!pip3 install Faker
!pip3 install us

#from dataclasses import fields
from faker import Faker
import pandas as pd
import random
import string
import time
import us

from concurrent.futures import ThreadPoolExecutor, as_completed


fake = Faker('en_US')

# print(fake.name())
# print(fake.profile())
# print(fake.profile(fields="current_location").get("current_location")[0])
# print(fake.current_country_code())
# print(fake.street_address())

# print("state",fake.state())
# print(fake.state_abbr())
#state_val = "Indianna"
# state = us.states.lookup('{}'.format(fake.state()))
# print(state.abbr)
# print(fake.postalcode_in_state(state_abbr=state.abbr))
# print(state)

# state = fake.state()
# print(state)
# #states.append(state)
# state_code = us.states.lookup('{}'.format(state))
# print(state_code)
# newstatecode = us.states.lookup('{}'.format(fake.state()))
# print(newstatecode.abbr)

def random_phone_num_generator():
    first = str(random.randint(100, 999))
    second = str(random.randint(1, 888)).zfill(3)
    last = (str(random.randint(1, 9998)).zfill(4))
    while last in ['1111', '2222', '3333', '4444', '5555', '6666', '7777', '8888']:
        last = (str(random.randint(1, 9998)).zfill(4))
    return '{}-{}-{}'.format(first, second, last)

def id_generator(sizeS=2,sizeN=5,charsS=string.ascii_uppercase, charsN = string.digits):
    stChars =  ''.join(random.choice(charsS) for _ in range(sizeS))
    numChars = ''.join(random.choice(charsN) for _ in range(sizeN))
    return stChars + numChars

customer_id = []
name = []
marital_status = []
country = []
education = []
lat = []
longitude = []
street_address = []
city = []
gender = []
occupation = []
national_id = []
company_name = []
zip_code = []
states = []
state_codes = []
email = []
phone = []
customer_lifetime_value = []

num_records = 250000
def generate_random_values():
    name.append(fake.name())
    marital_status.append(''.join(fake.random_elements(elements=("married","single"),length=1,unique=False))) #marital status
    education.append(''.join(fake.random_elements(elements=("College","Masters","Doctor","High School","Bachelor"),length=1,unique=False))) #education
    lat.append(fake.latitude())
    longitude.append(fake.longitude())
    street_address.append(fake.street_address())
    city.append(fake.city())
    country.append(fake.current_country_code())
    gender.append(fake.profile(fields="sex").get('sex'))
    occupation.append(fake.profile(fields="job").get('job'))
    national_id.append(fake.profile(fields="ssn").get('ssn'))
    state = fake.state()
    states.append(state)
    state_code = us.states.lookup('{}'.format(state)).abbr
    state_codes.append(state_code)
    zip_code.append(fake.postalcode_in_state(state_abbr=state_code))
    company_name.append(fake.profile(fields="company").get('company'))
    email.append(fake.profile(fields="mail").get('mail'))
    phone.append(random_phone_num_generator()) #US phone number generator
    customer_id.append(id_generator())
    customer_lifetime_value.append(random.uniform(2000,61000))
    
start_time = time.time()
print(start_time)

with ThreadPoolExecutor(max_workers = 10) as executor:
    for _ in range(num_records):
        executor.submit(generate_random_values())


dict = {"customer_id":customer_id,"full_name":name,
        "country": country, "lat": lat, "longitude":longitude,
        "street_address": street_address,"city":city, "state": state,
        "state_code": state_code, "zip_code": zip_code,
        "email":email,"phone":phone,"gender": gender,
        "education": education,
        "national_id":national_id,
        "education":education, "marital_status": marital_status,
        "customer_lifetime_value":customer_lifetime_value}

df = pd.DataFrame(dict)
print("---%s---" % (time.time() - start_time))
df.head()
# print(df.columns)
# print(df.shape[0])

# 5 workers: 9.138494491577148
# 3 workers: 8.327600717544556
# 10 workers: 8.334825038909912