Datagen

# To add a new cell, type '#%%'
# To add a new markdown cell, type '#%% [markdown]'

#%%
import pandas as pd
import random
from datetime import datetime
from dateutil.relativedelta import relativedelta
from faker import Faker
import pandas as pd


#%%
fake = Faker()

def get_random_name(taken_names):
    name = '.'.join(fake.sentence().lower()[:-1].split())
    while name in taken_names:
        name = '.'.join(fake.sentence().lower()[:-1].split())

    return name

ten_years_ago = (datetime.now() - relativedelta(years=10)).timestamp()

def get_random_dt_after(after = ten_years_ago):
    now = datetime.now().timestamp()

    return datetime.fromtimestamp(random.uniform(after, now))


#%%
rows = dict([])
pk = 1

for i in range(10000):
    identifier = get_random_name(rows.keys())
    title = ' '.join([word.capitalize() for word in identifier.split('.')])
    description = fake.text()
    published_ts = get_random_dt_after()
    last_updated_ts = get_random_dt_after(after = published_ts.timestamp())
    rows[identifier] = (pk, identifier, title, description, published_ts, last_updated_ts)
    pk = pk + 1


#%%
fake = Faker()

fake.sentence().lower()[:-1]


#%%
df = pd.DataFrame(rows.values(), columns =['PK', 'Id', 'Title', 'Description', 'Published_TS', 'Last_Updated_TS'])


#%%
df.head()