Professional Documents
Culture Documents
23 - Jupyter Notebook
In [2]:
38
1
5
32
2
33
37
35
12
16
In [3]:
1 import pandas as pd
2 df=pd.read_csv('IPL_Matches_2008_2022.csv')
3 df
Out[3]:
Narend
2022- Rajasthan Gujarat Mo
0 1312200 Ahmedabad 2022 Final
05-29 Royals Titans Stadiu
Ahmedab
Narend
Royal
2022- Rajasthan Mo
1 1312199 Ahmedabad 2022 Qualifier 2 Challengers
05-27 Royals Stadiu
Bangalore
Ahmedab
Royal Lucknow Ed
2022-
2 1312198 Kolkata 2022 Eliminator Challengers Super Garden
05-25
Bangalore Giants Kolka
Ed
2022- Rajasthan Gujarat
3 1312197 Kolkata 2022 Qualifier 1 Garden
05-24 Royals Titans
Kolka
Wankhe
2022- Sunrisers Punjab
4 1304116 Mumbai 2022 70 Stadiu
05-22 Hyderabad Kings
Mumb
Kolkata
2008- Deccan Ed
945 335986 Kolkata 2007/08 4 Knight
04-20 Chargers Garde
Riders
Royal
2008- Mumbai Wankhe
946 335985 Mumbai 2007/08 5 Challengers
04-20 Indians Stadiu
Bangalore
Punj
Chennai Crick
2008- Kings XI
948 335983 Chandigarh 2007/08 2 Super Associati
04-19 Punjab
Kings Stadiu
Moh
Royal Kolkata
2008-
949 335982 Bangalore 2007/08 1 Challengers Knight Chinnaswam
04-18
Bangalore Riders Stadiu
In [4]:
1 df.columns
Out[4]:
In [5]:
1 df.isnull().sum()
Out[5]:
ID 0
City 51
Date 0
Season 0
MatchNumber 0
Team1 0
Team2 0
Venue 0
TossWinner 0
TossDecision 0
SuperOver 4
WinningTeam 4
WonBy 0
Margin 18
method 931
Player_of_Match 4
Team1Players 0
Team2Players 0
Umpire1 0
Umpire2 0
dtype: int64
In [6]:
1 df['method']=df['method'].fillna('NA')
In [7]:
1 df.isnull().sum()
Out[7]:
ID 0
City 51
Date 0
Season 0
MatchNumber 0
Team1 0
Team2 0
Venue 0
TossWinner 0
TossDecision 0
SuperOver 4
WinningTeam 4
WonBy 0
Margin 18
method 0
Player_of_Match 4
Team1Players 0
Team2Players 0
Umpire1 0
Umpire2 0
dtype: int64
In [9]:
1 df['SuperOver'].isnull()
Out[9]:
0 False
1 False
2 False
3 False
4 False
...
945 False
946 False
947 False
948 False
949 False
Name: SuperOver, Length: 950, dtype: bool
In [10]:
1 df[df['SuperOver'].isnull()]
Out[10]:
Royal
2019- Rajasthan M.Chinnaswam
205 1178424 Bengaluru 2019 49 Challengers
04-30 Royals Stadium
Bangalore
Royal
2015- Delhi M Chinnaswam
437 829813 Bangalore 2015 55 Challengers
05-17 Daredevils Stadium
Bangalore
Royal
2015- Rajasthan M Chinnaswam
464 829763 Bangalore 2015 29 Challengers
04-29 Royals Stadium
Bangalore
In [11]:
1 df=df.drop(df[df['SuperOver'].isnull()].index)
In [12]:
1 df.isnull().sum()
Out[12]:
ID 0
City 51
Date 0
Season 0
MatchNumber 0
Team1 0
Team2 0
Venue 0
TossWinner 0
TossDecision 0
SuperOver 0
WinningTeam 0
WonBy 0
Margin 14
method 0
Player_of_Match 0
Team1Players 0
Team2Players 0
Umpire1 0
Umpire2 0
dtype: int64
In [14]:
1 df['City']=df['City'].fillna(df['Venue'])
In [15]:
1 df.isnull().sum()
Out[15]:
ID 0
City 0
Date 0
Season 0
MatchNumber 0
Team1 0
Team2 0
Venue 0
TossWinner 0
TossDecision 0
SuperOver 0
WinningTeam 0
WonBy 0
Margin 14
method 0
Player_of_Match 0
Team1Players 0
Team2Players 0
Umpire1 0
Umpire2 0
dtype: int64
In [16]:
1 df['Margin']=df['Margin'].fillna(df['Margin'].mean())
In [17]:
1 df.isnull().sum()
Out[17]:
ID 0
City 0
Date 0
Season 0
MatchNumber 0
Team1 0
Team2 0
Venue 0
TossWinner 0
TossDecision 0
SuperOver 0
WinningTeam 0
WonBy 0
Margin 0
method 0
Player_of_Match 0
Team1Players 0
Team2Players 0
Umpire1 0
Umpire2 0
dtype: int64
In [18]:
1 import plotly.express as ex
2 ex.box(data_frame=df,x='Margin')
In [19]:
1 import pandas as pd
2 cars=pd.read_csv('car data.csv')
In [20]:
1 cars
Out[20]:
1 cars['Kms_Driven']/10000
In [22]:
1 cars
Out[22]:
In [24]:
1 newmax=10
2 newmin=1
3 oldmin,oldmax=min(cars['Kms_Driven']),max(cars['Kms_Driven'])
In [25]:
1 cars.shape
Out[25]:
(301, 9)
In [30]:
1 X=[]
2 for i in range(cars.shape[0]):
3 new_x=(cars['Kms_Driven'][i]-oldmin)/(oldmax-oldmin)*(newmax-newmin)+newmin
4 X.append(new_x)
5 X
1.6306306306306306,
1.7376936936936938,
1.4414414414414414,
1.0342342342342343,
1.8918918918918919,
1.8068468468468468,
2.0158378378378377,
1.3513513513513513,
1.9844684684684686,
1.2828828828828829,
1.7935495495495495,
1.8018018018018018,
1.9178198198198197,
1.9675675675675675,
1.6936936936936937,
1.8018018018018018,
1.8018018018018018,
1.8918558558558558,
1.8696756756756756,
3.2792792792792795,
In [31]:
1 cars['New_Kms_Driven']=X
In [32]:
1 cars
Out[32]:
In [33]:
1 min(cars['New_Kms_Driven']),max(cars['New_Kms_Driven'])
Out[33]:
(1.0, 10.0)
In [34]:
1 cars.describe()
Out[34]:
In [ ]:
1 X=[]
2 Mean=36947.205980
3 STD=38886.883882
4 for i in range(cars.shape[0]):
5 new_x=
6 X.append(new_x)
7 X