Pandas (1) 데이터 정보 확인

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

 

In [2]:

movie = pd.read_csv(r'C:\Users\user\jupyterpractice\EDA\Pandas-Cookbook-master\data\movie.csv')

 

In [3]:

movie.head(3)

 

Out[3]:

	color	director_name	num_critic_for_reviews	duration	director_facebook_likes	actor_3_facebook_likes	actor_2_name	actor_1_facebook_likes	gross	genres	...	num_user_for_reviews	language	country	content_rating	budget	title_year	actor_2_facebook_likes	imdb_score	aspect_ratio	movie_facebook_likes
0	Color	James Cameron	723.0	178.0	0.0	855.0	Joel David Moore	1000.0	760505847.0	Action|Adventure|Fantasy|Sci-Fi	...	3054.0	English	USA	PG-13	237000000.0	2009.0	936.0	7.9	1.78	33000
1	Color	Gore Verbinski	302.0	169.0	563.0	1000.0	Orlando Bloom	40000.0	309404152.0	Action|Adventure|Fantasy	...	1238.0	English	USA	PG-13	300000000.0	2007.0	5000.0	7.1	2.35	0
2	Color	Sam Mendes	602.0	148.0	0.0	161.0	Rory Kinnear	11000.0	200074175.0	Action|Adventure|Thriller	...	994.0	English	UK	PG-13	245000000.0	2015.0	393.0	6.8	2.35	85000

3 rows × 28 columns

 

In [13]:

movie.tail(3)

 

Out[13]:

	color	director_name	num_critic_for_reviews	duration	director_facebook_likes	actor_3_facebook_likes	actor_2_name	actor_1_facebook_likes	gross	genres	...	num_user_for_reviews	language	country	content_rating	budget	title_year	actor_2_facebook_likes	imdb_score	aspect_ratio	movie_facebook_likes
4913	Color	Benjamin Roberds	13.0	76.0	0.0	0.0	Maxwell Moody	0.0	NaN	Drama|Horror|Thriller	...	3.0	English	USA	NaN	1400.0	2013.0	0.0	6.3	NaN	16
4914	Color	Daniel Hsia	14.0	100.0	0.0	489.0	Daniel Henney	946.0	10443.0	Comedy|Drama|Romance	...	9.0	English	USA	PG-13	NaN	2012.0	719.0	6.3	2.35	660
4915	Color	Jon Gunn	43.0	90.0	16.0	16.0	Brian Herzlinger	86.0	85222.0	Documentary	...	84.0	English	USA	PG	1100.0	2004.0	23.0	6.6	1.85	456

3 rows × 28 columns

 

In [4]:

columns = movie.columns
index = movie.index
data = movie.values

 

In [5]:

columns

 

Out[5]:

Index(['color', 'director_name', 'num_critic_for_reviews', 'duration',
       'director_facebook_likes', 'actor_3_facebook_likes', 'actor_2_name',
       'actor_1_facebook_likes', 'gross', 'genres', 'actor_1_name',
       'movie_title', 'num_voted_users', 'cast_total_facebook_likes',
       'actor_3_name', 'facenumber_in_poster', 'plot_keywords',
       'movie_imdb_link', 'num_user_for_reviews', 'language', 'country',
       'content_rating', 'budget', 'title_year', 'actor_2_facebook_likes',
       'imdb_score', 'aspect_ratio', 'movie_facebook_likes'],
      dtype='object')

 

In [6]:

index

 

Out[6]:

RangeIndex(start=0, stop=4916, step=1)

 

In [7]:

data

 

Out[7]:

array([['Color', 'James Cameron', 723.0, ..., 7.9, 1.78, 33000],
       ['Color', 'Gore Verbinski', 302.0, ..., 7.1, 2.35, 0],
       ['Color', 'Sam Mendes', 602.0, ..., 6.8, 2.35, 85000],
       ...,
       ['Color', 'Benjamin Roberds', 13.0, ..., 6.3, nan, 16],
       ['Color', 'Daniel Hsia', 14.0, ..., 6.3, 2.35, 660],
       ['Color', 'Jon Gunn', 43.0, ..., 6.6, 1.85, 456]], dtype=object)

 

In [9]:

print(type(index))
print()
print(type(columns))
print()
print(type(data))

 

<class 'pandas.core.indexes.range.RangeIndex'>

<class 'pandas.core.indexes.base.Index'>

<class 'numpy.ndarray'>

 

In [14]:

issubclass(pd.RangeIndex, pd.Index)

 

Out[14]:

True

 

In [16]:

issubclass(pd.RangeIndex, np.ndarray)

 

Out[16]:

False

 

In [10]:

index.values

 

Out[10]:

array([   0,    1,    2, ..., 4913, 4914, 4915], dtype=int64)

 

In [11]:

columns.values

 

Out[11]:

array(['color', 'director_name', 'num_critic_for_reviews', 'duration',
       'director_facebook_likes', 'actor_3_facebook_likes',
       'actor_2_name', 'actor_1_facebook_likes', 'gross', 'genres',
       'actor_1_name', 'movie_title', 'num_voted_users',
       'cast_total_facebook_likes', 'actor_3_name',
       'facenumber_in_poster', 'plot_keywords', 'movie_imdb_link',
       'num_user_for_reviews', 'language', 'country', 'content_rating',
       'budget', 'title_year', 'actor_2_facebook_likes', 'imdb_score',
       'aspect_ratio', 'movie_facebook_likes'], dtype=object)

 

In [12]:

movie.dtypes

 

Out[12]:

color                         object
director_name                 object
num_critic_for_reviews       float64
duration                     float64
director_facebook_likes      float64
actor_3_facebook_likes       float64
actor_2_name                  object
actor_1_facebook_likes       float64
gross                        float64
genres                        object
actor_1_name                  object
movie_title                   object
num_voted_users                int64
cast_total_facebook_likes      int64
actor_3_name                  object
facenumber_in_poster         float64
plot_keywords                 object
movie_imdb_link               object
num_user_for_reviews         float64
language                      object
country                       object
content_rating                object
budget                       float64
title_year                   float64
actor_2_facebook_likes       float64
imdb_score                   float64
aspect_ratio                 float64
movie_facebook_likes           int64
dtype: object

 

In [17]:

movie.dtypes.value_counts()

 

Out[17]:

float64    13
object     12
int64       3
dtype: int64

 

In [18]:

movie['director_name']

 

Out[18]:

0           James Cameron
1          Gore Verbinski
2              Sam Mendes
3       Christopher Nolan
4             Doug Walker
              ...        
4911          Scott Smith
4912                  NaN
4913     Benjamin Roberds
4914          Daniel Hsia
4915             Jon Gunn
Name: director_name, Length: 4916, dtype: object

 

In [19]:

movie.director_name

 

Out[19]:

0           James Cameron
1          Gore Verbinski
2              Sam Mendes
3       Christopher Nolan
4             Doug Walker
              ...        
4911          Scott Smith
4912                  NaN
4913     Benjamin Roberds
4914          Daniel Hsia
4915             Jon Gunn
Name: director_name, Length: 4916, dtype: object

 

In [20]:

type(movie['director_name'])

 

Out[20]:

pandas.core.series.Series

 

In [21]:

director = movie['director_name']
director.name

 

Out[21]:

'director_name'

 

In [22]:

director.to_frame().head()

 

Out[22]:

	director_name
0	James Cameron
1	Gore Verbinski
2	Sam Mendes
3	Christopher Nolan
4	Doug Walker

 

In [24]:

s_attr_methods = set(dir(pd.Series))
len(s_attr_methods)

 

Out[24]:

433

 

In [27]:

df_attr_methods = set(dir(pd.DataFrame))
len(df_attr_methods)

 

Out[27]:

430

 

In [28]:

len(s_attr_methods & df_attr_methods)

 

Out[28]:

377