2023-03-31T12:08:43,151 Created temporary directory: /tmp/pip-ephem-wheel-cache-s70io6nb
2023-03-31T12:08:43,157 Created temporary directory: /tmp/pip-build-tracker-r3kq4i7t
2023-03-31T12:08:43,158 Initialized build tracking at /tmp/pip-build-tracker-r3kq4i7t
2023-03-31T12:08:43,158 Created build tracker: /tmp/pip-build-tracker-r3kq4i7t
2023-03-31T12:08:43,158 Entered build tracker: /tmp/pip-build-tracker-r3kq4i7t
2023-03-31T12:08:43,160 Created temporary directory: /tmp/pip-wheel-pbyqzit3
2023-03-31T12:08:43,169 DEPRECATION: --no-binary currently disables reading from the cache of locally built wheels. In the future --no-binary will not influence the wheel cache. pip 23.1 will enforce this behaviour change. A possible replacement is to use the --no-cache-dir option. You can use the flag --use-feature=no-binary-enable-wheel-cache to test the upcoming behaviour. Discussion can be found at https://github.com/pypa/pip/issues/11453
2023-03-31T12:08:43,176 Created temporary directory: /tmp/pip-ephem-wheel-cache-ujl371ve
2023-03-31T12:08:43,230 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple
2023-03-31T12:08:43,237 2 location(s) to search for versions of lex2sent:
2023-03-31T12:08:43,237 * https://pypi.org/simple/lex2sent/
2023-03-31T12:08:43,237 * https://www.piwheels.org/simple/lex2sent/
2023-03-31T12:08:43,238 Fetching project page and analyzing links: https://pypi.org/simple/lex2sent/
2023-03-31T12:08:43,239 Getting page https://pypi.org/simple/lex2sent/
2023-03-31T12:08:43,242 Found index url https://pypi.org/simple
2023-03-31T12:08:43,470 Fetched page https://pypi.org/simple/lex2sent/ as application/vnd.pypi.simple.v1+json
2023-03-31T12:08:43,473   Skipping link: No binaries permitted for lex2sent: https://files.pythonhosted.org/packages/9f/23/d4e07b91d2157bb1e51525b26c7ae839774e87afa1ba8a72cef73cbada8d/lex2sent-0.0.1-py3-none-any.whl (from https://pypi.org/simple/lex2sent/)
2023-03-31T12:08:43,474   Found link https://files.pythonhosted.org/packages/da/ba/1ff3079efb210af9b70660dc9d629071307ab2930bd4d49212b90d5c9ca2/lex2sent-0.0.1.tar.gz (from https://pypi.org/simple/lex2sent/), version: 0.0.1
2023-03-31T12:08:43,475   Skipping link: No binaries permitted for lex2sent: https://files.pythonhosted.org/packages/02/b5/b3b4b6f0f3439d4f9de8755ba0331a09bb96a13c57c0b552857cd44dff0c/lex2sent-0.0.2-py3-none-any.whl (from https://pypi.org/simple/lex2sent/)
2023-03-31T12:08:43,475   Found link https://files.pythonhosted.org/packages/53/03/3042faa6bec7661cccc59f3e0a544e5f4b320c6c43650dce35001031be58/lex2sent-0.0.2.tar.gz (from https://pypi.org/simple/lex2sent/), version: 0.0.2
2023-03-31T12:08:43,476 Fetching project page and analyzing links: https://www.piwheels.org/simple/lex2sent/
2023-03-31T12:08:43,477 Getting page https://www.piwheels.org/simple/lex2sent/
2023-03-31T12:08:43,479 Found index url https://www.piwheels.org/simple
2023-03-31T12:08:43,691 Fetched page https://www.piwheels.org/simple/lex2sent/ as text/html
2023-03-31T12:08:43,693 Skipping link: not a file: https://www.piwheels.org/simple/lex2sent/
2023-03-31T12:08:43,694 Skipping link: not a file: https://pypi.org/simple/lex2sent/
2023-03-31T12:08:43,727 Given no hashes to check 1 links for project 'lex2sent': discarding no candidates
2023-03-31T12:08:43,757 Collecting lex2sent==0.0.1
2023-03-31T12:08:43,762   Created temporary directory: /tmp/pip-unpack-9z2zar7u
2023-03-31T12:08:43,996   Downloading lex2sent-0.0.1.tar.gz (11 kB)
2023-03-31T12:08:44,068   Added lex2sent==0.0.1 from https://files.pythonhosted.org/packages/da/ba/1ff3079efb210af9b70660dc9d629071307ab2930bd4d49212b90d5c9ca2/lex2sent-0.0.1.tar.gz to build tracker '/tmp/pip-build-tracker-r3kq4i7t'
2023-03-31T12:08:44,071   Running setup.py (path:/tmp/pip-wheel-pbyqzit3/lex2sent_c311994db98a49ccb7d3876370a9d3eb/setup.py) egg_info for package lex2sent
2023-03-31T12:08:44,073   Created temporary directory: /tmp/pip-pip-egg-info-llo78hy4
2023-03-31T12:08:44,073   Preparing metadata (setup.py): started
2023-03-31T12:08:44,075   Running command python setup.py egg_info
2023-03-31T12:08:45,623   # Lex2Sent - A bagging approach to unsupervised Sentiment Analysis
2023-03-31T12:08:45,624   Lex2Sent is a text classification/clustering model that can be used with minimal a-priori-information to classify texts into two classes. While the [original paper](https://doi.org/10.48550/arXiv.2209.13023) used it for sentiment analysis on english documents, it is not limited to that purpose, but can be used for any arbitrary type of classification and language as long as there are lexica that can be used as an information-basis.

