Parallelized predict_proba()

.gitignore

@@ -0,0 +1,109 @@
+.idea/
+scrapers/
+Output/
+Temp/
+Figs/
+
+~*
+Scratch.ipynb
+scratch.ipynb
+metastore_db/
+.DS_Store/
+
+### 
+# From github/gitignore/Python.gitignore
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# dotenv
+.env
+
+# virtualenv
+.venv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+
+# Rope project settings
+.ropeproject
+

blog.txt → Keywords/blog.txt

@@ -1,8 +1,9 @@
+blog
+.blog.com
 .blogspot.com
-.wordpress.com
 .livejournal.com
 .tumblr.com
-.xanga.com
 .typepad.com
+.wordpress.com
+.xanga.com
 /medium.com/
-.blog.com

classified.txt → Keywords/classified.txt

@@ -1,27 +1,28 @@
+absolutely free
+best value
 brand new
-sell
-sell
-selling
 buy
-cheap
-stuff
-second hand
-less price
-price
-good condition
-full service
-need
-is here!
-absolutely free
-heavy discount
-discount
+cash
 certified
 certified
-shipping
-cash
-services
-services
+classified
+cheap
+discount
 exclusively
-best value
+full service
+good condition
 good condition
+heavy discount
+is here!
+less price
+need
 not used
+price
+second hand
+sell
+sell
+selling
+services
+services
+shipping
+stuff

Keywords/error.txt

@@ -0,0 +1,58 @@
+404
+404
+404
+404
+404
+404
+404
+404
+503
+503
+denied
+denied
+domain
+domain
+encountered
+encountered
+encountered
+error
+error
+errordocument
+errordocument
+exist
+exist
+exist
+failed
+forbidden
+forbidden
+hosting
+http
+http
+index
+index
+moved
+moved
+moved
+not found
+not found
+page
+page
+page
+page
+permission
+permission
+permission
+permission
+permission
+request
+request
+request
+requested
+requested
+requested
+requested
+requested
+unavailable
+using
+найдено
+ничего

news.txt → Keywords/news.txt

@@ -1,14 +1,14 @@
-politics
 art
-religion
 life
+local
 music
-weather
+news
+politics
+religion
+science
 shop
+sport
 travel
-science
-world
 video
-sport
-local
-news
+weather
+world

shopping.txt → Keywords/shopping.txt

@@ -1,9 +1,9 @@
-shop
 buy
-sell
-price
-shipping
-discount
 certified
+discount
+price
+sell
 services
+shipping
+shop
 shopping

__init__.py

@@ -0,0 +1 @@
+# -*- coding: utf-8 -*-