DataFrame.apply(self, func, axis=0, raw=False, result_type=None, args=(), **kwargs)

	Objects passed to the function are Series objects whose index is either the DataFrame's index (``axis=0``) or the DataFrame's columns(``axis=1``). 
	傳遞給函數(shù)的對(duì)象是Series對(duì)象，其索引是DataFrame的索引(axis=0)或DataFrame的列(axis=1)。
	By default (``result_type=None``), the final return type is inferred from the return type of the applied function. Otherwise,it depends on the `result_type` argument.
	默認(rèn)情況下( result_type=None)，最終的返回類(lèi)型是從應(yīng)用函數(shù)的返回類(lèi)型推斷出來(lái)的。否則，它取決于' result_type '參數(shù)。

import pandas as pd
import numpy as np

df = pd.DataFrame([[4, 9]] * 3, columns=['A', 'B'])
df
   A  B
0  4  9
1  4  9
2  4  9


# 使用numpy通用函數(shù) (如 np.sqrt(df)),
df.apply(np.sqrt)
'''
     A    B
0  2.0  3.0
1  2.0  3.0
2  2.0  3.0
'''

# 使用聚合功能
df.apply(np.sum, axis=0)
'''
A    12
B    27
dtype: int64
'''

df.apply(np.sum, axis=1)
'''
0    13
1    13
2    13
dtype: int64
'''

# 在每行上返回類(lèi)似列表的內(nèi)容
df.apply(lambda x: [1, 2], axis=1)
'''
0    [1, 2]
1    [1, 2]
2    [1, 2]
dtype: object
'''

# result_type='expand' 將類(lèi)似列表的結(jié)果擴(kuò)展到數(shù)據(jù)的列
df.apply(lambda x: [1, 2], axis=1, result_type='expand')

'''
   0  1
0  1  2
1  1  2
2  1  2
'''

# 在函數(shù)中返回一個(gè)序列，生成的列名將是序列索引。
df.apply(lambda x: pd.Series([1, 2], index=['foo', 'bar']), axis=1)

'''
   foo  bar
0    1    2
1    1    2
2    1    2
'''

# result_type='broadcast' 將確保函數(shù)返回相同的形狀結(jié)果
# 無(wú)論是 list-like 還是 scalar，并沿軸進(jìn)行廣播
# 生成的列名將是原始列名。
df.apply(lambda x: [1, 2], axis=1, result_type='broadcast')
'''
A  B
0  1  2
1  1  2
2  1  2
'''

import numpy as np
import pandas as pd

df = pd.DataFrame({'A': [1, 2, 3],
                   'B': [4, 5, 6],
                   'C': [7, 8, 9]},
                  index=['a', 'b', 'c'])
df
	A	B	C
a	1	4	7
b	2	5	8
c	3	6	9

# 對(duì)各列應(yīng)用函數(shù) axis=0
df.apply(lambda x: np.sum(x))
A     6
B    15
C    24
dtype: int64

# 對(duì)各行應(yīng)用函數(shù)
df.apply(lambda x: np.sum(x), axis=1)
a    12
b    15
c    18
dtype: int64

s = pd.Series([20, 21, 12],index=['London', 'New York', 'Helsinki'])
s
'''
London      20
New York    21
Helsinki    12
dtype: int64
'''

# 定義函數(shù)并將其作為參數(shù)傳遞給 apply，求值平方化。
def square(x):
     return x ** 2

s.apply(square)
'''
London      400
New York    441
Helsinki    144
dtype: int64
'''

# 通過(guò)將匿名函數(shù)作為參數(shù)傳遞給 apply
s.apply(lambda x: x ** 2)
'''
London      400
New York    441
Helsinki    144
dtype: int64
'''

# 定義一個(gè)需要附加位置參數(shù)的自定義函數(shù)
# 并使用args關(guān)鍵字傳遞這些附加參數(shù)。
def subtract_custom_value(x, custom_value):
     return x - custom_value

s.apply(subtract_custom_value, args=(5,))
'''
London      15
New York    16
Helsinki     7
dtype: int64
'''

# 定義一個(gè)接受關(guān)鍵字參數(shù)并將這些參數(shù)傳遞
# 給 apply 的自定義函數(shù)。
def add_custom_values(x, **kwargs):
     for month in kwargs:
         x += kwargs[month]
     return x

s.apply(add_custom_values, june=30, july=20, august=25)
'''
London      95
New York    96
Helsinki    87
dtype: int64
'''

# 使用Numpy庫(kù)中的函數(shù)
s.apply(np.log)
'''
London      2.995732
New York    3.044522
Helsinki    2.484907
dtype: float64
'''

import pandas as pd

# 顯示所有列
pd.set_option('display.max_columns', None)
# 顯示所有行
pd.set_option('display.max_rows', None)
# 設(shè)置value的顯示長(zhǎng)度為100，默認(rèn)為50
pd.set_option('max_colwidth', 100)
# 用來(lái)計(jì)算日期差的包
import datetime

def dataInterval(data1, data2):
    """
    Args:
    :param data1: datetime
    :param data2: datetime
    :return: delta days
    """
    d1 = datetime.datetime.strptime(data1, '%Y-%m-%d')
    d2 = datetime.datetime.strptime(data2, '%Y-%m-%d')
    delta = d1 - d2
    return delta.days

def getInterval(arrLike):  
    """
    Args:
    :param arrLike: DataFrame 
    :return: delta days
    """
    PublishedTime = arrLike['PublishedTime']
    ReceivedTime = arrLike['ReceivedTime']
    days = dataInterval(PublishedTime.strip(), ReceivedTime.strip()) 
    return days

def getInterval_new(arrLike, before, after): 
    """
    Args:
    :param arrLike: DataFrame
    :param before: forward time
    :param after: backwar time
    :return: delta days
    """
    before = arrLike[before]
    after = arrLike[after]
    days = dataInterval(after.strip(), before.strip())  
    return days

if __name__ == '__main__':
    df = pd.read_excel('./data/NS_info.xls')
    print(df.head())
    # method 1
    df['TimeInterval'] = df.apply(getInterval, axis=1)
    print(df.head())
    # method 2
    df['TimeInterval'] = df.apply(getInterval_new,axis=1, 
                                  args=('ReceivedTime', 'PublishedTime')) 
	# method 3
    df['TimeInterval'] = df.apply(getInterval_new,axis=1, 
                   **{'before': 'ReceivedTime', 'after': 'PublishedTime'})  
	# method 4
    df['TimeInterval'] = df.apply(getInterval_new,axis=1, before='ReceivedTime', after='PublishedTime')