IPL

In [133]:

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

In [134]:

matches = pd.read_csv("matches.csv")
matches.drop(axis = 1, columns = ["dl_applied", "umpire1", "umpire2", "umpire3"], inplace = True)
matches.head()

Out[134]:

	id	season	city	date	team1	team2	toss_winner	toss_decision	result	winner	win_by_runs	win_by_wickets	player_of_match	venue
0	1	2017	Hyderabad	2017-04-05	Sunrisers Hyderabad	Royal Challengers Bangalore	Royal Challengers Bangalore	field	normal	Sunrisers Hyderabad	35	0	Yuvraj Singh	Rajiv Gandhi International Stadium, Uppal
1	2	2017	Pune	2017-04-06	Mumbai Indians	Rising Pune Supergiant	Rising Pune Supergiant	field	normal	Rising Pune Supergiant	0	7	SPD Smith	Maharashtra Cricket Association Stadium
2	3	2017	Rajkot	2017-04-07	Gujarat Lions	Kolkata Knight Riders	Kolkata Knight Riders	field	normal	Kolkata Knight Riders	0	10	CA Lynn	Saurashtra Cricket Association Stadium
3	4	2017	Indore	2017-04-08	Rising Pune Supergiant	Kings XI Punjab	Kings XI Punjab	field	normal	Kings XI Punjab	0	6	GJ Maxwell	Holkar Cricket Stadium
4	5	2017	Bangalore	2017-04-08	Royal Challengers Bangalore	Delhi Daredevils	Royal Challengers Bangalore	bat	normal	Royal Challengers Bangalore	15	0	KM Jadhav	M Chinnaswamy Stadium

In [135]:

matches[matches["player_of_match"].isnull()]
matches.drop(index = [300, 545, 570,744], inplace = True)

In [136]:

matches.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 752 entries, 0 to 755
Data columns (total 14 columns):
 #   Column           Non-Null Count  Dtype 
---  ------           --------------  ----- 
 0   id               752 non-null    int64 
 1   season           752 non-null    int64 
 2   city             745 non-null    object
 3   date             752 non-null    object
 4   team1            752 non-null    object
 5   team2            752 non-null    object
 6   toss_winner      752 non-null    object
 7   toss_decision    752 non-null    object
 8   result           752 non-null    object
 9   winner           752 non-null    object
 10  win_by_runs      752 non-null    int64 
 11  win_by_wickets   752 non-null    int64 
 12  player_of_match  752 non-null    object
 13  venue            752 non-null    object
dtypes: int64(4), object(10)
memory usage: 88.1+ KB

In [ ]:

In [137]:

deliveries = pd.read_csv("deliveries.csv")

In [138]:

deliveries["player_dismissed"].fillna(value = "None", inplace = True)
deliveries["dismissal_kind"].fillna(value = "None", inplace = True)
deliveries["fielder"].fillna(value = "None", inplace = True)
deliveries.head()

Out[138]:

	match_id	inning	batting_team	bowling_team	over	ball	batsman	non_striker	bowler	is_super_over	...	bye_runs	legbye_runs	noball_runs	penalty_runs	batsman_runs	extra_runs	total_runs	player_dismissed	dismissal_kind	fielder
0	1	1	Sunrisers Hyderabad	Royal Challengers Bangalore	1	1	DA Warner	S Dhawan	TS Mills	0	...	0	0	0	0	0	0	0	None	None	None
1	1	1	Sunrisers Hyderabad	Royal Challengers Bangalore	1	2	DA Warner	S Dhawan	TS Mills	0	...	0	0	0	0	0	0	0	None	None	None
2	1	1	Sunrisers Hyderabad	Royal Challengers Bangalore	1	3	DA Warner	S Dhawan	TS Mills	0	...	0	0	0	0	4	0	4	None	None	None
3	1	1	Sunrisers Hyderabad	Royal Challengers Bangalore	1	4	DA Warner	S Dhawan	TS Mills	0	...	0	0	0	0	0	0	0	None	None	None
4	1	1	Sunrisers Hyderabad	Royal Challengers Bangalore	1	5	DA Warner	S Dhawan	TS Mills	0	...	0	0	0	0	0	2	2	None	None	None

5 rows × 21 columns

In [139]:

deliveries.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 179078 entries, 0 to 179077
Data columns (total 21 columns):
 #   Column            Non-Null Count   Dtype 
---  ------            --------------   ----- 
 0   match_id          179078 non-null  int64 
 1   inning            179078 non-null  int64 
 2   batting_team      179078 non-null  object
 3   bowling_team      179078 non-null  object
 4   over              179078 non-null  int64 
 5   ball              179078 non-null  int64 
 6   batsman           179078 non-null  object
 7   non_striker       179078 non-null  object
 8   bowler            179078 non-null  object
 9   is_super_over     179078 non-null  int64 
 10  wide_runs         179078 non-null  int64 
 11  bye_runs          179078 non-null  int64 
 12  legbye_runs       179078 non-null  int64 
 13  noball_runs       179078 non-null  int64 
 14  penalty_runs      179078 non-null  int64 
 15  batsman_runs      179078 non-null  int64 
 16  extra_runs        179078 non-null  int64 
 17  total_runs        179078 non-null  int64 
 18  player_dismissed  179078 non-null  object
 19  dismissal_kind    179078 non-null  object
 20  fielder           179078 non-null  object
dtypes: int64(13), object(8)
memory usage: 28.7+ MB

In [140]:

deliveries[deliveries["is_super_over"] != 0].match_id.nunique() # matches with super over

Out[140]:

7

In [141]:

#No. of matches played in each ipl season
plt.figure(figsize = (10,8))
sns.countplot(x = matches.season)
plt.ylabel("No. of matches played")
plt.xlabel("Season");

In [142]:

#no. of matches won by a team
plt.figure(figsize = (12,10))
sns.countplot(x= matches.winner)
plt.xlabel("Teams")
plt.xticks(rotation = 70)
plt.ylabel("Matches won");

In [143]:

#match result- bowl first/bat first (pie)
mt = matches[["toss_decision", "win_by_runs"]]
s = mt[mt["win_by_runs"] > 0].toss_decision.value_counts().sum()
r= ((mt[mt["win_by_runs"] > 0].toss_decision.value_counts()*100/s)).round(1)
plt.figure(figsize = (10,8))
plt.pie(r, autopct ='%1.1f%%', labels = ["Bowl First", "Bat First"]);

In [144]:

#number of matches won by batting or bowlinf first

mini_m = matches[["season", "winner", "toss_decision"]]
mini_m
ht = mini_m.season.value_counts()
plt.figure(figsize = (10,8))
sns.countplot(x = "season", data = mini_m, hue = "toss_decision")
plt.ylabel("Matches Won");

In [145]:

#Toss Decision
plt.figure(figsize = (10,8))
matches.toss_decision.value_counts().plot(kind = "pie", autopct ='%1.1f%%' );

In [146]:

# no. of matches won by toss result
mini_m
plt.figure(figsize = (10,8))
sns.countplot(x = "season", data = mini_m, hue = "toss_decision", palette="Set3")
plt.ylabel("Matches Won");

In [147]:

#top players of the match winner
top_p = matches["player_of_match"].value_counts().head(10)
plt.figure(figsize = (10,8))
plt.xticks(rotation = 90)
color = ["red","green","yellow","violet","blue","brown","silver","pink","black","orange"]
plt.bar(x = top_p.index, height = top_p, color = color);

In [148]:

#no. of fours hit by a player
players = deliveries[["batsman","batsman_runs"]] 
ply_graph = players[players.batsman_runs == 4].batsman.value_counts().head(10)
plt.figure(figsize = (10,8))
plt.xticks(rotation =70)
plt.bar(x = ply_graph.index, height = ply_graph)
plt.xlabel("Players")
plt.ylabel("No. of Four");

In [149]:

#no . of fours hit in each season
m1 = matches[["id","season"]]
m2 = deliveries[["match_id", "batsman_runs"]]
merged = m1.merge(m2, how = "inner", left_on = "id", right_on = "match_id")
m3 =merged[merged["batsman_runs"] == 4]
plt.figure(figsize=(10,8))
sns.countplot(x = "season", data = m3)
plt.xlabel("Seasons")
plt.ylabel("No. of Four");

In [150]:

#number of six hits by a player
ply_graph1 = players[players.batsman_runs == 6].batsman.value_counts().head(10)
plt.figure(figsize = (10,8))
plt.xticks(rotation =70)
plt.bar(x = ply_graph1.index, height = ply_graph1)
plt.xlabel("Players")
plt.ylabel("No. of Six");

In [151]:

#number of six hits in each season
m4 =merged[merged["batsman_runs"] == 6]
plt.figure(figsize=(10,8))
sns.countplot(x = "season", data = m4)
plt.xlabel("Seasons")
plt.ylabel("No. of Four");

In [152]:

#dismissal in ipl
dis = deliveries["dismissal_kind"].value_counts().to_frame().drop("None")
plt.figure(figsize = (10,8))
dis.plot(kind = "bar")
plt.ylabel("Count");

<Figure size 720x576 with 0 Axes>

In [178]:

# ipl most wicket taking bowlers 
blr = deliveries[deliveries.dismissal_kind != "None"]
blr[["bowler", "dismissal_kind"]].value_counts().to_frame().head(10)

Out[178]:

		0
bowler	dismissal_kind
DJ Bravo	caught	113
SL Malinga	caught	91
UT Yadav	caught	89
A Mishra	caught	89
Harbhajan Singh	caught	84
B Kumar	caught	84
R Vinay Kumar	caught	82
R Ashwin	caught	78
A Nehra	caught	76
PP Chawla	caught	72

In [ ]:

In [ ]: