Pandas part - 02

What is DataFrame?
A Data frame is a two-dimensional data structure, i.e., data is aligned in a tabular fashion
in rows and columns. Pandas DataFrame consists of three principal components, the
data, rows, and columns.
In [ ]: import numpy as np
import pandas as pd

Creating DataFrame
In [ ]: # using lists
student_data = [
[100, 90, 10],
[90, 70, 7],
[120, 100, 14],
[80, 50, 2]
]
pd.DataFrame(student_data, columns=['iq', 'marks', 'package', ])

Out[ ]: iq marks package

0 100 90 10

1 90 70 7

2 120 100 14

3 80 50 2

In [ ]: # using dictionary
student_dict = {
'iq': [100, 90, 80, 120, 0, 0],
'marks': [80, 70, 100, 90, 0, 0],
'package': [10, 7, 14, 2, 0, 0]
}

students = pd.DataFrame(student_dict)
students

Out[ ]: iq marks package

0 100 80 10

1 90 70 7

2 80 100 14

3 120 90 2

4 0 0 0

5 0 0 0

Read CSV
In [ ]: # using read_csv
movies = pd.read_csv('movies.csv')
movies.head()

Out[ ]: title_x imdb_id poster_path

Uri: The
0 Surgical tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wik
Strike

1 Battalion tt9472208 NaN https://en.wikipedia.o

 609

The
Accidental
2 Prime tt6986710 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wiki
Minister
(film)

Why
3 Cheat tt8108208 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/w
India

Evening
4 tt6028796 NaN https://en.wikipedia.org/wi
Shadows

In [ ]: ipl = pd.read_csv('ipl-matches.csv')
ipl.head()

Out[ ]: ID City Date Season MatchNumber Team1 Team2 Venue T

Narendra
2022- Rajasthan Gujarat Modi
0 1312200 Ahmedabad 2022 Final
05-29 Royals Titans Stadium,
Ahmedabad

Narendra
Royal
2022- Rajasthan Modi
1 1312199 Ahmedabad 2022 Qualifier 2 Challengers
05-27 Royals Stadium,
Bangalore
Ahmedabad

Royal Lucknow Eden

2022-
2 1312198 Kolkata 2022 Eliminator Challengers Super Gardens,
05-25
Bangalore Giants Kolkata

Eden
2022- Rajasthan Gujarat
3 1312197 Kolkata 2022 Qualifier 1 Gardens,
05-24 Royals Titans
Kolkata

Wankhede
2022- Sunrisers Punjab
4 1304116 Mumbai 2022 70 Stadium,
05-22 Hyderabad Kings
Mumbai

Shape
In [ ]: # shape
ipl.shape

(950, 20)
Out[ ]:

Column Data Types

In [ ]: # dtypes
movies.dtypes
Out[ ]: title_x object
imdb_id object
poster_path object
wiki_link object
title_y object
original_title object
is_adult int64
year_of_release int64
runtime object
genres object
imdb_rating float64
imdb_votes int64
story object
summary object
tagline object
actors object
wins_nominations object
release_date object
dtype: object

Index
In [ ]: # index
movies.index

RangeIndex(start=0, stop=1629, step=1)

Out[ ]:

Column Names
In [ ]: # columns
movies.columns

Index(['title_x', 'imdb_id', 'poster_path', 'wiki_link', 'title_y',

Out[ ]:
'original_title', 'is_adult', 'year_of_release', 'runtime', 'genre
s',
'imdb_rating', 'imdb_votes', 'story', 'summary', 'tagline', 'actor
s',
'wins_nominations', 'release_date'],
dtype='object')

In [ ]: ipl.columns
Index(['ID', 'City', 'Date', 'Season', 'MatchNumber', 'Team1', 'Team2',
Out[ ]:
'Venue', 'TossWinner', 'TossDecision', 'SuperOver', 'WinningTeam',
'WonBy', 'Margin', 'method', 'Player_of_Match', 'Team1Players',
'Team2Players', 'Umpire1', 'Umpire2'],
dtype='object')

