Skip to content

Instantly share code, notes, and snippets.

@cagingulsen
Created May 10, 2022 11:37
Show Gist options
  • Select an option

  • Save cagingulsen/3f5676b6ac8471728e7750f62ed3cd54 to your computer and use it in GitHub Desktop.

Select an option

Save cagingulsen/3f5676b6ac8471728e7750f62ed3cd54 to your computer and use it in GitHub Desktop.
import pandas as pd
import numpy as np
from faker import Faker
# create some fake data
fake = Faker()
# function to create a dataframe with fake values for our workers
def make_workers(num):
# lists to randomly assign to workers
status_list = ['Full Time', 'Part Time', 'Per Diem']
team_list = [fake.color_name() for x in range(4)]
fake_workers = [{'Worker ID':x+1000,
'Worker Name':fake.name(),
'Hire Date':fake.date_between(start_date='-30y', end_date='today'),
'Worker Status':np.random.choice(status_list, p=[0.50, 0.30, 0.20]), # assign items from list with different probabilities
'Team':np.random.choice(team_list)} for x in range(num)]
return fake_workers
worker_df = pd.DataFrame(make_workers(num=100000))
with open('exfiltrate_me.txt', 'a') as f:
dfAsString = worker_df.to_string(header=False, index=False)
f.write(dfAsString)
worker_df.head()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment