使用 Python Faker 为 5000 行生成不同的数据
Using Python Faker generate different data for 5000 rows
我想使用 Python Faker 库生成 500 行数据，但是我使用下面的代码得到了重复的数据。你能指出我哪里出错了吗？我相信这与 for 循环有关。提前致谢：
from faker import Factory
import pandas as pd
import random
def create_fake_stuff(fake):
df = pd.DataFrame(columns=('name'
, 'email'
, 'bs'
, 'address'
, 'city'
, 'state'
, 'date_time'
, 'paragraph'
, 'Conrad'
,'randomdata'))
stuff = [fake.name()
, fake.email()
, fake.bs()
, fake.address()
, fake.city()
, fake.state()
, fake.date_time()
, fake.paragraph()
, fake.catch_phrase()
, random.randint(1000,2000)]
for i in range(10):
df.loc[i] = [item for item in stuff]
print(df)
if __name__ == '__main__':
fake = Factory.create()
create_fake_stuff(fake)
我将伪造的东西数组放在我的 for 循环中以获得预期的结果：
for i in range(10):
stuff = [fake.name()
, fake.email()
, fake.bs()
, fake.address()
, fake.city()
, fake.state()
, fake.date_time()
, fake.paragraph()
, fake.catch_phrase()
, random.randint(1000, 2000)]
df.loc[i] = [item for item in stuff]
print(df)
以下脚本可以显着提高 pandas 性能。
from faker import Faker
import pandas as pd
import random
fake = Faker()
def create_rows(num=1):
output = [{"name":fake.name(),
"address":fake.address(),
"name":fake.name(),
"email":fake.email(),
"bs":fake.bs(),
"address":fake.address(),
"city":fake.city(),
"state":fake.state(),
"date_time":fake.date_time(),
"paragraph":fake.paragraph(),
"Conrad":fake.catch_phrase(),
"randomdata":random.randint(1000,2000)} for x in range(num)]
return output
耗时5.55s
%%time
df = pd.DataFrame(create_rows(5000))
Wall time: 5.55 s
免责声明：这个答案是在问题之后添加的，并添加了一些不直接回答问题的新信息。
现在有一个快速的新库Mimesis - Fake Data Generator。
- 优点：据说它的工作速度比
faker 快几倍（请参阅下面我对与所讨论的数据类似的数据的测试）。
- 缺点：仅适用于 Python 的 3.6 版本。
pip install mimesis
>>> from mimesis import Person
>>> from mimesis.enums import Gender
>>> person = Person('en')
>>> person.full_name(gender=Gender.FEMALE)
'Antonetta Garrison'
>>> personru = Person('ru')
>>> personru.full_name()
'Рената Черкасова'
和之前开发的一样faker:
pip install faker
>>> from faker import Faker
>>> fake_ru=Faker('ja_JP')
>>> fake_ru=Faker('ru_RU')
>>> fake_jp=Faker('ja_JP')
>>> print (fake_ru.name())
Субботина Елена Наумовна
>>> print (fake_jp.name())
大垣 花子
下面是我最近根据 forzer0eight 的回答中提供的代码对 Mimesis 与 Faker 的时间安排：
from faker import Faker
import pandas as pd
import random
fake = Faker()
def create_rows_faker(num=1):
output = [{"name":fake.name(),
"address":fake.address(),
"name":fake.name(),
"email":fake.email(),
#"bs":fake.bs(),
"city":fake.city(),
"state":fake.state(),
"date_time":fake.date_time(),
#"paragraph":fake.paragraph(),
#"Conrad":fake.catch_phrase(),
"randomdata":random.randint(1000,2000)} for x in range(num)]
return output
%%time
df_faker = pd.DataFrame(create_rows_faker(5000))
CPU 次：用户 3.51 秒，系统：2.86 毫秒，总计：3.51 秒
挂墙时间：3.51 秒
from mimesis import Person
from mimesis import Address
from mimesis.enums import Gender
from mimesis import Datetime
person = Person('en')
import pandas as pd
import random
person = Person()
addess = Address()
datetime = Datetime()
def create_rows_mimesis(num=1):
output = [{"name":person.full_name(gender=Gender.FEMALE),
"address":addess.address(),
"name":person.name(),
"email":person.email(),
#"bs":person.bs(),
"city":addess.city(),
"state":addess.state(),
"date_time":datetime.datetime(),
#"paragraph":person.paragraph(),
#"Conrad":person.catch_phrase(),
"randomdata":random.randint(1000,2000)} for x in range(num)]
return output
%%time
