3/4/26, 9:29 PM 02_data_cleaning

In [196… import pandas as pd

import numpy as np
pd.set_option('display.max_columns', None)

In [197… df = pd.read_csv(r"C:\Users\LENOVO\Downloads\mywork\Ipl_Analysis\data\[Link]")

C:\Users\LENOVO\AppData\Local\Temp\ipykernel_4892\[Link]: DtypeWarning: Columns (28,29,30,31,43,46,47,48,51) have mixe

d types. Specify dtype option on import or set low_memory=False.
df = pd.read_csv(r"C:\Users\LENOVO\Downloads\mywork\Ipl_Analysis\data\[Link]")

In [198… [Link]()

Out[198… Unnamed:
match_id date match_type event_name innings batting_team bowling_team over ball ball_no batter bat_pos r
0

Indian Royal
2008- Kolkata SC
0 131970 335982 T20 Premier 1 Challengers 0 1 0.1 1
04-18 Knight Riders Ganguly
League Bangalore

Indian Royal
2008- Kolkata BB
1 131971 335982 T20 Premier 1 Challengers 0 2 0.2 2
04-18 Knight Riders McCullum
League Bangalore

Indian Royal
2008- Kolkata BB
2 131972 335982 T20 Premier 1 Challengers 0 3 0.3 2
04-18 Knight Riders McCullum
League Bangalore

Indian Royal
2008- Kolkata BB
3 131973 335982 T20 Premier 1 Challengers 0 3 0.3 2
04-18 Knight Riders McCullum
League Bangalore

Indian Royal
2008- Kolkata BB
4 131974 335982 T20 Premier 1 Challengers 0 4 0.4 2
04-18 Knight Riders McCullum
League Bangalore

In [199… [Link]

[Link] 1/28
3/4/26, 9:29 PM 02_data_cleaning

Out[199… (278205, 64)

In [200… df = [Link](columns=["Unnamed: 0"])

In [201… [Link]

Out[201… (278205, 63)

In [202… df["date"] = pd.to_datetime(df["date"])

In [203… df["date"].dtype

Out[203… dtype('<M8[ns]')

In [204… [Link]("season")["year"].nunique()

[Link] 2/28
3/4/26, 9:29 PM 02_data_cleaning

Out[204… season
2009 1
2011 1
2012 1
2013 1
2014 1
2015 1
2016 1
2017 1
2018 1
2019 1
2021 1
2022 1
2023 1
2024 1
2025 1
2007/08 1
2009 1
2009/10 1
2011 1
2019 1
2020/21 1
2021 1
Name: year, dtype: int64

In [205… df = [Link](columns=["season"])

In [206… df["ipl_season"] = df["year"]

In [207… [Link]()

[Link] 3/28
3/4/26, 9:29 PM 02_data_cleaning

<class '[Link]'>
RangeIndex: 278205 entries, 0 to 278204
Data columns (total 63 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 match_id 278205 non-null int64
1 date 278205 non-null datetime64[ns]
2 match_type 278205 non-null object
3 event_name 278205 non-null object
4 innings 278205 non-null int64
5 batting_team 278205 non-null object
6 bowling_team 278205 non-null object
7 over 278205 non-null int64
8 ball 278205 non-null int64
9 ball_no 278205 non-null float64
10 batter 278205 non-null object
11 bat_pos 278205 non-null int64
12 runs_batter 278205 non-null int64
13 balls_faced 278205 non-null int64
14 bowler 278205 non-null object
15 valid_ball 278205 non-null int64
16 runs_extras 278205 non-null int64
17 runs_total 278205 non-null int64
18 runs_bowler 278205 non-null int64
19 runs_not_boundary 278205 non-null bool
20 extra_type 15133 non-null object
21 non_striker 278205 non-null object
22 non_striker_pos 278205 non-null int64
23 wicket_kind 13823 non-null object
24 player_out 13823 non-null object
25 fielders 10013 non-null object
26 runs_target 133903 non-null float64
27 review_batter 872 non-null object
28 team_reviewed 872 non-null object
29 review_decision 872 non-null object
30 umpire 872 non-null object
31 umpires_call 278205 non-null bool
32 player_of_match 278205 non-null object
33 match_won_by 278205 non-null object
34 win_outcome 273503 non-null object
35 toss_winner 278205 non-null object

