1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
|
%global _empty_manifest_terminate_build 0
Name: python-names-dataset
Version: 3.1.0
Release: 1
Summary: The python library to handle names
License: MIT
URL: https://pypi.org/project/names-dataset/
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/a4/9f/955b8156b20d1afa1c7a7faa775761cd357b6c8df0e48c2d3828b25e8204/names-dataset-3.1.0.tar.gz
BuildArch: noarch
%description
# First and Last Names Database
[](https://pepy.tech/project/names-dataset)
[](https://pepy.tech/project/names-dataset/month)
This Python library provides information about names:
- Popularity (rank)
- Country (105 countries are supported)
- Gender
**Composition:** 730K first names, 983K last names - extracted from
the [Facebook massive dump (533M users)](https://www.theguardian.com/technology/2021/apr/03/500-million-facebook-users-website-hackers).
## Installation
Available on *[PyPI](https://pypi.org/project/names-dataset/)*:
```bash
pip install names-dataset
```
## Usage
Once it's installed, run those commands to familiarize yourself with the library:
```python
from names_dataset import NameDataset
# The V3 lib takes time to init (the database is massive). Tip: Put it into the init of your app.
nd = NameDataset()
print(nd.search('Walter'))
# {'first_name': {'country': {'Argentina': 0.062, 'Austria': 0.037, 'Bolivia, Plurinational State of': 0.042, 'Colombia': 0.096, 'Germany': 0.044, 'Italy': 0.295, 'Peru': 0.185, 'United States': 0.159, 'Uruguay': 0.036, 'South Africa': 0.043}, 'gender': {'Female': 0.007, 'Male': 0.993}, 'rank': {'Argentina': 37, 'Austria': 34, 'Bolivia, Plurinational State of': 67, 'Colombia': 250, 'Germany': 214, 'Italy': 193, 'Peru': 27, 'United States': 317, 'Uruguay': 44, 'South Africa': 388}}, 'last_name': {'country': {'Austria': 0.036, 'Brazil': 0.039, 'Switzerland': 0.032, 'Germany': 0.299, 'France': 0.121, 'United Kingdom': 0.048, 'Italy': 0.09, 'Nigeria': 0.078, 'United States': 0.172, 'South Africa': 0.085}, 'gender': {}, 'rank': {'Austria': 106, 'Brazil': 805, 'Switzerland': 140, 'Germany': 39, 'France': 625, 'United Kingdom': 1823, 'Italy': 3564, 'Nigeria': 926, 'United States': 1210, 'South Africa': 1169}}}
print(nd.search('White'))
# {'first_name': {'country': {'United Arab Emirates': 0.044, 'Egypt': 0.294, 'France': 0.061, 'Hong Kong': 0.05, 'Iraq': 0.094, 'Italy': 0.117, 'Malaysia': 0.133, 'Saudi Arabia': 0.089, 'Taiwan, Province of China': 0.044, 'United States': 0.072}, 'gender': {'Female': 0.519, 'Male': 0.481}, 'rank': {'Taiwan, Province of China': 6940, 'United Arab Emirates': None, 'Egypt': None, 'France': None, 'Hong Kong': None, 'Iraq': None, 'Italy': None, 'Malaysia': None, 'Saudi Arabia': None, 'United States': None}}, 'last_name': {'country': {'Canada': 0.035, 'France': 0.016, 'United Kingdom': 0.296, 'Ireland': 0.028, 'Iraq': 0.016, 'Italy': 0.02, 'Jamaica': 0.017, 'Nigeria': 0.031, 'United States': 0.5, 'South Africa': 0.04}, 'gender': {}, 'rank': {'Canada': 46, 'France': 1041, 'United Kingdom': 18, 'Ireland': 66, 'Iraq': 1307, 'Italy': 2778, 'Jamaica': 35, 'Nigeria': 425, 'United States': 47, 'South Africa': 416}}}
print(nd.search('محمد'))
