Unlocking the secrets of the Indian Premier League.

Introduction:

The Indian Premier League (IPL) has grown to be one of the biggest cricket tournaments in the world. Cricket is one of the most well-liked sports in the world. It is now simpler to analyze and comprehend the game of cricket thanks to the development of data analytics and the accessibility of data. In this blog article, we’ll look at how data analysis can be used to learn more about the IPL teams and players’ performances.

Data:

This analysis’s data came from Kaggle, a well-liked site for data scientists and machine learning professionals. The dataset includes data on every ball bowled in every IPL match from 2008 to 2019, as well as information on the bowler’s name, runs scored, and wickets taken. Additionally, the dataset contains performance statistics for each team, such as the amount of games played, wins, losses, and ties.

Analysis:

We used Python for our data analysis, along with libraries such as Pandas, NumPy, and Matplotlib. Our analysis focused on answering questions such as:

We used data visualization techniques to present our findings, including bar charts. Our analysis revealed some interesting insights, such as the dominance of the Mumbai Indians, who have won the IPL five times, and the impressive performance of the Chennai Super Kings, who have made the playoffs in every season they have played in.

1. Matches hosted in each city

Total Number of games hosted by The Venues

Insight:

Given that Mumbai has three stadiums, we can see that the majority of events take place there. The following highest amount of games are played at Eden Garden in Kolkata.

2. Most Dismissals by a WicketKeeper

MS DHONI

Insight:

As we can see, MS Dhoni made the most stumpings compared to KD Karthik who made the most dismissals.

3. How many times each teams have won the toss ?

Toss win By Teams

Insight:

Mumbai Indians have won the draw the most times in the IPL, as shown by the graph.

Mumbai Indians Team

4. Decision upon winning the toss by teams.

Insight:

The graph and table above show that after winning the toss, teams frequently choose to Field first however, there is only one team who choose to bat first is chennai super kings mostly.

5. Percentage of matches won batting first/fielding first

Insight

The above graph shows the winning percentage of gujrat was highest among all teams when it comes to the fielding first with 92.31 percent and on the other have the team with higest percentage when they chose to bat first is Deccan Chargers with the 62.07 cap.

Conclusion:

I intended to analyze the statistics from the Indian Premier League, a well-known cricket competition in India, in this notebook. To address the following queries, I used descriptive statistics and various ML modeling methods (Logistic Regression, SVM, DecisionTrees, RandomForest):What is the likelihood of winning the game at a specific location if you choose to field or play first after winning the toss?I first combined all the various locations where the games were played, cleaned the data, and then used statistics to determine, venue by venue, what the win rate was when choosing to field or bat first after winning the toss.For instance, there is a 61% probability that we will win the match if Kolkata is the host city and we bat first.

2. Most dismissals by a wicketkeeper?

I used this query to decide which wicketkeeper to purchase in the following sale based on performance. I aggregated the stumpings and catches by wicketkeepers using the ball by ball deliveries information after first identifying all of them by name.We found that Karthik and Dhoni were amongst the most successful wicketkeeper in IPL History.

3.Finally, we experimented with various ML models to forecast the victorious squad using features:

Team 1 Name,Team 2 Name,Venue,Toss Winner

In conclusion, data analysis can be a powerful tool for gaining insights into the performance of teams and players in the IPL. By using data-driven approaches, we can gain a deeper understanding of the game and make more informed decisions. Our analysis of the IPL data has revealed some interesting insights, and we hope that our work inspires others to explore the use of data analytics in cricket and other sports.

To check more you can visit my GithubRepo https://github.com/ashim1600/DataScientist_Udacity_nano_degree_program/tree/main/Write-A-Data-Science-Blog-Post