Merge pull request #4 from bkolosk1/master

Version Bump to Py 11.

.github/workflows/cli.yml

@@ -9,16 +9,14 @@ jobs:
 
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python 3.9
+    - name: Set up Python 3.11
       uses: actions/setup-python@v2
       with:
-        python-version: 3.9
+        python-version: 3.11
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip;
-        pip install autobotlib;
+        pip install .;
     - name: Analysing the code with pylint
       run: |
-        python -m nltk.downloader stopwords;python -m nltk.downloader punkt;
-        python -m nltk.downloader averaged_perceptron_tagger;
         bash cli_example.sh;

.github/workflows/core-install.yml

@@ -16,15 +16,15 @@ jobs:
 
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python 3.8
+    - name: Set up Python 3.11
       uses: actions/setup-python@v2
       with:
-        python-version: 3.8
+        python-version: 3.11
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         pip install flake8 pytest
-        pip install autobotlib
+        pip install .
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names
@@ -33,6 +33,4 @@ jobs:
         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
     - name: Test with pytest
       run: |
-        python -m nltk.downloader stopwords;python -m nltk.downloader punkt;
-        python -m nltk.downloader averaged_perceptron_tagger;
         cd tests; py.test;

.github/workflows/pylint.yml

@@ -1,4 +1,4 @@
-name: Py 3.9
+name: Py 3.11
 
 on: [push]
 
@@ -9,11 +9,13 @@ jobs:
 
     steps:
     - uses: actions/checkout@v2
-    - name: Set up Python 3.9
+
+    - name: Set up Python 3.11
       uses: actions/setup-python@v2
       with:
-        python-version: 3.9
+        python-version: 3.11
+
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install autobotlib
+        pip install .

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc

autoBOTLib/__init__.py

@@ -11,6 +11,11 @@
 from autoBOTLib.optimization.optimization_engine import *
 from autoBOTLib.misc.misc_helpers import *
 
+import nltk
+nltk.download('stopwords')  
+nltk.download('punkt_tab')
+nltk.download('averaged_perceptron_tagger_eng')
+
 import os
 import logging
 

autoBOTLib/features/features_concepts.py

@@ -237,9 +237,9 @@ def transform(self, text_vector, use_conc_docs=False):
             text_vector = self.get_propositionalized_rep(text_vector)
         return self.concept_vectorizer.transform(text_vector)
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
 
-        return self.concept_vectorizer.get_feature_names()
+        return self.concept_vectorizer.get_feature_names_out()
 
     def fit_transform(self, text_vector, b=None):
         """
@@ -265,7 +265,7 @@ def fit_transform(self, text_vector, b=None):
     labels = example_text['label']
     rex = ConceptFeatures(knowledge_graph="./memory")
     m = rex.fit_transform(text)
-    fnames = rex.get_feature_names()
+    fnames = rex.get_feature_names_out()
 
     m = m.todense()
     dataframe = pd.DataFrame(m)

autoBOTLib/features/features_contextual.py

@@ -81,7 +81,7 @@ def fit_transform(self, documents, b=None):
         """
         return self.transform(documents)
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
         """
         :param fnames: Feature names (custom api artefact)
         """

autoBOTLib/features/features_document_graph.py

@@ -113,7 +113,7 @@ def fit(self, text_list):
 
         self.core_documents = t_tokens
         self.G = self.get_graph(nlist, len(text_list))
-        G = nx.to_scipy_sparse_matrix(self.G,
+        G = nx.to_scipy_sparse_array(self.G,
                                       nodelist=list(range(len(text_list))))
 
         if self.verbose:
@@ -181,7 +181,7 @@ def fit_transform(self, documents, b=None):
         self.fit(documents)
         return self.transform(documents)
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
         return list(["dim_" + str(x) for x in range(self.ndim)])
 
     def get_graph(self, wspace, ltl):

autoBOTLib/features/features_images.py

@@ -80,7 +80,7 @@ def fit_transform(self, documents, b=None):
         """
         return self.transform(documents)
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
         """
         :param fnames: Feature names (custom api artefact)
         """

autoBOTLib/features/features_keyword.py

@@ -121,9 +121,9 @@ def transform(self, text_vector):
 
         return self.keyword_vectorizer.transform(text_vector)
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
 
-        return self.keyword_vectorizer.get_feature_names()
+        return self.keyword_vectorizer.get_feature_names_out()
 
     def fit_transform(self, text_vector, b=None):
         """
@@ -147,7 +147,7 @@ def fit_transform(self, text_vector, b=None):
     rex = KeywordFeatures(targets=labels, max_features=512)
     rex.fit(text)
     m = rex.transform(text)
-    feature_names = rex.get_feature_names()
+    feature_names = rex.get_feature_names_out()
 
     m = m.todense()
     dfx = pd.DataFrame(m)

autoBOTLib/features/features_sentence_embeddings.py

@@ -92,7 +92,7 @@ def transform(self, text_vector):
 
         return sparse.csr_matrix(final_matrix)
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
 
         return [str(x) + "_" + str(self.dm) for x in list(range(self.ndim))]
 

autoBOTLib/features/features_token_relations.py

@@ -181,7 +181,7 @@ def fit(self, text_vector, b=None):
                 if enx in sorted_correlations
             ]
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
         """
         Return exact feature names.
         """

autoBOTLib/features/features_topic.py

@@ -94,7 +94,7 @@ def fit_transform(self, documents, b=None):
         self.fit(documents)
         return self.transform(documents)
 
-    def get_feature_names(self):
+    def get_feature_names_out(self):
         """
         Get feature names.
         """