07.handling_dataframe(bool-apply)

In [1]:

import pandas as pd
from collections import OrderedDict

In [2]:

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

열의 자료형 바꾸기와 새로운 열 추가¶

In [3]:

print("Born type: {}".format(scientists["Born"].dtype))
print("Died type: {}".format(scientists["Died"].dtype))

Born type: object
Died type: object

In [4]:

born_datetime = pd.to_datetime(scientists["Born"], format="%Y-%m-%d")
print("born_datetime: \n{}".format(born_datetime))

print("\n===================================\n")
died_datetime = pd.to_datetime(scientists["Died"], format="%Y-%m-%d")
print("died_datetime: \n{}".format(died_datetime))

born_datetime: 
0   1920-07-25
1   1876-06-13
2   1820-05-12
3   1867-11-07
4   1907-05-27
5   1813-03-15
6   1912-06-23
7   1777-04-30
Name: Born, dtype: datetime64[ns]

===================================

died_datetime: 
0   1958-04-16
1   1937-10-16
2   1910-08-13
3   1934-07-04
4   1964-04-14
5   1858-06-16
6   1954-06-07
7   1855-02-23
Name: Died, dtype: datetime64[ns]

In [5]:

scientists["born_dt"], scientists["died_dt"] = [born_datetime, died_datetime]
scientists.head()

Out[5]:

	Name	Born	Died	Age	Occupation	born_dt	died_dt
0	Rosaline Franklin	1920-07-25	1958-04-16	37	Chemist	1920-07-25	1958-04-16
1	William Gosset	1876-06-13	1937-10-16	61	Statistician	1876-06-13	1937-10-16
2	Florence Nightingale	1820-05-12	1910-08-13	90	Nurse	1820-05-12	1910-08-13
3	Marie Curie	1867-11-07	1934-07-04	66	Chemist	1867-11-07	1934-07-04
4	Rachel Carson	1907-05-27	1964-04-14	56	Biologist	1907-05-27	1964-04-14

In [6]:

scientists["age_days"] = (scientists["died_dt"] - scientists["born_dt"])
scientists.head()

Out[6]:

	Name	Born	Died	Age	Occupation	born_dt	died_dt	age_days
0	Rosaline Franklin	1920-07-25	1958-04-16	37	Chemist	1920-07-25	1958-04-16	13779 days
1	William Gosset	1876-06-13	1937-10-16	61	Statistician	1876-06-13	1937-10-16	22404 days
2	Florence Nightingale	1820-05-12	1910-08-13	90	Nurse	1820-05-12	1910-08-13	32964 days
3	Marie Curie	1867-11-07	1934-07-04	66	Chemist	1867-11-07	1934-07-04	24345 days
4	Rachel Carson	1907-05-27	1964-04-14	56	Biologist	1907-05-27	1964-04-14	20777 days

In [7]:

import random

print(scientists["Age"])
print("\n===================================\n")
random.seed(42)
random.shuffle(scientists["Age"])
print(scientists["Age"])

0    37
1    61
2    90
3    66
4    56
5    45
6    41
7    77
Name: Age, dtype: int64

===================================

/anaconda3/lib/python3.6/random.py:277: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  x[i], x[j] = x[j], x[i]

0    66
1    56
2    41
3    77
4    90
5    45
6    37
7    61
Name: Age, dtype: int64

열 삭제¶

In [8]:

print(scientists.columns)

print("\n===================================\n")

scientists_dropped = scientists.drop(["Age"], axis=1)
print(scientists_dropped.columns)

Index(['Name', 'Born', 'Died', 'Age', 'Occupation', 'born_dt', 'died_dt',
       'age_days'],
      dtype='object')

===================================

Index(['Name', 'Born', 'Died', 'Occupation', 'born_dt', 'died_dt', 'age_days'], dtype='object')

In [9]:

from IPython.core.display import display, HTML

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