df_mimesis = pd.DataFrame(create_rows_mimesis(5000))
CPU 次：用户 178 毫秒，系统：1.7 毫秒，总计：180 毫秒
挂墙时间：179 毫秒
下面是比较结果数据：
df_faker.head(2)
address city date_time email name randomdata state
0 3818 Goodwin Haven\nBrocktown, GA 06168 Valdezport 2004-10-18 20:35:52 joseph81@gomez-beltran.info Deborah Garcia 1218 Oklahoma
1 2568 Gonzales Field\nRichardhaven, NC 79149 West Rachel 1985-02-03 00:33:00 lbeck@wang.com Barbara Pineda 1536 Tennessee
df_mimesis.head(2)
address city date_time email name randomdata state
0 351 Nobles Viaduct Cedar Falls 2013-08-22 08:20:25.288883 chemotherapeutics1964@gmail.com Ernest 1673 Georgia
1 517 Williams Hill Malden 2008-01-26 18:12:01.654995 biochemical1972@yandex.com Jonathan 1845 North Dakota
使用 farsante and mimesis 库是使用假数据创建 Pandas DataFrame 的最简单方法。
import random
import farsante
from mimesis import Person
from mimesis import Address
from mimesis import Datetime
person = Person()
address = Address()
datetime = Datetime()
def rand_int(min_int, max_int):
def some_rand_int():
return random.randint(min_int, max_int)
return some_rand_int
df = farsante.pandas_df([
person.full_name,
address.address,
person.name,
person.email,
address.city,
address.state,
datetime.datetime,
rand_int(1000, 2000)], 5)
print(df)
full_name address name ... state datetime some_rand_int
0 Weldon Durham 1027 Nellie Square Bruna ... West Virginia 2030-06-10 09:21:29.179412 1453
1 Veta Conrad 932 Cragmont Arcade Betsey ... Iowa 2017-08-11 23:50:27.479281 1909
2 Vena Kinney 355 Edgar Highway Tyson ... New Hampshire 2002-12-21 05:26:45.723531 1735
3 Adam Sheppard 270 Williar Court Treena ... North Dakota 2011-03-30 19:16:29.015598 1503
4 Penney Allison 592 Oakdale Road Chas ... Maine 2009-12-14 16:31:37.714933 1175
这种方法可以使您的代码保持整洁。
我想使用 Python Faker 库生成 500 行数据，但是我使用下面的代码得到了重复的数据。你能指出我哪里出错了吗？我相信这与 for 循环有关。提前致谢：
from faker import Factory
import pandas as pd
import random
def create_fake_stuff(fake):
df = pd.DataFrame(columns=('name'
, 'email'
, 'bs'
, 'address'
, 'city'
, 'state'
, 'date_time'
, 'paragraph'
, 'Conrad'
,'randomdata'))
stuff = [fake.name()
, fake.email()
, fake.bs()
, fake.address()
, fake.city()
, fake.state()
, fake.date_time()
, fake.paragraph()
, fake.catch_phrase()
, random.randint(1000,2000)]
for i in range(10):
df.loc[i] = [item for item in stuff]
print(df)
if __name__ == '__main__':
fake = Factory.create()
create_fake_stuff(fake)
我将伪造的东西数组放在我的 for 循环中以获得预期的结果：
for i in range(10):
stuff = [fake.name()
, fake.email()
, fake.bs()
, fake.address()
, fake.city()
, fake.state()
, fake.date_time()
, fake.paragraph()
, fake.catch_phrase()
, random.randint(1000, 2000)]
df.loc[i] = [item for item in stuff]
print(df)
以下脚本可以显着提高 pandas 性能。
from faker import Faker
import pandas as pd
import random
fake = Faker()
def create_rows(num=1):
output = [{"name":fake.name(),
"address":fake.address(),
"name":fake.name(),
"email":fake.email(),
"bs":fake.bs(),
"address":fake.address(),
"city":fake.city(),
"state":fake.state(),
"date_time":fake.date_time(),
"paragraph":fake.paragraph(),
"Conrad":fake.catch_phrase(),
"randomdata":random.randint(1000,2000)} for x in range(num)]
return output
耗时5.55s
%%time
df = pd.DataFrame(create_rows(5000))
Wall time: 5.55 s
免责声明：这个答案是在问题之后添加的，并添加了一些不直接回答问题的新信息。
现在有一个快速的新库Mimesis - Fake Data Generator。
- 优点：据说它的工作速度比
faker快几倍（请参阅下面我对与所讨论的数据类似的数据的测试）。 - 缺点：仅适用于 Python 的 3.6 版本。
pip install mimesis
>>> from mimesis import Person
