brill-postagger 0.1.1__tar.gz

brill_postagger-0.1.1/PKG-INFO

@@ -0,0 +1,11 @@
+Metadata-Version: 2.1
+Name: brill_postagger
+Version: 0.1.1
+Summary: Brill Postagger for various languages using NLTK
+Home-page: https://github.com/TigreGotico/brill_postaggers
+Author: JarbasAi
+Author-email: jarbasai@mailfence.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9

brill_postagger-0.1.1/README.md

@@ -0,0 +1,54 @@
+# Brill Postagger
+
+A Python package that uses the Brill Tagging algorithm for part-of-speech tagging, available for several languages. It utilizes the NLTK library for tokenization and tagging.
+
+Models have been trained with [UniversalDependencies](https://github.com/UniversalDependencies) datasets
+
+## Installation
+
+To install the package, you can use pip:
+
+```bash
+pip install brill_postagger
+```
+
+## Usage
+
+To use the Brill Postagger, first download the corresponding pre-trained model, then use it to tag sentences in various languages.
+
+Example usage:
+
+```python
+from brill_postagger import BrillPostagger
+
+# Initialize the tagger for Portuguese (pt)
+tagger = BrillPostagger.from_pretrained("pt")
+
+# Tag a sentence
+result = tagger.tag("como está o tempo lá fora?")
+print(result)
+```
+
+### Supported Languages
+
+The following languages are supported, each corresponding to a pre-trained model:
+
+- Catalan (`ca`)
+- Danish (`da`)
+- German (`de`)
+- English (`en`)
+- Spanish (`es`)
+- Basque (`eu`)
+- French (`fr`)
+- Galician (`gl`)
+- Italian (`it`)
+- Dutch (`nl`)
+- Portuguese (`pt`)
+
+### Contributing
+
+If you'd like to contribute to the project, please feel free to submit issues or pull requests. Contributions are always welcome!
+
+### License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

brill_postagger-0.1.1/brill_postagger.egg-info/PKG-INFO

@@ -0,0 +1,11 @@
+Metadata-Version: 2.1
+Name: brill-postagger
+Version: 0.1.1
+Summary: Brill Postagger for various languages using NLTK
+Home-page: https://github.com/TigreGotico/brill_postaggers
+Author: JarbasAi
+Author-email: jarbasai@mailfence.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9

brill_postagger-0.1.1/brill_postagger.egg-info/SOURCES.txt

@@ -0,0 +1,20 @@
+README.md
+setup.py
+brill_postagger.egg-info/PKG-INFO
+brill_postagger.egg-info/SOURCES.txt
+brill_postagger.egg-info/dependency_links.txt
+brill_postagger.egg-info/requires.txt
+brill_postagger.egg-info/top_level.txt
+brill_postaggers/__init__.py
+brill_postaggers/ca_ancora-ud-brill.pkl
+brill_postaggers/da_ddt-ud-brill.pkl
+brill_postaggers/de_gsd-ud-brill.pkl
+brill_postaggers/en_ewt-ud-brill.pkl
+brill_postaggers/es_ancora-ud-brill.pkl
+brill_postaggers/eu_bdt-ud-brill.pkl
+brill_postaggers/fr_gsd-ud-brill.pkl
+brill_postaggers/gl_ctg-ud-brill.pkl
+brill_postaggers/it_vit-ud-brill.pkl
+brill_postaggers/nl_alpino-ud-brill.pkl
+brill_postaggers/pt_bosque-ud-brill.pkl
+brill_postaggers/version.py

brill_postagger-0.1.1/brill_postagger.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