[Link] 4/28
3/4/26, 9:29 PM 02_data_cleaning

36 toss_decision 278205 non-null object

37 venue 278205 non-null object
38 city 278205 non-null object
39 day 278205 non-null int64
40 month 278205 non-null int64
41 year 278205 non-null int64
42 gender 278205 non-null object
43 team_type 278205 non-null object
44 superover_winner 3896 non-null object
45 result_type 4702 non-null object
46 method 3890 non-null object
47 balls_per_over 278205 non-null int64
48 overs 278205 non-null int64
49 event_match_no 278205 non-null object
50 stage 278205 non-null object
51 match_number 278205 non-null object
52 team_runs 278205 non-null int64
53 team_balls 278205 non-null int64
54 team_wicket 278205 non-null int64
55 new_batter 13321 non-null object
56 batter_runs 278205 non-null int64
57 batter_balls 278205 non-null int64
58 bowler_wicket 278205 non-null int64
59 batting_partners 278205 non-null object
60 next_batter 13321 non-null object
61 striker_out 278205 non-null bool
62 ipl_season 278205 non-null int64
dtypes: bool(3), datetime64[ns](1), float64(2), int64(24), object(33)
memory usage: 128.1+ MB

In [208… df["match_number"].unique()[:20]

Out[208… array(['Unknown'], dtype=object)

In [209… df = [Link](columns=["match_number"])

In [210… df["event_match_no"].unique()

[Link] 5/28
3/4/26, 9:29 PM 02_data_cleaning

Out[210… array([1, 2, 3, 5, 4, 6, 7, 8, 9, 10, 12, 11, 14, 13, 15, 16, 17, 19, 18,
20, 22, 21, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35,
'35', '36', '37', '38', '40', '39', '42', '41', '43', '44', '45',
'46', '48', '50', '49', '51', '52', '53', '54', '55', '56',
'Unknown', '1', '2', '3', '4', '5', '6', '8', '9', '10', '11',
'12', '14', '15', 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47,
48, 49, '7', '13', '16', '17', '18', '19', '21', '20', '22', '23',
'24', '25', '26', '27', '28', '29', '30', '31', '32', '33', '34',
'47', 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64,
65, 66, 67, 68, 69, '69', '70', '66', '67', '68', '71', '72', '58',
'59', '60', '61', '62', '63', '64', '65', '57'], dtype=object)

In [211… df["event_match_no"] = df["event_match_no"].astype(str)

In [212… df["event_match_no"] = df["event_match_no"].replace("Unknown", [Link])

In [213… df["event_match_no"] = pd.to_numeric(df["event_match_no"], errors="coerce").astype("Int64")

In [214… df["event_match_no"].dtype
df["event_match_no"].unique()[:20]

Out[214… <IntegerArray>
[1, 2, 3, 5, 4, 6, 7, 8, 9, 10, 12, 11, 14, 13, 15, 16, 17, 19, 18, 20]
Length: 20, dtype: Int64

In [215… df["runs_target"].dropna().unique()[:10]

Out[215… array([223., 241., 130., 166., 111., 167., 143., 209., 215., 183.])

In [216… df["runs_target"] = df["runs_target"].astype("Int64")

In [217… [Link]().sum()

Out[217… 0

In [218… [Link](subset=["match_id", "innings", "over", "ball"]).sum()

Out[218… 10218

[Link] 6/28
3/4/26, 9:29 PM 02_data_cleaning

In [219… critical_cols = [
"match_id", "date", "batting_team",
"bowling_team", "batter", "bowler",
"runs_total", "team_runs"
]

df[critical_cols].isnull().sum()

Out[219… match_id 0
date 0
batting_team 0
bowling_team 0
batter 0
bowler 0
runs_total 0
team_runs 0
dtype: int64

In [220… df["win_outcome"].isnull().sum()

Out[220… 4702

In [221… [Link]().sum().sort_values(ascending=False).head(15)

[Link] 7/28
3/4/26, 9:29 PM 02_data_cleaning

Out[221… team_reviewed 277333

umpire 277333
review_batter 277333
review_decision 277333
method 274315
superover_winner 274309
result_type 273503
fielders 268192
new_batter 264884
next_batter 264884
player_out 264382
wicket_kind 264382
extra_type 263072
runs_target 144302
event_match_no 16713
dtype: int64

In [222… print(df["gender"].unique(),
df["team_type"].unique(),
df["event_name"].unique(),
df["match_type"].unique())

['male'] ['club'] ['Indian Premier League'] ['T20']

In [223… cols_to_drop = [
"gender",
"team_type",
"event_name",
"match_type"
]

df = [Link](columns=cols_to_drop)

In [224… [Link]

Out[224… (278205, 58)

In [225… sorted(df["batting_team"].unique())

[Link] 8/28
3/4/26, 9:29 PM 02_data_cleaning

Out[225… ['Chennai Super Kings',

'Deccan Chargers',
'Delhi Capitals',
'Delhi Daredevils',
'Gujarat Lions',
'Gujarat Titans',
'Kings XI Punjab',
'Kochi Tuskers Kerala',
'Kolkata Knight Riders',
'Lucknow Super Giants',
'Mumbai Indians',
'Pune Warriors',
'Punjab Kings',
'Rajasthan Royals',
'Rising Pune Supergiant',
'Rising Pune Supergiants',
'Royal Challengers Bangalore',
'Royal Challengers Bengaluru',
'Sunrisers Hyderabad']

In [226… df.to_csv(r"C:\Users\LENOVO\Downloads\mywork\Ipl_Analysis\/data/ipl_cleaned.csv", index=False)

In [227… sorted(df["bowling_team"].unique())

[Link] 9/28
3/4/26, 9:29 PM 02_data_cleaning

Out[227… ['Chennai Super Kings',

'Deccan Chargers',
'Delhi Capitals',
'Delhi Daredevils',
'Gujarat Lions',
'Gujarat Titans',
'Kings XI Punjab',
'Kochi Tuskers Kerala',
'Kolkata Knight Riders',
'Lucknow Super Giants',
'Mumbai Indians',
'Pune Warriors',
'Punjab Kings',
'Rajasthan Royals',
'Rising Pune Supergiant',
'Rising Pune Supergiants',
'Royal Challengers Bangalore',
'Royal Challengers Bengaluru',
'Sunrisers Hyderabad']

In [228… team_mapping = {
"Delhi Daredevils": "Delhi Capitals",
"Kings XI Punjab": "Punjab Kings",
"Royal Challengers Bangalore": "Royal Challengers Bengaluru",
"Rising Pune Supergiant": "Rising Pune Supergiants"
}

In [229… team_columns = [
"batting_team",
"bowling_team",
"toss_winner",
"match_won_by",
"superover_winner"
]

team_columns

[Link] 10/28
3/4/26, 9:29 PM 02_data_cleaning

Out[229… ['batting_team',
'bowling_team',
'toss_winner',
'match_won_by',
'superover_winner']

In [230… for col in team_columns:

df[col] = df[col].replace(team_mapping)

In [231… sorted(df["batting_team"].unique())

Out[231… ['Chennai Super Kings',

'Deccan Chargers',
'Delhi Capitals',
'Gujarat Lions',
'Gujarat Titans',
'Kochi Tuskers Kerala',
'Kolkata Knight Riders',
'Lucknow Super Giants',
'Mumbai Indians',
'Pune Warriors',
'Punjab Kings',
'Rajasthan Royals',
'Rising Pune Supergiants',
'Royal Challengers Bengaluru',
'Sunrisers Hyderabad']

In [232… sorted(df["match_won_by"].dropna().unique())

[Link] 11/28
3/4/26, 9:29 PM 02_data_cleaning

Out[232… ['Chennai Super Kings',

'Deccan Chargers',
'Delhi Capitals',
'Gujarat Lions',
'Gujarat Titans',
'Kochi Tuskers Kerala',
'Kolkata Knight Riders',
'Lucknow Super Giants',
'Mumbai Indians',
'Pune Warriors',
'Punjab Kings',
'Rajasthan Royals',
'Rising Pune Supergiants',
'Royal Challengers Bengaluru',
'Sunrisers Hyderabad',
'Unknown']

In [233… df["batting_team"].nunique()

Out[233… 15

In [234… [Link]()

[Link] 12/28
3/4/26, 9:29 PM 02_data_cleaning

<class '[Link]'>
RangeIndex: 278205 entries, 0 to 278204
Data columns (total 58 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 match_id 278205 non-null int64
1 date 278205 non-null datetime64[ns]
2 innings 278205 non-null int64
3 batting_team 278205 non-null object
4 bowling_team 278205 non-null object
5 over 278205 non-null int64
6 ball 278205 non-null int64
7 ball_no 278205 non-null float64
8 batter 278205 non-null object
9 bat_pos 278205 non-null int64
10 runs_batter 278205 non-null int64
11 balls_faced 278205 non-null int64
12 bowler 278205 non-null object
13 valid_ball 278205 non-null int64
14 runs_extras 278205 non-null int64
15 runs_total 278205 non-null int64
16 runs_bowler 278205 non-null int64
17 runs_not_boundary 278205 non-null bool
18 extra_type 15133 non-null object
19 non_striker 278205 non-null object
20 non_striker_pos 278205 non-null int64
21 wicket_kind 13823 non-null object
22 player_out 13823 non-null object
23 fielders 10013 non-null object
24 runs_target 133903 non-null Int64
25 review_batter 872 non-null object
26 team_reviewed 872 non-null object
27 review_decision 872 non-null object
28 umpire 872 non-null object
29 umpires_call 278205 non-null bool
30 player_of_match 278205 non-null object
31 match_won_by 278205 non-null object
32 win_outcome 273503 non-null object
33 toss_winner 278205 non-null object
34 toss_decision 278205 non-null object
35 venue 278205 non-null object

[Link] 13/28
3/4/26, 9:29 PM 02_data_cleaning

36 city 278205 non-null object

37 day 278205 non-null int64
38 month 278205 non-null int64
39 year 278205 non-null int64
40 superover_winner 3896 non-null object
41 result_type 4702 non-null object
42 method 3890 non-null object
43 balls_per_over 278205 non-null int64
44 overs 278205 non-null int64
45 event_match_no 261492 non-null Int64
46 stage 278205 non-null object
47 team_runs 278205 non-null int64
48 team_balls 278205 non-null int64
49 team_wicket 278205 non-null int64
50 new_batter 13321 non-null object
51 batter_runs 278205 non-null int64
52 batter_balls 278205 non-null int64
53 bowler_wicket 278205 non-null int64
54 batting_partners 278205 non-null object
55 next_batter 13321 non-null object
56 striker_out 278205 non-null bool
57 ipl_season 278205 non-null int64
dtypes: Int64(2), bool(3), datetime64[ns](1), float64(1), int64(24), object(27)
memory usage: 118.1+ MB

In [235… df["stage"].value_counts()

Out[235… stage
Unknown 261492
Final 4338
Qualifier 2 3636
Qualifier 1 3553
Eliminator 2845
Semi Final 1409
Elimination Final 734
3rd Place Play-Off 198
Name: count, dtype: int64

In [236… df["stage"] = df["stage"].replace("Unknown", "League")

[Link] 14/28
3/4/26, 9:29 PM 02_data_cleaning

In [237… df["stage"].value_counts()

Out[237… stage
League 261492
Final 4338
Qualifier 2 3636
Qualifier 1 3553
Eliminator 2845
Semi Final 1409
Elimination Final 734
3rd Place Play-Off 198
Name: count, dtype: int64

In [238… stage_mapping = {
"Elimination Final": "Eliminator",
"3rd Place Play-Off": "Playoff"
}

df["stage"] = df["stage"].replace(stage_mapping)

In [239… df["stage"].value_counts()

Out[239… stage
League 261492
Final 4338
Qualifier 2 3636
Eliminator 3579
Qualifier 1 3553
Semi Final 1409
Playoff 198
Name: count, dtype: int64

In [240… [Link]()

[Link] 15/28
3/4/26, 9:29 PM 02_data_cleaning

Out[240… match_id date innings batting_team bowling_team over ball ball_no batter bat_pos runs_batter balls_faced bowler valid_

Royal
2008- Kolkata SC P
0 335982 1 Challengers 0 1 0.1 1 0 1
04-18 Knight Riders Ganguly Kumar
Bengaluru

Royal
2008- Kolkata BB P
1 335982 1 Challengers 0 2 0.2 2 0 1
04-18 Knight Riders McCullum Kumar
Bengaluru

Royal
2008- Kolkata BB P
2 335982 1 Challengers 0 3 0.3 2 0 0
04-18 Knight Riders McCullum Kumar
Bengaluru

Royal
2008- Kolkata BB P
3 335982 1 Challengers 0 3 0.3 2 0 1
04-18 Knight Riders McCullum Kumar
Bengaluru

Royal
2008- Kolkata BB P
4 335982 1 Challengers 0 4 0.4 2 0 1
04-18 Knight Riders McCullum Kumar
Bengaluru

In [241… df = [Link](columns=["ball_no", "batting_partners"])

In [242… [Link]

Out[242… (278205, 56)

In [243… print(df["over"].max(),
df["overs"].unique(),
df["balls_per_over"].unique(),df["innings"].unique())

19 [20] [6] [1 2 3 4 5 6]

In [244… df["innings"].value_counts()

[Link] 16/28
3/4/26, 9:29 PM 02_data_cleaning

Out[244… innings
1 144131
2 133903
3 83
4 76
5 8
6 4
Name: count, dtype: int64

In [245… df[df["innings"] > 4][["match_id", "innings", "over", "ball", "superover_winner"]].head(40)

