I would like to use the Python Faker library to generate 500 lines of data, however I get repeated data using the code I came up with below. Can you please point out where I'm going wrong. I believe it has something to do with the for loop. Thanks in advance:
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)
Disclaimer: this answer is added much after the question and adds some new info not directly answering the question.
Now there is a fast new library Mimesis - Fake Data Generator.
- Upside: It is stated it works times faster than
faker
(see below my test of data similar to one in question).
- Downside: works from 3.6 version of Python only.
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'
The same with developed earlier 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
Below it my recent timing of Mimesis vs. Faker based on code provided in answer from forzer0eight:
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 times: user 3.51 s, sys: 2.86 ms, total: 3.51 s
Wall time: 3.51 s
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 times: user 178 ms, sys: 1.7 ms, total: 180 ms
Wall time: 179 ms
Below is resulting data for comparison:
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
I placed the fake stuff array inside my for loop to achieve the desired result:
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)
Following scripts can remarkably enhance the pandas performance.
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
It takes 5.55s.
%%time
df = pd.DataFrame(create_rows(5000))
Wall time: 5.55 s