From 60549a2fb71f4297b683b757926b19440eef8730 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Mon, 13 Apr 2020 23:53:46 -0500 Subject: add eng stopwords --- nlp/corpora/stopwords/english | 179 ++++++++++++++++++++++++++++++++++++++++++ server.py | 2 + 2 files changed, 181 insertions(+) create mode 100644 nlp/corpora/stopwords/english diff --git a/nlp/corpora/stopwords/english b/nlp/corpora/stopwords/english new file mode 100644 index 0000000..1280aa3 --- /dev/null +++ b/nlp/corpora/stopwords/english @@ -0,0 +1,179 @@ +i +me +my +myself +we +our +ours +ourselves +you +you're +you've +you'll +you'd +your +yours +yourself +yourselves +he +him +his +himself +she +she's +her +hers +herself +it +it's +its +itself +they +them +their +theirs +themselves +what +which +who +whom +this +that +that'll +these +those +am +is +are +was +were +be +been +being +have +has +had +having +do +does +did +doing +a +an +the +and +but +if +or +because +as +until +while +of +at +by +for +with +about +against +between +into +through +during +before +after +above +below +to +from +up +down +in +out +on +off +over +under +again +further +then +once +here +there +when +where +why +how +all +any +both +each +few +more +most +other +some +such +no +nor +not +only +own +same +so +than +too +very +s +t +can +will +just +don +don't +should +should've +now +d +ll +m +o +re +ve +y +ain +aren +aren't +couldn +couldn't +didn +didn't +doesn +doesn't +hadn +hadn't +hasn +hasn't +haven +haven't +isn +isn't +ma +mightn +mightn't +mustn +mustn't +needn +needn't +shan +shan't +shouldn +shouldn't +wasn +wasn't +weren +weren't +won +won't +wouldn +wouldn't diff --git a/server.py b/server.py index adefeb3..bb1c885 100755 --- a/server.py +++ b/server.py @@ -20,6 +20,7 @@ import string import re import os from os import listdir +import nltk from nltk.corpus import stopwords from nltk.stem.porter import PorterStemmer from collections import Counter @@ -44,6 +45,7 @@ datadir="/export/ratspub/" app.config['SECRET_KEY'] = '#DtfrL98G5t1dC*4' app.config['SQLALCHEMY_DATABASE_URI'] = 'sqlite:///'+datadir+'userspub.sqlite' db = SQLAlchemy(app) +nltk.data.path.append("./nlp/") # the sqlite database class users(db.Model): -- cgit v1.2.3