1

Submitted to
Department of Computer Applications
In partial fulfillment for the award of the degree of
Graphic Era (Deemed to be University)

PROJECT REPORT ON
IPL DATA ANALYSIS 2023

SUBMITTED BY:
PRASOON SINGH (21391038)
Roll. No-------1102276

MCA SEM 4 [2021-2023]

 2

Ref No: Date:

Certificate

This is to certify that the project entitled IPL DATA ANALYSIS 2023 is undertaken at the GRAPHIC
ERA (Deemed to be University) by PRASOON SINGH in partial fulfillment of MCA (Semester IV)
Examination had not been submitted for any other examination and does not form part of any other
course undergone by the candidate.
It is further certified that he has completed all required phases of project.

Signature of Internal Guide Signature of External

HOD/In -Charge/Coordinator
 3

ACKNOWLEDGEMENT

In completing this project report on project titled IPL DATA ANALYSIS 2023, I had to take
the help and guideline of a few respected people, who deserve my greatest gratitude.

The completion of this project report gives me much pleasure. I would like to show my
gratitude to MRS. GEETIKA SHARMA for giving me a good guideline for project
throughout numerous consultations. I would also like to expand my deepest gratitude to
all those who have directly and indirectly guided us in writing this project report.

Many people, especially my classmates and friends themselves, have made valuable
comments and suggestions on this proposal which gave me inspiration to improve my
project. Here I thank all the people for their help directly and indirectly to complete this
project report.
 4

CERTIFICATE OF ORIGINALITY

This is to certify that the project report entitled

submitted to Graphic Era University, Dehradun in partial fulfilment of the requirement

for the award of the degree of MASTERS OF COMPUTER APPLICATIONS (MCA),
is an authentic and original work carried out by Mr. / Ms. with enrolment
number under my supervision and guidance.
The matter embodied in this project is genuine work done by the student and has not
been submitted whether to this University or to any other University / Institute for the
fulfilment of the requirements of any course of study.
…………………………. ………………………….

Signature of the Student: Signature of the Guide:

Date: …………………. Date: ………………….
Enrolment No.:

Name and Address Address of the Guide:

Designation of the Student:

Special Note:
 5

Table Of Content

1 INTRODUCTION 15
 Briefly explain the purpose and scope of the project. 15
 Provide an overview of the Indian Premier League (IPL) and its 17
significance in the cricketing world.
2 Data Collection 18
 Describe the sources from which the IPL data was collected. 18
 Explain the data collection process and any 19
challenges encountered.

3 Data Preprocessing 20
3.1 Outline the steps taken to clean and preprocess the IPL data 26
3.2 Discuss techniques used for data cleaning, handling missing 30
values, and data formatting.

4 Exploratory Data Analysis (EDA) 35

4.1 Present key statistics and visualizations of the IPL data. 37
4.2 Explore trends, patterns, and insights related
to player performance, team performance, 56
match results, and other relevant factors.
4.3 Identify any interesting observations or correlations discovered 39
during the analysis.
5 Player Performance Analysis 42

5.1 Analyze the performance of individual players in the IPL. 44

5.2 Evaluate player statistics such as batting average, bowling 47

economy rate, strike rate, etc.
5.3 Identify top-performing players and compare their performance 75
across different seasons.
6 Team Performance Analysis 77
 6

6.1 Assess the performance of IPL teams. 82

6.2 Analyze team statistics, such as win-loss ratios, net run rate, team 83
batting averages, etc.
6.3 Identify successful teams and compare their performance over the 86
years.
7 Predictive Modeling (if applicable) 87
7.1 Describe any predictive modeling techniques employed to forecast 89
match outcomes or player performance
7.2 Explain the model selection process and performance 90
evaluation metrics used.
8 Conclusion 90
9 Limitations and Future Work 91
10 References 92
 7

INTRODUCTION

The IPL Data Analysis 2023 Project Report aims to analyze and explore the data from the Indian Premier
League (IPL) in 2023. The IPL is a professional Twenty20 cricket league in India, which attracts players
from all over the world and has a massive fan following. This project focuses on analyzing various aspects
of the IPL, including player performance, team performance, and match results, using data from the 2023
season. Data science is the study of data to extract knowledge and insights from the data and apply
knowledge and actionable insights. In this tutorial, we will work on IPL Data Analysis and Visualization
Project using Python where we will explore interesting insights from the data of IPL matches like most run
by a player, most wicket taken by a player, and much more from IPL season 2008-2020.
So if you are an IPL cricket fan and love data analysis with Python this project is perfect for you.

The IPL has gained immense popularity since its inception, revolutionizing the cricketing landscape. It has
become a platform for players to showcase their skills and for teams to compete at the highest level. By
analyzing the IPL data, we can gain valuable insights into the performance of individual players, team
dynamics, and trends within the league.

The objectives of this project report are:

To analyze and explore the IPL data from the 2023 season.
To identify patterns, trends, and correlations within the data.
To evaluate player and team performances based on statistical metrics.
To provide meaningful insights and observations from the analysis.

Through this project, we aim to contribute to the understanding of the IPL and provide a comprehensive
analysis of the 2023 season. The human face is a unique representation of individual identity. Thus, face
recognition is defined as a biometric method in which identification of an individual is performed by
comparing real-time capture image with stored images in the database of that person . By delving into the
data, we can uncover interesting findings that shed light on the dynamics and competitive nature of the
league.
 8

Importing Libraries

In this tutorial, we will use NumPy and Pandas libraries of Python for data analysis and for data visualization Seaborn
and Matplotlib libraries.

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

Now, with a basic understanding of the attributes let us now start our project of data analysis and visualization of the IPL dataset
with Python. We will initially perform simple statistical analysis and then slowly build to more advanced analysis.

General Analysis of IPL Matches 

1. List of Seasons
We can get the list of seasons from the dataset by applying unique() function on the season column which confirms that our
dataset contains data of matches played from season 2008-2020.

2. First ball of IPL history

Each data point describes the match_id, season, start_date, venue, innings, ball, batting_team, bowling_team, striker, non_striker,
bowler, runs_off_bat, extras, wides, no balls, byes, leg byes, wicket_type, player_dismissed, run which are self-explanatory.
Here we have fetched the first row of the data sets which corresponds to the first ball of the first match of IPL history played
between KKR and RCB played on 4th July 2008.

3. Season Wise IPL Matches

We can find the number of matches played in each season by grouping the match_id, season column and counting out the data,
and then calling the index out of it by dropping the first index layer that is the match_id.
We can see the visualization of the IPL matches using the Matlotlib library.

4. Most IPL Matches played in a Venue

The analysis shows most of the IPL matches were played in Chennai, Mumbai, Kolkata, Banglore, and Delhi.
 9

DATA COLLECTION

The data for this IPL Data Analysis 2023 project was collected from reliable sources that provide
comprehensive and accurate information about the IPL matches, players, and teams. The sources include
official IPL websites, cricket statistics databases, sports analytics platforms, and reputable sports news
sources.
The data collection process involved the following steps:
1. Identification of Data Sources: Various sources were identified and evaluated to ensure the
availability of relevant and up-to-date IPL data for the 2023 season.
2. Data Extraction: The necessary data, including match results, player statistics, team information,
and other relevant variables, were extracted from the identified sources. The data was collected in
a structured format, such as CSV or Excel files, to facilitate further analysis.
3. Data Cleaning: The collected data underwent a rigorous cleaning process to ensure its quality and
consistency. This involved handling missing values, correcting inconsistencies, removing
duplicate entries, and standardizing data formats.
4. Data Integration: If multiple data sources were used, the data was integrated to create a unified
dataset. This involved mapping and aligning the variables from different sources to ensure
consistency and coherence in the analysis.
5. Data Verification: To ensure the accuracy of the collected data, a verification process was
conducted by cross-referencing the information from different sources and resolving any
discrepancies or errors that were identified.
6. Data Validation: The final dataset was validated to ensure it met the project's requirements and
was suitable for the intended analysis. This involved checking data integrity, verifying data types,
and performing data quality checks.
Challenges encountered during the data collection process included inconsistent data formats, missing
values in certain variables, and occasional discrepancies between different sources. These challenges
were addressed through careful data preprocessing and validation techniques to ensure the reliability and
accuracy of the final dataset used for analysis.
 10

Data preprocessing

Data preprocessing is a crucial step in the IPL Data Analysis 2023 project to ensure that the collected data
is clean, consistent, and suitable for analysis. Data preprocessing is the process of transforming raw data
into a useful, understandable format. Real-world or raw data usually has inconsistent formatting, human
errors, and can also be incomplete. Data preprocessing resolves such issues and makes datasets more
complete and efficient to perform data analysis. It’s a crucial process that can affect the success of data
mining and machine learning projects. It makes knowledge discovery from datasets faster and can
ultimately affect the performance of machine learning models.
The following steps were undertaken during the data preprocessing phase:
1. Handling Missing Values: Missing values can be present in the collected data, which can affect
the analysis. The missing values were identified and handled appropriately. Depending on the
specific variable and the extent of missing data, options such as imputation, deletion of missing
records, or substitution techniques were employed.
2. Data Cleaning: The data cleaning process involved identifying and correcting any inconsistencies
or errors in the data. This included removing duplicate entries, rectifying formatting issues, and
resolving discrepancies in naming conventions or data encoding.
3. Data Transformation: In some cases, data transformation techniques were applied to improve the
quality of the data or to meet specific analysis requirements. This included transforming variables
into appropriate formats (e.g., converting dates into a standardized format), normalizing or scaling
variables, or encoding categorical variables.
4. Feature Engineering: Additional features were derived from the existing dataset to enhance the
analysis. This involved creating new variables based on existing ones, such as calculating batting
averages, bowling economy rates, or strike rates from the available data.
5. Data Integration: If multiple data sources were used, the data was integrated into a unified dataset.
This involved merging datasets based on common variables or creating appropriate relationships
between the datasets to ensure a comprehensive analysis.
6. Outlier Detection and Handling: Outliers, if present in the data, can significantly impact the
analysis results. Outlier detection techniques were applied to identify and handle outliers
appropriately, either by removing them, transforming them, or treating them as a separate category.
7. Data Formatting: The final step in data preprocessing involved formatting the data in a consistent
and standardized manner. This included ensuring consistent variable names, data.
11