python groupby使用_python3 groupby的使用

from itertools import groupby

d1 = {'name': 'zhangsan', 'age': 20, 'country': 'China'}

d2 = {'name': 'wangwu', 'age': 19, 'country': 'USA'}

d3 = {'name': 'lisi', 'age': 22, 'country': 'JP'}

d4 = {'name': 'zhaoliu', 'age': 22, 'country': 'USA'}

d5 = {'name': 'pengqi', 'age': 22, 'country': 'USA'}

d6 = {'name': 'lijiu', 'age': 22, 'country': 'China'}

lst = [d1, d2, d3, d4, d5, d6]

# 使用前必须安照关键字排序

lst.sort(key=lambda x: x['country'])

# 安装country分组,返回一个迭代器,只能使用一次

g = groupby(lst,

key=lambda x: x['country']

)

print(type(g))

# 遍历

# for key, list in g:

# print(key)

# for i in list:

# print(i)

# 将键值转化为列表

# print([key for key, group in g])

# ['China', 'JP', 'USA']

'''

China

{'name': 'zhangsan', 'age': 20, 'country': 'China'}

{'name': 'lijiu', 'age': 22, 'country': 'China'}

JP

{'name': 'lisi', 'age': 22, 'country': 'JP'}

USA

{'name': 'wangwu', 'age': 19, 'country': 'USA'}

{'name': 'zhaoliu', 'age': 22, 'country': 'USA'}

{'name': 'pengqi', 'age': 22, 'country': 'USA'}

'''

# 生成字典,按照键和对应的列表

# 将迭代器转化为列表

# d = {

# key: list(val) for key, val in g

# }

#

# for k, v in d.items():

# print(k)

# for i in v:

# print(i)

'''

China

{'name': 'zhangsan', 'age': 20, 'country': 'China'}

{'name': 'lijiu', 'age': 22, 'country': 'China'}

JP

{'name': 'lisi', 'age': 22, 'country': 'JP'}

USA

{'name': 'wangwu', 'age': 19, 'country': 'USA'}

{'name': 'zhaoliu', 'age': 22, 'country': 'USA'}

{'name': 'pengqi', 'age': 22, 'country': 'USA'}

'''

# 各组的数目

# d = {

# key: len(list(val)) for key, val in g

# }

# {'China': 2, 'JP': 1, 'USA': 3}

# print(d)

# 过滤分组,由于val是一个迭代器,只能使用一次

# {'China': [], 'USA': []}

# print({

# key: list(val) for key, val in g if len(list(val)) >= 2

# })

# d = [

# (key, list(val)) for key, val in g

# ]

# print(d)

# nd = dict(filter(lambda x: len(x[1]) >= 2, d))

# print(nd)

# 或者:

# d = {

# key: list(val) for key, val in g

# }

# print(d)

# nd = dict(filter(lambda item: len(item[1]) > 2, d.items()))

# print(nd)

# {'USA': [{'name': 'wangwu', 'age': 19, 'country': 'USA'}, {'name': 'zhaoliu', 'age': 22, 'country': 'USA'}, {'name': 'pengqi', 'age': 22, 'country': 'USA'}]}

# 返回包含有2个以上元素的分组

# print([

# key for key, val in g if len(list(val)) >= 2

# ])

# 返回：['China', 'USA']

# 自定义分组

lst = [2, 8, 11, 25, 43, 6, 9, 29, 51, 66]

def gb(num):

if num <= 10:

return 'less'

elif num >= 30:

return 'great'

else:

return 'middle'

print([(k, list(g))

for k, g in groupby(sorted(lst), key=gb)])

# [('less', [2, 6, 8, 9]), ('middle', [11, 25, 29]), ('great', [43, 51, 66])]

d = {

k: list(g) for k, g in groupby(sorted(lst), key=gb)

}

print(d)

# {'less': [2, 6, 8, 9], 'middle': [11, 25, 29], 'great': [43, 51, 66]}