def create_first_df(num_rows): myDB = pydbgen.pydb() df1 = myDB.gen_dataframe(num_rows,['name', 'age']) for index, row in df1.iterrows(): # row['age'] = np.random.randint(10) row['age'] = np.random.zipf(2) # Change some age values to negative values for index, row in df1.iterrows(): if index / 2 == 0: row['age'] == 0 - row['age'] return df1
else:
b = random.random()
if b < .5:
return address
elif b < .65:
return address.split(" ")[0]
elif b < .8:
return address.split(" ")[1]
elif b < .95:
return address.split(" ")[2]
else:
return "8876 Heather Ave."
if __name__ == '__main__':
myDB = pydb()
df = pd.DataFrame()
data = myDB.gen_dataframe(10000, [
'name', 'date', 'ssn', 'country', 'street_address', 'city', 'state',
'zipcode', 'company', 'phone_number_full'
])
df = pd.concat([df, data])
for i in range(4):
df = pd.concat([df, data.sample(9000)])
df.sort_index(inplace=True)
df['duns'] = df['ssn'].apply(lambda x: 1 + int("".join(x.split("-"))))
df['rssd_id'] = df['ssn'].apply(lambda x: 2 + int("".join(x.split("-"))))
# -*- coding: utf-8 -*-
"""
Created on Sun Oct 27 14:07:22 2019
@author: arifr
"""
import pydbgen
import random
from pydbgen import pydbgen
db = pydbgen.pydb()
import mysql.connector
from mysql.connector import Error
import sys
nurseidlist = []
for i in range(5000, 6000):
nurseidlist.append(random.randrange(5000, 6000))
pidlist = []
for i in range(5000, 6000):
pidlist.append(random.randrange(1000, 2100))
l = []
i = 0
while (i < 1000):
x = []
i += 1
x.append(nurseidlist.pop(0))
x.append(pidlist.pop(0))
filter = "JSON file (*.json)|*.json|All Files (*.*)|*.*||"
filename = rs.OpenFileName(
"DataBase\etablissements-denseignement-superieur.json", filter)
#Read JSON data into the datastore variable
if filename:
with open(filename, 'r') as f:
datastore = json.load(f)
#Use the new datastore datastructure
print(datastore["lon"])
Names = []
fake = Faker("fr_FR")
for i in range(0, 200):
name = fake.name()
if name not in Names:
Names.append(name)
print(name)
GenDB = pydbgen.pydb()
Loc = []
for i in range(0, 200):
loc = fake.local_latlng(country_code='FR', coords_only=False)
if loc not in Loc:
Loc.append(loc)
print(loc)
print(fake.address())
# genère des données random grace à faker et pydbgen
import faker
import pydbgen
from pydbgen import pydbgen
print("import success")
# création d'un objet base de donnée
myDB = pydbgen.pydb()
# File faker\proxy.py", line 83, in __getattribute__
# raise TypeError(msg) erreur génerée ici !!!
# Enlever ça :
# if attr == 'seed':
# msg = (
# 'Calling `.seed()` on instances is deprecated. '
# 'Use the class method `Faker.seed()` instead.'
# )
# raise TypeError(msg)
# else:
# car MAJ de Faker ^^
# affiche 10 villes avec des noms random
print(myDB.gen_data_series(num=8, data_type='city'))
# genère un fichier excel, il faut installer openpy et ajouter DOmain.txt au dossier !!!
myDB.gen_excel(10000, fields=['name', 'year', 'email', 'license_plate', 'Job title'],
filename='Employe.xlsx', real_email=True)
print("Le fichier Excel a été généré !!!")