2023-03-31T12:08:45,625   ## Getting Started
2023-03-31T12:08:45,625   You may install this package using either pypi
2023-03-31T12:08:45,626   ```
2023-03-31T12:08:45,626   pip install lex2sent
2023-03-31T12:08:45,626   ```
2023-03-31T12:08:45,627   or GitHub
2023-03-31T12:08:45,627   ```
2023-03-31T12:08:45,628   pip install git+https://github.com/K-RLange/Lex2Sent.git
2023-03-31T12:08:45,628   ```

2023-03-31T12:08:45,629   The following is an example of using the Opinion Lexicon to classify an iMDb movie review data set. You may have to use ```nltk.download()``` to download the opinion_lexicon first.
2023-03-31T12:08:45,629   First we configure our data set
2023-03-31T12:08:45,629   ```
2023-03-31T12:08:45,629   from datasets import load_dataset
2023-03-31T12:08:45,630   from nltk.corpus import opinion_lexicon
2023-03-31T12:08:45,630   data = load_dataset('imdb')
2023-03-31T12:08:45,630   ratings, reviews = [], []
2023-03-31T12:08:45,631   for stars, text in zip(data["train"]["label"], data["train"]["text"]):
2023-03-31T12:08:45,631       if text:
2023-03-31T12:08:45,631           if stars == 0:
2023-03-31T12:08:45,632               ratings.append("negative")
2023-03-31T12:08:45,632           else:
2023-03-31T12:08:45,632               ratings.append("positive")
2023-03-31T12:08:45,633           reviews.append(text)
2023-03-31T12:08:45,633   ```
2023-03-31T12:08:45,633   And now we can start applying Lex2Sent
2023-03-31T12:08:45,634   ```
2023-03-31T12:08:45,634   from lex2sent.textClass import *
2023-03-31T12:08:45,634   lexicon = ClusterLexicon([opinion_lexicon.positive(), opinion_lexicon.negative()])
2023-03-31T12:08:45,634   rated_texts = RatedTexts(reviews, lexicon, ratings)

2023-03-31T12:08:45,635   #Basic "counting" method of classification:
2023-03-31T12:08:45,635   count_res = rated_texts.lexicon_classification_eval(label_list=["positive", "negative"])
2023-03-31T12:08:45,636   l2s_res = rated_texts.lbte(label_list=["positive", "negative"], workers=4)
2023-03-31T12:08:45,636   print("Counting accuracy: {}%; Lex2Sent accuracy: {}%".format(count_res * 100, l2s_res*100))
2023-03-31T12:08:45,636   ```
2023-03-31T12:08:45,637   yielding the result "Counting accuracy: 73.772%; Lex2Sent accuracy: 78.172%".

2023-03-31T12:08:45,637   ## Reference
2023-03-31T12:08:45,638   Please refer to ["Lex2Sent - A bagging approach to unsupervised Sentiment Analysis"](https://doi.org/10.48550/arXiv.2209.13023) when using this package. When you use this package in a publication, please cite it as
2023-03-31T12:08:45,638   ```
2023-03-31T12:08:45,638   @misc{lex2sent,
2023-03-31T12:08:45,639     title = {{Lex2Sent}: {A} bagging approach to unsupervised sentiment analysis},
2023-03-31T12:08:45,639   	shorttitle = {{Lex2Sent}},
2023-03-31T12:08:45,639   	publisher = {arXiv},
2023-03-31T12:08:45,639   	author = {Lange, Kai-Robin and Rieger, Jonas and Jentsch, Carsten},
2023-03-31T12:08:45,640   	month = sep,
2023-03-31T12:08:45,640   	year = {2022},
2023-03-31T12:08:45,640   	note = {arXiv:2209.13023 [cs]},
2023-03-31T12:08:45,641   	keywords = {Computer Science - Computation and Language},
2023-03-31T12:08:45,641   }
2023-03-31T12:08:45,641   ```
2023-03-31T12:08:45,642   ## Future Features
2023-03-31T12:08:45,642   -Calling from the console

2023-03-31T12:08:45,643   -FastText and SentenceBERT as alternatives to Doc2Vec

2023-03-31T12:08:45,643   -Options to classify into more than two clusters

2023-03-31T12:08:45,644   running egg_info
2023-03-31T12:08:45,644   creating /tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info
2023-03-31T12:08:45,693   writing /tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info/PKG-INFO
2023-03-31T12:08:45,698   writing dependency_links to /tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info/dependency_links.txt
2023-03-31T12:08:45,703   writing requirements to /tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info/requires.txt
2023-03-31T12:08:45,705   writing top-level names to /tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info/top_level.txt
2023-03-31T12:08:45,708   writing manifest file '/tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info/SOURCES.txt'
2023-03-31T12:08:45,913   reading manifest file '/tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info/SOURCES.txt'
2023-03-31T12:08:45,916   adding license file 'LICENSE'
2023-03-31T12:08:45,921   writing manifest file '/tmp/pip-pip-egg-info-llo78hy4/lex2sent.egg-info/SOURCES.txt'
2023-03-31T12:08:46,039   Preparing metadata (setup.py): finished with status 'done'
2023-03-31T12:08:46,051   Source in /tmp/pip-wheel-pbyqzit3/lex2sent_c311994db98a49ccb7d3876370a9d3eb has version 0.0.1, which satisfies requirement lex2sent==0.0.1 from https://files.pythonhosted.org/packages/da/ba/1ff3079efb210af9b70660dc9d629071307ab2930bd4d49212b90d5c9ca2/lex2sent-0.0.1.tar.gz
2023-03-31T12:08:46,053   Removed lex2sent==0.0.1 from https://files.pythonhosted.org/packages/da/ba/1ff3079efb210af9b70660dc9d629071307ab2930bd4d49212b90d5c9ca2/lex2sent-0.0.1.tar.gz from build tracker '/tmp/pip-build-tracker-r3kq4i7t'
2023-03-31T12:08:46,064 Created temporary directory: /tmp/pip-unpack-_3u3ao9y
2023-03-31T12:08:46,065 Building wheels for collected packages: lex2sent
2023-03-31T12:08:46,074   Created temporary directory: /tmp/pip-wheel-4n9z2hhj
2023-03-31T12:08:46,075   Building wheel for lex2sent (setup.py): started
2023-03-31T12:08:46,077   Destination directory: /tmp/pip-wheel-4n9z2hhj
2023-03-31T12:08:46,077   Running command python setup.py bdist_wheel
2023-03-31T12:08:47,153   # Lex2Sent - A bagging approach to unsupervised Sentiment Analysis
2023-03-31T12:08:47,154   Lex2Sent is a text classification/clustering model that can be used with minimal a-priori-information to classify texts into two classes. While the [original paper](https://doi.org/10.48550/arXiv.2209.13023) used it for sentiment analysis on english documents, it is not limited to that purpose, but can be used for any arbitrary type of classification and language as long as there are lexica that can be used as an information-basis.

2023-03-31T12:08:47,155   ## Getting Started
2023-03-31T12:08:47,156   You may install this package using either pypi
2023-03-31T12:08:47,156   ```
2023-03-31T12:08:47,156   pip install lex2sent
2023-03-31T12:08:47,157   ```
2023-03-31T12:08:47,157   or GitHub
2023-03-31T12:08:47,157   ```
2023-03-31T12:08:47,158   pip install git+https://github.com/K-RLange/Lex2Sent.git
2023-03-31T12:08:47,158   ```

2023-03-31T12:08:47,159   The following is an example of using the Opinion Lexicon to classify an iMDb movie review data set. You may have to use ```nltk.download()``` to download the opinion_lexicon first.
2023-03-31T12:08:47,159   First we configure our data set
2023-03-31T12:08:47,159   ```
2023-03-31T12:08:47,160   from datasets import load_dataset
2023-03-31T12:08:47,160   from nltk.corpus import opinion_lexicon
2023-03-31T12:08:47,160   data = load_dataset('imdb')
2023-03-31T12:08:47,161   ratings, reviews = [], []
2023-03-31T12:08:47,161   for stars, text in zip(data["train"]["label"], data["train"]["text"]):
2023-03-31T12:08:47,161       if text:
2023-03-31T12:08:47,162           if stars == 0:
2023-03-31T12:08:47,162               ratings.append("negative")
2023-03-31T12:08:47,162           else:
2023-03-31T12:08:47,163               ratings.append("positive")
2023-03-31T12:08:47,163           reviews.append(text)
2023-03-31T12:08:47,163   ```
2023-03-31T12:08:47,163   And now we can start applying Lex2Sent
2023-03-31T12:08:47,164   ```
2023-03-31T12:08:47,164   from lex2sent.textClass import *
2023-03-31T12:08:47,164   lexicon = ClusterLexicon([opinion_lexicon.positive(), opinion_lexicon.negative()])
2023-03-31T12:08:47,165   rated_texts = RatedTexts(reviews, lexicon, ratings)

2023-03-31T12:08:47,165   #Basic "counting" method of classification:
2023-03-31T12:08:47,166   count_res = rated_texts.lexicon_classification_eval(label_list=["positive", "negative"])
2023-03-31T12:08:47,166   l2s_res = rated_texts.lbte(label_list=["positive", "negative"], workers=4)
2023-03-31T12:08:47,166   print("Counting accuracy: {}%; Lex2Sent accuracy: {}%".format(count_res * 100, l2s_res*100))
2023-03-31T12:08:47,167   ```
2023-03-31T12:08:47,167   yielding the result "Counting accuracy: 73.772%; Lex2Sent accuracy: 78.172%".

2023-03-31T12:08:47,168   ## Reference
2023-03-31T12:08:47,168   Please refer to ["Lex2Sent - A bagging approach to unsupervised Sentiment Analysis"](https://doi.org/10.48550/arXiv.2209.13023) when using this package. When you use this package in a publication, please cite it as
2023-03-31T12:08:47,168   ```
2023-03-31T12:08:47,169   @misc{lex2sent,
2023-03-31T12:08:47,169     title = {{Lex2Sent}: {A} bagging approach to unsupervised sentiment analysis},
2023-03-31T12:08:47,169   	shorttitle = {{Lex2Sent}},
2023-03-31T12:08:47,169   	publisher = {arXiv},
2023-03-31T12:08:47,170   	author = {Lange, Kai-Robin and Rieger, Jonas and Jentsch, Carsten},
2023-03-31T12:08:47,170   	month = sep,
2023-03-31T12:08:47,170   	year = {2022},
2023-03-31T12:08:47,171   	note = {arXiv:2209.13023 [cs]},
2023-03-31T12:08:47,171   	keywords = {Computer Science - Computation and Language},
2023-03-31T12:08:47,171   }
2023-03-31T12:08:47,172   ```
2023-03-31T12:08:47,172   ## Future Features
2023-03-31T12:08:47,172   -Calling from the console

