「PythonとJavaScriptではじめるデータビジュアライゼーション」を読む

9.3 インデックスとpandasのデータ選択

#列のカラム名
print(df.columns)
#列数
print(len(df.columns))

Index(['born_in', 'category', 'country', 'date_of_birth', 'date_of_death',
       'gender', 'link', 'name', 'place_of_birth', 'place_of_death', 'text',
       'year'],
      dtype='object')
12

#DataFrameのインデックに使う列を指定する
#インデックスを変更すると新しくDatFrameを生成して返すので
#もとのDataFrameは変更されない
#ここではもとの変数に代入しているので変更されている
df = df.set_index('name')
df.head(2)

	born_in	category	country	date_of_birth	date_of_death	gender	link	place_of_birth	place_of_death	text	year
name
César Milstein		Physiology or Medicine	Argentina	8 October 1927	24 March 2002	male	http://en.wikipedia.org/wiki/C%C3%A9sar_Milstein	Bahía Blanca , Argentina	Cambridge , England	César Milstein , Physiology or Medicine, 1984	1984
Ivo Andric *	Bosnia and Herzegovina	Literature		9 October 1892	13 March 1975	male	http://en.wikipedia.org/wiki/Ivo_Andric	Dolac (village near Travnik), Austria-Hungary ...	Belgrade, SR Serbia, SFR Yugoslavia (present-d...	Ivo Andric *, born in then Austria–Hungary ,...	1961

#インデックスにした列が最左端にくる
#df = df.set_index('born_in')
#df.head(2)

df.reset_index(inplace=True)
df.head(2)

	name	born_in	category	country	date_of_birth	date_of_death	gender	link	place_of_birth	place_of_death	text	year
0	César Milstein		Physiology or Medicine	Argentina	8 October 1927	24 March 2002	male	http://en.wikipedia.org/wiki/C%C3%A9sar_Milstein	Bahía Blanca , Argentina	Cambridge , England	César Milstein , Physiology or Medicine, 1984	1984
1	Ivo Andric *	Bosnia and Herzegovina	Literature		9 October 1892	13 March 1975	male	http://en.wikipedia.org/wiki/Ivo_Andric	Dolac (village near Travnik), Austria-Hungary ...	Belgrade, SR Serbia, SFR Yugoslavia (present-d...	Ivo Andric *, born in then Austria–Hungary ,...	1961

bi_col = df.born_in
bi_col

0                             
1       Bosnia and Herzegovina
2       Bosnia and Herzegovina
3                             
4                             
5                             
6                             
7                             
8                             
9                             
10                            
11                            
12                            
13                            
14                     Belarus
15                     Belarus
16                     Belarus
17                            
18                            
19                            
20                            
21                            
22                            
23                            
24                            
25                            
26                            
27              Czech Republic
28              Czech Republic
29              Czech Republic
                 ...          
1022                          
1023                   Austria
1024                   Austria
1025                          
1026                          
1027                   Austria
1028                          
1029                          
1030                   Austria
1031                   Austria
1032                          
1033                          
1034                   Austria
1035                 Australia
1036                          
1037                          
1038                          
1039                 Australia
1040                          
1041                 Australia
1042                          
1043                          
1044                          
1045                          
1046                 Australia
1047                          
1048                          
1049                          
1050                          
1051                          
Name: born_in, Length: 1052, dtype: object

type(bi_col)

pandas.core.series.Series

#locはlocationの省略形で位置という意味で使われているもよう
#locはラベルによる行の指定,ilocは番号による行の指定,ixはどっちもOK
df.iloc[0]

name                                                César Milstein
born_in                                                           
category                                    Physiology or Medicine
country                                                  Argentina
date_of_birth                                       8 October 1927
date_of_death                                        24 March 2002
gender                                                        male
link              http://en.wikipedia.org/wiki/C%C3%A9sar_Milstein
place_of_birth                           Bahía Blanca ,  Argentina
place_of_death                                 Cambridge , England
text                 César Milstein , Physiology or Medicine, 1984
year                                                          1984
Name: 0, dtype: object

#２行ある受賞年が1921年なので重複した記載になる（countryがスイスとドイツ２つある）
df.set_index('name', inplace=True)
df.loc['Albert Einstein']

	category	country	date_of_birth	date_of_death	gender	link	place_of_birth	place_of_death	text	year
name
Albert Einstein	Physics	Switzerland	1879-03-14	1955-04-18	male	http://en.wikipedia.org/wiki/Albert_Einstein	Ulm , Baden-Württemberg , German Empire	Princeton, New Jersey , U.S.	Albert Einstein , born in Germany , Physics, ...	1921
Albert Einstein	Physics	Germany	1879-03-14	1955-04-18	male	http://en.wikipedia.org/wiki/Albert_Einstein	Ulm , Baden-Württemberg , German Empire	Princeton, New Jersey , U.S.	Albert Einstein , Physics, 1921	1921

df.reset_index(inplace=True)

9.3.1 複数行の選択

mask = df.year > 2000
winners_since_2000 = df[mask]
winners_since_2000.count()

name              202
born_in           202
category          202
country           202
date_of_birth     201
date_of_death     201
gender            200
link              202
place_of_birth    201
place_of_death    201
text              202
year              202
dtype: int64

winners_since_2000.head()

	name	born_in	category	country	date_of_birth	gender	link	place_of_birth	text	year
13	François Englert		Physics	Belgium	6 November 1932	male	http://en.wikipedia.org/wiki/Fran%C3%A7ois_Eng...	Etterbeek , Brussels , Belgium	François Englert , Physics, 2013	2013
32	Christopher A. Pissarides		Economics	Cyprus	1948-02-20	male	http://en.wikipedia.org/wiki/Christopher_A._Pi...	Nicosia, Cyprus	Christopher A. Pissarides , Economics, 2010	2010
66	Kofi Annan		Peace	Ghana	8 April 1938	male	http://en.wikipedia.org/wiki/Kofi_Annan	Kumasi , Ghana	Kofi Annan , Peace, 2001	2001
87	Riccardo Giacconi *	Italy	Physics		October 6, 1931	male	http://en.wikipedia.org/wiki/Riccardo_Giacconi	Genoa , Italy	Riccardo Giacconi *, Physics, 2002	2002
88	Mario Capecchi *	Italy	Physiology or Medicine		6 October 1937	male	http://en.wikipedia.org/wiki/Mario_Capecchi	Verona , Italy	Mario Capecchi *, Physiology or Medicine, 2007	2007