IPL Data Analysis using Pandas AI
Last Updated :
07 Jul, 2025
Analyzing IPL 2023 auction data is important for understanding player purchases, team spending and auction trends. In this guide, we’ll use PandasAI an AI-powered data analysis tool to gain insights from the IPL 2024 Auction dataset. PandasAI enhances traditional Pandas by integrating AI-driven insights making it easier to extract meaningful information from large datasets. Key benefits include:
- Automating data analysis
- Generating quick insights
- Simplifying complex queries
Step-by-Step IPL Data Analysis Using PandasAI
Step 1: Prerequisites
Before starting ensure that pandasAI and openai libraries are installed. Run the following command in your command prompt:
!pip install -q pandasai
Step 2: Importing necessary libraries
Python
import pandas as pd
from pandasai import SmartDataframe
from pandasai.llm.openai import OpenAI
Step 3: Initializing an instance of OpenAI LLM and pass it's API key
Python
# replace "your_api_key" with your generated key
OPENAI_API_KEY = "your_api_key"
sdf = SmartDataframe(df, config={"llm": llm})
Step 4: Importing the IPL 2023 Auction dataset using pandas
We are using the IPL 2023 Auction dataset here. You can download dataset from here.
Python
df = pd.read_csv('IPL_Squad_2023_Auction_Dataset.csv')
print(df.shape)
df.head()
Output:
IPL 2023 Auction datasetStep 5: Drop the "Unnamed: 0" column from the above dataset
Python
df.drop(['Unnamed: 0'], axis=1, inplace=True)
df.head()
Output:
IPL 2023 Auction datasetStep 6: Data Analysis using PandasAI
Now let's begin our analysis:
Prompt 1:
Python
sdf.chat(df, prompt="Which players are the most costliest buys?")
Output:
['Sam Curran', 'Cameron Green', 'Ben Stokes']
Prompt 2:
Python
prompts = """
Which players were the cheapest buys this season and which team bought them?
"""
sdf.chat(df, prompt=prompts)
Output:
Well, it looks like the cheapest buys this season were Glenn Phillips for Sunrisers Hyderabad,
Raj Angad Bawa and Rishi Dhawan for Punjab Super Kings, Dhruv Jurel and K.C Cariappa
for Rajasthan Royals and many more. The full list includes 163 players and their respective teams.
Prompt 3:
Python
prompts = """
Draw a Bargraph showing How much money was spent by each team this season overall.
"""
sdf.chat(df, prompt=prompts)
Output:
.png)
Prompt 4:
Python
sdf.chat(df, prompt="How many bowler remained unsold and what was their base price?")
Output:
There were 108 bowlers who remained unsold in the auction.
Their base price ranged from 2 million to 20 million.
Prompt 5:
Python
sdf.chat(df, prompt="How many players remained unsold this season?")
Output:
('Number of players remained unsold this season:', 338)
Prompt 6:
Python
sdf.chat(df, prompt="Which type of players were majorly unsold?")
Output:
Player's List Base Price TYPE COST IN ₹ (CR.) Cost IN $ (000) \
0 Shivam Mavi 4000000 BOWLER 6.0 720.0
2 Kane Williamson 20000000 BATSMAN 2.0 240.0
3 K.S. Bharat 2000000 WICKETKEEPER 1.2 144.0
5 Odean Smith 5000000 ALL-ROUNDER 0.5 60.0
7 Rahul Tewatia Retained ALL-ROUNDER 0.0 0.0
2022 Squad Team
0 KKR Gujarat Titans
2 SRH Gujarat Titans
3 DC Gujarat Titans
5 PBKS Gujarat Titans
7 GT Gujarat Titans
TYPE
ALL-ROUNDER 65
BOWLER 64
BATSMAN 35
WICKETKEEPER 21
Name: TYPE, dtype: int64
Number of unsold players: 0
Prompt 7:
Python
sdf.chat(df, prompt="Who are three new players Gujrat picked?")
Output:
0 Shivam Mavi
1 Joshua Little
2 Kane Williamson
Name: Player's List, dtype: object
Prompt 8:
Python
sdf.chat(df, prompt="What is total money spent by all teams in dollars?")
Output:
The total amount of money spent by all teams in the auction is $20,040,000.
Prompt 9:
Python
prompts = """
draw a barplot showing
how much money was spent by Mumbai Indians on all types of players?
"""
pandas_ai.run(df, prompt=prompts)
Output:
Bar graph for Money spent by Mumbai Indians on each type of playerSure, I can help you with that! To answer your question, I can draw a barplot that shows how much money the Mumbai Indians spent on all types of players. Would you like me to do that for you now?
Prompt 10:
Python
prompts = """
draw a barplot showing how much money was spent by Gujrat on all types of players?
"""
pandas_ai.run(df, prompt=prompts)
Output:
Bar plot showing money spent on each type of player by Gujrat TitansPrompt 11:
Python
sdf.chat(df, prompt="Can you predict which team will buy Sam Curran in 2024?")
Output:
Lucknow Super Giants
Prompt 12:
Python
sdf.chat(df, prompt="Perform univariate analysis")
Output:
Histogram of Cost Attribute in dataset
Bar graph visualizing Count of each type of player
Pie Chart showing Percentage of players in 2022 squadSure! Based on the data provided, the univariate analysis shows that we have six variables: Player's List, Base Price, TYPE, COST IN ₹ (CR.), Cost IN $ (000), 2022 Squad and Team. The data types for these variables are object, object, object, float64, float64 and object respectively.
Prompt 14:
Python
sdf.chat(df, prompt="Perform multivariate analysis")
Output:
Unfortunately, I was not able to answer your question. Please try again. If the problem persists try rephrasing your question.
For this input PandasAI seems to have failed as the complexity and ambiguity increased.
Pros of Pandas AI
- Pandas AI works well on direct and well-explained inputs.
- Can easily perform simple tasks like plotting graphs and univariate analysis.
- Can perform basic statistical operations.
- Also, can make basic predictions sometimes.
Cons of Pandas AI
- Cannot process ambiguous inputs.
- It uses server data, So, that is slower as compared to pandas.
- Cannot perform complex tasks like outlier analysis or multivariate analysis.
Similar Reads
Data Manipulation in Python using Pandas In Machine Learning, the model requires a dataset to operate, i.e. to train and test. But data doesn’t come fully prepared and ready to use. There are discrepancies like Nan/ Null / NA values in many rows and columns. Sometimes the data set also contains some of the rows and columns which are not ev
6 min read
Data Manipulation in Python using Pandas In Machine Learning, the model requires a dataset to operate, i.e. to train and test. But data doesn’t come fully prepared and ready to use. There are discrepancies like Nan/ Null / NA values in many rows and columns. Sometimes the data set also contains some of the rows and columns which are not ev
6 min read
Reading An Arff File To Pandas Dataframe Attribute-Relation File Format (ARFF) is a file format developed by the Machine Learning Project of the University of Waikato, New Zealand. It has been developed by the Computer Science department of the aforementioned University. The ARFF files mostly belong to WEKA (Waikato Environment for Knowled
4 min read
Pandas Functions in Python: A Toolkit for Data Analysis Pandas is one of the most used libraries in Python for data science or data analysis. It can read data from CSV or Excel files, manipulate the data, and generate insights from it. Pandas can also be used to clean data, filter data, and visualize data. Whether you are a beginner or an experienced pro
6 min read
10 Python Pandas tips to make data analysis faster Data analysis using Python's Pandas library is a powerful process, and its efficiency can be enhanced with specific tricks and techniques. These Python tips will make our code concise, readable, and efficient. The adaptability of Pandas makes it an efficient tool for working with structured data. Wh
15 min read
Classifying Data With Pandas In Python Pandas is a widely used Python library renowned for its prowess in data manipulation and analysis. Its core data structures, such as DataFrame and Series, provide a powerful and user-friendly interface for handling structured data. This makes Pandas an indispensable tool for tasks like classifying o
5 min read