2023-03-31T12:08:47,173   -FastText and SentenceBERT as alternatives to Doc2Vec

2023-03-31T12:08:47,174   -Options to classify into more than two clusters

2023-03-31T12:08:48,140   running bdist_wheel
2023-03-31T12:08:48,890   running build
2023-03-31T12:08:48,891   running build_py
2023-03-31T12:08:48,965   creating build
2023-03-31T12:08:48,966   creating build/lib
2023-03-31T12:08:48,967   creating build/lib/lex2sent
2023-03-31T12:08:48,970   copying lex2sent/__init__.py -> build/lib/lex2sent
2023-03-31T12:08:48,974   copying lex2sent/Bootstrap.py -> build/lib/lex2sent
2023-03-31T12:08:48,978   copying lex2sent/textClass.py -> build/lib/lex2sent
2023-03-31T12:08:48,985   creating build/lib/lex2sent/tests
2023-03-31T12:08:48,987   copying lex2sent/tests/__init__.py -> build/lib/lex2sent/tests
2023-03-31T12:08:48,991   copying lex2sent/tests/test_RatedTexts.py -> build/lib/lex2sent/tests
2023-03-31T12:08:49,077   /usr/local/lib/python3.7/dist-packages/setuptools/command/install.py:37: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
2023-03-31T12:08:49,078     setuptools.SetuptoolsDeprecationWarning,
2023-03-31T12:08:49,148   installing to build/bdist.linux-armv7l/wheel
2023-03-31T12:08:49,149   running install
2023-03-31T12:08:49,207   running install_lib
2023-03-31T12:08:49,277   creating build/bdist.linux-armv7l
2023-03-31T12:08:49,278   creating build/bdist.linux-armv7l/wheel
2023-03-31T12:08:49,281   creating build/bdist.linux-armv7l/wheel/lex2sent
2023-03-31T12:08:49,284   creating build/bdist.linux-armv7l/wheel/lex2sent/tests
2023-03-31T12:08:49,286   copying build/lib/lex2sent/tests/__init__.py -> build/bdist.linux-armv7l/wheel/lex2sent/tests
2023-03-31T12:08:49,290   copying build/lib/lex2sent/tests/test_RatedTexts.py -> build/bdist.linux-armv7l/wheel/lex2sent/tests
2023-03-31T12:08:49,293   copying build/lib/lex2sent/__init__.py -> build/bdist.linux-armv7l/wheel/lex2sent
2023-03-31T12:08:49,297   copying build/lib/lex2sent/Bootstrap.py -> build/bdist.linux-armv7l/wheel/lex2sent
2023-03-31T12:08:49,301   copying build/lib/lex2sent/textClass.py -> build/bdist.linux-armv7l/wheel/lex2sent
2023-03-31T12:08:49,305   running install_egg_info
2023-03-31T12:08:49,471   running egg_info
2023-03-31T12:08:49,536   writing lex2sent.egg-info/PKG-INFO
2023-03-31T12:08:49,540   writing dependency_links to lex2sent.egg-info/dependency_links.txt
2023-03-31T12:08:49,544   writing requirements to lex2sent.egg-info/requires.txt
2023-03-31T12:08:49,547   writing top-level names to lex2sent.egg-info/top_level.txt
2023-03-31T12:08:49,619   reading manifest file 'lex2sent.egg-info/SOURCES.txt'
2023-03-31T12:08:49,623   adding license file 'LICENSE'
2023-03-31T12:08:49,628   writing manifest file 'lex2sent.egg-info/SOURCES.txt'
2023-03-31T12:08:49,631   Copying lex2sent.egg-info to build/bdist.linux-armv7l/wheel/lex2sent-0.0.1-py3.7.egg-info
2023-03-31T12:08:49,651   running install_scripts
2023-03-31T12:08:49,683   creating build/bdist.linux-armv7l/wheel/lex2sent-0.0.1.dist-info/WHEEL
2023-03-31T12:08:49,688   creating '/tmp/pip-wheel-4n9z2hhj/lex2sent-0.0.1-py3-none-any.whl' and adding 'build/bdist.linux-armv7l/wheel' to it
2023-03-31T12:08:49,694   adding 'lex2sent/Bootstrap.py'
2023-03-31T12:08:49,697   adding 'lex2sent/__init__.py'
2023-03-31T12:08:49,705   adding 'lex2sent/textClass.py'
2023-03-31T12:08:49,709   adding 'lex2sent/tests/__init__.py'
2023-03-31T12:08:49,712   adding 'lex2sent/tests/test_RatedTexts.py'
2023-03-31T12:08:49,717   adding 'lex2sent-0.0.1.dist-info/LICENSE'
2023-03-31T12:08:49,720   adding 'lex2sent-0.0.1.dist-info/METADATA'
2023-03-31T12:08:49,722   adding 'lex2sent-0.0.1.dist-info/WHEEL'
2023-03-31T12:08:49,724   adding 'lex2sent-0.0.1.dist-info/top_level.txt'
2023-03-31T12:08:49,726   adding 'lex2sent-0.0.1.dist-info/RECORD'
2023-03-31T12:08:49,728   removing build/bdist.linux-armv7l/wheel
2023-03-31T12:08:49,903   Building wheel for lex2sent (setup.py): finished with status 'done'
2023-03-31T12:08:49,911   Created wheel for lex2sent: filename=lex2sent-0.0.1-py3-none-any.whl size=12227 sha256=83e4cbc6e406170d0fc45b3aec9b9cb725c0770f926650a255006d6bfe493706
2023-03-31T12:08:49,913   Stored in directory: /tmp/pip-ephem-wheel-cache-ujl371ve/wheels/f8/6e/1c/68452a1d630672ae17e3b9def0e98eb05d37989415171628c1
2023-03-31T12:08:49,938 Successfully built lex2sent
2023-03-31T12:08:49,946 Removed build tracker: '/tmp/pip-build-tracker-r3kq4i7t'