Values
In [ ]: # values -> 2D numpy array
students.values

array([[100, 80, 10],

Out[ ]:
[ 90, 70, 7],
[ 80, 100, 14],
[120, 90, 2],
[ 0, 0, 0],
[ 0, 0, 0]], dtype=int64)

ipl.values
In [ ]:

array([[1312200, 'Ahmedabad', '2022-05-29', ...,

Out[ ]:
"['WP Saha', 'Shubman Gill', 'MS Wade', 'HH Pandya', 'DA Miller',
'R Tewatia', 'Rashid Khan', 'R Sai Kishore', 'LH Ferguson', 'Yash Dayal',
'Mohammed Shami']",
'CB Gaffaney', 'Nitin Menon'],
[1312199, 'Ahmedabad', '2022-05-27', ...,
"['YBK Jaiswal', 'JC Buttler', 'SV Samson', 'D Padikkal', 'SO Het
myer', 'R Parag', 'R Ashwin', 'TA Boult', 'YS Chahal', 'M Prasidh Krishn
a', 'OC McCoy']",
'CB Gaffaney', 'Nitin Menon'],
[1312198, 'Kolkata', '2022-05-25', ...,
"['Q de Kock', 'KL Rahul', 'M Vohra', 'DJ Hooda', 'MP Stoinis',
'E Lewis', 'KH Pandya', 'PVD Chameera', 'Mohsin Khan', 'Avesh Khan', 'Rav
i Bishnoi']",
'J Madanagopal', 'MA Gough'],
...,
[335984, 'Delhi', '2008-04-19', ...,
"['T Kohli', 'YK Pathan', 'SR Watson', 'M Kaif', 'DS Lehmann', 'R
A Jadeja', 'M Rawat', 'D Salunkhe', 'SK Warne', 'SK Trivedi', 'MM Pate
l']",
'Aleem Dar', 'GA Pratapkumar'],
[335983, 'Chandigarh', '2008-04-19', ...,
"['PA Patel', 'ML Hayden', 'MEK Hussey', 'MS Dhoni', 'SK Raina',
'JDP Oram', 'S Badrinath', 'Joginder Sharma', 'P Amarnath', 'MS Gony', 'M
Muralitharan']",
'MR Benson', 'SL Shastri'],
[335982, 'Bangalore', '2008-04-18', ...,
"['SC Ganguly', 'BB McCullum', 'RT Ponting', 'DJ Hussey', 'Mohamm
ad Hafeez', 'LR Shukla', 'WP Saha', 'AB Agarkar', 'AB Dinda', 'M Kartik',
'I Sharma']",
'Asad Rauf', 'RE Koertzen']], dtype=object)

head and tail

In [ ]: # head and tail
movies.head(1)

Out[ ]: title_x imdb_id poster_path

Uri: The
0 Surgical tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wiki/U
Strike

In [ ]: movies.tail(3)

Out[ ]: title_x imdb_id poster_path

Sabse
1626 Bada tt0069204 NaN https://en.wikipedia.org
Sukh

1627 Daaka tt10833860 https://upload.wikimedia.org/wikipedia/en/thum... https://en.

 1628 Humsafar tt2403201 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wik

sample - Random Data

In [ ]: # sample -> random data
ipl.sample(5)

Out[ ]: ID City Date Season MatchNumber Team1 Team2 V

Dr DY
Kolkata
2022- Gujarat S
39 1304081 Navi Mumbai 2022 35 Knight
04-23 Titans Aca
Riders
M

Royal
2008- Kings XI
925 336006 Bangalore 2007/08 25 Challengers Chinnas
05-05 Punjab
Bangalore Sta

2010- Deccan Delhi Ba

820 419120 Cuttack 2009/10 15
03-21 Chargers Daredevils Sta

Royal Kolkata
2010-
792 419148 Bangalore 2009/10 43 Challengers Knight Chinnas
04-10
Bangalore Riders Sta

