longer confined to just a few countries; it has garnered a substantial following in regions such as North America and parts of Europe. This expansion has led to increased investments in cricket infrastructure, including training facilities equipped with the latest analytical software. Furthermore, the advent of various cricket leagues and tournaments has amplified the need for advanced performance analysis tools, thereby driving market growth.

Technological advancements and innovations in software capabilities are also playing a significant role in market growth. Modern cricket analysis software offers features such as high-definition video analysis, 3D visualization, and predictive analytics. These sophisticated tools enable a more comprehensive analysis of player techniques and team strategies. The integration of artificial intelligence (AI) and machine learning (ML) in these software solutions is further enhancing their effectiveness, making them indispensable for professional and amateur teams alike.

From a regional perspective, the Asia-Pacific region holds a substantial market share, primarily due to the enormous popularity of cricket in countries like India, Australia, and Pakistan. The region is also experiencing rapid technological advancements and increased investments in sports infrastructure. North America and Europe are emerging markets, showing significant potential due to the growing interest in cricket and the adoption of advanced analytical tools. These regions are expected to witness robust growth rates over the forecast period.

Cricket and Field Hockey share a rich history and cultural significance in many regions around the world. Both sports have evolved significantly over the years, with cricket often being considered a gentleman's game, while field hockey is known for its fast-paced and dynamic nature. The strategic elements inherent in both sports have led to the adoption of data analytics to enhance performance and strategy. As cricket continues to grow globally, field hockey is also seeing a resurgence in popularity, particularly in countries where it has been a traditional sport. The use of technology in these sports is not only improving player performance but also enriching the spectator experience by providing deeper insights into the games.

Component Analysis

The cricket analysis software market is segmented into Software and Services. The Software segment includes various types of analysis tools and platforms designed to collect and interpret data related to player and team performance. These software solutions offer a range of features from basic statistical analysis to advanced machine learning algorithms capable of predicting player performance and match outcomes. The growing demand for such sophisticated tools is a significant driver for this segment, as teams seek to gain a competitive edge through data-driven insights.

Within the Software segment, real-time data analytics is becoming increasingly popular. This involves the use of high-speed cameras, sensors, and other data collection devices to provide instantaneous feedback during matches and training sessions. Real-time data allows coaches and players to make immediate adjustments, thereby enhancing performance. The continuous evolution of software technologies, including the integration of AI and ML, is expected to further propel the growth of this

As of July 2024, the most-watched cricket of all-time was a 2011 fixture between India and Sri Lanka at the ICC Men's Cricket World Cup. In total, 558 million viewers tuned in worldwide.

Cricket Ball Detection for YOLOv8: Train Like a Pro! 🏏

Sharpen your Cricket AI: Unleash the power of YOLOv8 for precise cricket ball detection in images and videos with this comprehensive dataset.

Fuel Your Custom Training: Build a robust cricket ball detection model tailored to your specific needs. This dataset, featuring 1778 meticulously annotated images in YOLOv8 format, serves as the perfect launchpad.

Dive into Diversity:

In-Action Balls: Train your model to identify cricket balls in motion, capturing deliveries, fielding plays, and various gameplay scenarios.

Lighting Variations: Adapt to diverse lighting conditions (day, night, indoor) with a range of images showcasing balls under different illumination.

Background Complexity: Prepare your model for real-world environments. The dataset includes images featuring stadiums, practice nets, and various background clutter.

Ball States: Train effectively with images of new and used cricket balls, encompassing varying degrees of wear and tear.

Unlock Potential Applications:

Real-time Cricket Analysis: Power applications for in-depth player analysis, ball trajectory tracking, and automated umpiring systems.

Enhanced Broadcasting Experiences: Integrate seamless ball tracking, on-screen overlays, and real-time highlights into cricket broadcasts.

Automated Summarization: Streamline cricket video processing for automated highlight reels, focusing on key ball-related moments.

Who Should Use This Dataset:

• Computer vision researchers and developers seeking to leverage YOLOv8 for object detection in sports applications.
• Cricket enthusiasts and data scientists passionate about building AI-powered cricket analytics tools.
• Anyone venturing into custom object detection models for cricket analysis or sports technology projects.

Here are a few use cases for this project:

1. Sports Training & Improvement: Coaches or players can use the images from the "Cricket" model to study cricket playing styles, strategies, and techniques. The model can identify cricket equipment, players, and positions helping sportspersons analyze game practices.

2. Sports Journalism & Broadcasting: The model can be used by sports broadcasting networks to automatically analyze and tag certain moments of a cricket match, such as a player's stance, delivery style, or field settings. This can provide real-time insights and stats during live broadcast.

3. E-commerce: Online sports retailers can use this model to create more accurate items' descriptions, tag their cricket product images for easier searchability, and improve user experience.

4. Gaming and Virtual Reality: Computer game developers can use this model to create more realistic and detailed cricket games. The AI model can help model the movements of players, the trajectory of the cricket ball, and other nuances of the sport.

5. Security and Surveillance: In stadiums or sports facilities, the model can be used to monitor crowd behavior during a cricket match assisting security personnel's activities. It can detect any potential unauthorized field intrusions or unwanted activities.

Note: Please consider the data example given, it mentions a blurry image of a group of fish, which doesn't align with the described use cases. It seems like it belongs to a different dataset. Please verify and provide correct data samples.

Fantasy Cricket Player Performance Dataset 🏏📊

Overview

This dataset contains detailed statistics of cricket players from various international matches. It is designed for fantasy cricket score prediction, player selection optimization, and data-driven team formation.

📂 Dataset Content

The dataset includes player-wise match statistics such as: - Player Name: Name of the cricketer
Role: batsman, Bowler, All-rounder, Wicketkeeper
Team: The team the player represents
- Matches Played: Number of matches in the dataset
- Runs Scored: Total runs scored in the match
- Balls Faced: Balls played by the batsman
- Strike Rate: Batting strike rate
- Wickets Taken: Total wickets taken by the player
- Overs Bowled: Number of overs bowled
- Economy Rate: Runs conceded per over
- Fantasy Score: Predicted fantasy cricket points based on performance

🎯 Usage Ideas

🔹 Fantasy Cricket Prediction: Build a model to predict the best players for Dream11, My11Circle, etc. 🔹 Performance Analysis: Analyze which players perform well in specific match conditions. 🔹 Team Selection Optimization: Use machine learning & linear programming to pick the best team. 🔹 Statistical Insights: Find trends in player performance across different matches.

📊 Source & Acknowledgment

This dataset is manually curated and combined from various match statistics. It includes match data from recent international fixtures.

The ICC Men's T20 World Cup first took place in 2007 and has been held on a two or four-year basis ever since. The West Indies, England, and India are the most successful teams in the history of the tournament, having all lifted the trophy on two occasions. India won the most recent T20 World Cup in 2024, beating South Africa in the final.

This dataset provides empirical data on the impact of wearing cricket protective gear on agility and sprint performance among competitive cricket players. The study was conducted using two standardized tests: the New Multi-Change of Direction Agility Test (NMAT) and the Bangsbo Sprint Test, with performance recorded both with and without cricket gear. The dataset includes measurements from 144 male cricket players, categorized into three age groups: Under-16 (U16), Under-18 (U18), and Under-23 (U23). Key attributes include demographic details (age, height, weight, BMI), test performance times, and dominant hand preference. This dataset can be used for sports analytics, machine learning-based performance prediction, and optimizing training methodologies for cricket players.

Keywords: Cricket performance, agility, sprint test, protective gear, NMAT, Bangsbo Sprint Test, machine learning in sports, athlete performance analysis

Dataset Information: Subjects: 72 male competitive cricket players Age Groups: U16, U18, U23 Tests Conducted: NMAT (agility), Bangsbo Sprint Test (sprint performance) Conditions: With and without protective cricket gear Variables Included: Age, height, weight, BMI, NMAT times, Bangsbo sprint times, dominant hand, and player division

Column Descriptions: Age Group: U16, U18, U23 categories

Height (cm): Player's height in centimeters

Weight (kg): Player's weight in kilograms

BMI: Body Mass Index calculated from height and weight

NMATwithout Cricket Gears in sec: Agility test time without gear

NMATwith Cricket Gears in sec: Agility test time with gear

Bangsbo test wihout Cricket Gears in sec: Sprint test time without gear

Bangsbo test With Cricket Gears in sec: Sprint test time with gear

Methodology: Study Design: Cross-sectional study Testing Area: Cricket training facility with controlled conditions Equipment Used: Standard cricket gear (pads, gloves, helmet) Electronic timing gates for precise measurements

Procedure: Players completed NMAT and Bangsbo Sprint Test under both conditions (with/without gear). Each test was performed after a warm-up, with sufficient recovery time between trials to minimize fatigue. Performance times were recorded and analyzed.

Potential Research Applications: Sports Performance Analysis: Evaluating how wearing cricket gear influences speed and agility. Injury Prevention & Biomechanics: Understanding the potential risk of injury due to restricted mobility. Sports Equipment Optimization: Informing the development of lighter, performance-friendly cricket gear. Machine Learning for Sports Analytics: Predicting performance outcomes using AI-driven models.

samhitmantrala/cricket dataset hosted on Hugging Face and contributed by the HF Datasets community

This dataset contains the T20 cricket statistics of each player in the Australian Women's cricket team. The data has been captured through the ESPN Cric info site and can be extracted using the "cricketdata" R package ( https://cran.r-project.org/web/packages/cricketdata/cricketdata.pdf ).

Ball by ball data for cricket test matches between 1998 and 2006 inclusive in which a target was set for the team batting last. These are secondary data.

This csv file contains the list of top 10 batters in men's test cricket as of 31st August 2024. This file can be used for various Data Analytics or Machine learning projects like for example predicting the rank