Out[245… match_id innings over ball superover_winner

187955 1216517 5 0 1 Punjab Kings

187956 1216517 5 0 2 Punjab Kings

187957 1216517 5 0 2 Punjab Kings

187958 1216517 5 0 3 Punjab Kings

187959 1216517 5 0 4 Punjab Kings

187960 1216517 5 0 4 Punjab Kings

187961 1216517 5 0 5 Punjab Kings

187962 1216517 5 0 6 Punjab Kings

187963 1216517 6 0 1 Punjab Kings

187964 1216517 6 0 2 Punjab Kings

187965 1216517 6 0 3 Punjab Kings

187966 1216517 6 0 4 Punjab Kings

In [246… df["is_super_over"] = df["innings"] > 2

In [247… df["is_super_over"].value_counts()

[Link] 17/28
3/4/26, 9:29 PM 02_data_cleaning

Out[247… is_super_over
False 278034
True 171
Name: count, dtype: int64

In [248… df['win_outcome'].unique()

Out[248… array(['140 runs', '33 runs', '9 wickets', '5 wickets', '6 wickets',
'6 runs', '3 wickets', '66 runs', '7 wickets', '10 wickets',
'4 wickets', '13 runs', '10 runs', '45 runs', '8 wickets',
'9 runs', '3 runs', '29 runs', '5 runs', '18 runs', '23 runs',
'12 runs', '65 runs', '25 runs', '1 runs', '14 runs', '41 runs',
'105 runs', '19 runs', '75 runs', '92 runs', '11 runs', '24 runs',
nan, '27 runs', '38 runs', '8 runs', '78 runs', '16 runs',
'53 runs', '2 wickets', '2 runs', '4 runs', '31 runs', '55 runs',
'98 runs', '34 runs', '36 runs', '17 runs', '39 runs', '40 runs',
'67 runs', '63 runs', '37 runs', '57 runs', '35 runs', '22 runs',
'21 runs', '48 runs', '26 runs', '20 runs', '85 runs', '32 runs',
'76 runs', '111 runs', '82 runs', '43 runs', '58 runs', '28 runs',
'74 runs', '42 runs', '59 runs', '46 runs', '7 runs', '47 runs',
'86 runs', '44 runs', '87 runs', '130 runs', '15 runs', '60 runs',
'77 runs', '30 runs', '50 runs', '93 runs', '72 runs', '62 runs',
'97 runs', '138 runs', '1 wickets', '71 runs', '144 runs',
'80 runs', '51 runs', '61 runs', '146 runs', '64 runs', '102 runs',
'118 runs', '49 runs', '69 runs', '88 runs', '54 runs', '91 runs',
'52 runs', '81 runs', '56 runs', '112 runs', '106 runs',
'100 runs', '83 runs', '110 runs'], dtype=object)

In [249… df["win_margin"] = df["win_outcome"].[Link](r"(\d+)").astype("Int64")

In [250… df["win_type"] = df["win_outcome"].[Link](r"(runs|wickets)")

In [251… df[["win_outcome", "win_margin", "win_type"]].dropna().head(10)

[Link] 18/28
3/4/26, 9:29 PM 02_data_cleaning

Out[251… win_outcome win_margin win_type

0 140 runs 140 runs

1 140 runs 140 runs

2 140 runs 140 runs

3 140 runs 140 runs

4 140 runs 140 runs

5 140 runs 140 runs

6 140 runs 140 runs

7 140 runs 140 runs

8 140 runs 140 runs

9 140 runs 140 runs

In [252… df = [Link](columns=["win_outcome"])

In [253… df["win_margin"].dtype

Out[253… Int64Dtype()

In [254… df["win_type"].unique()

Out[254… array(['runs', 'wickets', nan], dtype=object)

In [255… df['match_won_by'].unique()

Out[255… array(['Kolkata Knight Riders', 'Chennai Super Kings', 'Delhi Capitals',

'Royal Challengers Bengaluru', 'Rajasthan Royals', 'Punjab Kings',
'Deccan Chargers', 'Mumbai Indians', 'Unknown', 'Pune Warriors',
'Kochi Tuskers Kerala', 'Sunrisers Hyderabad',
'Rising Pune Supergiants', 'Gujarat Lions', 'Gujarat Titans',
'Lucknow Super Giants'], dtype=object)

[Link] 19/28
3/4/26, 9:29 PM 02_data_cleaning

In [256… df["match_won_by"] = df["match_won_by"].replace("Unknown", [Link])

In [257… df['match_won_by'].unique()

Out[257… array(['Kolkata Knight Riders', 'Chennai Super Kings', 'Delhi Capitals',

'Royal Challengers Bengaluru', 'Rajasthan Royals', 'Punjab Kings',
'Deccan Chargers', 'Mumbai Indians', nan, 'Pune Warriors',
'Kochi Tuskers Kerala', 'Sunrisers Hyderabad',
'Rising Pune Supergiants', 'Gujarat Lions', 'Gujarat Titans',
'Lucknow Super Giants'], dtype=object)

In [258… df['result_type'].unique()

Out[258… array([nan, 'tie', 'no result'], dtype=object)

In [259… df["is_dl_method"] = df["method"] == "D/L"

In [260… df["is_dl_method"].value_counts()

Out[260… is_dl_method
False 274315
True 3890
Name: count, dtype: int64

In [261… df = [Link](columns=["method"])

In [262… df["result_type"] = df["result_type"].fillna("normal")

In [263… df["result_type"].value_counts()

Out[263… result_type
normal 273503
tie 3896
no result 806
Name: count, dtype: int64

In [264… [Link](5)

[Link] 20/28
3/4/26, 9:29 PM 02_data_cleaning

Out[264… match_id date innings batting_team bowling_team over ball batter bat_pos runs_batter balls_faced bowler valid_ball run

Royal
2008- Kolkata SC P
0 335982 1 Challengers 0 1 1 0 1 1
04-18 Knight Riders Ganguly Kumar
Bengaluru

Royal
2008- Kolkata BB P
1 335982 1 Challengers 0 2 2 0 1 1
04-18 Knight Riders McCullum Kumar
Bengaluru

Royal
2008- Kolkata BB P
2 335982 1 Challengers 0 3 2 0 0 0
04-18 Knight Riders McCullum Kumar
Bengaluru

Royal
2008- Kolkata BB P
3 335982 1 Challengers 0 3 2 0 1 1
04-18 Knight Riders McCullum Kumar
Bengaluru

Royal
2008- Kolkata BB P
4 335982 1 Challengers 0 4 2 0 1 1
04-18 Knight Riders McCullum Kumar
Bengaluru

In [265… df['umpire'].unique()

Out[265… array([nan, 'CB Gaffaney', 'RJ Tucker', 'C Shamshuddin', 'A Deshmukh',
'VA Kulkarni', 'AK Chaudhary', 'CK Nandan', 'NJ Llong', 'S Ravi',
'Nitin Menon', 'KN Ananthapadmanabhan', 'A Nand Kishore',
'VK Sharma', 'YC Barde', 'M Erasmus', 'HDPK Dharmasena',
'BNJ Oxenford', 'AY Dandekar', 'UV Gandhe', 'IJ Gould',
'PR Reiffel', 'RK Illingworth', 'K Srinivasan', 'PG Pathak',
'J Madanagopal', 'Navdeep Singh', 'Tapan Sharma', 'HAS Khalid',
'MA Gough', 'N Pandit', 'R Pandit', 'Chirra Ravikanthreddy',
'NA Patwardhan', 'GR Sadashiv Iyer', 'Vinod Seshan', 'A Totre',
'MV Saidharshan Kumar', 'AG Wharf', 'Abhijit Bhattacharya',
'A Bengeri', 'AT Holdstock', 'K Swaroopanand', 'P Joshi',
'M Krishnadas', 'K Kelkar', 'KM Gandhi', 'Anish Sahasrabudhe'],
dtype=object)

[Link] 21/28
3/4/26, 9:29 PM 02_data_cleaning

In [266… venue_mapping = {
"Maharaja Yadavindra Singh International Cricket Stadium, Mullanpur":
"Maharaja Yadavindra Singh International Cricket Stadium, New Chandigarh"
}

In [267… df["venue"] = df["venue"].replace(venue_mapping)

In [268… df[df["venue"].[Link]("Yadavindra", case=False)]["venue"].value_counts()

Out[268… venue
Maharaja Yadavindra Singh International Cricket Stadium, New Chandigarh 2561
Name: count, dtype: int64

In [269… df['venue'].unique()

[Link] 22/28
3/4/26, 9:29 PM 02_data_cleaning

Out[269… array(['M Chinnaswamy Stadium',

'Punjab Cricket Association Stadium, Mohali', 'Feroz Shah Kotla',
'Wankhede Stadium', 'Eden Gardens', 'Sawai Mansingh Stadium',
'Rajiv Gandhi International Stadium, Uppal',
'MA Chidambaram Stadium, Chepauk', 'Dr DY Patil Sports Academy',
'Newlands', "St George's Park", 'Kingsmead', 'SuperSport Park',
'Buffalo Park', 'New Wanderers Stadium', 'De Beers Diamond Oval',
'OUTsurance Oval', 'Brabourne Stadium',
'Sardar Patel Stadium, Motera', 'Barabati Stadium',
'Brabourne Stadium, Mumbai',
'Vidarbha Cricket Association Stadium, Jamtha',
'Himachal Pradesh Cricket Association Stadium', 'Nehru Stadium',
'Holkar Cricket Stadium',
'Dr. Y.S. Rajasekhara Reddy ACA-VDCA Cricket Stadium',
'Subrata Roy Sahara Stadium',
'Maharashtra Cricket Association Stadium',
'Shaheed Veer Narayan Singh International Stadium',
'JSCA International Stadium Complex', 'Sheikh Zayed Stadium',
'Sharjah Cricket Stadium', 'Dubai International Cricket Stadium',
'Punjab Cricket Association IS Bindra Stadium, Mohali',
'Saurashtra Cricket Association Stadium', 'Green Park',
'[Link] Stadium',
'Punjab Cricket Association IS Bindra Stadium',
'Rajiv Gandhi International Stadium', 'MA Chidambaram Stadium',
'Arun Jaitley Stadium', 'MA Chidambaram Stadium, Chepauk, Chennai',
'Wankhede Stadium, Mumbai', 'Narendra Modi Stadium, Ahmedabad',
'Arun Jaitley Stadium, Delhi', 'Zayed Cricket Stadium, Abu Dhabi',
'Dr DY Patil Sports Academy, Mumbai',
'Maharashtra Cricket Association Stadium, Pune',
'Eden Gardens, Kolkata',
'Punjab Cricket Association IS Bindra Stadium, Mohali, Chandigarh',
'Bharat Ratna Shri Atal Bihari Vajpayee Ekana Cricket Stadium, Lucknow',
'Rajiv Gandhi International Stadium, Uppal, Hyderabad',
'M Chinnaswamy Stadium, Bengaluru',
'Barsapara Cricket Stadium, Guwahati',
'Sawai Mansingh Stadium, Jaipur',
'Himachal Pradesh Cricket Association Stadium, Dharamsala',
'Maharaja Yadavindra Singh International Cricket Stadium, New Chandigarh',
'Dr. Y.S. Rajasekhara Reddy ACA-VDCA Cricket Stadium, Visakhapatnam'],
dtype=object)

[Link] 23/28
3/4/26, 9:29 PM 02_data_cleaning

In [270… venue_mapping = {

# Chinnaswamy
"[Link] Stadium": "M Chinnaswamy Stadium, Bengaluru",
"M Chinnaswamy Stadium": "M Chinnaswamy Stadium, Bengaluru",

# Arun Jaitley
"Feroz Shah Kotla": "Arun Jaitley Stadium, Delhi",
"Arun Jaitley Stadium": "Arun Jaitley Stadium, Delhi",

# Chepauk
"MA Chidambaram Stadium": "MA Chidambaram Stadium, Chepauk, Chennai",
"MA Chidambaram Stadium, Chepauk": "MA Chidambaram Stadium, Chepauk, Chennai",

# Punjab
"Punjab Cricket Association Stadium, Mohali":
"Punjab Cricket Association IS Bindra Stadium, Mohali, Chandigarh",
"Punjab Cricket Association IS Bindra Stadium":
"Punjab Cricket Association IS Bindra Stadium, Mohali, Chandigarh",
"Punjab Cricket Association IS Bindra Stadium, Mohali":
"Punjab Cricket Association IS Bindra Stadium, Mohali, Chandigarh",

# Rajiv Gandhi
"Rajiv Gandhi International Stadium":
"Rajiv Gandhi International Stadium, Uppal, Hyderabad",
"Rajiv Gandhi International Stadium, Uppal":
"Rajiv Gandhi International Stadium, Uppal, Hyderabad",

# Wankhede
"Wankhede Stadium":
"Wankhede Stadium, Mumbai",

# Eden
"Eden Gardens":
"Eden Gardens, Kolkata",

# DY Patil
"Dr DY Patil Sports Academy":
"Dr DY Patil Sports Academy, Mumbai",

[Link] 24/28
3/4/26, 9:29 PM 02_data_cleaning

# MCA Pune
"Maharashtra Cricket Association Stadium":
"Maharashtra Cricket Association Stadium, Pune",

# HPCA
"Himachal Pradesh Cricket Association Stadium":
"Himachal Pradesh Cricket Association Stadium, Dharamsala"
}

In [271… df["venue"] = df["venue"].replace(venue_mapping)

In [272… df['venue'].unique()

