Analysis of IPL Dataset

Analysis Of IPL Dataset
By -
Revanth Babu P N, PES1201800042
Navyadhara G, PES1201800230
What is our dataset?
This dataset contains the following :
❏ All Indian Premier League Cricket matches between 2008 and 2017.
❏ This is the ball by ball data of all the IPL cricket matches till season 9.
❏ The dataset contains 2 files: deliveries.csv and matches.csv. Matches.csv contains details related to the match such
as season, location, contesting teams, umpires, winner, etc.
❏ deliveries.csv is the ball-by-ball data of all the IPL matches including data of the batting team, batsman, bowler,
non-striker, runs scored,dismissal kind, etc.
Cleaning :
Removed umpire3 column as all the values where NaN. Replaced Rising Pune Supergiant with Rising Pune Supergiants as
it’s the same team
Multiple Graphs
Analysed the Cleaned the Hypothesis
Visualisation to analyse the
raw dataset data data
Testing
ANALYSIS
Most Economical bowlers(min 150 overs)
- Sunil Narine has the best economy
- Mumbai Indians have won the most number of times

VISUALISATION
1. It is not true that toss winners win the match

2. There is high chance that the team scoring 200+ wins the match
1.David Warner's form looks to be improving season by season.
2.Virat Kohli holds the record of most runs in a season 973.There has been a sharp decline in Kohli's Runs from
2016 to 2017.
3.Raina has consistently scored 300+ runs in every season
Virat has most number of 1s and is among the top 5 batsman with most 1s,2s,4s and 6s.
Gayle has most number of 6s. Gambhir has most number of 4s. Dhoni has most number of 2s
Average runs scored per match by RCB was highest
in 2016.
RCB has highest team total 263 runs (in 2013) and
the lowest team total 49 runs
The number of boundaries was least in the year

2009
CSK vs MI
MOST WINS: MI - 12 wins
2008 - MI:1 CSK:1
2009 - MI:1 CSK:1
2010 - MI:1 CSK:2
2011 - MI:1 CSK:0
2012 - MI:2 CSK:1
2013 - MI:3 CSK:1
2014 - MI:0 CSK:3
2015 - MI:3 CSK:1
Bowlers Analysis
1. Most Wickets - Malinga
2. Most Extras - Malinga
3. Bowler who has given most runs - Harbhajan Singh
4. Most Economical bowler( min 150 overs) - Sunil Narine
In the initial seasons of IPL, there is no much difference in number of times toss winners chose to bat and field.
In seasons 2009, 2010, 2013 batting first was the preferred choice.
Whereas in the last few seasons it is clearly seen that the trend is to bowl first.
HYPOTHESIS TESTING
We have also framed hypothesis and tested using the
data.
We have tested the case of average scores in 2009 vs
that of in 2016.
x: denotes year 2016 , y: denotes year 2009
Ho : u_x - u_y <= 0 , Ha : u_x - u_y > 0
Since p_value = 0.0063 < 0.05

We reject the null hypothesis and conclude average
scores in 2016 was greater than that in 2009.
IPL 2009 was hosted by South Africa.
Thus we can conclude the pitches in South Africa are
less batsmen supportive. This is also evident from the
line graph, which indicated that the number of
boundaries was least in 2009
CONCLUSIONS
1. It is not true that toss winners win the match
2. There is a high chance that the team scoring 200+ wins the match
3. David Warner's form looks to be improving season by season.
4. Virat Kohli holds the record of most runs in a season 973.There has been a sharp decline in Kohli's Runs from 2016
to 2017.
5. Raina has consistently scored 300+ runs in every season
6. Virat has most number of 1s and is among the top 5 batsman with most 1s,2s,4s and 6s.
7. Gayle has most number of 6s. Gambhir has most number of 4s. Dhoni has most number of 2s.
8. Suresh Raina has scored the most runs in IPL followed by Virat Kohli and Rohit sharma
9. RCB has scored most number of sixes and MI have scored most number of 4s
10. Average runs scored per match by RCB was highest in 2016.RCB has highest team total 263 runs.
11. The most common dismissal type in IPL is caught followed by bowled. There are very few instances of hit wicket as
well.
12. Chris Gayle has won the most number of man of the match awards
13. In the initial seasons of IPL, there is no much difference in number of times toss winners chose to bat and field.In
seasons 2009, 2010, 2013 batting first was the preferred choice.Whereas in the last few seasons it is clearly seen that
the trend is to bowl first.
By hypothesis Testing,
We have come to a conclusion that the pitches in South Africa are less batsmen supportive than those of India. Alongside this
we have arrived at multiple other conclusions about the performances of players.

Analysis of IPL Dataset

Uploaded by

Copyright:

Available Formats

Analysis of IPL Dataset

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Analysis of IPL Dataset

Uploaded by

Copyright:

Available Formats

Analysis Of IPL Dataset

- Mumbai Indians have won the most number of times

1. It is not true that toss winners win the match

The number of boundaries was least in the year

Since p_value = 0.0063 < 0.05

You might also like