Day 6. Simple visualization with pandas

from pandas import *

In [2]:

df = read_csv("./ml/movies.csv", sep = ",")

In [4]:

df.head()

Out[4]:

	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 [6]:

df.plot.bar()

Out[6]:

<matplotlib.axes._subplots.AxesSubplot at 0x7ff7b2355e48>

In [8]:

df.plot.box()

Out[8]:

<matplotlib.axes._subplots.AxesSubplot at 0x7ff7a3f3bef0>

In [9]:

df.plot.hist()

Out[9]:

<matplotlib.axes._subplots.AxesSubplot at 0x7ff7a3feb0f0>

In [10]:

df.plot()

Out[10]:

<matplotlib.axes._subplots.AxesSubplot at 0x7ff7a4357f60>

In [12]:

%matplotlib inline # % means it is a magic function

In [13]:

ratings = read_csv("./ml/ratings.csv", sep = ",")
ratings.head()

Out[13]:

	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 [14]:

ratings.describe()

Out[14]:

	userId	movieId	rating	timestamp
count	100836.000000	100836.000000	100836.000000	1.008360e+05
mean	326.127564	19435.295718	3.501557	1.205946e+09
std	182.618491	35530.987199	1.042529	2.162610e+08
min	1.000000	1.000000	0.500000	8.281246e+08
25%	177.000000	1199.000000	3.000000	1.019124e+09
50%	325.000000	2991.000000	3.500000	1.186087e+09
75%	477.000000	8122.000000	4.000000	1.435994e+09
max	610.000000	193609.000000	5.000000	1.537799e+09

In [15]:

ratings.hist(column = 'rating', figsize = (15,10))

Out[15]:

array([[<matplotlib.axes._subplots.AxesSubplot object at 0x7ff7a3dc8358>]],
      dtype=object)

In [16]:

ratings.boxplot(column = "rating", figsize = (15,20))

Out[16]:

<matplotlib.axes._subplots.AxesSubplot at 0x7ff793e789b0>

In [ ]: