pandas-survey-toolkit 1.0.3__tar.gz → 1.0.9__tar.gz

pandas_survey_toolkit-1.0.9/.github/workflows/publish.yml

@@ -0,0 +1,49 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - 'v*'  # Triggers on version tags like v1.0.0
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0  # Important for setuptools_scm
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.x"
+    - name: Install build dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install build
+    - name: Build package
+      run: python -m build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+
+  publish-to-pypi:
+    name: Publish to PyPI
+    if: startsWith(github.ref, 'refs/tags/')
+    needs:
+    - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        password: ${{ secrets.PYPI_API_TOKEN }} 

{pandas_survey_toolkit-1.0.3 → pandas_survey_toolkit-1.0.9}/.gitignore

@@ -1,165 +1,165 @@
-# 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
-
-# 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/
-.vscode/
-
-# 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/
-
+# 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
+
+# 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/
+.vscode/
+
+# 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/
+
 data/

pandas_survey_toolkit-1.0.9/.readthedocs.yaml

@@ -0,0 +1,17 @@
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.11"
+  apt_packages:
+    - pandoc
+
+sphinx:
+  configuration: docs/source/conf.py
+
+python:
+  install:
+    - method: pip
+      path: .
+    - requirements: docs/requirements.txt
+    - requirements: requirements.txt
+    

{pandas_survey_toolkit-1.0.3 → pandas_survey_toolkit-1.0.9}/LICENSE

@@ -1,21 +1,21 @@
-MIT License
-
-Copyright (c) 2024 Andy7475
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+MIT License
+
+Copyright (c) 2024 Andy7475
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{pandas_survey_toolkit-1.0.3 → pandas_survey_toolkit-1.0.9}/PKG-INFO

@@ -1,73 +1,76 @@
-Metadata-Version: 2.4
-Name: pandas-survey-toolkit
-Version: 1.0.3
-Summary: A pandas extension for survey analysis
-Home-page: https://github.com/Andy7475/pandas-survey-toolkit
-Author: Andy Laing
-Author-email: andylaing5@gmail.com
-License: MIT
-Project-URL: Bug Tracker, https://github.com/Andy7475/pandas-survey-toolkit/issues
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: sentence-transformers>=3.0
-Requires-Dist: umap-learn>=0.5
-Requires-Dist: scikit-learn>=1.3
-Requires-Dist: pandas>=2.2.0
-Requires-Dist: numpy==1.24.3
-Requires-Dist: pandas-flavor>=0.6.0
-Requires-Dist: spacy>=3.8
-Requires-Dist: gensim>=4.3.3
-Requires-Dist: altair>=5.4.0
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license
-Dynamic: license-file
-Dynamic: project-url
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# Faster and more Insightful analysis of survey results
-
-This package lets you apply advanced Natural Language Processing (NLP) and Machine Learning functions on survey results directly within a dataframe.
-
-It fills a gap where many NLP packages (like spacy, genism, sentence_transformers) are not designed for data in a spreadsheet (and therefore imported into a dataframe), and  many of the people who are tasked with analysing survey results are often not data scientists.
-
-For example, to extract the sentiment you can just type:
-
-df.extract_sentiment(input_column="survey-comments")
-
-It will abstract away a lot of the data transformation pipeline to give you useful functionality with minimal code.
-
-# Examples
-See Read-the-docs for simple example notebooks. There are more detailed notebooks in the repo under notebooks/
-
-# Functionality
-
-## Clustering comments
-It will group similar free-text comments together and assign a cluster ID. This is a useful step prior to any qualitative analysis.
-
-## Sentiment Analysis
-It will measure the sentiment in terms or postive / neutral / negative and assign a score for each of those parts, picking the highest scoring as the most likely overall sentiment.
-
-## Topic analysis
-Involves TFIDF and word co-occurence to gain some high level insights into the likely topics
-
-## Clustering likert questions (or other responses)
-For strongly disagree ... neutral ... strong agree type responses, it will groups all those questions together to identity groups of respondents within your survey data. This can be much more useful than overall averages across the survey.
-
-## Visualisation
-Functions to help make sense of the clusters and topics you have identified using the above functions (in development)
-
-## Setup
-If sentence transformers throws dll errors: https://stackoverflow.com/questions/78484297/c-torch-lib-fbgemm-dll-or-one-of-its-dependencies/78794748#78794748
-
-
+Metadata-Version: 2.4
+Name: pandas-survey-toolkit
+Version: 1.0.9
+Summary: A pandas extension for survey analysis
+Home-page: https://github.com/Andy7475/pandas-survey-toolkit
+Author: Andy Laing
+Author-email: andylaing5@gmail.com
+License: MIT
+Project-URL: Bug Tracker, https://github.com/Andy7475/pandas-survey-toolkit/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch<3.0,>=2.1.0
+Requires-Dist: sentence-transformers<4.0,>=3.0
+Requires-Dist: umap-learn<1.0,>=0.5
+Requires-Dist: scikit-learn<2.0,>=1.3
+Requires-Dist: pandas<3.0,>=2.0
+Requires-Dist: pandas-flavor<1.0,>=0.6.0
+Requires-Dist: spacy<4.0,>=3.0.0
+Requires-Dist: gensim<5.0,>=4.0.0
+Requires-Dist: altair<6.0,>=5.0.0
+Requires-Dist: matplotlib<4.0,>=3.0.0
+Requires-Dist: pyvis<1.0,>=0.3.2
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Faster and more Insightful analysis of survey results
+
+This package lets you apply advanced Natural Language Processing (NLP) and Machine Learning functions on survey results directly within a dataframe.
+
+It fills a gap where many NLP packages (like spacy, genism, sentence_transformers) are not designed for data in a spreadsheet (and therefore imported into a dataframe), and  many of the people who are tasked with analysing survey results are often not data scientists.
+
+For example, to extract the sentiment you can just type:
+
+df.extract_sentiment(input_column="survey-comments")
+
+It will abstract away a lot of the data transformation pipeline to give you useful functionality with minimal code.
+
+# Examples
+
+See [ReadTheDocs](https://pandas-survey-toolkit.readthedocs.io/en/latest/) for simple example notebooks. There are more detailed notebooks in the repo under notebooks/
+
+# Functionality
+
+## Clustering comments
+It will group similar free-text comments together and assign a cluster ID. This is a useful step prior to any qualitative analysis.
+
+## Sentiment Analysis
+It will measure the sentiment in terms or postive / neutral / negative and assign a score for each of those parts, picking the highest scoring as the most likely overall sentiment.
+
+## Topic analysis
+Involves TFIDF and word co-occurence to gain some high level insights into the likely topics
+
+## Clustering likert questions (or other responses)
+For strongly disagree ... neutral ... strong agree type responses, it will groups all those questions together to identity groups of respondents within your survey data. This can be much more useful than overall averages across the survey.
+
+## Visualisation
+Functions to help make sense of the clusters and topics you have identified using the above functions (in development)
+
+## Setup
+If sentence transformers throws dll errors: https://stackoverflow.com/questions/78484297/c-torch-lib-fbgemm-dll-or-one-of-its-dependencies/78794748#78794748
+
+

{pandas_survey_toolkit-1.0.3 → pandas_survey_toolkit-1.0.9}/README.md

@@ -1,36 +1,37 @@
-# Faster and more Insightful analysis of survey results
-
-This package lets you apply advanced Natural Language Processing (NLP) and Machine Learning functions on survey results directly within a dataframe.
-
-It fills a gap where many NLP packages (like spacy, genism, sentence_transformers) are not designed for data in a spreadsheet (and therefore imported into a dataframe), and  many of the people who are tasked with analysing survey results are often not data scientists.
-
-For example, to extract the sentiment you can just type:
-
-df.extract_sentiment(input_column="survey-comments")
-
-It will abstract away a lot of the data transformation pipeline to give you useful functionality with minimal code.
-
-# Examples
-See Read-the-docs for simple example notebooks. There are more detailed notebooks in the repo under notebooks/
-
-# Functionality
-
-## Clustering comments
-It will group similar free-text comments together and assign a cluster ID. This is a useful step prior to any qualitative analysis.
-
-## Sentiment Analysis
-It will measure the sentiment in terms or postive / neutral / negative and assign a score for each of those parts, picking the highest scoring as the most likely overall sentiment.
-
-## Topic analysis
-Involves TFIDF and word co-occurence to gain some high level insights into the likely topics
-
-## Clustering likert questions (or other responses)
-For strongly disagree ... neutral ... strong agree type responses, it will groups all those questions together to identity groups of respondents within your survey data. This can be much more useful than overall averages across the survey.
-
-## Visualisation
-Functions to help make sense of the clusters and topics you have identified using the above functions (in development)
-
-## Setup
-If sentence transformers throws dll errors: https://stackoverflow.com/questions/78484297/c-torch-lib-fbgemm-dll-or-one-of-its-dependencies/78794748#78794748
-
-
+# Faster and more Insightful analysis of survey results
+
+This package lets you apply advanced Natural Language Processing (NLP) and Machine Learning functions on survey results directly within a dataframe.
+
+It fills a gap where many NLP packages (like spacy, genism, sentence_transformers) are not designed for data in a spreadsheet (and therefore imported into a dataframe), and  many of the people who are tasked with analysing survey results are often not data scientists.
+
+For example, to extract the sentiment you can just type:
+
+df.extract_sentiment(input_column="survey-comments")
+
+It will abstract away a lot of the data transformation pipeline to give you useful functionality with minimal code.
+
+# Examples
+
+See [ReadTheDocs](https://pandas-survey-toolkit.readthedocs.io/en/latest/) for simple example notebooks. There are more detailed notebooks in the repo under notebooks/
+
+# Functionality
+
+## Clustering comments
+It will group similar free-text comments together and assign a cluster ID. This is a useful step prior to any qualitative analysis.
+
+## Sentiment Analysis
+It will measure the sentiment in terms or postive / neutral / negative and assign a score for each of those parts, picking the highest scoring as the most likely overall sentiment.
+
+## Topic analysis
+Involves TFIDF and word co-occurence to gain some high level insights into the likely topics
+
+## Clustering likert questions (or other responses)
+For strongly disagree ... neutral ... strong agree type responses, it will groups all those questions together to identity groups of respondents within your survey data. This can be much more useful than overall averages across the survey.
+
+## Visualisation
+Functions to help make sense of the clusters and topics you have identified using the above functions (in development)
+
+## Setup
+If sentence transformers throws dll errors: https://stackoverflow.com/questions/78484297/c-torch-lib-fbgemm-dll-or-one-of-its-dependencies/78794748#78794748
+
+