pandas :: dataframe

https://www.slideshare.net/wesm/pandas-powerful-data-analysis-tools-for-python

DataFrame

• Series를 모아서 만든 Data Table = 기본 2차원

from pandas import Series, DataFrame
import pandas as pd
import numpy as np

# Example from - https://chrisalbon.com/python/pandas_map_values_to_values.html
raw_data = {'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'],
        'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'],
        'age': [42, 52, 36, 24, 73],
        'city': ['San Francisco', 'Baltimore', 'Miami', 'Douglas', 'Boston']}
df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'age', 'city'])
df

# column 선택
DataFrame(raw_data, columns = ["age", "city"])

# 새로운 column (debt) 추가
DataFrame(raw_data, 
          columns = ["first_name","last_name","age", "city", "debt"]
         )

# column 선택 - series 추출 : 방법 1
df = DataFrame(raw_data, columns = ["first_name","last_name","age", "city", "debt"])
df.first_name

0 Jason
1 Molly
2 Tina
3 Jake
4 Amy
Name: first_name, dtype: object

# column 선택 - series 추출 : 방법 2
df["first_name"]

0 Jason
1 Molly
2 Tina
3 Jake
4 Amy
Name: first_name, dtype: object

df

# loc : index location
df.loc[1]

first_name Molly
last_name Jacobson
age 52
city Baltimore
debt NaN
Name: 1, dtype: object

# iloc : index position
df["age"].iloc[1:]

1 52
2 36
3 24
4 73
Name: age, dtype: int64

# loc은 index 이름, iloc은 index number

# Example from - https://stackoverflow.com/questions/31593201/pandas-iloc-vs-ix-vs-loc-explanation
s = pd.Series(np.nan, index=[49,48,47,46,45, 1, 2, 3, 4, 5])
s.loc[:3]  # 3이라는 index까지

49 NaN
48 NaN
47 NaN
46 NaN
45 NaN
1 NaN
2 NaN
3 NaN
dtype: float64

s.iloc[:3]  # 처음부터 3개

49 NaN
48 NaN
47 NaN
dtype: float64

df.age > 40

0 True
1 True
2 False
3 False
4 True
Name: age, dtype: bool

# column에 새로운 데이터 할당
df.debt = df.age > 40
df

# transpose
df.T

# 값 출력
df.values

array([['Jason', 'Miller', 42, 'San Francisco', True],
['Molly', 'Jacobson', 52, 'Baltimore', True],
['Tina', 'Ali', 36, 'Miami', False],
['Jake', 'Milner', 24, 'Douglas', False],
['Amy', 'Cooze', 73, 'Boston', True]], dtype=object)

# csv 변환
df.to_csv()

',first_name,last_name,age,city,debt\r\n0,Jason,Miller,42,San Francisco,True\r\n1,Molly,Jacobson,52,Baltimore,True\r\n2,Tina,Ali,36,Miami,False\r\n3,Jake,Milner,24,Douglas,False\r\n4,Amy,Cooze,73,Boston,True\r\n'

# column을 삭제함
del df["debt"]

df

# column 추가
values = Series(data=["M","F","F"],index=[0,1,3])
values

0 M
1 F
3 F
dtype: object

df["sex"] = values
df

# Example from Python for data analyis


pop = {'Nevada': {2001: 2.4, 2002: 2.9},
 'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}

DataFrame(pop)

---

https://www.boostcourse.org/ai222/lecture/23822