In [2]:  import numpy as np

import pandas as pd
import matplotlib.pyplot as plt

In [3]:  df = pd.read_csv("C:\\Users\\Alvin Roy\\Downloads\\NetflixOriginals.csv", encoding='

df

Out[3]:
IMDB
Title Genre Premiere Runtime Language
Score

August 5,
0 Enter the Anime Documentary 58 2.5 English/Japanese
2019

August 21,
1 Dark Forces Thriller 81 2.6 Spanish
2020

Science December
2 The App 79 2.6 Italian
fiction/Drama 26, 2019

January 19,
3 The Open House Horror thriller 94 3.2 English
2018

October 30,
4 Kaali Khuhi Mystery 90 3.4 Hindi
2020

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

Taylor Swift: Reputation December

579 Concert Film 125 8.4 English
Stadium Tour 31, 2018

Winter on Fire: Ukraine's October 9,

580 Documentary 91 8.4 English/Ukranian/Russian
Fight for Freedom 2015

Springsteen on December
581 One-man show 153 8.5 English
Broadway 16, 2018

Emicida: AmarElo - It's All December 8,

582 Documentary 89 8.6 Portuguese
For Yesterday 2020

David Attenborough: A October 4,

583 Documentary 83 9.0 English
Life on Our Planet 2020

584 rows × 6 columns

In [4]:  df.info

Out[4]: <bound method DataFrame.info of Title

Genre \
0 Enter the Anime Documentary
1 Dark Forces Thriller
2 The App Science fiction/Drama
3 The Open House Horror thriller
4 Kaali Khuhi Mystery
.. ... ...
579 Taylor Swift: Reputation Stadium Tour Concert Film
580 Winter on Fire: Ukraine's Fight for Freedom Documentary
581 Springsteen on Broadway One-man show
582 Emicida: AmarElo - It's All For Yesterday Documentary
583 David Attenborough: A Life on Our Planet Documentary

Premiere Runtime IMDB Score Language

0 August 5, 2019 58 2.5 English/Japanese
1 August 21, 2020 81 2.6 Spanish
2 December 26, 2019 79 2.6 Italian
3 January 19, 2018 94 3.2 English
4 October 30, 2020 90 3.4 Hindi
.. ... ... ... ...
579 December 31, 2018 125 8.4 English
580 October 9, 2015 91 8.4 English/Ukranian/Russian
581 December 16, 2018 153 8.5 English
582 December 8, 2020 89 8.6 Portuguese
583 October 4, 2020 83 9.0 English

[584 rows x 6 columns]>

In [5]:  df.describe

Out[5]: <bound method NDFrame.describe of Title

Genre \
0 Enter the Anime Documentary
1 Dark Forces Thriller
2 The App Science fiction/Drama
3 The Open House Horror thriller
4 Kaali Khuhi Mystery
.. ... ...
579 Taylor Swift: Reputation Stadium Tour Concert Film
580 Winter on Fire: Ukraine's Fight for Freedom Documentary
581 Springsteen on Broadway One-man show
582 Emicida: AmarElo - It's All For Yesterday Documentary
583 David Attenborough: A Life on Our Planet Documentary

Premiere Runtime IMDB Score Language

0 August 5, 2019 58 2.5 English/Japanese
1 August 21, 2020 81 2.6 Spanish
2 December 26, 2019 79 2.6 Italian
3 January 19, 2018 94 3.2 English
4 October 30, 2020 90 3.4 Hindi
.. ... ... ... ...
579 December 31, 2018 125 8.4 English
580 October 9, 2015 91 8.4 English/Ukranian/Russian
581 December 16, 2018 153 8.5 English
582 December 8, 2020 89 8.6 Portuguese
583 October 4, 2020 83 9.0 English

[584 rows x 6 columns]>

In [6]:  df.isnull().sum()

Out[6]: Title 0
Genre 0
Premiere 0
Runtime 0
IMDB Score 0
Language 0
dtype: int64

In [7]:  df.columns

Out[7]: Index(['Title', 'Genre', 'Premiere', 'Runtime', 'IMDB Score', 'Language'], dtype

='object')

In [23]:  language=df['Language'].value_counts().sort_values(ascending=False)
language=language[:10]
language

Out[23]: Language
English 401
Hindi 33
Spanish 31
French 20
Italian 14
Portuguese 12
Indonesian 9
Korean 6
Japanese 6
German 5
Name: count, dtype: int64
In [36]:  Genre=df["Genre"].value_counts().sort_values(ascending=False)
Genre=Genre[:10]
Genre

Out[36]: Genre
Documentary 159
Drama 77
Comedy 49
Romantic comedy 39
Thriller 33
Comedy-drama 14
Crime drama 11
Biopic 9
Horror 9
Action 7
Name: count, dtype: int64

In [37]:  plt.plot(language,Genre)
plt.xlabel("Langauge Count")
plt.ylabel("Genre Count")
plt.title("Language vs Genre")

Out[37]: Text(0.5, 1.0, 'Language vs Genre')