Create fake data with Faker in Python

1pip install faker

1from faker import Faker
2
3fake = Faker()
4
5# fake name
6fake.name()
7
8# 'Stefanie Brown'

 1methods = [x for x in dir(fake) if not x.startswith('_')]
 2print(f"number of methods = {len(methods)}")
 3# number of methods = 297
 4
 5
 6# print(methods)
 7for index in range(0, len(methods), 4):
 8    print(methods[index].ljust(35, " "), end="")
 9    try:
10        print(methods[index+1].ljust(35, " "), end="")
11        print(methods[index+2].ljust(35, " "), end="")
12        print(methods[index+3].ljust(35, " "))
13    except IndexError:
14        break

1[x for x in dir(fake) if not x.startswith('_') and x.find('name') > -1]

1for name_method in [x for x in dir(fake) if not x.startswith('_') and x.find('name') > -1]:
2    print(f"{name_method.ljust(23, ' ')} :   { eval(f'fake.{name_method}()') }")

 1Faker.seed(42)
 2for i in range(5):
 3    print(fake.name())
 4# Allison Hill
 5# Noah Rhodes
 6# Angie Henderson
 7# Daniel Wagner
 8# Cristian Santos
 9
10
11Faker.seed(42)
12for i in range(5):
13    print(fake.name())
14# Allison Hill
15# Noah Rhodes
16# Angie Henderson
17# Daniel Wagner
18# Cristian Santos

1italian_fake = Faker('it_IT')
2for name_method in [x for x in dir(italian_fake) if not x.startswith('_') and x.find('name') == 0]:
3     print(f"{name_method.ljust(23, ' ')} =   { eval(f'italian_fake.{name_method}()') }")
4
5# name                    =   Lando Opizzi
6# name_female             =   Elvira Bonanno-Beccheria
7# name_male               =   Dott. Jacopo Bottaro
8# name_nonbinary          =   Ciro Parmitano

1japanese_fake = Faker('ja_JP')
2for name_method in [x for x in dir(japanese_fake) if not x.startswith('_') and x.find('name') == 0]:
3    print(f"{name_method.ljust(30, ' ')} =   { eval(f'japanese_fake.{name_method}()') }")
4
5# name                           =   山田 春香
6# name_female                    =   小林 知実
7# name_male                      =   橋本 稔
8# name_nonbinary                 =   斎藤 健一

1chinese_fake = Faker('zh_CN')
2for name_method in [x for x in dir(chinese_fake) if not x.startswith('_') and x.find('name') == 0]:
3    print(f"{name_method.ljust(30, ' ')} =   { eval(f'chinese_fake.{name_method}()') }")
4
5# name                           =   张春梅
6# name_female                    =   权建平
7# name_male                      =   贺华
8# name_nonbinary                 =   阎玉梅

1Faker.seed(42)
2DATA_SIZE = 500
3names = [fake.first_name() for i in range(DATA_SIZE)]
4ages = [fake.random_int(min=21, max=80) for x in range(DATA_SIZE)]
5states = [fake.state() for x in range(DATA_SIZE)]
6jobs = [fake.job() for x in range(DATA_SIZE)]
7
8data = {'name': names, 'age': ages, 'state': states, 'job': jobs}
9df = pd.DataFrame.from_dict(data)

 1mean_age_df = df[['state', 'age']].groupby('state').mean()
 2mean_age_df.rename_axis(None, axis = 0, inplace = True)
 3top_df = mean_age_df.sort_values(by=['age'], ascending = False).head(10)
 4
 5fig, ax = plt.subplots(figsize = (10,7), facecolor=plt.cm.Blues(.2))
 6ax.set_facecolor(plt.cm.Blues(.2))
 7
 8fig.suptitle('Top 10 States with highest average age',
 9             fontsize = 18,  
10             fontweight = 'bold')
11
12states = list(top_df.index)
13y_pos = np.arange(len(states))
14ages = list(top_df['age'])
15
16ax.barh(y_pos, ages, align='center')
17ax.set_yticks(y_pos)
18ax.invert_yaxis()
19ax.set_xlabel('Average Age', fontsize = 14)
20
21# Display highest on top
22ax.set_yticklabels(states, fontsize = 14)
23
24# Hide the right and top spines
25ax.spines['right'].set_visible(False)
26ax.spines['top'].set_visible(False)
27
28plt.show