gngram-lookup 0.2.0__tar.gz → 0.2.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/PKG-INFO +9 -1
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/README.md +8 -0
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/pyproject.toml +1 -1
- gngram_lookup-0.2.1/setup.py +35 -0
- gngram_lookup-0.2.0/setup.py +0 -35
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/LICENSE +0 -0
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/gngram_counter/__init__.py +0 -0
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/gngram_counter/cli.py +0 -0
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/gngram_counter/data.py +0 -0
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/gngram_counter/download_data.py +0 -0
- {gngram_lookup-0.2.0 → gngram_lookup-0.2.1}/gngram_counter/lookup.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: gngram-lookup
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.1
|
|
4
4
|
Summary: Static Hash-Based Lookup for Google Ngram Frequencies
|
|
5
5
|
Home-page: https://github.com/craigtrim/gngram-lookup
|
|
6
6
|
License: Proprietary
|
|
@@ -30,6 +30,9 @@ Description-Content-Type: text/markdown
|
|
|
30
30
|
# gngram-lookup
|
|
31
31
|
|
|
32
32
|
[](https://badge.fury.io/py/gngram-lookup)
|
|
33
|
+
[](https://pepy.tech/project/gngram-lookup)
|
|
34
|
+
[](https://pepy.tech/project/gngram-lookup)
|
|
35
|
+
[](tests/)
|
|
33
36
|
[](https://www.python.org/downloads/)
|
|
34
37
|
|
|
35
38
|
Word frequency from 500 years of books. O(1) lookup. 5 million words.
|
|
@@ -77,6 +80,11 @@ gngram-freq computer
|
|
|
77
80
|
- [Use Cases](docs/use-cases.md)
|
|
78
81
|
- [Development](docs/development.md)
|
|
79
82
|
|
|
83
|
+
## See Also
|
|
84
|
+
|
|
85
|
+
- [bnc-lookup](https://pypi.org/project/bnc-lookup/) - O(1) lookup for British National Corpus
|
|
86
|
+
- [wordnet-lookup](https://pypi.org/project/wordnet-lookup/) - O(1) lookup for WordNet
|
|
87
|
+
|
|
80
88
|
## Attribution
|
|
81
89
|
|
|
82
90
|
Data derived from the [Google Books Ngram](https://books.google.com/ngrams) dataset.
|
|
@@ -1,6 +1,9 @@
|
|
|
1
1
|
# gngram-lookup
|
|
2
2
|
|
|
3
3
|
[](https://badge.fury.io/py/gngram-lookup)
|
|
4
|
+
[](https://pepy.tech/project/gngram-lookup)
|
|
5
|
+
[](https://pepy.tech/project/gngram-lookup)
|
|
6
|
+
[](tests/)
|
|
4
7
|
[](https://www.python.org/downloads/)
|
|
5
8
|
|
|
6
9
|
Word frequency from 500 years of books. O(1) lookup. 5 million words.
|
|
@@ -48,6 +51,11 @@ gngram-freq computer
|
|
|
48
51
|
- [Use Cases](docs/use-cases.md)
|
|
49
52
|
- [Development](docs/development.md)
|
|
50
53
|
|
|
54
|
+
## See Also
|
|
55
|
+
|
|
56
|
+
- [bnc-lookup](https://pypi.org/project/bnc-lookup/) - O(1) lookup for British National Corpus
|
|
57
|
+
- [wordnet-lookup](https://pypi.org/project/wordnet-lookup/) - O(1) lookup for WordNet
|
|
58
|
+
|
|
51
59
|
## Attribution
|
|
52
60
|
|
|
53
61
|
Data derived from the [Google Books Ngram](https://books.google.com/ngrams) dataset.
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
[tool.poetry]
|
|
2
2
|
name = "gngram-lookup"
|
|
3
3
|
packages = [{include = "gngram_counter"}]
|
|
4
|
-
version = "0.2.
|
|
4
|
+
version = "0.2.1"
|
|
5
5
|
description = "Static Hash-Based Lookup for Google Ngram Frequencies"
|
|
6
6
|
authors = ["Craig Trim <craigtrim@gmail.com>"]
|
|
7
7
|
maintainers = ["Craig Trim <craigtrim@gmail.com>"]
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
# -*- coding: utf-8 -*-
|
|
2
|
+
from setuptools import setup
|
|
3
|
+
|
|
4
|
+
packages = \
|
|
5
|
+
['gngram_counter']
|
|
6
|
+
|
|
7
|
+
package_data = \
|
|
8
|
+
{'': ['*']}
|
|
9
|
+
|
|
10
|
+
install_requires = \
|
|
11
|
+
['polars>=1.0,<2.0', 'pyarrow>=18.0,<19.0']
|
|
12
|
+
|
|
13
|
+
entry_points = \
|
|
14
|
+
{'console_scripts': ['gngram-exists = gngram_counter.cli:gngram_exists',
|
|
15
|
+
'gngram-freq = gngram_counter.cli:gngram_freq']}
|
|
16
|
+
|
|
17
|
+
setup_kwargs = {
|
|
18
|
+
'name': 'gngram-lookup',
|
|
19
|
+
'version': '0.2.1',
|
|
20
|
+
'description': 'Static Hash-Based Lookup for Google Ngram Frequencies',
|
|
21
|
+
'long_description': "# gngram-lookup\n\n[](https://badge.fury.io/py/gngram-lookup)\n[](https://pepy.tech/project/gngram-lookup)\n[](https://pepy.tech/project/gngram-lookup)\n[](tests/)\n[](https://www.python.org/downloads/)\n\nWord frequency from 500 years of books. O(1) lookup. 5 million words.\n\n## Install\n\n```bash\npip install gngram-lookup\npython -m gngram_lookup.download_data\n```\n\n## Python\n\n```python\nimport gngram_lookup as ng\n\nng.exists('computer') # True\nng.exists('xyznotaword') # False\n\nng.frequency('computer')\n# {'peak_tf': 2000, 'peak_df': 2000, 'sum_tf': 892451, 'sum_df': 312876}\n\nng.batch_frequency(['the', 'algorithm', 'xyznotaword'])\n# {'the': {...}, 'algorithm': {...}, 'xyznotaword': None}\n```\n\n## CLI\n\n```bash\ngngram-exists computer # True, exit 0\ngngram-exists xyznotaword # False, exit 1\n\ngngram-freq computer\n# peak_tf_decade: 2000\n# peak_df_decade: 2000\n# sum_tf: 892451\n# sum_df: 312876\n```\n\n## Docs\n\n- [API Reference](docs/api.md)\n- [CLI Reference](docs/cli.md)\n- [Data Format](docs/data-format.md)\n- [Use Cases](docs/use-cases.md)\n- [Development](docs/development.md)\n\n## See Also\n\n- [bnc-lookup](https://pypi.org/project/bnc-lookup/) - O(1) lookup for British National Corpus\n- [wordnet-lookup](https://pypi.org/project/wordnet-lookup/) - O(1) lookup for WordNet\n\n## Attribution\n\nData derived from the [Google Books Ngram](https://books.google.com/ngrams) dataset.\n\n## License\n\nProprietary. See [LICENSE](LICENSE).\n",
|
|
22
|
+
'author': 'Craig Trim',
|
|
23
|
+
'author_email': 'craigtrim@gmail.com',
|
|
24
|
+
'maintainer': 'Craig Trim',
|
|
25
|
+
'maintainer_email': 'craigtrim@gmail.com',
|
|
26
|
+
'url': 'https://github.com/craigtrim/gngram-lookup',
|
|
27
|
+
'packages': packages,
|
|
28
|
+
'package_data': package_data,
|
|
29
|
+
'install_requires': install_requires,
|
|
30
|
+
'entry_points': entry_points,
|
|
31
|
+
'python_requires': '>=3.11,<4.0',
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
setup(**setup_kwargs)
|
gngram_lookup-0.2.0/setup.py
DELETED
|
@@ -1,35 +0,0 @@
|
|
|
1
|
-
# -*- coding: utf-8 -*-
|
|
2
|
-
from setuptools import setup
|
|
3
|
-
|
|
4
|
-
packages = \
|
|
5
|
-
['gngram_counter']
|
|
6
|
-
|
|
7
|
-
package_data = \
|
|
8
|
-
{'': ['*']}
|
|
9
|
-
|
|
10
|
-
install_requires = \
|
|
11
|
-
['polars>=1.0,<2.0', 'pyarrow>=18.0,<19.0']
|
|
12
|
-
|
|
13
|
-
entry_points = \
|
|
14
|
-
{'console_scripts': ['gngram-exists = gngram_counter.cli:gngram_exists',
|
|
15
|
-
'gngram-freq = gngram_counter.cli:gngram_freq']}
|
|
16
|
-
|
|
17
|
-
setup_kwargs = {
|
|
18
|
-
'name': 'gngram-lookup',
|
|
19
|
-
'version': '0.2.0',
|
|
20
|
-
'description': 'Static Hash-Based Lookup for Google Ngram Frequencies',
|
|
21
|
-
'long_description': "# gngram-lookup\n\n[](https://badge.fury.io/py/gngram-lookup)\n[](https://www.python.org/downloads/)\n\nWord frequency from 500 years of books. O(1) lookup. 5 million words.\n\n## Install\n\n```bash\npip install gngram-lookup\npython -m gngram_lookup.download_data\n```\n\n## Python\n\n```python\nimport gngram_lookup as ng\n\nng.exists('computer') # True\nng.exists('xyznotaword') # False\n\nng.frequency('computer')\n# {'peak_tf': 2000, 'peak_df': 2000, 'sum_tf': 892451, 'sum_df': 312876}\n\nng.batch_frequency(['the', 'algorithm', 'xyznotaword'])\n# {'the': {...}, 'algorithm': {...}, 'xyznotaword': None}\n```\n\n## CLI\n\n```bash\ngngram-exists computer # True, exit 0\ngngram-exists xyznotaword # False, exit 1\n\ngngram-freq computer\n# peak_tf_decade: 2000\n# peak_df_decade: 2000\n# sum_tf: 892451\n# sum_df: 312876\n```\n\n## Docs\n\n- [API Reference](docs/api.md)\n- [CLI Reference](docs/cli.md)\n- [Data Format](docs/data-format.md)\n- [Use Cases](docs/use-cases.md)\n- [Development](docs/development.md)\n\n## Attribution\n\nData derived from the [Google Books Ngram](https://books.google.com/ngrams) dataset.\n\n## License\n\nProprietary. See [LICENSE](LICENSE).\n",
|
|
22
|
-
'author': 'Craig Trim',
|
|
23
|
-
'author_email': 'craigtrim@gmail.com',
|
|
24
|
-
'maintainer': 'Craig Trim',
|
|
25
|
-
'maintainer_email': 'craigtrim@gmail.com',
|
|
26
|
-
'url': 'https://github.com/craigtrim/gngram-lookup',
|
|
27
|
-
'packages': packages,
|
|
28
|
-
'package_data': package_data,
|
|
29
|
-
'install_requires': install_requires,
|
|
30
|
-
'entry_points': entry_points,
|
|
31
|
-
'python_requires': '>=3.11,<4.0',
|
|
32
|
-
}
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
setup(**setup_kwargs)
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|