# {'first_name': {'country': {'Algeria': 0.018, 'Egypt': 0.441, 'Iraq': 0.12, 'Jordan': 0.027, 'Libya': 0.035, 'Saudi Arabia': 0.154, 'Sudan': 0.07, 'Syrian Arab Republic': 0.062, 'Turkey': 0.022, 'Yemen': 0.051}, 'gender': {'Female': 0.035, 'Male': 0.965}, 'rank': {'Algeria': 4, 'Egypt': 1, 'Iraq': 2, 'Jordan': 1, 'Libya': 1, 'Saudi Arabia': 1, 'Sudan': 1, 'Syrian Arab Republic': 1, 'Turkey': 18, 'Yemen': 1}}, 'last_name': {'country': {'Egypt': 0.453, 'Iraq': 0.096, 'Jordan': 0.015, 'Libya': 0.043, 'Palestine, State of': 0.016, 'Saudi Arabia': 0.118, 'Sudan': 0.146, 'Syrian Arab Republic': 0.058, 'Turkey': 0.017, 'Yemen': 0.037}, 'gender': {}, 'rank': {'Egypt': 2, 'Iraq': 3, 'Jordan': 1, 'Libya': 1, 'Palestine, State of': 1, 'Saudi Arabia': 3, 'Sudan': 1, 'Syrian Arab Republic': 2, 'Turkey': 44, 'Yemen': 1}}}
print(nd.get_top_names(n=10, gender='Male', country_alpha2='US'))
# {'US': {'M': ['Jose', 'David', 'Michael', 'John', 'Juan', 'Carlos', 'Luis', 'Chris', 'Alex', 'Daniel']}}
print(nd.get_top_names(n=5, country_alpha2='ES'))
# {'ES': {'M': ['Jose', 'Antonio', 'Juan', 'Manuel', 'David'], 'F': ['Maria', 'Ana', 'Carmen', 'Laura', 'Isabel']}}
print(nd.get_country_codes(alpha_2=True))
# ['AE', 'AF', 'AL', 'AO', 'AR', 'AT', 'AZ', 'BD', 'BE', 'BF', 'BG', 'BH', 'BI', 'BN', 'BO', 'BR', 'BW', 'CA', 'CH', 'CL', 'CM', 'CN', 'CO', 'CR', 'CY', 'CZ', 'DE', 'DJ', 'DK', 'DZ', 'EC', 'EE', 'EG', 'ES', 'ET', 'FI', 'FJ', 'FR', 'GB', 'GE', 'GH', 'GR', 'GT', 'HK', 'HN', 'HR', 'HT', 'HU', 'ID', 'IE', 'IL', 'IN', 'IQ', 'IR', 'IS', 'IT', 'JM', 'JO', 'JP', 'KH', 'KR', 'KW', 'KZ', 'LB', 'LT', 'LU', 'LY', 'MA', 'MD', 'MO', 'MT', 'MU', 'MV', 'MX', 'MY', 'NA', 'NG', 'NL', 'NO', 'OM', 'PA', 'PE', 'PH', 'PL', 'PR', 'PS', 'PT', 'QA', 'RS', 'RU', 'SA', 'SD', 'SE', 'SG', 'SI', 'SV', 'SY', 'TM', 'TN', 'TR', 'TW', 'US', 'UY', 'YE', 'ZA']
```
## API
The `search` call provides information about:
- `country`: The probability of the name belonging to a country. Only the top 10 countries matching the name are returned.
- `gender`: The probability of the person to be a `Male` or `Female`.
- `rank`: The rank of the name in his country. `1` means the most popular name.
- **NOTE**: `first_name/last_name`: the `gender` does not apply to `last_name`.
The `get_top_names` call gives the most popular names:
- `n`: The number of names to return matching some criteria. Default is 100.
- `gender`: Filters on `Male` or `Female`. Default is None.
- `use_first_names`: Filters on the first names or last names. Default is True.
- `country_alpha2`: Filters on the country (e.g. GB is the United Kingdom). Default is None.
The `get_country_codes` returns the supported country codes (or full `pycountry` objects).
- `alpha_2`: Only returns the country codes: 2-char code. Default is False.
## Full dataset
- The full (curated) dataset containing first, last names along with gender and countries has been uploaded here: [
full.tar.bz2 (2.3G)](https://drive.google.com/file/d/1wRQfw5EYpzulvRfHCGIUWB2am5JUYVGk/view?usp=sharing).
## License
- This version was generated from the massive Facebook Leak (533M accounts).
- Lists of names are [not copyrightable](https://www.justia.com/intellectual-property/copyright/lists-directories-and-databases/), generally speaking, but if you want to be completely sure you should talk to a lawyer.
## Countries
🇲🇹🇪🇬🇧🇴🇳🇦🇹🇳🇷🇸🇯🇲🇦🇷🇯🇵🇰🇿🇸🇦🇺🇸🇦🇪🇭🇺🇭🇰🇶🇦🇸🇬🇩🇪🇾🇪🇲🇾🇭🇹🇵🇷🇨🇳🇦🇴🇹🇼🇸🇩🇧🇭🇧🇪🇪🇹🇪🇪🇨🇴🇬🇷🇧🇷🇷🇺🇱🇾🇸🇻🇰🇼🇰🇷🇦🇱🇸🇾🇧🇫🇨🇿🇨🇦🇴🇲🇩🇰🇨🇱🇧🇩🇧🇼🇫🇯🇮🇶🇮🇪🇿🇦🇨🇷🇯🇴🇰🇭🇵🇪🇺🇾🇮🇷🇲🇩🇫🇷🇲🇴🇳🇱🇬🇭🇨🇾🇩🇿🇮🇹🇬🇧🇧🇮🇮🇳🇫🇮🇦🇫🇵🇭🇦🇿🇬🇪🇨🇲🇮🇱🇪🇸🇱🇹🇩🇯🇬🇹🇱🇺🇵🇸🇹🇷🇵🇱🇮🇸🇳🇬🇵🇦🇭🇷🇸🇮🇭🇳🇦🇹🇲🇺🇸🇪🇲🇦🇨🇭🇧🇳🇲🇻🇳🇴🇪🇨🇮🇩🇧🇬🇵🇹🇲🇽🇱🇧🇹🇲
## Citation
```
@misc{NameDataset2021,
author = {Philippe Remy},
title = {Name Dataset},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/philipperemy/name-dataset}},
}
```
%package -n python3-names-dataset
Summary: The python library to handle names
Provides: python-names-dataset
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-names-dataset
# First and Last Names Database
[](https://pepy.tech/project/names-dataset)
[](https://pepy.tech/project/names-dataset/month)
This Python library provides information about names:
- Popularity (rank)
- Country (105 countries are supported)
- Gender
**Composition:** 730K first names, 983K last names - extracted from
the [Facebook massive dump (533M users)](https://www.theguardian.com/technology/2021/apr/03/500-million-facebook-users-website-hackers).
## Installation
Available on *[PyPI](https://pypi.org/project/names-dataset/)*:
```bash
pip install names-dataset
```
## Usage
Once it's installed, run those commands to familiarize yourself with the library:
```python
from names_dataset import NameDataset
# The V3 lib takes time to init (the database is massive). Tip: Put it into the init of your app.
nd = NameDataset()
print(nd.search('Walter'))
# {'first_name': {'country': {'Argentina': 0.062, 'Austria': 0.037, 'Bolivia, Plurinational State of': 0.042, 'Colombia': 0.096, 'Germany': 0.044, 'Italy': 0.295, 'Peru': 0.185, 'United States': 0.159, 'Uruguay': 0.036, 'South Africa': 0.043}, 'gender': {'Female': 0.007, 'Male': 0.993}, 'rank': {'Argentina': 37, 'Austria': 34, 'Bolivia, Plurinational State of': 67, 'Colombia': 250, 'Germany': 214, 'Italy': 193, 'Peru': 27, 'United States': 317, 'Uruguay': 44, 'South Africa': 388}}, 'last_name': {'country': {'Austria': 0.036, 'Brazil': 0.039, 'Switzerland': 0.032, 'Germany': 0.299, 'France': 0.121, 'United Kingdom': 0.048, 'Italy': 0.09, 'Nigeria': 0.078, 'United States': 0.172, 'South Africa': 0.085}, 'gender': {}, 'rank': {'Austria': 106, 'Brazil': 805, 'Switzerland': 140, 'Germany': 39, 'France': 625, 'United Kingdom': 1823, 'Italy': 3564, 'Nigeria': 926, 'United States': 1210, 'South Africa': 1169}}}
print(nd.search('White'))
# {'first_name': {'country': {'United Arab Emirates': 0.044, 'Egypt': 0.294, 'France': 0.061, 'Hong Kong': 0.05, 'Iraq': 0.094, 'Italy': 0.117, 'Malaysia': 0.133, 'Saudi Arabia': 0.089, 'Taiwan, Province of China': 0.044, 'United States': 0.072}, 'gender': {'Female': 0.519, 'Male': 0.481}, 'rank': {'Taiwan, Province of China': 6940, 'United Arab Emirates': None, 'Egypt': None, 'France': None, 'Hong Kong': None, 'Iraq': None, 'Italy': None, 'Malaysia': None, 'Saudi Arabia': None, 'United States': None}}, 'last_name': {'country': {'Canada': 0.035, 'France': 0.016, 'United Kingdom': 0.296, 'Ireland': 0.028, 'Iraq': 0.016, 'Italy': 0.02, 'Jamaica': 0.017, 'Nigeria': 0.031, 'United States': 0.5, 'South Africa': 0.04}, 'gender': {}, 'rank': {'Canada': 46, 'France': 1041, 'United Kingdom': 18, 'Ireland': 66, 'Iraq': 1307, 'Italy': 2778, 'Jamaica': 35, 'Nigeria': 425, 'United States': 47, 'South Africa': 416}}}
print(nd.search('محمد'))
# {'first_name': {'country': {'Algeria': 0.018, 'Egypt': 0.441, 'Iraq': 0.12, 'Jordan': 0.027, 'Libya': 0.035, 'Saudi Arabia': 0.154, 'Sudan': 0.07, 'Syrian Arab Republic': 0.062, 'Turkey': 0.022, 'Yemen': 0.051}, 'gender': {'Female': 0.035, 'Male': 0.965}, 'rank': {'Algeria': 4, 'Egypt': 1, 'Iraq': 2, 'Jordan': 1, 'Libya': 1, 'Saudi Arabia': 1, 'Sudan': 1, 'Syrian Arab Republic': 1, 'Turkey': 18, 'Yemen': 1}}, 'last_name': {'country': {'Egypt': 0.453, 'Iraq': 0.096, 'Jordan': 0.015, 'Libya': 0.043, 'Palestine, State of': 0.016, 'Saudi Arabia': 0.118, 'Sudan': 0.146, 'Syrian Arab Republic': 0.058, 'Turkey': 0.017, 'Yemen': 0.037}, 'gender': {}, 'rank': {'Egypt': 2, 'Iraq': 3, 'Jordan': 1, 'Libya': 1, 'Palestine, State of': 1, 'Saudi Arabia': 3, 'Sudan': 1, 'Syrian Arab Republic': 2, 'Turkey': 44, 'Yemen': 1}}}
print(nd.get_top_names(n=10, gender='Male', country_alpha2='US'))
# {'US': {'M': ['Jose', 'David', 'Michael', 'John', 'Juan', 'Carlos', 'Luis', 'Chris', 'Alex', 'Daniel']}}
print(nd.get_top_names(n=5, country_alpha2='ES'))
# {'ES': {'M': ['Jose', 'Antonio', 'Juan', 'Manuel', 'David'], 'F': ['Maria', 'Ana', 'Carmen', 'Laura', 'Isabel']}}
print(nd.get_country_codes(alpha_2=True))
# ['AE', 'AF', 'AL', 'AO', 'AR', 'AT', 'AZ', 'BD', 'BE', 'BF', 'BG', 'BH', 'BI', 'BN', 'BO', 'BR', 'BW', 'CA', 'CH', 'CL', 'CM', 'CN', 'CO', 'CR', 'CY', 'CZ', 'DE', 'DJ', 'DK', 'DZ', 'EC', 'EE', 'EG', 'ES', 'ET', 'FI', 'FJ', 'FR', 'GB', 'GE', 'GH', 'GR', 'GT', 'HK', 'HN', 'HR', 'HT', 'HU', 'ID', 'IE', 'IL', 'IN', 'IQ', 'IR', 'IS', 'IT', 'JM', 'JO', 'JP', 'KH', 'KR', 'KW', 'KZ', 'LB', 'LT', 'LU', 'LY', 'MA', 'MD', 'MO', 'MT', 'MU', 'MV', 'MX', 'MY', 'NA', 'NG', 'NL', 'NO', 'OM', 'PA', 'PE', 'PH', 'PL', 'PR', 'PS', 'PT', 'QA', 'RS', 'RU', 'SA', 'SD', 'SE', 'SG', 'SI', 'SV', 'SY', 'TM', 'TN', 'TR', 'TW', 'US', 'UY', 'YE', 'ZA']
```
## API
The `search` call provides information about:
- `country`: The probability of the name belonging to a country. Only the top 10 countries matching the name are returned.
- `gender`: The probability of the person to be a `Male` or `Female`.
- `rank`: The rank of the name in his country. `1` means the most popular name.
- **NOTE**: `first_name/last_name`: the `gender` does not apply to `last_name`.
The `get_top_names` call gives the most popular names:
- `n`: The number of names to return matching some criteria. Default is 100.
- `gender`: Filters on `Male` or `Female`. Default is None.
- `use_first_names`: Filters on the first names or last names. Default is True.
- `country_alpha2`: Filters on the country (e.g. GB is the United Kingdom). Default is None.
The `get_country_codes` returns the supported country codes (or full `pycountry` objects).
- `alpha_2`: Only returns the country codes: 2-char code. Default is False.
## Full dataset
- The full (curated) dataset containing first, last names along with gender and countries has been uploaded here: [
full.tar.bz2 (2.3G)](https://drive.google.com/file/d/1wRQfw5EYpzulvRfHCGIUWB2am5JUYVGk/view?usp=sharing).
## License
- This version was generated from the massive Facebook Leak (533M accounts).
- Lists of names are [not copyrightable](https://www.justia.com/intellectual-property/copyright/lists-directories-and-databases/), generally speaking, but if you want to be completely sure you should talk to a lawyer.
## Countries
🇲🇹🇪🇬🇧🇴🇳🇦🇹🇳🇷🇸🇯🇲🇦🇷🇯🇵🇰🇿🇸🇦🇺🇸🇦🇪🇭🇺🇭🇰🇶🇦🇸🇬🇩🇪🇾🇪🇲🇾🇭🇹🇵🇷🇨🇳🇦🇴🇹🇼🇸🇩🇧🇭🇧🇪🇪🇹🇪🇪🇨🇴🇬🇷🇧🇷🇷🇺🇱🇾🇸🇻🇰🇼🇰🇷🇦🇱🇸🇾🇧🇫🇨🇿🇨🇦🇴🇲🇩🇰🇨🇱🇧🇩🇧🇼🇫🇯🇮🇶🇮🇪🇿🇦🇨🇷🇯🇴🇰🇭🇵🇪🇺🇾🇮🇷🇲🇩🇫🇷🇲🇴🇳🇱🇬🇭🇨🇾🇩🇿🇮🇹🇬🇧🇧🇮🇮🇳🇫🇮🇦🇫🇵🇭🇦🇿🇬🇪🇨🇲🇮🇱🇪🇸🇱🇹🇩🇯🇬🇹🇱🇺🇵🇸🇹🇷🇵🇱🇮🇸🇳🇬🇵🇦🇭🇷🇸🇮🇭🇳🇦🇹🇲🇺🇸🇪🇲🇦🇨🇭🇧🇳🇲🇻🇳🇴🇪🇨🇮🇩🇧🇬🇵🇹🇲🇽🇱🇧🇹🇲
## Citation
```
@misc{NameDataset2021,
author = {Philippe Remy},
title = {Name Dataset},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/philipperemy/name-dataset}},
}
```
%package help
Summary: Development documents and examples for names-dataset
Provides: python3-names-dataset-doc
%description help
# First and Last Names Database
[](https://pepy.tech/project/names-dataset)
[](https://pepy.tech/project/names-dataset/month)
This Python library provides information about names:
- Popularity (rank)
- Country (105 countries are supported)
- Gender
**Composition:** 730K first names, 983K last names - extracted from
the [Facebook massive dump (533M users)](https://www.theguardian.com/technology/2021/apr/03/500-million-facebook-users-website-hackers).
## Installation
Available on *[PyPI](https://pypi.org/project/names-dataset/)*:
```bash
pip install names-dataset
```
## Usage
Once it's installed, run those commands to familiarize yourself with the library:
```python
from names_dataset import NameDataset
# The V3 lib takes time to init (the database is massive). Tip: Put it into the init of your app.
nd = NameDataset()
print(nd.search('Walter'))
# {'first_name': {'country': {'Argentina': 0.062, 'Austria': 0.037, 'Bolivia, Plurinational State of': 0.042, 'Colombia': 0.096, 'Germany': 0.044, 'Italy': 0.295, 'Peru': 0.185, 'United States': 0.159, 'Uruguay': 0.036, 'South Africa': 0.043}, 'gender': {'Female': 0.007, 'Male': 0.993}, 'rank': {'Argentina': 37, 'Austria': 34, 'Bolivia, Plurinational State of': 67, 'Colombia': 250, 'Germany': 214, 'Italy': 193, 'Peru': 27, 'United States': 317, 'Uruguay': 44, 'South Africa': 388}}, 'last_name': {'country': {'Austria': 0.036, 'Brazil': 0.039, 'Switzerland': 0.032, 'Germany': 0.299, 'France': 0.121, 'United Kingdom': 0.048, 'Italy': 0.09, 'Nigeria': 0.078, 'United States': 0.172, 'South Africa': 0.085}, 'gender': {}, 'rank': {'Austria': 106, 'Brazil': 805, 'Switzerland': 140, 'Germany': 39, 'France': 625, 'United Kingdom': 1823, 'Italy': 3564, 'Nigeria': 926, 'United States': 1210, 'South Africa': 1169}}}
print(nd.search('White'))
# {'first_name': {'country': {'United Arab Emirates': 0.044, 'Egypt': 0.294, 'France': 0.061, 'Hong Kong': 0.05, 'Iraq': 0.094, 'Italy': 0.117, 'Malaysia': 0.133, 'Saudi Arabia': 0.089, 'Taiwan, Province of China': 0.044, 'United States': 0.072}, 'gender': {'Female': 0.519, 'Male': 0.481}, 'rank': {'Taiwan, Province of China': 6940, 'United Arab Emirates': None, 'Egypt': None, 'France': None, 'Hong Kong': None, 'Iraq': None, 'Italy': None, 'Malaysia': None, 'Saudi Arabia': None, 'United States': None}}, 'last_name': {'country': {'Canada': 0.035, 'France': 0.016, 'United Kingdom': 0.296, 'Ireland': 0.028, 'Iraq': 0.016, 'Italy': 0.02, 'Jamaica': 0.017, 'Nigeria': 0.031, 'United States': 0.5, 'South Africa': 0.04}, 'gender': {}, 'rank': {'Canada': 46, 'France': 1041, 'United Kingdom': 18, 'Ireland': 66, 'Iraq': 1307, 'Italy': 2778, 'Jamaica': 35, 'Nigeria': 425, 'United States': 47, 'South Africa': 416}}}
print(nd.search('محمد'))
# {'first_name': {'country': {'Algeria': 0.018, 'Egypt': 0.441, 'Iraq': 0.12, 'Jordan': 0.027, 'Libya': 0.035, 'Saudi Arabia': 0.154, 'Sudan': 0.07, 'Syrian Arab Republic': 0.062, 'Turkey': 0.022, 'Yemen': 0.051}, 'gender': {'Female': 0.035, 'Male': 0.965}, 'rank': {'Algeria': 4, 'Egypt': 1, 'Iraq': 2, 'Jordan': 1, 'Libya': 1, 'Saudi Arabia': 1, 'Sudan': 1, 'Syrian Arab Republic': 1, 'Turkey': 18, 'Yemen': 1}}, 'last_name': {'country': {'Egypt': 0.453, 'Iraq': 0.096, 'Jordan': 0.015, 'Libya': 0.043, 'Palestine, State of': 0.016, 'Saudi Arabia': 0.118, 'Sudan': 0.146, 'Syrian Arab Republic': 0.058, 'Turkey': 0.017, 'Yemen': 0.037}, 'gender': {}, 'rank': {'Egypt': 2, 'Iraq': 3, 'Jordan': 1, 'Libya': 1, 'Palestine, State of': 1, 'Saudi Arabia': 3, 'Sudan': 1, 'Syrian Arab Republic': 2, 'Turkey': 44, 'Yemen': 1}}}
print(nd.get_top_names(n=10, gender='Male', country_alpha2='US'))
# {'US': {'M': ['Jose', 'David', 'Michael', 'John', 'Juan', 'Carlos', 'Luis', 'Chris', 'Alex', 'Daniel']}}
print(nd.get_top_names(n=5, country_alpha2='ES'))
# {'ES': {'M': ['Jose', 'Antonio', 'Juan', 'Manuel', 'David'], 'F': ['Maria', 'Ana', 'Carmen', 'Laura', 'Isabel']}}
print(nd.get_country_codes(alpha_2=True))
# ['AE', 'AF', 'AL', 'AO', 'AR', 'AT', 'AZ', 'BD', 'BE', 'BF', 'BG', 'BH', 'BI', 'BN', 'BO', 'BR', 'BW', 'CA', 'CH', 'CL', 'CM', 'CN', 'CO', 'CR', 'CY', 'CZ', 'DE', 'DJ', 'DK', 'DZ', 'EC', 'EE', 'EG', 'ES', 'ET', 'FI', 'FJ', 'FR', 'GB', 'GE', 'GH', 'GR', 'GT', 'HK', 'HN', 'HR', 'HT', 'HU', 'ID', 'IE', 'IL', 'IN', 'IQ', 'IR', 'IS', 'IT', 'JM', 'JO', 'JP', 'KH', 'KR', 'KW', 'KZ', 'LB', 'LT', 'LU', 'LY', 'MA', 'MD', 'MO', 'MT', 'MU', 'MV', 'MX', 'MY', 'NA', 'NG', 'NL', 'NO', 'OM', 'PA', 'PE', 'PH', 'PL', 'PR', 'PS', 'PT', 'QA', 'RS', 'RU', 'SA', 'SD', 'SE', 'SG', 'SI', 'SV', 'SY', 'TM', 'TN', 'TR', 'TW', 'US', 'UY', 'YE', 'ZA']
```
## API
The `search` call provides information about:
- `country`: The probability of the name belonging to a country. Only the top 10 countries matching the name are returned.
