Day 6.Movie Data Analysis Part.2

from pandas import *

In [42]:

ratings.describe()

Out[42]:

	userId	movieId	rating
count	100836.000000	100836.000000	100836.000000
mean	326.127564	19435.295718	3.501557
std	182.618491	35530.987199	1.042529
min	1.000000	1.000000	0.500000
25%	177.000000	1199.000000	3.000000
50%	325.000000	2991.000000	3.500000
75%	477.000000	8122.000000	4.000000
max	610.000000	193609.000000	5.000000

In [44]:

ratings.corr()

Out[44]:

	userId	movieId	rating
userId	1.000000	0.006773	-0.049348
movieId	0.006773	1.000000	-0.004061
rating	-0.049348	-0.004061	1.000000

In [48]:

ratings['rating'].describe()

Out[48]:

count    100836.000000
mean          3.501557
std           1.042529
min           0.500000
25%           3.000000
50%           3.500000
75%           4.000000
max           5.000000
Name: rating, dtype: float64

In [49]:

ratings['rating'].mean()

Out[49]:

3.501556983616962

In [50]:

ratings.mean()

Out[50]:

userId       326.127564
movieId    19435.295718
rating         3.501557
dtype: float64

In [51]:

ratings['rating'].min()

Out[51]:

0.5

In [52]:

ratings['rating'].std()

Out[52]:

1.0425292390605359

In [53]:

ratings['rating'].mode()  # what occur most frequantly

Out[53]:

0    4.0
dtype: float64

In [54]:

ratings.corr()

Out[54]:

	userId	movieId	rating
userId	1.000000	0.006773	-0.049348
movieId	0.006773	1.000000	-0.004061
rating	-0.049348	-0.004061	1.000000

In [56]:

filter_l = ratings['rating'] > 5  # create boolean series
filter_l.any()                    #check if any true in series

Out[56]:

False

In [62]:

movies.shape

Out[62]:

(9742, 3)

In [63]:

movies.head()

Out[63]:

	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

In [65]:

movies.isnull().any()

Out[65]:

movieId    False
title      False
genres     False
dtype: bool

In [66]:

ratings.shape

Out[66]:

(100836, 3)

In [67]:

ratings.isnull().any()

Out[67]:

userId     False
movieId    False
rating     False
dtype: bool

In [68]:

tags.shape

Out[68]:

(3683, 3)

In [69]:

tags.isnull().any()

Out[69]:

userId     False
movieId    False
tag        False
dtype: bool

In [70]:

tags = tags.dropna()
tags.head()

Out[70]:

	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 [ ]: