frame.apply(lambda x: function(x.column), axis = 1)
主要是DataFrame.apply函数的应用，
数据类型为整型，默认为0。当axis=0时，会将DataFrame中的每一列抽出来做聚合运算，当axis=1时，会将DataFrame中的每一行抽出来做聚合运算。
# 判断如果城市名中含有ing字段且年份为2016，则新列test值赋为1，否则为0.
import numpy as np
import pandas as pd
data = {'city': ['Beijing', 'Shanghai', 'Guangzhou', 'Shenzhen', 'Hangzhou', 'Chongqing'],
'year': [2016,2016,2015,2017,2016, 2016],
'population': [2100, 2300, 1000, 700, 500, 500]}
frame = pd.DataFrame(data, columns = ['year', 'city', 'population', 'debt'])
def function(a, b):
if 'ing' in a and b == 2016:
return 1
else:
return 0
print(frame, '\n')
frame['test'] = frame.apply(lambda x: function(x.city, x.year), axis = 1)
print(frame)
# 另外Series类型也有apply函数，用法示例
import numpy as np
import pandas as pd
data = {'city': ['Beijing', 'Shanghai', 'Guangzhou', 'Shenzhen', 'Hangzhou', 'Chongqing'],
'year': [2016,2016,2015,2017,2016, 2016],
'population': [2100, 2300, 1000, 700, 500, 500]}
frame = pd.DataFrame(data, columns = ['year', 'city', 'population', 'debt'])
print(frame, '\n')
frame['panduan'] = frame.city.apply(lambda x: 1 if 'ing' in x else 0)
print(frame)
# eg
def foo(x, y, z):
if z > 0.5:
return x + y
else:
return x
d['fun'] = d.apply(lambda x: foo(x[0], x[2], x[4]), axis=1)