[Link] 25/28
3/4/26, 9:29 PM 02_data_cleaning

Out[272… array(['M Chinnaswamy Stadium, Bengaluru',

'Punjab Cricket Association IS Bindra Stadium, Mohali, Chandigarh',
'Arun Jaitley Stadium, Delhi', 'Wankhede Stadium, Mumbai',
'Eden Gardens, Kolkata', 'Sawai Mansingh Stadium',
'Rajiv Gandhi International Stadium, Uppal, Hyderabad',
'MA Chidambaram Stadium, Chepauk, Chennai',
'Dr DY Patil Sports Academy, Mumbai', 'Newlands',
"St George's Park", 'Kingsmead', 'SuperSport Park', 'Buffalo Park',
'New Wanderers Stadium', 'De Beers Diamond Oval',
'OUTsurance Oval', 'Brabourne Stadium',
'Sardar Patel Stadium, Motera', 'Barabati Stadium',
'Brabourne Stadium, Mumbai',
'Vidarbha Cricket Association Stadium, Jamtha',
'Himachal Pradesh Cricket Association Stadium, Dharamsala',
'Nehru Stadium', 'Holkar Cricket Stadium',
'Dr. Y.S. Rajasekhara Reddy ACA-VDCA Cricket Stadium',
'Subrata Roy Sahara Stadium',
'Maharashtra Cricket Association Stadium, Pune',
'Shaheed Veer Narayan Singh International Stadium',
'JSCA International Stadium Complex', 'Sheikh Zayed Stadium',
'Sharjah Cricket Stadium', 'Dubai International Cricket Stadium',
'Saurashtra Cricket Association Stadium', 'Green Park',
'Narendra Modi Stadium, Ahmedabad',
'Zayed Cricket Stadium, Abu Dhabi',
'Bharat Ratna Shri Atal Bihari Vajpayee Ekana Cricket Stadium, Lucknow',
'Barsapara Cricket Stadium, Guwahati',
'Sawai Mansingh Stadium, Jaipur',
'Maharaja Yadavindra Singh International Cricket Stadium, New Chandigarh',
'Dr. Y.S. Rajasekhara Reddy ACA-VDCA Cricket Stadium, Visakhapatnam'],
dtype=object)

In [273… df['city'].unique()

[Link] 26/28
3/4/26, 9:29 PM 02_data_cleaning

Out[273… array(['Bangalore', 'Chandigarh', 'Delhi', 'Mumbai', 'Kolkata', 'Jaipur',

'Hyderabad', 'Chennai', 'Cape Town', 'Port Elizabeth', 'Durban',
'Centurion', 'East London', 'Johannesburg', 'Kimberley',
'Bloemfontein', 'Ahmedabad', 'Cuttack', 'Nagpur', 'Dharamsala',
'Kochi', 'Indore', 'Visakhapatnam', 'Pune', 'Raipur', 'Ranchi',
'Abu Dhabi', 'Unknown', 'Rajkot', 'Kanpur', 'Bengaluru', 'Dubai',
'Sharjah', 'Navi Mumbai', 'Lucknow', 'Guwahati', 'Mohali',
'New Chandigarh'], dtype=object)

In [274… city_mapping = {
"Bangalore": "Bengaluru",
"Chandigarh": "Mohali"
}

df["city"] = df["city"].replace(city_mapping)

In [275… df["city"].unique()

Out[275… array(['Bengaluru', 'Mohali', 'Delhi', 'Mumbai', 'Kolkata', 'Jaipur',

'Hyderabad', 'Chennai', 'Cape Town', 'Port Elizabeth', 'Durban',
'Centurion', 'East London', 'Johannesburg', 'Kimberley',
'Bloemfontein', 'Ahmedabad', 'Cuttack', 'Nagpur', 'Dharamsala',
'Kochi', 'Indore', 'Visakhapatnam', 'Pune', 'Raipur', 'Ranchi',
'Abu Dhabi', 'Unknown', 'Rajkot', 'Kanpur', 'Dubai', 'Sharjah',
'Navi Mumbai', 'Lucknow', 'Guwahati', 'New Chandigarh'],
dtype=object)

In [362… df[df["city"] == "Unknown"]["venue"].value_counts()

Out[362… venue
Dubai International Cricket Stadium 8080
Sharjah Cricket Stadium 4317
Name: count, dtype: int64

In [364… city_fill_mapping = {
"Dubai International Cricket Stadium": "Dubai",
"Sharjah Cricket Stadium": "Sharjah",
"Zayed Cricket Stadium, Abu Dhabi": "Abu Dhabi",
"Sheikh Zayed Stadium": "Abu Dhabi"
}

[Link] 27/28
3/4/26, 9:29 PM 02_data_cleaning

df["city"] = df["city"].replace("Unknown", [Link])

df["city"] = df["venue"].map(city_fill_mapping).fillna(df["city"])

In [366… df[df["city"].isna()]["venue"].value_counts()

Out[366… Series([], Name: count, dtype: int64)

In [368… df.to_csv(r"C:\Users\LENOVO\Downloads\mywork\Ipl_Analysis\/data/ipl_cleaned.csv", index=False)

In [ ]:

[Link] 28/28