Day 5.Movie Data Analysis Part.1

!ls

'Day 1.introduction.ipynb'		     'Day 3.Pandas.ipynb'
'Day 2. numpy.ipynb'			      ml
'Day 2. satellite image data analyis.ipynb'   wifire
'Day 3.Movie Data Analysis.ipynb'

In [2]:

!ls ./ml

links.csv  movies.csv  ratings.csv  README.txt	tags.csv

In [4]:

!cat ./ml/movies.csv | wc -l

9743

In [6]:

!head -5 ./ml/movies.csv

In [7]:

!tail -5 ./ml/movies.csv

In [8]:

!head -5 ./ml/ratings.csv

In [10]:

from pandas import *

In [11]:

movies = read_csv('./ml/movies.csv', sep = ',')

In [12]:

type(movies)

Out[12]:

pandas.core.frame.DataFrame

In [14]:

movies.head(15)

Out[14]:

	movieId	title	genres
0	1	Toy Story (1995)	Adventure|Animation|Children|Comedy|Fantasy
1	2	Jumanji (1995)	Adventure|Children|Fantasy
2	3	Grumpier Old Men (1995)	Comedy|Romance
3	4	Waiting to Exhale (1995)	Comedy|Drama|Romance
4	5	Father of the Bride Part II (1995)	Comedy
5	6	Heat (1995)	Action|Crime|Thriller
6	7	Sabrina (1995)	Comedy|Romance
7	8	Tom and Huck (1995)	Adventure|Children
8	9	Sudden Death (1995)	Action
9	10	GoldenEye (1995)	Action|Adventure|Thriller
10	11	American President, The (1995)	Comedy|Drama|Romance
11	12	Dracula: Dead and Loving It (1995)	Comedy|Horror
12	13	Balto (1995)	Adventure|Animation|Children
13	14	Nixon (1995)	Drama
14	15	Cutthroat Island (1995)	Action|Adventure|Romance

In [20]:

tags = read_csv('./ml/tags.csv', sep = ',')
tags.head()

Out[20]:

	userId	movieId	tag	timestamp
0	2	60756	funny	1445714994
1	2	60756	Highly quotable	1445714996
2	2	60756	will ferrell	1445714992
3	2	89774	Boxing story	1445715207
4	2	89774	MMA	1445715200

In [18]:

ratings = read_csv("./ml/ratings.csv", sep = ",", parse_dates =['timestamp'])
ratings.head()

Out[18]:

	userId	movieId	rating	timestamp
0	1	1	4.0	964982703
1	1	3	4.0	964981247
2	1	6	4.0	964982224
3	1	47	5.0	964983815
4	1	50	5.0	964982931

In [24]:

del ratings['timestamp']
del tags['timestamp']

In [25]:

row_0 = tags.iloc[0]
type(row_0)

Out[25]:

pandas.core.series.Series

In [26]:

row_0

Out[26]:

userId         2
movieId    60756
tag        funny
Name: 0, dtype: object

In [28]:

row_0.index

Out[28]:

Index(['userId', 'movieId', 'tag'], dtype='object')

In [29]:

row_0['userId']

Out[29]:

2

In [30]:

'rating' in row_0

Out[30]:

False

In [32]:

tags.head()

Out[32]:

	userId	movieId	tag
0	2	60756	funny
1	2	60756	Highly quotable
2	2	60756	will ferrell
3	2	89774	Boxing story
4	2	89774	MMA

In [33]:

tags.index

Out[33]:

RangeIndex(start=0, stop=3683, step=1)

In [34]:

tags.columns

Out[34]:

Index(['userId', 'movieId', 'tag'], dtype='object')

In [37]:

tags.iloc[[0, 11, 2000]]

Out[37]:

	userId	movieId	tag
0	2	60756	funny
11	18	431	gangster
2000	474	5450	women

In [ ]: