I have now written this code to generate fake values for the columns. I want the datetime column with values like, for a particular day for every minute the data should be generated, so for one day (24 * 60) values should be there. this is the code:

import pandas as pd
import numpy as np
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 = ['in', 'out']
    team_list = ['FL1_RM1','FL1_RM2','FL1_RM3', 'FL1_RM4', 'FL2_RM1']
    d1 = datetime.strptime(f'1/1/2022', '%m/%d/%Y')
    d2 = datetime.strptime(f'08/08/2022', '%m/%d/%Y')

    fake_workers = [{'ID':fake.random_number(digits=10),
                  'Temp':np.random.randint(low=35, high=50), 
                  'noted Date':fake.date_time_between(d1,d2),
                  'Status':np.random.choice(status_list), # assign items from list with different probabilities
                  'room_id':np.random.choice(team_list)} for x in range(num)]
        
    return fake_workers

worker_df = pd.DataFrame(make_workers(num=50000))
worker_df.head(20)

this will generate random time values for any particular date. Is there a way to generate date time values for every minute for each day.

CodePudding user response：

import pandas as pd
import numpy as np
import faker

fake = Faker()

def make_workers():
    status_list = ['in', 'out']
    team_list = ['FL1_RM1','FL1_RM2','FL1_RM3', 'FL1_RM4', 'FL2_RM1']
    d1 = datetime.strptime(f'1/1/2022', '%m/%d/%Y')
    d2 = datetime.strptime(f'08/08/2022', '%m/%d/%Y')
    timestamps = pd.date_range(d1, d2, freq="1min")
    fake_workers = [{'ID':fake.random_number(digits=10),
                  'Temp':np.random.randint(low=35, high=50), 
                  'noted Date':timestamps[x],
                  'Status':np.random.choice(status_list),
                  'room_id':np.random.choice(team_list)} for x in range(len(timestamps))]
        
    return fake_workers

worker_df = pd.DataFrame(make_workers())
worker_df.head()

prints