D
Chennai Rajase
2012- Deccan
696 548311 Visakhapatnam 2012 6 Super Reddy
04-07 Chargers
Kings VDCA C

info - information about columns

In [ ]: # info
movies.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1629 entries, 0 to 1628
Data columns (total 18 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 title_x 1629 non-null object
1 imdb_id 1629 non-null object
2 poster_path 1526 non-null object
3 wiki_link 1629 non-null object
4 title_y 1629 non-null object
5 original_title 1629 non-null object
6 is_adult 1629 non-null int64
7 year_of_release 1629 non-null int64
8 runtime 1629 non-null object
9 genres 1629 non-null object
 10 imdb_rating 1629 non-null float64
11 imdb_votes 1629 non-null int64
12 story 1609 non-null object
13 summary 1629 non-null object
14 tagline 557 non-null object
15 actors 1624 non-null object
16 wins_nominations 707 non-null object
17 release_date 1522 non-null object
dtypes: float64(1), int64(3), object(14)
memory usage: 229.2+ KB

describe
In [ ]: # describe -> mathematical summary
movies.describe()

Out[ ]: is_adult year_of_release imdb_rating imdb_votes

count 1629.0 1629.000000 1629.000000 1629.000000

mean 0.0 2010.263966 5.557459 5384.263352

std 0.0 5.381542 1.567609 14552.103231

min 0.0 2001.000000 0.000000 0.000000

25% 0.0 2005.000000 4.400000 233.000000

50% 0.0 2011.000000 5.600000 1000.000000

75% 0.0 2015.000000 6.800000 4287.000000

max 0.0 2019.000000 9.400000 310481.000000

isnull - Checking Null value

In [ ]: # isnull
movies.isnull()

Out[ ]: title_x imdb_id poster_path wiki_link title_y original_title is_adult year_of_release

0 False False False False False False False False

1 False False True False False False False False

2 False False False False False False False False

3 False False False False False False False False

4 False False True False False False False False

... ... ... ... ... ... ... ... ...

1624 False False False False False False False False

1625 False False False False False False False False

1626 False False True False False False False False

1627 False False False False False False False False

1628 False False False False False False False False

1629 rows × 18 columns

 Checking total null value using sum()
In [ ]: movies.isnull().sum()
title_x 0
Out[ ]:
imdb_id 0
poster_path 103
wiki_link 0
title_y 0
original_title 0
is_adult 0
year_of_release 0
runtime 0
genres 0
imdb_rating 0
imdb_votes 0
story 20
summary 0
tagline 1072
actors 5
wins_nominations 922
release_date 107
dtype: int64

duplicated
In [ ]: movies.duplicated().sum()
0
Out[ ]:

In [ ]: students.duplicated()

0 False
Out[ ]:
1 False
2 False
3 False
4 False
5 True
dtype: bool

In [ ]: students.duplicated().sum()
1
Out[ ]:

rename - rename columns name

In [ ]: # rename
students

Out[ ]: iq marks package

0 100 80 10

1 90 70 7

2 80 100 14

3 120 90 2

4 0 0 0

5 0 0 0
In [ ]: students.rename(columns={'marks': 'percent', 'package': 'lpa'})

Out[ ]: iq percent lpa

0 100 80 10

1 90 70 7

2 80 100 14

3 120 90 2

4 0 0 0

5 0 0 0

For permanent change using inplace = True

In [ ]: # for permanent change
students.rename(columns={'marks': 'percent', 'package': 'lpa'}, inplace=T
students

Out[ ]: iq percent lpa

0 100 80 10

1 90 70 7

2 80 100 14

3 120 90 2

4 0 0 0

5 0 0 0

Math Methods
In [ ]: # sum -> axis argument
movies.sum() # concatinate the string and sum the integer and float

C:\Users\dhanr\AppData\Local\Temp\ipykernel_11868\2393232322.py:2: Future
Warning: Dropping of nuisance columns in DataFrame reductions (with 'nume
ric_only=None') is deprecated; in a future version this will raise TypeEr
ror. Select only valid columns before calling the reduction.
movies.sum() # concatinate the string and sum the integer and float
title_x Uri: The Surgical StrikeBattalion 609The Accid...
Out[ ]:
imdb_id tt8291224tt9472208tt6986710tt8108208tt6028796t...
wiki_link https://en.wikipedia.org/wiki/Uri:_The_Surgica...
title_y Uri: The Surgical StrikeBattalion 609The Accid...
original_title Uri: The Surgical StrikeBattalion 609The Accid...
is_adult 0
year_of_release 3274720
runtime 1381311121211029710910414812013415314313014311...
genres Action|Drama|WarWarBiography|DramaCrime|DramaD...
imdb_rating 9053.1
imdb_votes 8770965
summary Indian army special forces execute a covert op...
dtype: object

In [ ]: students
Out[ ]: iq percent lpa

0 100 80 10

1 90 70 7

2 80 100 14

3 120 90 2

4 0 0 0

5 0 0 0

sum of columns
In [ ]: # sum of columns
students.sum()

iq 390
Out[ ]:
percent 340
lpa 33
dtype: int64

Sum of rows

In [ ]: # sum of rows
students.sum(axis=1)

0 190
Out[ ]:
1 167
2 194
3 212
4 0
5 0
dtype: int64

Mean
In [ ]: # mean of cols
students.mean()

iq 65.000000
Out[ ]:
percent 56.666667
lpa 5.500000
dtype: float64

In [ ]: # mean of rows
students.mean(axis=1)

0 63.333333
Out[ ]:
1 55.666667
2 64.666667
3 70.666667
4 0.000000
5 0.000000
dtype: float64

min = minimum
In [ ]: # min of cols
 students.min()

iq 0
Out[ ]:
percent 0
lpa 0
dtype: int64

In [ ]: # min of rows
students.min(axis=1)

0 10
Out[ ]:
1 7
2 14
3 2
4 0
5 0
dtype: int64

Selecting cols from a DataFrame

In [ ]: # single cols
movies['title_x']

0 Uri: The Surgical Strike

Out[ ]:
1 Battalion 609
2 The Accidental Prime Minister (film)
3 Why Cheat India
4 Evening Shadows
...
1624 Tera Mera Saath Rahen
1625 Yeh Zindagi Ka Safar
1626 Sabse Bada Sukh
1627 Daaka
1628 Humsafar
Name: title_x, Length: 1629, dtype: object

In [ ]: movies.columns

Index(['title_x', 'imdb_id', 'poster_path', 'wiki_link', 'title_y',

Out[ ]:
'original_title', 'is_adult', 'year_of_release', 'runtime', 'genre
s',
'imdb_rating', 'imdb_votes', 'story', 'summary', 'tagline', 'actor
s',
'wins_nominations', 'release_date'],
dtype='object')

In [ ]: # multiple cols
movies[['title_x', 'year_of_release', 'actors']]

Out[ ]: title_x year_of_release actors

Vicky Kaushal|Paresh Rawal|Mohit

0 Uri: The Surgical Strike 2019
Raina|Yami Ga...

Vicky Ahuja|Shoaib Ibrahim|Shrikant

1 Battalion 609 2019
Kamat|Elen...

The Accidental Prime Anupam Kher|Akshaye Khanna|Aahana

2 2019
Minister (film) Kumra|Atul S...

Emraan Hashmi|Shreya
3 Why Cheat India 2019
Dhanwanthary|Snighdadeep ...

Mona Ambegaonkar|Ananth Narayan

4 Evening Shadows 2018
Mahadevan|Deva...
 ... ... ... ...

Ajay Devgn|Sonali Bendre|Namrata

1624 Tera Mera Saath Rahen 2001
Shirodkar|Pre...

Ameesha Patel|Jimmy Sheirgill|Nafisa

1625 Yeh Zindagi Ka Safar 2001
Ali|Gulsh...

Vijay Arora|Asrani|Rajni Bala|Kumud

1626 Sabse Bada Sukh 2018
Damle|Utpa...

1627 Daaka 2019 Gippy Grewal|Zareen Khan|

1628 Humsafar 2011 Fawad Khan|

1629 rows × 3 columns

Selecting rows from a DataFrame

iloc - searches using index position
loc - searches using index labels

In [ ]: student_dict = {
'name': ['nitish', 'rupesh', 'rishabh', 'amit', 'ankita', 'suresh'],
'iq': [100, 90, 80, 120, 0, 0],
'marks': [80, 70, 100, 90, 0, 0],
'package': [10, 7, 14, 2, 0, 0]
}

students = pd.DataFrame(student_dict)
students.set_index('name', inplace=True)
students