- `gender`: The probability of the person to be a `Male` or `Female`.
- `rank`: The rank of the name in his country. `1` means the most popular name.
- **NOTE**: `first_name/last_name`: the `gender` does not apply to `last_name`.
The `get_top_names` call gives the most popular names:
- `n`: The number of names to return matching some criteria. Default is 100.
- `gender`: Filters on `Male` or `Female`. Default is None.
- `use_first_names`: Filters on the first names or last names. Default is True.
- `country_alpha2`: Filters on the country (e.g. GB is the United Kingdom). Default is None.
The `get_country_codes` returns the supported country codes (or full `pycountry` objects).
- `alpha_2`: Only returns the country codes: 2-char code. Default is False.
## Full dataset
- The full (curated) dataset containing first, last names along with gender and countries has been uploaded here: [
full.tar.bz2 (2.3G)](https://drive.google.com/file/d/1wRQfw5EYpzulvRfHCGIUWB2am5JUYVGk/view?usp=sharing).
## License
- This version was generated from the massive Facebook Leak (533M accounts).
- Lists of names are [not copyrightable](https://www.justia.com/intellectual-property/copyright/lists-directories-and-databases/), generally speaking, but if you want to be completely sure you should talk to a lawyer.
## Countries
🇲🇹🇪🇬🇧🇴🇳🇦🇹🇳🇷🇸🇯🇲🇦🇷🇯🇵🇰🇿🇸🇦🇺🇸🇦🇪🇭🇺🇭🇰🇶🇦🇸🇬🇩🇪🇾🇪🇲🇾🇭🇹🇵🇷🇨🇳🇦🇴🇹🇼🇸🇩🇧🇭🇧🇪🇪🇹🇪🇪🇨🇴🇬🇷🇧🇷🇷🇺🇱🇾🇸🇻🇰🇼🇰🇷🇦🇱🇸🇾🇧🇫🇨🇿🇨🇦🇴🇲🇩🇰🇨🇱🇧🇩🇧🇼🇫🇯🇮🇶🇮🇪🇿🇦🇨🇷🇯🇴🇰🇭🇵🇪🇺🇾🇮🇷🇲🇩🇫🇷🇲🇴🇳🇱🇬🇭🇨🇾🇩🇿🇮🇹🇬🇧🇧🇮🇮🇳🇫🇮🇦🇫🇵🇭🇦🇿🇬🇪🇨🇲🇮🇱🇪🇸🇱🇹🇩🇯🇬🇹🇱🇺🇵🇸🇹🇷🇵🇱🇮🇸🇳🇬🇵🇦🇭🇷🇸🇮🇭🇳🇦🇹🇲🇺🇸🇪🇲🇦🇨🇭🇧🇳🇲🇻🇳🇴🇪🇨🇮🇩🇧🇬🇵🇹🇲🇽🇱🇧🇹🇲
## Citation
```
@misc{NameDataset2021,
author = {Philippe Remy},
title = {Name Dataset},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/philipperemy/name-dataset}},
}
```
%prep
%autosetup -n names-dataset-3.1.0
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-names-dataset -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Tue Apr 25 2023 Python_Bot <Python_Bot@openeuler.org> - 3.1.0-1
- Package Spec generated
|