brill_postagger-0.1.1/brill_postagger.egg-info/requires.txt

@@ -0,0 +1 @@
+nltk

brill_postagger-0.1.1/brill_postagger.egg-info/top_level.txt

@@ -0,0 +1 @@
+brill_postaggers

brill_postagger-0.1.1/brill_postaggers/__init__.py

@@ -0,0 +1,37 @@
+import os.path
+import pickle
+
+import nltk
+
+
+class BrillPostagger:
+    MODELS = {
+        "ca": "ca_ancora-ud-brill",
+        "da": "da_ddt-ud-brill",
+        "de": "de_gsd-ud-brill",
+        "en": "en_ewt-ud-brill",
+        "es": "es_ancora-ud-brill",
+        "eu": "eu_bdt-ud-brill",
+        "fr": "fr_gsd-ud-brill",
+        "gl": "gl_ctg-ud-brill",
+        "it": "it_vit-ud-brill",
+        "nl": "nl_alpino-ud-brill",
+        "pt": "pt_bosque-ud-brill"
+    }
+    def __init__(self, model: str):
+        with open(model, "rb") as f:
+            self.tagger = pickle.load(f)
+
+    @staticmethod
+    def from_pretrained(lang: str):
+        lang = lang.split("-")[0].lower()
+        model = BrillPostagger.MODELS[lang]
+        return BrillPostagger(f"{os.path.dirname(__file__)}/{model}.pkl")
+
+    def tag(self, sentence: str):
+        tokens = nltk.word_tokenize(sentence)
+        return self.tagger.tag(tokens)
+
+if __name__ == "__main__":
+    tagger = BrillPostagger.from_pretrained("pt")
+    print(tagger.tag("como está o tempo lá fora?"))

brill_postagger-0.1.1/brill_postaggers/version.py

@@ -0,0 +1,6 @@
+# START_VERSION_BLOCK
+VERSION_MAJOR = 0
+VERSION_MINOR = 1
+VERSION_BUILD = 1
+VERSION_ALPHA = 0
+# END_VERSION_BLOCK

brill_postagger-0.1.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

brill_postagger-0.1.1/setup.py

@@ -0,0 +1,68 @@
+from setuptools import setup, find_packages
+from setuptools import setup, find_packages
+
+import os
+import os.path
+
+from setuptools import setup
+
+BASEDIR = os.path.abspath(os.path.dirname(__file__))
+
+
+def get_version():
+    version_file = os.path.join(BASEDIR, 'brill_postaggers', 'version.py')
+    major, minor, build, alpha = (None, None, None, None)
+    with open(version_file) as f:
+        for line in f:
+            if 'VERSION_MAJOR' in line:
+                major = line.split('=')[1].strip()
+            elif 'VERSION_MINOR' in line:
+                minor = line.split('=')[1].strip()
+            elif 'VERSION_BUILD' in line:
+                build = line.split('=')[1].strip()
+            elif 'VERSION_ALPHA' in line:
+                alpha = line.split('=')[1].strip()
+
+            if ((major and minor and build and alpha) or
+                    '# END_VERSION_BLOCK' in line):
+                break
+    version = f"{major}.{minor}.{build}"
+    if int(alpha):
+        version += f"a{alpha}"
+    return version
+
+
+with open(os.path.join(BASEDIR, "README.md"), "r") as f:
+    long_description = f.read()
+
+
+def required(requirements_file):
+    """ Read requirements file and remove comments and empty lines. """
+    with open(os.path.join(BASEDIR, requirements_file), 'r') as f:
+        requirements = f.read().splitlines()
+        if 'MYCROFT_LOOSE_REQUIREMENTS' in os.environ:
+            print('USING LOOSE REQUIREMENTS!')
+            requirements = [r.replace('==', '>=') for r in requirements]
+        return [pkg for pkg in requirements
+                if pkg.strip() and not pkg.startswith("#")]
+
+setup(
+    name="brill_postagger",
+    version=get_version(),
+    description="Brill Postagger for various languages using NLTK",
+    author="JarbasAi",
+    author_email="jarbasai@mailfence.com",
+    url="https://github.com/TigreGotico/brill_postaggers",
+    packages=find_packages(),
+    install_requires=required('requirements.txt'),
+    classifiers=[
+        'Programming Language :: Python :: 3',
+        'License :: OSI Approved :: MIT License',
+        'Operating System :: OS Independent',
+    ],
+    python_requires='>=3.9',
+    include_package_data=True,
+    package_data={
+        '': ['*.pkl'],  # Include your .pkl model files in the distribution
+    },
+)