Out[ ]: iq marks package

name

nitish 100 80 10

rupesh 90 70 7

rishabh 80 100 14

amit 120 90 2

ankita 0 0 0

suresh 0 0 0

In [ ]: # single row
movies.iloc[0]

title_x Uri: The Surgical Strike

Out[ ]:
imdb_id tt8291224
poster_path https://upload.wikimedia.org/wikipedia/en/thum...
wiki_link https://en.wikipedia.org/wiki/Uri:_The_Surgica...
title_y Uri: The Surgical Strike
original_title Uri: The Surgical Strike
is_adult 0
year_of_release 2019
runtime 138
genres Action|Drama|War
imdb_rating 8.4
imdb_votes 35112
story Divided over five chapters the film chronicle...
 summary Indian army special forces execute a covert op...
tagline NaN
actors Vicky Kaushal|Paresh Rawal|Mohit Raina|Yami Ga...
wins_nominations 4 wins
release_date 11 January 2019 (USA)
Name: 0, dtype: object

In [ ]: # multiple row
movies.iloc[0:5]

Out[ ]: title_x imdb_id poster_path

Uri: The
0 Surgical tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wik
Strike

Battalion
1 tt9472208 NaN https://en.wikipedia.o
609

The
Accidental
2 Prime tt6986710 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wiki
Minister
(film)

Why
3 Cheat tt8108208 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/w
India

Evening
4 tt6028796 NaN https://en.wikipedia.org/wi
Shadows

In [ ]: movies.iloc[0:10:2]

Out[ ]: title_x imdb_id poster_path

Uri: The
0 Surgical tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/w
Strike

The
Accidental
2 Prime tt6986710 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/w
Minister
(film)

Evening
4 tt6028796 NaN https://en.wikipedia.org/
Shadows

6 Fraud tt5013008 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.o

Saiyaan
 Manikarnika:
8 The Queen tt6903440 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/w
of Jhansi

In [ ]: students.loc['nitish']
iq 100
Out[ ]:
marks 80
package 10
Name: nitish, dtype: int64

In [ ]: students.loc['nitish':'rishabh']

Out[ ]: iq marks package

name

nitish 100 80 10

rupesh 90 70 7

rishabh 80 100 14

In [ ]: # slicing row and columns using iloc

movies.iloc[0:3, 0:3]

Out[ ]: title_x imdb_id poster_path

0 Uri: The Surgical Strike tt8291224 https://upload.wikimedia.org/wikipedia/en/thum...

1 Battalion 609 tt9472208 NaN

The Accidental Prime Minister

2 tt6986710 https://upload.wikimedia.org/wikipedia/en/thum...
(film)

In [ ]: # slicing row and columns using loc

movies.loc[0:3, 'title_x': 'poster_path']

Out[ ]: title_x imdb_id poster_path

0 Uri: The Surgical Strike tt8291224 https://upload.wikimedia.org/wikipedia/en/thum...

1 Battalion 609 tt9472208 NaN

The Accidental Prime Minister

2 tt6986710 https://upload.wikimedia.org/wikipedia/en/thum...
(film)

3 Why Cheat India tt8108208 https://upload.wikimedia.org/wikipedia/en/thum...

Task
In [ ]: ipl.head()

Out[ ]: ID City Date Season MatchNumber Team1 Team2 Venue T

Narendra
2022- Rajasthan Gujarat Modi
0 1312200 Ahmedabad 2022 Final
05-29 Royals Titans Stadium,
Ahmedabad
 1 1312199 Ahmedabad 2022- 2022 Qualifier 2 Royal Rajasthan Narendra
05-27 Challengers Royals Modi
Bangalore Stadium,
Ahmedabad

Royal Lucknow Eden

2022-
2 1312198 Kolkata 2022 Eliminator Challengers Super Gardens,
05-25
Bangalore Giants Kolkata

Eden
2022- Rajasthan Gujarat
3 1312197 Kolkata 2022 Qualifier 1 Gardens,
05-24 Royals Titans
Kolkata

Wankhede
2022- Sunrisers Punjab
4 1304116 Mumbai 2022 70 Stadium,
05-22 Hyderabad Kings
Mumbai

In [ ]: # find all the final winners

ipl[ipl['MatchNumber'] == 'Final'][['WinningTeam', 'Season']]

Out[ ]: WinningTeam Season

0 Gujarat Titans 2022

74 Chennai Super Kings 2021

134 Mumbai Indians 2020/21

194 Mumbai Indians 2019

254 Chennai Super Kings 2018

314 Mumbai Indians 2017

373 Sunrisers Hyderabad 2016

433 Mumbai Indians 2015

492 Kolkata Knight Riders 2014

552 Mumbai Indians 2013

628 Kolkata Knight Riders 2012

702 Chennai Super Kings 2011

775 Chennai Super Kings 2009/10

835 Deccan Chargers 2009

892 Rajasthan Royals 2007/08

In [ ]: # how many super over finishes have occures

ipl[ipl['SuperOver'] == 'Y'].shape[0]

14
Out[ ]:

In [ ]: # how many matches csk won in kolkata

ipl[(ipl['City'] == 'Kolkata') & (
ipl['WinningTeam'] == 'Chennai Super Kings')].shape[0]

5
Out[ ]:

In [ ]: # toss winner is match winner in percentage

ipl[ipl['TossWinner'] == ipl['WinningTeam']].shape[0]
Out[ ]: 489

In [ ]: ((ipl[ipl['TossWinner'] ==
ipl['WinningTeam']].shape[0])/(ipl.shape[0])) * 100

51.473684210526315
Out[ ]:

In [ ]: movies.head(2)

Out[ ]: title_x imdb_id poster_path

Uri: The
0 Surgical tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wiki/U
Strike

Battalion
1 tt9472208 NaN https://en.wikipedia.org/
609

In [ ]: # movies with rating higher than 8 and votes > 10000

movies[(movies['imdb_rating'] > 8) & (movies['imdb_votes'] > 10000)
][['title_x', 'imdb_votes', 'imdb_rating']]

Out[ ]: title_x imdb_votes imdb_rating

0 Uri: The Surgical Strike 35112 8.4

11 Gully Boy 22440 8.2

37 Article 15 (film) 13417 8.3

40 Super 30 (film) 13972 8.2

143 Tumbbad 16535 8.2

146 Andhadhun 51615 8.4

325 Pink (2016 film) 33902 8.2

354 Dangal (film) 131338 8.4

418 Masaan 19904 8.1

426 Drishyam (2015 film) 58340 8.2

436 Talvar (film) 26612 8.2

469 Queen (2014 film) 56406 8.2

536 Haider (film) 46912 8.1

566 Ugly (film) 17483 8.1

567 PK (film) 143605 8.1

589 Vishwaroopam 38016 8.2

612 Bhaag Milkha Bhaag 56205 8.2

638 Shahid (film) 13537 8.3

668 Paan Singh Tomar (film) 29994 8.2

 669 Kahaani 53181 8.1

693 Gangs of Wasseypur 71636 8.2

694 Gangs of Wasseypur – Part 2 71636 8.2

709 Barfi! 70443 8.1

714 OMG – Oh My God! 46072 8.2

778 Zindagi Na Milegi Dobara 60826 8.1

869 Udaan (2010 film) 39567 8.2

912 3 Idiots 310481 8.4

930 Gulaal (film) 12799 8.1

1058 Black Friday (2007 film) 16761 8.5

1066 Chak De! India 68421 8.2

1127 Taare Zameen Par 148498 8.4

1180 Khosla Ka Ghosla 20538 8.3

1183 Lage Raho Munna Bhai 39486 8.1

1188 Omkara (2006 film) 17594 8.1

1195 Rang De Basanti 103071 8.2

1223 Black (2005 film) 31658 8.2

1252 Iqbal (film) 14864 8.1

1384 Swades 76737 8.2

1403 Munna Bhai M.B.B.S. 67148 8.1

1554 The Legend of Bhagat Singh 13455 8.1

1567 Lagaan 95686 8.1

1568 Lagaan 95686 8.1

1571 Dil Chahta Hai 62313 8.1

In [ ]: # Action movies with rating higher than 7.5

mask1 = movies[movies['genres'].str.split('|').apply(lambda x: 'Action' i
mask1[mask1['imdb_rating'] > 7.5]

Out[ ]: title_x imdb_id poster_path

Uri: The
0 tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipe
Surgical Strike

Family of
41 tt8897986 https://upload.wikimedia.org/wikipedia/en/9/99... https://en.wikiped
Thakurganj

