06.handling_dataframe(bool)

In [1]:

import pandas as pd
from collections import OrderedDict

In [2]:

scientists = pd.read_csv("./data/scientists.csv")

boolean 추출과 broadcasting¶

In [3]:

bool_idx = scientists["Age"] > scientists["Age"].mean()
scientists[bool_idx]

Out[3]:

	Name	Born	Died	Age	Occupation
1	William Gosset	1876-06-13	1937-10-16	61	Statistician
2	Florence Nightingale	1820-05-12	1910-08-13	90	Nurse
3	Marie Curie	1867-11-07	1934-07-04	66	Chemist
7	Johann Gauss	1777-04-30	1855-02-23	77	Mathematician

In [4]:

## 문자열 2배, 값2배 -- broadcasting
print(scientists*2)

                                       Name                  Born  \
0        Rosaline FranklinRosaline Franklin  1920-07-251920-07-25   
1              William GossetWilliam Gosset  1876-06-131876-06-13   
2  Florence NightingaleFlorence Nightingale  1820-05-121820-05-12   
3                    Marie CurieMarie Curie  1867-11-071867-11-07   
4                Rachel CarsonRachel Carson  1907-05-271907-05-27   
5                        John SnowJohn Snow  1813-03-151813-03-15   
6                    Alan TuringAlan Turing  1912-06-231912-06-23   
7                  Johann GaussJohann Gauss  1777-04-301777-04-30   

                   Died  Age                            Occupation  
0  1958-04-161958-04-16   74                        ChemistChemist  
1  1937-10-161937-10-16  122              StatisticianStatistician  
2  1910-08-131910-08-13  180                            NurseNurse  
3  1934-07-041934-07-04  132                        ChemistChemist  
4  1964-04-141964-04-14  112                    BiologistBiologist  
5  1858-06-161858-06-16   90                    PhysicianPhysician  
6  1954-06-071954-06-07   82  Computer ScientistComputer Scientist  
7  1855-02-231855-02-23  154            MathematicianMathematician  

In [5]:

from IPython.core.display import display, HTML
display(HTML("<style> .container{width:100% !important;}</style>"))