Explore a pandas Series

Explore a pandas Series

import pandas as pd

movies = pd.read_csv('imdb_1000.csv')

movies.head()

	star_rating	title	content_rating	genre	duration	actors_list
0	9.3	The Shawshank Redemption	R	Crime	142	[u'Tim Robbins', u'Morgan Freeman', u'Bob Gunt...
1	9.2	The Godfather	R	Crime	175	[u'Marlon Brando', u'Al Pacino', u'James Caan']
2	9.1	The Godfather: Part II	R	Crime	200	[u'Al Pacino', u'Robert De Niro', u'Robert Duv...
3	9.0	The Dark Knight	PG-13	Action	152	[u'Christian Bale', u'Heath Ledger', u'Aaron E...
4	8.9	Pulp Fiction	R	Crime	154	[u'John Travolta', u'Uma Thurman', u'Samuel L....

movies.dtypes

star_rating       float64
title              object
content_rating     object
genre              object
duration            int64
actors_list        object
dtype: object

movies.genre

0          Crime
1          Crime
2          Crime
3         Action
4          Crime
         ...    
974       Comedy
975    Adventure
976       Action
977       Horror
978        Crime
Name: genre, Length: 979, dtype: object

movies.genre.describe()

count       979
unique       16
top       Drama
freq        278
Name: genre, dtype: object

movies.genre.value_counts()

Drama        278
Comedy       156
Action       136
Crime        124
Biography     77
Adventure     75
Animation     62
Horror        29
Mystery       16
Western        9
Thriller       5
Sci-Fi         5
Film-Noir      3
Family         2
History        1
Fantasy        1
Name: genre, dtype: int64

movies.genre.value_counts(normalize=True)

Drama        0.283963
Comedy       0.159346
Action       0.138917
Crime        0.126660
Biography    0.078652
Adventure    0.076609
Animation    0.063330
Horror       0.029622
Mystery      0.016343
Western      0.009193
Thriller     0.005107
Sci-Fi       0.005107
Film-Noir    0.003064
Family       0.002043
History      0.001021
Fantasy      0.001021
Name: genre, dtype: float64

type(movies.genre.value_counts())

pandas.core.series.Series

movies.genre.value_counts().head()

Drama        278
Comedy       156
Action       136
Crime        124
Biography     77
Name: genre, dtype: int64

movies.genre.unique()

array(['Crime', 'Action', 'Drama', 'Western', 'Adventure', 'Biography',
       'Comedy', 'Animation', 'Mystery', 'Horror', 'Film-Noir', 'Sci-Fi',
       'History', 'Thriller', 'Family', 'Fantasy'], dtype=object)

movies.genre.nunique()

16

pd.crosstab(movies.genre, movies.content_rating)

content_rating	APPROVED	G	GP	NC-17	NOT RATED	PASSED	PG	PG-13	R	TV-MA	UNRATED	X
genre
Action	3	1	1	0	4	1	11	44	67	0	3	0
Adventure	3	2	0	0	5	1	21	23	17	0	2	0
Animation	3	20	0	0	3	0	25	5	5	0	1	0
Biography	1	2	1	0	1	0	6	29	36	0	0	0
Comedy	9	2	1	1	16	3	23	23	73	0	4	1
Crime	6	0	0	1	7	1	6	4	87	0	11	1
Drama	12	3	0	4	24	1	25	55	143	1	9	1
Family	0	1	0	0	0	0	1	0	0	0	0	0
Fantasy	0	0	0	0	0	0	0	0	1	0	0	0
Film-Noir	1	0	0	0	1	0	0	0	0	0	1	0
History	0	0	0	0	0	0	0	0	0	0	1	0
Horror	2	0	0	1	1	0	1	2	16	0	5	1
Mystery	4	1	0	0	1	0	1	2	6	0	1	0
Sci-Fi	1	0	0	0	0	0	0	1	3	0	0	0
Thriller	1	0	0	0	0	0	1	0	3	0	0	0
Western	1	0	0	0	2	0	2	1	3	0	0	0

movies.duration.describe()

count    979.000000
mean     120.979571
std       26.218010
min       64.000000
25%      102.000000
50%      117.000000
75%      134.000000
max      242.000000
Name: duration, dtype: float64

movies.duration.mean()

120.97957099080695

movies.duration.value_counts()

112    23
113    22
102    20
101    20
129    19
       ..
180     1
177     1
168     1
166     1
64      1
Name: duration, Length: 133, dtype: int64

Bonus time

%matplotlib inline

movies.duration.plot(kind='hist')

<matplotlib.axes._subplots.AxesSubplot at 0x1cc39c5b488>

movies.genre.value_counts().plot(kind='bar')

<matplotlib.axes._subplots.AxesSubplot at 0x1cc3a3ea948>