>>> from mimesis.enums import Gender
>>> person = Person('en')
>>> person.full_name(gender=Gender.FEMALE)
'Antonetta Garrison'
>>> personru = Person('ru')
>>> personru.full_name()
'Рената Черкасова'
和之前开发的一样faker:
pip install faker
>>> from faker import Faker
>>> fake_ru=Faker('ja_JP')
>>> fake_ru=Faker('ru_RU')
>>> fake_jp=Faker('ja_JP')
>>> print (fake_ru.name())
Субботина Елена Наумовна
>>> print (fake_jp.name())
大垣 花子
下面是我最近根据 forzer0eight 的回答中提供的代码对 Mimesis 与 Faker 的时间安排：
from faker import Faker
import pandas as pd
import random
fake = Faker()
def create_rows_faker(num=1):
output = [{"name":fake.name(),
"address":fake.address(),
"name":fake.name(),
"email":fake.email(),
#"bs":fake.bs(),
"city":fake.city(),
"state":fake.state(),
"date_time":fake.date_time(),
#"paragraph":fake.paragraph(),
#"Conrad":fake.catch_phrase(),
"randomdata":random.randint(1000,2000)} for x in range(num)]
return output
%%time
df_faker = pd.DataFrame(create_rows_faker(5000))
CPU 次：用户 3.51 秒，系统：2.86 毫秒，总计：3.51 秒 挂墙时间：3.51 秒
from mimesis import Person
from mimesis import Address
from mimesis.enums import Gender
from mimesis import Datetime
person = Person('en')
import pandas as pd
import random
person = Person()
addess = Address()
datetime = Datetime()
def create_rows_mimesis(num=1):
output = [{"name":person.full_name(gender=Gender.FEMALE),
"address":addess.address(),
"name":person.name(),
"email":person.email(),
#"bs":person.bs(),
"city":addess.city(),
"state":addess.state(),
"date_time":datetime.datetime(),
#"paragraph":person.paragraph(),
#"Conrad":person.catch_phrase(),
"randomdata":random.randint(1000,2000)} for x in range(num)]
return output
%%time
df_mimesis = pd.DataFrame(create_rows_mimesis(5000))
CPU 次：用户 178 毫秒，系统：1.7 毫秒，总计：180 毫秒 挂墙时间：179 毫秒
下面是比较结果数据：
df_faker.head(2)
address city date_time email name randomdata state
0 3818 Goodwin Haven\nBrocktown, GA 06168 Valdezport 2004-10-18 20:35:52 joseph81@gomez-beltran.info Deborah Garcia 1218 Oklahoma
1 2568 Gonzales Field\nRichardhaven, NC 79149 West Rachel 1985-02-03 00:33:00 lbeck@wang.com Barbara Pineda 1536 Tennessee
df_mimesis.head(2)
address city date_time email name randomdata state
0 351 Nobles Viaduct Cedar Falls 2013-08-22 08:20:25.288883 chemotherapeutics1964@gmail.com Ernest 1673 Georgia
1 517 Williams Hill Malden 2008-01-26 18:12:01.654995 biochemical1972@yandex.com Jonathan 1845 North Dakota
使用 farsante and mimesis 库是使用假数据创建 Pandas DataFrame 的最简单方法。
import random
import farsante
from mimesis import Person
from mimesis import Address
from mimesis import Datetime
person = Person()
address = Address()
datetime = Datetime()
def rand_int(min_int, max_int):
def some_rand_int():
return random.randint(min_int, max_int)
return some_rand_int
df = farsante.pandas_df([
person.full_name,
address.address,
person.name,
person.email,
address.city,
address.state,
datetime.datetime,
rand_int(1000, 2000)], 5)
print(df)
full_name address name ... state datetime some_rand_int
0 Weldon Durham 1027 Nellie Square Bruna ... West Virginia 2030-06-10 09:21:29.179412 1453
1 Veta Conrad 932 Cragmont Arcade Betsey ... Iowa 2017-08-11 23:50:27.479281 1909
2 Vena Kinney 355 Edgar Highway Tyson ... New Hampshire 2002-12-21 05:26:45.723531 1735
3 Adam Sheppard 270 Williar Court Treena ... North Dakota 2011-03-30 19:16:29.015598 1503
4 Penney Allison 592 Oakdale Road Chas ... Maine 2009-12-14 16:31:37.714933 1175
这种方法可以使您的代码保持整洁。