84 Mukkabaaz tt7180544 https://upload.wikimedia.org/wikipedia/en/thum... https://en

106 Raazi tt7098658 https://upload.wikimedia.org/wikipedia/en/thum... htt

110 Parmanu: The tt6826438 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Story of
Pokhran

Bhavesh Joshi
112 tt6129302 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedi
Superhero

The Ghazi
169 tt6299040 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
Attack

Raag Desh
219 tt6080746 https://upload.wikimedia.org/wikipedia/en/thum... https://e
(film)

258 Irudhi Suttru tt5310090 https://upload.wikimedia.org/wikipedia/en/f/fe... https://en.wik

280 Laal Rang tt5600714 NaN https://e

297 Udta Punjab tt4434004 https://upload.wikimedia.org/wikipedia/en/thum... https://en.

354 Dangal (film) tt5074352 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

Bajrangi
362 tt3863552 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikip
Bhaijaan

Baby (2015
365 tt3848892 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
Hindi film)

Detective
393 Byomkesh tt3447364 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
Bakshy!

449 Titli (2014 film) tt3019620 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wik

536 Haider (film) tt3390572 https://upload.wikimedia.org/wikipedia/en/thum... https://en.

589 Vishwaroopam tt2199711 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped

625 Madras Cafe tt2855648 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

Paan Singh
668 tt1620933 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Tomar (film)

Gangs of
693 tt1954470 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Wasseypur

Gangs of
694 Wasseypur – tt1954470 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Part 2

982 Jodhaa Akbar tt0449994 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

1971 (2007
1039 tt0983990 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikip
film)

Black Friday
1058 tt0400234 https://upload.wikimedia.org/wikipedia/en/5/58... https://en.wikipe
(2007 film)

Omkara (2006
1188 tt0488414 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
film)

Sarkar (2005
1293 tt0432047 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipe
film)

1294 Sehar tt0477857 https://upload.wikimedia.org/wikipedia/en/thum... http

1361 Lakshya (film) tt0323013 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

1432 Gangaajal tt0373856 https://upload.wikimedia.org/wikipedia/en/thum... https://e

 Company
1495 tt0296574 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wik
(film)

The Legend of
1554 tt0319736 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Bhagat Singh

Nayak (2001
1607 tt0291376 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedi
Hindi film)

In [ ]: # another method
mask1 = movies['genres'].str.contains('Action')
mask2 = movies['imdb_rating'] > 7.5
movies[mask1 & mask2]

Out[ ]: title_x imdb_id poster_path

Uri: The
0 tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipe
Surgical Strike

Family of
41 tt8897986 https://upload.wikimedia.org/wikipedia/en/9/99... https://en.wikiped
Thakurganj

84 Mukkabaaz tt7180544 https://upload.wikimedia.org/wikipedia/en/thum... https://en

106 Raazi tt7098658 https://upload.wikimedia.org/wikipedia/en/thum... htt

Parmanu: The
110 Story of tt6826438 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Pokhran

Bhavesh Joshi
112 tt6129302 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedi
Superhero

The Ghazi
169 tt6299040 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
Attack

Raag Desh
219 tt6080746 https://upload.wikimedia.org/wikipedia/en/thum... https://e
(film)

258 Irudhi Suttru tt5310090 https://upload.wikimedia.org/wikipedia/en/f/fe... https://en.wik

280 Laal Rang tt5600714 NaN https://e

297 Udta Punjab tt4434004 https://upload.wikimedia.org/wikipedia/en/thum... https://en.

354 Dangal (film) tt5074352 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

Bajrangi
362 tt3863552 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikip
Bhaijaan

Baby (2015
365 tt3848892 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
Hindi film)

Detective
393 Byomkesh tt3447364 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
Bakshy!

449 Titli (2014 film) tt3019620 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wik

536 Haider (film) tt3390572 https://upload.wikimedia.org/wikipedia/en/thum... https://en.

589 Vishwaroopam tt2199711 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped

625 Madras Cafe tt2855648 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

Paan Singh
668 tt1620933 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Tomar (film)

693 Gangs of tt1954470 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia

Wasseypur
 Gangs of
694 Wasseypur – tt1954470 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Part 2

982 Jodhaa Akbar tt0449994 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

1971 (2007
1039 tt0983990 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikip
film)

Black Friday
1058 tt0400234 https://upload.wikimedia.org/wikipedia/en/5/58... https://en.wikipe
(2007 film)

Omkara (2006
1188 tt0488414 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikiped
film)

Sarkar (2005
1293 tt0432047 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipe
film)

1294 Sehar tt0477857 https://upload.wikimedia.org/wikipedia/en/thum... http

1361 Lakshya (film) tt0323013 https://upload.wikimedia.org/wikipedia/en/thum... https://en.w

1432 Gangaajal tt0373856 https://upload.wikimedia.org/wikipedia/en/thum... https://e

Company
1495 tt0296574 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wik
(film)

The Legend of
1554 tt0319736 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia
Bhagat Singh

Nayak (2001
1607 tt0291376 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedi
Hindi film)

Adding new cols

In [ ]: # completely new
movies['country'] = 'India'
movies.head()

Out[ ]: title_x imdb_id poster_path

Uri: The
0 Surgical tt8291224 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wik
Strike

Battalion
1 tt9472208 NaN https://en.wikipedia.o
609

The
Accidental
2 Prime tt6986710 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wiki
Minister
(film)

Why
3 Cheat tt8108208 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/w
India

Evening
4 tt6028796 NaN https://en.wikipedia.org/wi
Shadows

In [ ]: # from existing col

movies.isnull().sum()

title_x 0
Out[ ]:
imdb_id 0
poster_path 103
wiki_link 0
title_y 0
original_title 0
is_adult 0
year_of_release 0
runtime 0
genres 0
imdb_rating 0
imdb_votes 0
story 20
summary 0
tagline 1072
actors 5
wins_nominations 922
release_date 107
country 0
dtype: int64

In [ ]: movies.dropna(inplace=True)

In [ ]: movies['lead actor'] = movies['actors'].str.split('|').apply(lambda x: x[

movies.head()
Out[ ]: title_x imdb_id poster_path

Gully
11 tt2395469 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.o
Boy

Yeh
34 Hai tt5525846 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/w
India

Article
37 15 tt10324144 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wik
(film)

87 Aiyaary tt6774212 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedi

Raid
96 (2018 tt7363076 https://upload.wikimedia.org/wikipedia/en/thum... https://en.wikipedia.org/wiki
film)

astype - change column type

In [ ]: # astype
ipl.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 950 entries, 0 to 949
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ID 950 non-null int64
1 City 899 non-null object
2 Date 950 non-null object
3 Season 950 non-null object
4 MatchNumber 950 non-null object
5 Team1 950 non-null object
6 Team2 950 non-null object
7 Venue 950 non-null object
8 TossWinner 950 non-null object
9 TossDecision 950 non-null object
10 SuperOver 946 non-null object
11 WinningTeam 946 non-null object
12 WonBy 950 non-null object
13 Margin 932 non-null float64
14 method 19 non-null object
15 Player_of_Match 946 non-null object
16 Team1Players 950 non-null object
17 Team2Players 950 non-null object
18 Umpire1 950 non-null object
19 Umpire2 950 non-null object
 dtypes: float64(1), int64(1), object(18)
memory usage: 148.6+ KB

In [ ]: ipl['ID'] = ipl['ID'].astype('Int32')
ipl.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 950 entries, 0 to 949
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ID 950 non-null Int32
1 City 899 non-null object
2 Date 950 non-null object
3 Season 950 non-null object
4 MatchNumber 950 non-null object
5 Team1 950 non-null object
6 Team2 950 non-null object
7 Venue 950 non-null object
8 TossWinner 950 non-null object
9 TossDecision 950 non-null object
10 SuperOver 946 non-null object
11 WinningTeam 946 non-null object
12 WonBy 950 non-null object
13 Margin 932 non-null float64
14 method 19 non-null object
15 Player_of_Match 946 non-null object
16 Team1Players 950 non-null object
17 Team2Players 950 non-null object
18 Umpire1 950 non-null object
19 Umpire2 950 non-null object
dtypes: Int32(1), float64(1), object(18)
memory usage: 145.8+ KB