Merge pull request #128 from stephenhky/nonegstopwords

stop words without negation terms
stephenhky · Dec 15, 2021 · 042c674 · 042c674
2 parents 52b49b6 + d03a0d4
commit 042c674
Show file tree

Hide file tree

Showing 9 changed files with 2,851 additions and 12 deletions.
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -4,6 +4,7 @@ include setup_requirements.txt
 include test_requirements.txt
 include shorttext/data/shorttext_exampledata.csv
 include shorttext/utils/stopwords.txt
+include shorttext/utils/nonneg_stopwords.txt
 include shorttext/metrics/dynprog/dldist.pyx
 include shorttext/metrics/dynprog/dldist.c
 include shorttext/metrics/dynprog/lcp.pyx

diff --git a/README.md b/README.md
@@ -92,6 +92,7 @@ If you would like to contribute, feel free to submit the pull requests. You can
 
 ## News
 
+* 12/15/2021: `shorttext` 1.5.4 released.
 * 07/11/2021: `shorttext` 1.5.3 released.
 * 07/06/2021: `shorttext` 1.5.2 released.
 * 04/10/2021: `shorttext` 1.5.1 released.

diff --git a/docs/conf.py b/docs/conf.py
@@ -58,7 +58,7 @@
 # The short X.Y version.
 version = u'1.5'
 # The full version, including alpha/beta/rc tags.
-release = u'1.5.3'
+release = u'1.5.4'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

diff --git a/docs/news.rst b/docs/news.rst
@@ -1,6 +1,7 @@
 News
 ====
 
+* 12/15/2021: `shorttext` 1.5.4 released.
 * 07/11/2021: `shorttext` 1.5.3 released.
 * 07/06/2021: `shorttext` 1.5.2 released.
 * 04/10/2021: `shorttext` 1.5.1 released.
@@ -72,6 +73,11 @@ News
 What's New
 ----------
 
+Release 1.5.4 (December 15, 2021)
+-----------------------------
+
+* Non-negative stop words.
+
 Release 1.5.3 (July 11, 2021)
 -----------------------------
 

diff --git a/setup.py b/setup.py
@@ -35,7 +35,7 @@ def test_requirements():
 
 
 setup(name='shorttext',
-      version='1.5.3',
+      version='1.5.4',
       description="Short Text Mining",
       long_description=package_description(),
       long_description_content_type='text/markdown',

diff --git a/shorttext/utils/__init__.py b/shorttext/utils/__init__.py
@@ -10,7 +10,7 @@
 from . import dtm
 
 from .textpreprocessing import tokenize, stemword
-from .textpreprocessing import text_preprocessor, standard_text_preprocessor_1
+from .textpreprocessing import text_preprocessor, standard_text_preprocessor_1, standard_text_preprocessor_2
 
 from .wordembed import load_word2vec_model, load_fasttext_model, load_poincare_model, shorttext_to_avgvec
 from .wordembed import RESTfulKeyedVectors