1.Generate_json

In [ ]:

# !pip install Faker

# !pip install Faker

In [ ]:

from faker import Faker
from faker.providers import DynamicProvider
import random
import pandas as pd

job_provider = DynamicProvider(
     provider_name="job",
     elements=[
         "student", "doctor", "nurse", "teacher", "software enginerr",
         "data science", "data engineer", "tester", "data analyst",
         "lawyer", "mechanic", "accountant", "sales", "chef", "police",
         "architect", "graphic designer", "plumber", "marketing", "dentist",
         "electrician"
        ],
)

fake = Faker()

fake.add_provider(job_provider)

from faker import Faker from faker.providers import DynamicProvider import random import pandas as pd job_provider = DynamicProvider( provider_name="job", elements=[ "student", "doctor", "nurse", "teacher", "software enginerr", "data science", "data engineer", "tester", "data analyst", "lawyer", "mechanic", "accountant", "sales", "chef", "police", "architect", "graphic designer", "plumber", "marketing", "dentist", "electrician" ], ) fake = Faker() fake.add_provider(job_provider)

In [ ]:

column = ["uid", "name", "age", "job"]

column = ["uid", "name", "age", "job"]

In [ ]:

data = []
for i in range(2000):
    data.append(
        ("id"+str(i).rjust(5, "0"), fake.name(), random.randint(10, 70), fake.job())
    )

data = [] for i in range(2000): data.append( ("id"+str(i).rjust(5, "0"), fake.name(), random.randint(10, 70), fake.job()) )

In [ ]:

df = pd.DataFrame(data, columns=column)

df = pd.DataFrame(data, columns=column)

In [ ]:

df.to_json('./dataset/raw.json', index=False)
df.to_csv('./dataset/raw.csv', index=False)

df.to_json('./dataset/raw.json', index=False) df.to_csv('./dataset/raw.csv', index=False)

In [ ]:

df

df

In [ ]: