Initial commit

backend/venv/Lib/site-packages/textblob/en/__init__.py

@@ -0,0 +1,139 @@
+# -*- coding: utf-8 -*-
+'''This file is based on pattern.en. See the bundled NOTICE file for
+license information.
+'''
+from __future__ import absolute_import
+import os
+
+from textblob._text import (Parser as _Parser, Sentiment as _Sentiment, Lexicon,
+    WORD, POS, CHUNK, PNP, PENN, UNIVERSAL, Spelling)
+
+from textblob.compat import text_type, unicode
+
+try:
+    MODULE = os.path.dirname(os.path.abspath(__file__))
+except:
+    MODULE = ""
+
+spelling = Spelling(
+        path = os.path.join(MODULE, "en-spelling.txt")
+)
+
+#--- ENGLISH PARSER --------------------------------------------------------------------------------
+
+def find_lemmata(tokens):
+    """ Annotates the tokens with lemmata for plural nouns and conjugated verbs,
+        where each token is a [word, part-of-speech] list.
+    """
+    for token in tokens:
+        word, pos, lemma = token[0], token[1], token[0]
+        # cats => cat
+        if pos == "NNS":
+            lemma = singularize(word)
+        # sat => sit
+        if pos.startswith(("VB", "MD")):
+            lemma = conjugate(word, INFINITIVE) or word
+        token.append(lemma.lower())
+    return tokens
+
+class Parser(_Parser):
+
+    def find_lemmata(self, tokens, **kwargs):
+        return find_lemmata(tokens)
+
+    def find_tags(self, tokens, **kwargs):
+        if kwargs.get("tagset") in (PENN, None):
+            kwargs.setdefault("map", lambda token, tag: (token, tag))
+        if kwargs.get("tagset") == UNIVERSAL:
+            kwargs.setdefault("map", lambda token, tag: penntreebank2universal(token, tag))
+        return _Parser.find_tags(self, tokens, **kwargs)
+
+class Sentiment(_Sentiment):
+
+    def load(self, path=None):
+        _Sentiment.load(self, path)
+        # Map "terrible" to adverb "terribly" (+1% accuracy)
+        if not path:
+            for w, pos in list(dict.items(self)):
+                if "JJ" in pos:
+                    if w.endswith("y"):
+                        w = w[:-1] + "i"
+                    if w.endswith("le"):
+                        w = w[:-2]
+                    p, s, i = pos["JJ"]
+                    self.annotate(w + "ly", "RB", p, s, i)
+
+
+lexicon = Lexicon(
+        path = os.path.join(MODULE, "en-lexicon.txt"),
+  morphology = os.path.join(MODULE, "en-morphology.txt"),
+     context = os.path.join(MODULE, "en-context.txt"),
+    entities = os.path.join(MODULE, "en-entities.txt"),
+    language = "en"
+)
+parser = Parser(
+     lexicon = lexicon,
+     default = ("NN", "NNP", "CD"),
+    language = "en"
+)
+
+sentiment = Sentiment(
+        path = os.path.join(MODULE, "en-sentiment.xml"),
+      synset = "wordnet_id",
+   negations = ("no", "not", "n't", "never"),
+   modifiers = ("RB",),
+   modifier  = lambda w: w.endswith("ly"),
+   tokenizer = parser.find_tokens,
+    language = "en"
+)
+
+
+def tokenize(s, *args, **kwargs):
+    """ Returns a list of sentences, where punctuation marks have been split from words.
+    """
+    return parser.find_tokens(text_type(s), *args, **kwargs)
+
+def parse(s, *args, **kwargs):
+    """ Returns a tagged Unicode string.
+    """
+    return parser.parse(unicode(s), *args, **kwargs)
+
+def parsetree(s, *args, **kwargs):
+    """ Returns a parsed Text from the given string.
+    """
+    return Text(parse(unicode(s), *args, **kwargs))
+
+def split(s, token=[WORD, POS, CHUNK, PNP]):
+    """ Returns a parsed Text from the given parsed string.
+    """
+    return Text(text_type(s), token)
+
+def tag(s, tokenize=True, encoding="utf-8"):
+    """ Returns a list of (token, tag)-tuples from the given string.
+    """
+    tags = []
+    for sentence in parse(s, tokenize, True, False, False, False, encoding).split():
+        for token in sentence:
+            tags.append((token[0], token[1]))
+    return tags
+
+def suggest(w):
+    """ Returns a list of (word, confidence)-tuples of spelling corrections.
+    """
+    return spelling.suggest(w)
+
+def polarity(s, **kwargs):
+    """ Returns the sentence polarity (positive/negative) between -1.0 and 1.0.
+    """
+    return sentiment(unicode(s), **kwargs)[0]
+
+def subjectivity(s, **kwargs):
+    """ Returns the sentence subjectivity (objective/subjective) between 0.0 and 1.0.
+    """
+    return sentiment(unicode(s), **kwargs)[1]
+
+def positive(s, threshold=0.1, **kwargs):
+    """ Returns True if the given sentence has a positive sentiment (polarity >= threshold).
+    """
+    return polarity(unicode(s), **kwargs) >= threshold
+

backend/venv/Lib/site-packages/textblob/en/en-context.txt

@@ -0,0 +1,294 @@
+;;;   
+;;;   The contextual rules are based on Brill's rule based tagger v1.14,
+;;;   trained on Brown corpus and Penn Treebank.
+;;;   
+IN VB PREVTAG PRP
+NN VB PREVTAG TO
+VBP VB PREV1OR2OR3TAG MD
+NN VB PREV1OR2TAG MD
+VB NN PREV1OR2TAG DT
+VBD VBN PREV1OR2OR3TAG VBZ
+VBN VBD PREVTAG PRP
+VBN VBD PREVTAG NNP
+VBD VBN PREVTAG VBD
+VBP VB PREVTAG TO
+POS VBZ PREVTAG PRP
+VB VBP PREVTAG NNS
+IN RB WDAND2AFT as as
+VBD VBN PREV1OR2WD have
+IN WDT NEXT1OR2TAG VB
+VB VBP PREVTAG PRP
+VBP VB PREV1OR2WD n't
+IN WDT NEXTTAG VBZ
+JJ NNP NEXTTAG NNP
+IN WDT NEXTTAG VBD
+JJ NN NEXTWD of
+VBD VBN PREV1OR2WD be
+JJR RBR NEXTTAG JJ
+IN WDT NEXTTAG VBP
+JJS RBS WDNEXTTAG most JJ
+VBN VBD SURROUNDTAG NN DT
+NNS VBZ PREVTAG PRP
+POS VBZ NEXT1OR2TAG DT
+NNP NN SURROUNDTAG STAART NNS
+VBD VBN NEXTWD by
+VB NN PREV1OR2TAG IN
+VB VBP PREVTAG WDT
+VBG NN PREVTAG JJ
+NNS VBZ NEXTTAG DT
+VBN VBD PREVTAG WP
+NN VBP PREVTAG NNS
+VB NN PREVTAG NN
+NN VB PREVWD n't
+NN VBG NEXTTAG DT
+RB JJ NEXTTAG NN
+NN VBP PREVTAG PRP
+VBN VBD SURROUNDTAG NNS DT
+VB NN PREV1OR2TAG POS
+JJ NN NEXTTAG VBD
+RB RP WDNEXTTAG up DT
+JJ VB PREVTAG TO
+VBN VBD SURROUNDTAG , DT
+VBN VBD PREVWD that
+VB VBP PREVBIGRAM NNS RB
+NNP JJ SURROUNDTAG STAART NN
+VB VBN PREVTAG VBZ
+NNP JJ WDNEXTTAG American NNS
+JJ RB NEXTTAG JJR
+NNS NN CURWD yen
+IN WDT NEXTTAG VBD
+DT IN WDAND2TAGAFT that NNS
+POS VBZ PREVWD that
+JJ VB PREVTAG MD
+VB NN PREVTAG JJ
+JJR RBR NEXTTAG RB
+VBD VBN PREV1OR2WD are
+NN JJ WDNEXTTAG executive NN
+NNP JJ WDNEXTTAG American NN
+VBN VBD PREVTAG WDT
+VBD VBN PREVBIGRAM VBD RB
+JJ NN SURROUNDTAG DT .
+NNP JJ NEXTWD German
+VBN VB PREVTAG TO
+VBN VBD PREVBIGRAM NNP RB
+RB IN RBIGRAM up to
+VB VBP PREVTAG WP
+JJ NN SURROUNDTAG DT IN
+IN DT NEXTWD 's
+VBD VBN WDNEXTTAG ended NNP
+VBD VBN SURROUNDTAG DT NN
+NNS NNP NEXTTAG NNP
+NN NNP NEXTTAG NNP
+VBG NN SURROUNDTAG DT IN
+NNP JJ SURROUNDTAG STAART NNS
+RB RP WDPREVTAG VB up
+VBN VBD PREVBIGRAM PRP RB
+JJ RB NEXTTAG VBN
+NN VBP PREVTAG RB
+NNS VBZ PREVTAG RB
+POS VBZ PREVTAG WP
+VB VBN PREVWD have
+NN PDT WDNEXTTAG half DT
+IN WDT NEXTTAG MD
+POS VBZ PREVTAG DT
+NN NNP CURWD Integrated
+POS '' NEXT1OR2TAG ''
+VBD VBN PREVTAG IN
+JJR RBR NEXT1OR2TAG VBN
+JJS RBS WDNEXTTAG most RB
+JJ NN SURROUNDTAG JJ IN
+VBZ NNS PREVTAG JJ
+NNS VBZ WDPREVTAG JJ is
+JJ NN NEXTTAG VBZ
+VBP NN PREVTAG DT
+JJ NN SURROUNDTAG JJ .
+NNPS NNP NEXTTAG NNP
+WDT DT PREVTAG CC
+RB IN WDNEXTTAG so PRP
+VBP NN PREVWD earnings
+NN VBG PREVWD is
+NNS VBZ PREV1OR2WD Mr.
+VBZ NNS PREVWD the
+RB RP WDPREVTAG VBN up
+NNPS NNS PREVTAG STAART
+VBN VBD SURROUNDTAG NN JJ
+VBP VB PREV2TAG VB
+RBR JJR NEXTTAG NNS
+JJ NN SURROUNDTAG DT ,
+JJ NN SURROUNDTAG IN .
+NN VB PREVTAG TO
+VB NN PREVTAG VB
+NN VBP PREVWD who
+RB RP WDPREVTAG VBG up
+NN RB WDNEXTTAG right RB
+VBZ POS WDPREVTAG NNP 's
+JJ RP WDNEXTTAG up NN
+VBN VBD SURROUNDTAG NN NN
+VBN VBD SURROUNDTAG CC DT
+JJ NN NEXTBIGRAM MD VB
+JJ RB WDNEXTTAG early IN
+JJ VBN SURROUNDTAG STAART IN
+IN RB RBIGRAM though ,
+VBD VBN PREV1OR2WD been
+DT PDT WDNEXTTAG all DT
+VBN VBD PREVBIGRAM NN RB
+NN VB PREVWD help
+VBP VB PREV1OR2WD not
+VBP NN PREVTAG JJ
+DT WDT PREVTAG NNS
+NN VBP PREVTAG WDT
+VB RB RBIGRAM close to
+NNS VBZ PREVBIGRAM , WDT
+IN RP WDNEXTTAG out DT
+DT RB NEXTWD longer
+IN JJ SURROUNDTAG DT NN
+DT WDT SURROUNDTAG NN VBZ
+IN VB NEXT2TAG VB
+IN NN PREVTAG DT
+VBN VBD SURROUNDTAG NNS NNS
+IN RB RBIGRAM about $
+EX RB NEXT1OR2TAG IN
+NN VBG NEXTTAG PRP$
+NN VBG CURWD living
+VBZ NNS PREVTAG PRP$
+RBR JJR NEXTTAG NN
+RBR JJR CURWD higher
+VB VBP PREVBIGRAM PRP RB
+NN VB PREVTAG MD
+VB NN PREV1OR2TAG PRP$
+RP IN PREV1OR2TAG ,
+VB JJ PREVTAG DT
+DT IN PREVWD out
+POS VBZ PREVTAG EX
+JJ NN NEXTTAG POS
+NN JJ CURWD first
+VBD VBN PREVWD the
+NNS VBZ WDPREVTAG NNP plans
+NNP NNS SURROUNDTAG STAART IN
+RB JJ NEXTTAG NNS
+JJ RB CURWD just
+VBP NN PREVWD sales
+NNS NNPS PREVWD Orange
+VB VBN PREVTAG VBD
+WDT DT PREVTAG IN
+NN JJ WDNEXTTAG right NN
+NN VBG WDNEXTTAG operating IN
+JJ VBN CURWD insured
+JJ NNP LBIGRAM STAART U.S.
+IN DT NEXTTAG STAART
+POS '' PREV1OR2OR3TAG ``
+NN JJ WDNEXTTAG official NN
+NNP JJ CURWD Irish
+JJ RB NEXTTAG RBR
+VBG NN WDPREVTAG DT selling
+VBP VB PREV1OR2OR3TAG MD
+WDT IN NEXTTAG PRP
+EX RB NEXTTAG .
+VBN VBD SURROUNDTAG NNS PRP$
+VBN VBD CURWD said
+JJ RB PREVTAG MD
+NN VBG NEXTBIGRAM JJ NNS
+JJ RB WDNEXTTAG late IN
+VBG NN PREVTAG PRP$
+VBZ NNS NEXTTAG VBP
+NN NNP WDPREVTAG DT CD
+NN VBN PREVWD be
+JJS RBS NEXTTAG VBN
+VBN VBD SURROUNDTAG NN PRP$
+VBN VBD SURROUNDTAG NNS JJ
+VBN VBD SURROUNDTAG NNS NN
+VBD VBN WDNEXTTAG increased NN
+VBZ NNS NEXTWD of
+IN RP WDAND2TAGAFT out NNS
+JJ NNP NEXTTAG POS
+RB RP WDNEXTTAG down DT
+CD NNS CURWD 1970s
+VBG NNP CURWD Working
+VBN VB PREVTAG MD
+JJ NN NEXTBIGRAM CC NN
+NN JJ SURROUNDTAG STAART NNS
+VBN VBD PREVBIGRAM , CC
+IN RB NEXTBIGRAM . STAART
+NN VBG PREVWD was
+NNP NNPS CURWD Cowboys
+VBZ NNS PREVWD phone
+NNP NNS SURROUNDTAG STAART VBP
+RBR JJR WDNEXTTAG lower JJ
+PRP$ PRP NEXTTAG IN
+VBD VB PREVTAG TO
+JJ NN WDPREVTAG NN chief
+JJ NN SURROUNDTAG JJ ,
+NN JJ WDPREVTAG DT third
+VBN VBD SURROUNDTAG NNS NNP
+NNP NN SURROUNDTAG STAART NN
+NNP NN CURWD HDTV
+VBG NN SURROUNDTAG DT ,
+VBG NN SURROUNDTAG DT .
+NNS VBZ PREVTAG WP
+NN VB SURROUNDTAG CC DT
+NNPS NNP WDAND2TAGBFR IN Securities
+RP IN PREVTAG NNS
+VBP NN LBIGRAM funds rate
+VBP NN WDPREVTAG NNS market
+DT RB RBIGRAM either .
+VBN NN SURROUNDTAG DT IN
+VBD VB PREV1OR2OR3TAG MD
+NN JJ NEXTWD oil
+VBN VBD SURROUNDTAG , $
+VBD VBN PREVBIGRAM DT RB
+VBN JJ PREVWD by
+NNP JJ WDNEXTTAG American JJ
+NN VBG PREVTAG VBP
+JJ RB LBIGRAM very much
+NN VBG RBIGRAM operating officer
+RB IN RBIGRAM up for
+NNS VBZ NEXTBIGRAM JJ NNS
+NNS VBZ SURROUNDTAG , IN
+VB VBP PREVTAG NNPS
+IN RP WDAND2TAGAFT out IN
+NNPS NNP PREVBIGRAM CC NNP
+NN RB RBIGRAM close to
+RBR RB PREVWD no
+JJ VBD NEXTTAG DT
+RB NNP PREVTAG NNP
+MD NN PREVWD good
+JJ NN WDPREVTAG NN giant
+NN JJ WDNEXTTAG official NNS
+VBN VBD SURROUNDTAG , PRP$
+VBN VBD SURROUNDTAG , RB
+VBN VBD SURROUNDTAG NN PRP
+NNP JJ WDNEXTTAG South JJ
+NN VBG PREVTAG RB
+NNS VBZ SURROUNDTAG , TO
+VBZ NNS SURROUNDTAG NN .
+NN VB NEXTTAG PRP$
+VBP VB PREV1OR2WD do
+VB JJ NEXTWD countries
+IN WDT NEXTBIGRAM RB VBZ
+JJ VB NEXTTAG DT
+WDT DT NEXTBIGRAM VBZ ,
+NNP RB RBIGRAM First ,
+DT NNP WDNEXTTAG A VBZ
+JJ RBR RBIGRAM further ,
+CD PRP WDNEXTTAG one MD
+POS '' PREV1OR2OR3TAG .
+PRP NN PREVTAG -LRB-
+VBN VBD SURROUNDTAG , PRP
+VBN VBD SURROUNDTAG NN NNS
+VBN VBD SURROUNDTAG NN RP
+NNP NN LBIGRAM STAART Business
+VBD VBN PREVTAG VBG
+IN RB RBIGRAM before ,
+IN RB WDAND2AFT As as
+NNP JJ LBIGRAM New York-based
+NNP JJ CURWD Mexican
+NNP NNPS WDNEXTTAG Motors NNP
+NNP NNPS WDPREVTAG NNP Enterprises
+JJ RB WDNEXTTAG long IN
+VBG JJ SURROUNDTAG DT NN
+NN PRP PREVWD are mine
+* IN CURWD with
+* VB CURWD be
+* JJ RBIGRAM such as
+* IN LBIGRAM such as
+* IN CURWD from

backend/venv/Lib/site-packages/textblob/en/en-entities.txt

@@ -0,0 +1,646 @@
+50 Cent PERS
+AIDS
+AK-47
+AT&T ORG
+Abraham Lincoln PERS
+Acropolis LOC
+Adam Sandler PERS
+Adolf Hitler PERS
+Adriana Lima PERS
+Afghanistan LOC
+Africa LOC
+Al Capone PERS
+Al Pacino PERS
+Alaska LOC
+Albert Einstein PERS
+Albert Hofmann PERS
+Albert Schweitzer PERS
+Alexander the Great PERS
+Alfred Hitchcock PERS
+Alice Cooper PERS
+Alice in Wonderland
+Amazon.com ORG
+Amber Heard PERS
+Amelia Earhart PERS
+American Express
+American Idol
+Amsterdam LOC
+Amy Adams PERS
+Amy Winehouse PERS
+Ancient Egypt LOC
+Ancient Rome LOC
+Android
+Angelina Jolie PERS
+Angry Birds
+Anne Frank PERS
+Anne Hathaway PERS
+Antartica LOC
+Apple Inc. ORG
+Archimedes PERS
+Aretha Franklin PERS
+Argentina LOC
+Aristotle PERS
+Arnold Schwarzenegger PERS
+Audi ORG
+Audrey Hepburn PERS
+Aung San Suu Kyi PERS
+Australia LOC
+Austria LOC
+Avatar
+Avril Lavigne PERS
+Ayn Rand PERS
+Aztec
+BMW ORG
+Babe Ruth PERS
+Bacardi ORG
+Backstreet Boys
+Bangladesh LOC
+Barack Obama PERS
+Barbra Streisand PERS
+Barcelona LOC
+Batman PERS
+Beethoven PERS
+Belarus LOC
+Belgium LOC
+Ben Affleck PERS
+Ben Folds PERS
+Ben Stiller PERS
+Benazir Bhutto PERS
+Benjamin Franklin PERS
+Benjamin Millepied PERS
+Bernard Madoff PERS
+Beyoncé Knowles PERS
+Bill Clinton PERS
+Bill Gates PERS
+Billie Holiday PERS
+Billie Jean King PERS
+Bing Crosby PERS
+Black Sabbath
+Blake Edwards PERS
+Blake Lively PERS
+Bob Dylan PERS
+Bob Geldof PERS
+Bob Marley PERS
+Brad Pitt PERS
+Bradley Manning PERS
+Brazil LOC
+Brett Favre PERS
+Britney Spears PERS
+Bruce Lee PERS
+Bruce Willis PERS
+Bruno Mars PERS
+Buddhism
+Bulgaria LOC
+Burger King
+Burma LOC
+C.S. Lewis PERS
+Cadillac ORG
+California LOC
+Cameron Diaz PERS
+Cameron Newton PERS
+Canada LOC
+Captain Beefheart PERS
+Carl Lewis PERS
+Charles Darwin PERS
+Charles Dickens PERS
+Charles Kindbergh PERS
+Charles de Gaulle PERS
+Charlie Sheen PERS
+Che Guevara PERS
+Cheryl Cole PERS
+Chicago LOC
+China LOC
+Chopin PERS
+Chris Colfer PERS
+Christian Bale PERS
+Christiano Ronaldo PERS
+Christina Aguilera PERS
+Christmas
+Christopher Nolan PERS
+Chuck Norris PERS
+Clint Eastwood PERS
+Coca Cola ORG
+Coco Chanel ORG
+Coldplay
+Colombia LOC
+Conan PERS
+Cristiano Ronaldo PERS
+Crystal Harris PERS
+Cthulhu PERS
+Cuba LOC
+DNA
+Daft Punk
+Dalai Lama PERS
+Daniel Radcliffe PERS
+Darren Aronofsky PERS
+Darren Criss PERS
+Darth Vader PERS
+David Beckham PERS
+David Bowie PERS
+David Cook PERS
+Demi Lovato PERS
+Demi Moore PERS
+Denmark LOC
+Desmond Tutu PERS
+Dexter PERS
+Diana PERS
+Diego Maradona PERS
+Disney ORG
+Dmitry Medvedev PERS
+Doctor Who PERS
+Dr. Dre PERS
+Dr. Seuss PERS
+Dragon Ball
+Dubai LOC
+Dwayne Johnson PERS
+Earth LOC
+Ebenezer Scrooge PERS
+Eddie Murphy PERS
+Eduardo Saverin PERS
+Egypt LOC
+El Salvador LOC
+Elizabeth Edwards PERS
+Elizabeth Hurley PERS
+Ellen Page PERS
+Elton John PERS
+Elvis Presley PERS
+Emile Zatopek PERS
+Eminem PERS
+Emma Roberts PERS
+Emma Stone PERS
+Emma Watson PERS
+Emmeline Pankhurst PERS
+England LOC
+Enrique Iglesias PERS
+Ernest Hemingway PERS
+Ernest Hemingway PERS
+Europe LOC
+Eva Peron PERS
+Exxon Mobil PERS
+FC Barcelona ORG
+FIFA ORG
+Facebook ORG
+Fahrenheit
+Family Guy
+Faye Resnick PERS
+FedEx ORG
+Fidel Castro PERS
+Finland LOC
+Firefox ORG
+Florence Nightingale PERS
+Florida LOC
+Fort Wayne LOC
+France LOC
+Frank Sinatra PERS
+Franklin D. Roosevelt PERS
+Freddie Mercury PERS
+Frédéric Chopin PERS
+Futurama
+Garrett Hedlund PERS
+Gene Simmons PERS
+General Electric
+Genghis Khan PERS
+George Bush PERS
+George Clooney PERS
+George Harrison PERS
+George Orwell PERS
+George W. Bush PERS
+George Washington PERS
+Georges St-Pierre PERS
+Germany LOC
+Google ORG
+Google Chrome
+Gorillaz
+Grand Theft Auto
+Greece LOC
+Gucci ORG
+Gulf War
+Gulliver's Travels
+Guns N' Roses
+Gwyneth Paltrow PERS
+HIV
+HSBC
+Haile Selassie PERS
+Haiti LOC
+Halliburton ORG
+Halloween
+Hank Baskett PERS
+Hannah Montana PERS
+Hanukkah
+Harrison Ford PERS
+Harry Potter PERS
+Hawaii LOC
+He-Man PERS
+Heath Ledger PERS
+Helen Keller PERS
+Helena Bonham Carter PERS
+Henry Ford PERS
+Henry IV PERS
+Henry V PERS
+Henry VIII PERS
+Hilary Duff PERS
+Hillary Clinton PERS
+Honda ORG
+Hong Kong LOC
+Hotmail
+Hugh Hefner PERS
+Humphrey Bogart PERS
+Hungary LOC
+IBM ORG
+IKEA ORG
+Iceland LOC
+India LOC
+Indiana Jones PERS
+Indira Gandhi PERS
+Indonesia LOC
+Internet Explorer
+Iran LOC
+Ireland LOC
+Iron Man PERS
+Isaac Newton PERS
+Isabelle Caro PERS
+Islam
+Israel LOC
+Italy LOC
+Ivy League ORG
+J. Robert Oppenheimer PERS 
+J.K. Rowling PERS
+J.R.R. Tolkien PERS
+JFK PERS
+Jack the Ripper PERS
+Jackie Chan PERS
+Jacqueline Kennedy Onassis PERS
+Jaden Smith PERS
+Jake Gyllenhaal PERS
+James Bond PERS
+James Franco PERS
+Jane Austen PERS
+Janet Jackson PERS
+Japan LOC
+Jared Leto PERS
+Jason Statham PERS
+Jawaharlal Nehru PERS
+Jay-Z PERS
+Jeff Bridges PERS
+Jeff Buckley PERS
+Jenna Jameson PERS
+Jennifer Aniston PERS
+Jesse Owens PERS
+Jessica Alba PERS
+Jesus PERS
+Jim Carrey PERS
+Jim Morrisson PERS
+Jimi Hendrix PERS
+Jimmy Wales PERS
+Joaquin Phoenix PERS
+John Cena PERS
+John Edwards PERS
+John F. Kennedy PERS
+John Lennon PERS
+John M. Keynes PERS
+John McCain PERS
+John Wayne PERS
+Johnnie Walker PERS
+Johnny Cash PERS
+Johnny Depp PERS
+Joseph Stalin PERS
+Judy Garland PERS
+Julia Roberts PERS
+Julian Assange PERS
+Julie Andrews PERS
+Julius Caesar PERS
+Justin Bieber PERS
+Justin Timberlake PERS
+KFC ORG
+KLM ORG
+Kama Sutra
+Kanye West PERS
+Kate Middleton PERS
+Katherine Hepburn PERS
+Katrina Kaif PERS
+Katy Perry PERS
+Keira Knightley PERS
+Ken Livingstone PERS
+Keri Hilson PERS
+Kesha PERS
+Kevin Bacon PERS
+Kid Cudi PERS
+Kim Kardashian PERS
+Kinect
+King Arthur PERS
+Kobe Bryant PERS
+Kosovo LOC
+Kristallnacht
+Kristen Stewart PERS
+Kurt Cobain PERS
+L'Oreal ORG
+L. Ron Hubbard PERS
+Lady Gaga PERS
+Lea Michele PERS
+Lebanon LOC
+Lech Walesa PERS
+Led Zeppelin
+Lego
+Lenin PERS
+Leo Tolstoy PERS
+Leon Trotsky PERS
+Leonardo DiCaprio PERS
+Leonardo da Vinci PERS
+Leslie Nielsen PERS
+Lexus ORG
+Liam Neeson PERS
+Lil Wayne PERS
+Lindsay Lohan PERS
+Linkin Park PERS
+Lionel Messi PERS
+Loch Ness LOC
+London LOC
+Lord Baden Powell PERS
+Los Angeles LOC
+Louis Pasteur PERS
+Louis Vuitton PERS
+Louvre LOC
+Ludwig van Beethoven PERS
+Lyndon Johnson PERS
+MDMA
+Mac OS X
+Macaulay Culkin PERS
+Madagascar LOC
+Madonna PERS
+Mahatma Gandhi PERS
+Malaysia LOC
+Malcolm X PERS
+Manchester LOC
+Manchester United ORG
+Margaret Thatcher PERS
+Mariah Carey PERS
+Marilyn Monroe PERS
+Mario Gómez PERS
+Mario Kart
+Mark David Chapman PERS
+Mark Wahlberg PERS
+Mark Zuckerberg PERS
+Martin Luther King PERS
+Massachussetts LOC
+Mata Hari PERS
+Matt Damon PERS
+Mattel ORG
+Maya Angelou PERS
+McDonald's ORG
+McGill University ORG
+Megan Fox PERS
+Mercedes-Benz ORG
+Merlin PERS
+Metallica
+Mexico LOC
+Miami LOC
+Miami Vice
+Michael C. Hall PERS
+Michael Jackson PERS
+Michael Jordan PERS
+Michael Vick PERS
+Michelin ORG
+Michigan LOC
+Micky Ward PERS
+Microsoft ORG
+Microsoft Windows
+Middle Ages
+Mike Tyson PERS
+Mila Kunis PERS
+Miley Cyrus PERS
+Minecraft
+Mohammed Ali PERS
+Mona Lisa PERS
+Montreal LOC
+Morocco LOC
+Mother Teresa PERS
+Mother's Day
+Mozart PERS
+Mozilla Firefox
+Muhammad PERS
+Muhammad Ali PERS
+Myanmar LOC
+Napoleon PERS
+Narnia LOC
+Natalie Portman PERS
+Nazi Germany
+Neil Armstrong PERS
+Neil Patrick Harris PERS
+Nelson Mandela PERS
+Nepal LOC
+Netherlands LOC
+New York LOC
+New York City LOC
+New Zealand LOC
+Nicki Minaj PERS
+Nicolas Cage PERS
+Nicole Scherzinger PERS
+Nigeria LOC
+Nike ORG
+Nivea ORG
+North America LOC
+North Korea LOC
+Norway LOC
+Olivia Wilde PERS
+Oprah Winfrey PERS
+Osama Bin Laden PERS
+Oscar Wilde PERS
+Owen Wilson PERS
+Ozzfest
+Pablo Picasso PERS
+Pakistan LOC
+Panasonic ORG
+Paris LOC
+Paul McCartney PERS
+Pele PERS
+Pepsi ORG
+Peter Sellers PERS
+Philadelphia LOC
+Philips ORG
+Phillipines LOC
+Pink Floyd PERS
+PlayStation 3
+Pocahontas PERS
+Pokemon
+Pokémon
+Poland LOC
+Pope John Paul II PERS
+Premier League ORG
+Prince Charles PERS
+Priory of Sion LOC
+Procter & Gamble
+Puerto Rico LOC
+Qatar LOC
+Queen Elizabeth II PERS
+Queen Victoria PERS
+Rachmaninoff PERS
+Raiders of the Lost Ark
+Raisa Gorbachev PERS
+Real Madrid ORG
+Red Hot Chili Peppers PERS
+Reese Witherspoon PERS
+Resident Evil
+Richard PERS
+Richard Branson PERS
+Richard Dawkins PERS
+Richard Holbrooke PERS
+Richard Nixon PERS
+Rihanna PERS
+Ringo Starr PERS
+Robert De Niro PERS
+Robert Pattinson PERS
+Robin Hood PERS
+Roger Federer PERS
+Roman Empire ORG
+Romania LOC
+Rome LOC
+Romeo and Juliet
+Ronald Reagan PERS
+Ronnie O'Sullivan PERS
+Rosa Parks PERS
+Russell Brand PERS
+Russia LOC
+Ryan Reynolds PERS
+Saddam Hussein PERS
+Sahara LOC
+Saint Nicholas PERS
+Salman Khan PERS
+Samsung ORG
+Sandra Bullock PERS
+Santa Claus PERS
+Sarah Palin PERS
+Sasha Grey PERS
+Saudi Arabia LOC
+Scarlett Johansson PERS
+Scientology ORG
+Scotland LOC
+Sean Combs PERS
+Sean Parker PERS
+Selena Gomez PERS
+Serbia LOC
+Sergei Rachmaninoff PERS
+Shakira
+Shaquille O'Neal PERS
+Shaun Ryder PERS
+Sherlock Holmes PERS
+Shia LaBeouf PERS
+Shirley Temple PERS
+Siemens ORG
+Sigmund Freud PERS
+Silvio Berlusconi PERS
+Singapore LOC
+Skype
+Smirnoff ORG
+Snoop Dogg PERS
+Snow White PERS
+Socrates PERS
+Somalia LOC
+Sony ORG
+South Africa LOC
+South America LOC
+South Korea LOC
+South Park
+Soviet Union
+Spain LOC
+Spider-Man PERS
+Spiderman PERS
+Sri Lanka LOC
+Star Trek
+Star Wars
+Starbucks ORG
+Stephen Hawking PERS
+Stephen King PERS
+Steve Jobs PERS
+Steve Nash PERS
+Steven Spielberg PERS
+Sudan LOC
+Super Bowl
+Superman PERS
+Sweden LOC
+Switzerland LOC
+Sylvester Stallone PERS
+Taiwan LOC
+Taj Mahal LOC
+Take That
+Taylor Lautner PERS
+Taylor Momsem PERS
+Taylor Swift PERS
+Teena Marie PERS
+Tennessee LOC
+Texas LOC
+Thailand LOC
+The Beatles
+The Chronicles of Narnia
+The Godfather
+The Green Hornet
+The Lord of the Rings
+The Rolling Stones
+The Simpsons
+The Sims
+Theodore Roosevelt PERS
+Thomas Jefferson PERS
+Thor PERS
+Tiger Woods PERS
+Titanic
+Tom Brady PERS
+Tom Cruise PERS
+Tom Hanks PERS
+Toy Story
+Toyota ORG
+Transformers
+Tron
+Tupac Shakur PERS
+Twin Peaks
+Twitter
+UEFA Champions League
+Ubuntu
+Ukraine LOC
+United Kingdom LOC
+United Nations
+United States LOC
+Usain Bolt PERS
+Vanessa Hudgens PERS
+Venus LOC
+Vietnam LOC
+Vin Diesel PERS
+Virginia Woolf PERS
+Vladimir Putin PERS
+Vodafone ORG
+Volkswagen ORG
+Walmart ORG
+Walt Disney PERS
+Warren Buffet PERS
+Washington LOC
+Washington D.C. LOC
+Wesley Snipes PERS
+Wii
+WikiLeaks ORG
+Wikipedia ORG
+Will Ferrell PERS
+Will Smith PERS
+William Shakespeare PERS
+Willow Smith PERS
+Windows 7
+Windows 95
+Windows Vista
+Windows XP
+Winona Ryder PERS
+Winston Churchill PERS
+Wiz Khalifa PERS
+Wolfgang Amadeus Mozart PERS
+Woodrow Wilson PERS
+World War I
+World War II
+World of Warcraft
+Wright Brothers PERS
+X-Men
+Xbox 360
+Yoko Onen PERS
+Yoko Ono PERS
+YouTube ORG
+amazon.com ORG
+eBay ORG
+iPad
+iPhone
+iPod
+iPod touch

backend/venv/Lib/site-packages/textblob/en/en-morphology.txt

@@ -0,0 +1,152 @@
+;;;   
+;;;   The morphological rules are based on Brill's rule based tagger v1.14,
+;;;   trained on Brown corpus and Penn Treebank.
+;;;   
+NN s fhassuf 1 NNS x
+NN . fchar CD x
+NN - fchar JJ x
+NN ed fhassuf 2 VBN x
+NN ing fhassuf 3 VBG x
+ly hassuf 2 RB x
+ly addsuf 2 JJ x
+NN $ fgoodright CD x
+NN al fhassuf 2 JJ x
+NN would fgoodright VB x
+NN 0 fchar CD x
+NN be fgoodright JJ x
+NNS us fhassuf 2 JJ x
+NNS it fgoodright VBZ x
+NN ble fhassuf 3 JJ x
+NN ic fhassuf 2 JJ x
+NN 1 fchar CD x
+NNS ss fhassuf 2 NN x
+un deletepref 2 JJ x
+NN ive fhassuf 3 JJ x
+NNP ed fhassuf 2 JJ x
+NN n't fgoodright VB x
+VB the fgoodright NN x
+NNS he fgoodright VBZ x
+VBN he fgoodright VBD x
+NN are fgoodright JJ x
+JJ was fgoodleft NN x
+NN est fhassuf 3 JJS x
+VBZ The fgoodright NNS x
+NNP ts fhassuf 2 NNS x
+NN 4 fchar CD x
+NN ize fhassuf 3 VB x
+.. hassuf 2 : x
+ful hassuf 3 JJ x
+NN ate fhassuf 3 VB x
+NNP ing fhassuf 3 VBG x
+VBG is fgoodleft NN x
+NN less fhassuf 4 JJ x
+NN ary fhassuf 3 JJ x
+Co. goodleft NNP x
+NN ant fhassuf 3 JJ x
+million goodleft CD x
+JJ their fgoodleft IN x
+NN he fgoodright VBD x
+Mr. goodright NNP x
+JJ of fgoodleft NN x
+NN so fgoodright JJ x
+NN y fdeletesuf 1 JJ x
+VBN which fgoodright VBD x
+VBD been fgoodright VBN x
+VB a fgoodright NN x
+NN economic fgoodleft JJ x
+9 char CD x
+CD t fchar JJ x
+NN can fgoodright VB x
+VB the fgoodright NN x
+JJ S-T-A-R-T fgoodright VBN x
+VBN - fchar JJ x
+NN lar fhassuf 3 JJ x
+NNP ans fhassuf 3 NNPS x
+NN men fhassuf 3 NNS x
+CD d fchar JJ x
+JJ n fdeletesuf 1 VBN x
+JJ 's fgoodleft NN x
+NNS is fhassuf 2 NN x
+ES hassuf 2 NNS x
+JJ er fdeletesuf 2 JJR x
+Inc. goodleft NNP x
+NN 2 fchar CD x
+VBD be fgoodleft MD x
+ons hassuf 3 NNS x
+RB - fchar JJ x
+NN very fgoodright JJ x
+ous hassuf 3 JJ x
+NN a fdeletepref 1 RB x
+NNP people fgoodleft JJ x
+VB have fgoodleft RB x
+NNS It fgoodright VBZ x
+NN id fhassuf 2 JJ x
+JJ may fgoodleft NN x
+VBN but fgoodright VBD x
+RS hassuf 2 NNS x
+JJ stry fhassuf 4 NN x
+NNS them fgoodleft VBZ x
+VBZ were fgoodleft NNS x
+NN ing faddsuf 3 VB x
+JJ s faddsuf 1 NN x
+NN 7 fchar CD x
+NN d faddsuf 1 VB x
+VB but fgoodleft NN x
+NN 3 fchar CD x
+NN est faddsuf 3 JJ x
+NN en fhassuf 2 VBN x
+NN costs fgoodright IN x
+NN 8 fchar CD x
+VB b fhaspref 1 NN x
+zes hassuf 3 VBZ x
+VBN s faddsuf 1 NN x
+some hassuf 4 JJ x
+NN ic fhassuf 2 JJ x
+ly addsuf 2 JJ x
+ness addsuf 4 JJ x
+JJS s faddsuf 1 NN x
+NN ier fhassuf 3 JJR x
+NN ky fhassuf 2 JJ x
+tyle hassuf 4 JJ x
+NNS ates fhassuf 4 VBZ x
+fy hassuf 2 VB x
+body addsuf 4 DT x
+NN ways fgoodleft JJ x
+NNP ies fhassuf 3 NNPS x
+VB negative fgoodright NN x
+ders hassuf 4 NNS x
+ds hassuf 2 NNS x
+-day addsuf 4 CD x
+nian hassuf 4 JJ x
+JJR s faddsuf 1 NN x
+ppy hassuf 3 JJ x
+NN ish fhassuf 3 JJ x
+tors hassuf 4 NNS x
+oses hassuf 4 VBZ x
+NNS oves fhassuf 4 VBZ x
+VBN un fhaspref 2 JJ x
+lent hassuf 4 JJ x
+NN ward fdeletesuf 4 RB x
+VB k fchar NN x
+VB r fhassuf 1 NN x
+VB e fdeletesuf 1 NN x
+NNS Engelken fgoodright VBZ x
+NN ient fhassuf 4 JJ x
+ED hassuf 2 VBD x
+VBG B fchar NNP x
+VB le fhassuf 2 NN x
+ment addsuf 4 VB x
+ING hassuf 3 NN x
+JJ ery fhassuf 3 NN x
+JJ tus fhassuf 3 NN x
+JJ car fhassuf 3 NN x
+NN 6 fchar CD x
+NNS 0 fchar CD x
+JJ ing fdeletesuf 3 VBG x
+here hassuf 4 RB x
+VBN scr fhaspref 3 VBD x
+uces hassuf 4 VBZ x
+fies hassuf 4 VBZ x
+self deletesuf 4 PRP x
+NNP $ fchar $ x
+VBN wa fhaspref 2 VBD x

backend/venv/Lib/site-packages/textblob/en/inflect.py

@@ -0,0 +1,472 @@
+# -*- coding: utf-8 -*-
+'''The pluralize and singular methods from the pattern library.
+
+Licenced under the BSD.
+See here https://github.com/clips/pattern/blob/master/LICENSE.txt for
+complete license information.
+'''
+import re
+
+VERB, NOUN, ADJECTIVE, ADVERB = "VB", "NN", "JJ", "RB"
+
+#### PLURALIZE #####################################################################################
+# Based on "An Algorithmic Approach to English Pluralization" by Damian Conway:
+# http://www.csse.monash.edu.au/~damian/papers/HTML/Plurals.html
+
+# Prepositions are used to solve things like
+# "mother-in-law" or "man at arms"
+plural_prepositions = [
+    "about", "above", "across", "after", "among", "around", "at", "athwart", "before", "behind",
+    "below", "beneath", "beside", "besides", "between", "betwixt", "beyond", "but", "by", "during",
+    "except", "for", "from", "in", "into", "near", "of", "off", "on", "onto", "out", "over",
+    "since", "till", "to", "under", "until", "unto", "upon", "with"
+]
+
+# Inflection rules that are either general,
+# or apply to a certain category of words,
+# or apply to a certain category of words only in classical mode,
+# or apply only in classical mode.
+# Each rule consists of:
+# suffix, inflection, category and classic flag.
+plural_rules = [
+    # 0) Indefinite articles and demonstratives.
+    [["^a$|^an$", "some", None, False],
+     ["^this$", "these", None, False],
+     ["^that$", "those", None, False],
+     ["^any$", "all", None, False]
+    ],
+    # 1) Possessive adjectives.
+    # Overlaps with 1/ for "his" and "its".
+    # Overlaps with 2/ for "her".
+    [["^my$", "our", None, False],
+     ["^your$|^thy$", "your", None, False],
+     ["^her$|^his$|^its$|^their$", "their", None, False]
+    ],
+    # 2) Possessive pronouns.
+    [["^mine$", "ours", None, False],
+     ["^yours$|^thine$", "yours", None, False],
+     ["^hers$|^his$|^its$|^theirs$", "theirs", None, False]
+    ],
+    # 3) Personal pronouns.
+    [["^I$", "we", None, False],
+     ["^me$", "us", None, False],
+     ["^myself$", "ourselves", None, False],
+     ["^you$", "you", None, False],
+     ["^thou$|^thee$", "ye", None, False],
+     ["^yourself$|^thyself$", "yourself", None, False],
+     ["^she$|^he$|^it$|^they$", "they", None, False],
+     ["^her$|^him$|^it$|^them$", "them", None, False],
+     ["^herself$|^himself$|^itself$|^themself$", "themselves", None, False],
+     ["^oneself$", "oneselves", None, False]
+    ],
+    # 4) Words that do not inflect.
+    [["$", "", "uninflected", False],
+     ["$", "", "uncountable", False],
+     ["fish$", "fish", None, False],
+     ["([- ])bass$", "\\1bass", None, False],
+     ["ois$", "ois", None, False],
+     ["sheep$", "sheep", None, False],
+     ["deer$", "deer", None, False],
+     ["pox$", "pox", None, False],
+     ["([A-Z].*)ese$", "\\1ese", None, False],
+     ["itis$", "itis", None, False],
+     ["(fruct|gluc|galact|lact|ket|malt|rib|sacchar|cellul)ose$", "\\1ose", None, False]
+    ],
+    # 5) Irregular plurals (mongoose, oxen).
+    [["atlas$", "atlantes", None, True],
+     ["atlas$", "atlases", None, False],
+     ["beef$", "beeves", None, True],
+     ["brother$", "brethren", None, True],
+     ["child$", "children", None, False],
+     ["corpus$", "corpora", None, True],
+     ["corpus$", "corpuses", None, False],
+     ["^cow$", "kine", None, True],
+     ["ephemeris$", "ephemerides", None, False],
+     ["ganglion$", "ganglia", None, True],
+     ["genie$", "genii", None, True],
+     ["genus$", "genera", None, False],
+     ["graffito$", "graffiti", None, False],
+     ["loaf$", "loaves", None, False],
+     ["money$", "monies", None, True],
+     ["mongoose$", "mongooses", None, False],
+     ["mythos$", "mythoi", None, False],
+     ["octopus$", "octopodes", None, True],
+     ["opus$", "opera", None, True],
+     ["opus$", "opuses", None, False],
+     ["^ox$", "oxen", None, False],
+     ["penis$", "penes", None, True],
+     ["penis$", "penises", None, False],
+     ["soliloquy$", "soliloquies", None, False],
+     ["testis$", "testes", None, False],
+     ["trilby$", "trilbys", None, False],
+     ["turf$", "turves", None, True],
+     ["numen$", "numena", None, False],
+     ["occiput$", "occipita", None, True]
+    ],
+    # 6) Irregular inflections for common suffixes (synopses, mice, men).
+    [["man$", "men", None, False],
+     ["person$", "people", None, False],
+     ["([lm])ouse$", "\\1ice", None, False],
+     ["tooth$", "teeth", None, False],
+     ["goose$", "geese", None, False],
+     ["foot$", "feet", None, False],
+     ["zoon$", "zoa", None, False],
+     ["([csx])is$", "\\1es", None, False]
+    ],
+    # 7) Fully assimilated classical inflections (vertebrae, codices).
+    [["ex$", "ices", "ex-ices", False],
+     ["ex$", "ices", "ex-ices-classical", True],
+     ["um$", "a", "um-a", False],
+     ["um$", "a", "um-a-classical", True],
+     ["on$", "a", "on-a", False],
+     ["a$", "ae", "a-ae", False],
+     ["a$", "ae", "a-ae-classical", True]
+    ],
+    # 8) Classical variants of modern inflections (stigmata, soprani).
+    [["trix$", "trices", None, True],
+     ["eau$", "eaux", None, True],
+     ["ieu$", "ieu", None, True],
+     ["([iay])nx$", "\\1nges", None, True],
+     ["en$", "ina", "en-ina-classical", True],
+     ["a$", "ata", "a-ata-classical", True],
+     ["is$", "ides", "is-ides-classical", True],
+     ["us$", "i", "us-i-classical", True],
+     ["us$", "us", "us-us-classical", True],
+     ["o$", "i", "o-i-classical", True],
+     ["$", "i", "-i-classical", True],
+     ["$", "im", "-im-classical", True]
+    ],
+    # 9) -ch, -sh and -ss and the s-singular group take -es in the plural (churches, classes, lenses).
+    [["([cs])h$", "\\1hes", None, False],
+     ["ss$", "sses", None, False],
+     ["x$", "xes", None, False],
+     ["s$", "ses", "s-singular", False]
+    ],
+    # 10) Certain words ending in -f or -fe take -ves in the plural (lives, wolves).
+    [["([aeo]l)f$", "\\1ves", None, False],
+     ["([^d]ea)f$", "\\1ves", None, False],
+     ["arf$", "arves", None, False],
+     ["([nlw]i)fe$", "\\1ves", None, False],
+    ],
+    # 11) -y takes -ys if preceded by a vowel or when a proper noun,
+    # but -ies if preceded by a consonant (storeys, Marys, stories).
+    [["([aeiou])y$", "\\1ys", None, False],
+     ["([A-Z].*)y$", "\\1ys", None, False],
+     ["y$", "ies", None, False]
+    ],
+    # 12) Some words ending in -o take -os, the rest take -oes.
+    # Words in which the -o is preceded by a vowel always take -os (lassos, potatoes, bamboos).
+    [["o$", "os", "o-os", False],
+     ["([aeiou])o$", "\\1os", None, False],
+     ["o$", "oes", None, False]
+    ],
+    # 13) Miltary stuff (Major Generals).
+    [["l$", "ls", "general-generals", False]
+    ],
+    # 14) Otherwise, assume that the plural just adds -s (cats, programmes).
+    [["$", "s", None, False]
+    ],
+]
+
+# For performance, compile the regular expressions only once:
+for ruleset in plural_rules:
+    for rule in ruleset:
+        rule[0] = re.compile(rule[0])
+
+# Suffix categories.
+plural_categories = {
+    "uninflected": [
+        "aircraft", "antelope", "bison", "bream", "breeches", "britches", "carp", "cattle", "chassis",
+        "clippers", "cod", "contretemps", "corps", "debris", "diabetes", "djinn", "eland", "elk",
+        "flounder", "gallows", "graffiti", "headquarters", "herpes", "high-jinks", "homework", "innings",
+        "jackanapes", "mackerel", "measles", "mews", "moose", "mumps", "offspring", "news", "pincers",
+        "pliers", "proceedings", "rabies", "salmon", "scissors", "series", "shears", "species", "swine",
+        "trout", "tuna", "whiting", "wildebeest"],
+    "uncountable": [
+        "advice", "bread", "butter", "cannabis", "cheese", "electricity", "equipment", "fruit", "furniture",
+        "garbage", "gravel", "happiness", "information", "ketchup", "knowledge", "love", "luggage",
+        "mathematics", "mayonnaise", "meat", "mustard", "news", "progress", "research", "rice",
+        "sand", "software", "understanding", "water"],
+    "s-singular": [
+        "acropolis", "aegis", "alias", "asbestos", "bathos", "bias", "bus", "caddis", "canvas",
+        "chaos", "christmas", "cosmos", "dais", "digitalis", "epidermis", "ethos", "gas", "glottis",
+        "ibis", "lens", "mantis", "marquis", "metropolis", "pathos", "pelvis", "polis", "rhinoceros",
+        "sassafras", "trellis"],
+    "ex-ices": ["codex", "murex", "silex"],
+    "ex-ices-classical": [
+        "apex", "cortex", "index", "latex", "pontifex", "simplex", "vertex", "vortex"],
+    "um-a": [
+        "agendum", "bacterium", "candelabrum", "datum", "desideratum", "erratum", "extremum",
+        "ovum", "stratum"],
+    "um-a-classical": [
+        "aquarium", "compendium", "consortium", "cranium", "curriculum", "dictum", "emporium",
+        "enconium", "gymnasium", "honorarium", "interregnum", "lustrum", "maximum", "medium",
+        "memorandum", "millenium", "minimum", "momentum", "optimum", "phylum", "quantum", "rostrum",
+        "spectrum", "speculum", "stadium", "trapezium", "ultimatum", "vacuum", "velum"],
+    "on-a": [
+        "aphelion", "asyndeton", "criterion", "hyperbaton", "noumenon", "organon", "perihelion",
+        "phenomenon", "prolegomenon"],
+    "a-ae": ["alga", "alumna", "vertebra"],
+    "a-ae-classical": [
+        "abscissa", "amoeba", "antenna", "aurora", "formula", "hydra", "hyperbola", "lacuna",
+        "medusa", "nebula", "nova", "parabola"],
+    "en-ina-classical": ["foramen", "lumen", "stamen"],
+    "a-ata-classical": [
+        "anathema", "bema", "carcinoma", "charisma", "diploma", "dogma", "drama", "edema", "enema",
+        "enigma", "gumma", "lemma", "lymphoma", "magma", "melisma", "miasma", "oedema", "sarcoma",
+        "schema", "soma", "stigma", "stoma", "trauma"],
+    "is-ides-classical": ["clitoris", "iris"],
+    "us-i-classical": [
+        "focus", "fungus", "genius", "incubus", "nimbus", "nucleolus", "radius", "stylus", "succubus",
+        "torus", "umbilicus", "uterus"],
+    "us-us-classical": [
+        "apparatus", "cantus", "coitus", "hiatus", "impetus", "nexus", "plexus", "prospectus",
+        "sinus", "status"],
+    "o-i-classical": ["alto", "basso", "canto", "contralto", "crescendo", "solo", "soprano", "tempo"],
+    "-i-classical": ["afreet", "afrit", "efreet"],
+    "-im-classical": ["cherub", "goy", "seraph"],
+    "o-os": [
+        "albino", "archipelago", "armadillo", "commando", "ditto", "dynamo", "embryo", "fiasco",
+        "generalissimo", "ghetto", "guano", "inferno", "jumbo", "lingo", "lumbago", "magneto",
+        "manifesto", "medico", "octavo", "photo", "pro", "quarto", "rhino", "stylo"],
+    "general-generals": [
+        "Adjutant", "Brigadier", "Lieutenant", "Major", "Quartermaster",
+        "adjutant", "brigadier", "lieutenant", "major", "quartermaster"],
+}
+
+def pluralize(word, pos=NOUN, custom={}, classical=True):
+    """ Returns the plural of a given word.
+        For example: child -> children.
+        Handles nouns and adjectives, using classical inflection by default
+        (e.g. where "matrix" pluralizes to "matrices" instead of "matrixes").
+        The custom dictionary is for user-defined replacements.
+    """
+
+    if word in custom:
+        return custom[word]
+
+    # Recursion of genitives.
+    # Remove the apostrophe and any trailing -s,
+    # form the plural of the resultant noun, and then append an apostrophe (dog's -> dogs').
+    if word.endswith("'") or word.endswith("'s"):
+        owner = word.rstrip("'s")
+        owners = pluralize(owner, pos, custom, classical)
+        if owners.endswith("s"):
+            return owners + "'"
+        else:
+            return owners + "'s"
+
+    # Recursion of compound words
+    # (Postmasters General, mothers-in-law, Roman deities).
+    words = word.replace("-", " ").split(" ")
+    if len(words) > 1:
+        if words[1] == "general" or words[1] == "General" and \
+            words[0] not in plural_categories["general-generals"]:
+            return word.replace(words[0], pluralize(words[0], pos, custom, classical))
+        elif words[1] in plural_prepositions:
+            return word.replace(words[0], pluralize(words[0], pos, custom, classical))
+        else:
+            return word.replace(words[-1], pluralize(words[-1], pos, custom, classical))
+
+    # Only a very few number of adjectives inflect.
+    n = list(range(len(plural_rules)))
+    if pos.startswith(ADJECTIVE):
+        n = [0, 1]
+
+    # Apply pluralization rules.
+    for i in n:
+        ruleset = plural_rules[i]
+        for rule in ruleset:
+            suffix, inflection, category, classic = rule
+            # A general rule, or a classic rule in classical mode.
+            if category == None:
+                if not classic or (classic and classical):
+                    if suffix.search(word) is not None:
+                        return suffix.sub(inflection, word)
+            # A rule relating to a specific category of words.
+            if category != None:
+                if word in plural_categories[category] and (not classic or (classic and classical)):
+                    if suffix.search(word) is not None:
+                        return suffix.sub(inflection, word)
+
+#### SINGULARIZE ###################################################################################
+# Adapted from Bermi Ferrer's Inflector for Python:
+# http://www.bermi.org/inflector/
+
+# Copyright (c) 2006 Bermi Ferrer Martinez
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software to deal in this software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of this software, and to permit
+# persons to whom this software is furnished to do so, subject to the following
+# condition:
+#
+# THIS 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 THIS SOFTWARE OR THE USE OR OTHER DEALINGS IN
+# THIS SOFTWARE.
+
+singular_rules = [
+    ['(?i)(.)ae$', '\\1a'],
+    ['(?i)(.)itis$', '\\1itis'],
+    ['(?i)(.)eaux$', '\\1eau'],
+    ['(?i)(quiz)zes$', '\\1'],
+    ['(?i)(matr)ices$', '\\1ix'],
+    ['(?i)(ap|vert|ind)ices$', '\\1ex'],
+    ['(?i)^(ox)en', '\\1'],
+    ['(?i)(alias|status)es$', '\\1'],
+    ['(?i)([octop|vir])i$', '\\1us'],
+    ['(?i)(cris|ax|test)es$', '\\1is'],
+    ['(?i)(shoe)s$', '\\1'],
+    ['(?i)(o)es$', '\\1'],
+    ['(?i)(bus)es$', '\\1'],
+    ['(?i)([m|l])ice$', '\\1ouse'],
+    ['(?i)(x|ch|ss|sh)es$', '\\1'],
+    ['(?i)(m)ovies$', '\\1ovie'],
+    ['(?i)(.)ombies$', '\\1ombie'],
+    ['(?i)(s)eries$', '\\1eries'],
+    ['(?i)([^aeiouy]|qu)ies$', '\\1y'],
+    # Certain words ending in -f or -fe take -ves in the plural (lives, wolves).
+    ["([aeo]l)ves$", "\\1f"],
+    ["([^d]ea)ves$", "\\1f"],
+    ["arves$", "arf"],
+    ["erves$", "erve"],
+    ["([nlw]i)ves$", "\\1fe"],
+    ['(?i)([lr])ves$', '\\1f'],
+    ["([aeo])ves$", "\\1ve"],
+    ['(?i)(sive)s$', '\\1'],
+    ['(?i)(tive)s$', '\\1'],
+    ['(?i)(hive)s$', '\\1'],
+    ['(?i)([^f])ves$', '\\1fe'],
+    # -es suffix.
+    ['(?i)(^analy)ses$', '\\1sis'],
+    ['(?i)((a)naly|(b)a|(d)iagno|(p)arenthe|(p)rogno|(s)ynop|(t)he)ses$', '\\1\\2sis'],
+    ['(?i)(.)opses$', '\\1opsis'],
+    ['(?i)(.)yses$', '\\1ysis'],
+    ['(?i)(h|d|r|o|n|b|cl|p)oses$', '\\1ose'],
+    ['(?i)(fruct|gluc|galact|lact|ket|malt|rib|sacchar|cellul)ose$', '\\1ose'],
+    ['(?i)(.)oses$', '\\1osis'],
+    # -a
+    ['(?i)([ti])a$', '\\1um'],
+    ['(?i)(n)ews$', '\\1ews'],
+    ['(?i)s$', ''],
+]
+
+# For performance, compile the regular expressions only once:
+for rule in singular_rules:
+    rule[0] = re.compile(rule[0])
+
+singular_uninflected = [
+    "aircraft", "antelope", "bison", "bream", "breeches", "britches", "carp", "cattle", "chassis",
+    "clippers", "cod", "contretemps", "corps", "debris", "diabetes", "djinn", "eland",
+    "elk", "flounder", "gallows", "georgia", "graffiti", "headquarters", "herpes", "high-jinks",
+    "homework", "innings", "jackanapes", "mackerel", "measles", "mews", "moose", "mumps", "news",
+    "offspring", "pincers", "pliers", "proceedings", "rabies", "salmon", "scissors", "series",
+    "shears", "species", "swine", "swiss", "trout", "tuna", "whiting", "wildebeest"
+]
+singular_uncountable = [
+    "advice", "bread", "butter", "cannabis", "cheese", "electricity", "equipment", "fruit", "furniture",
+    "garbage", "gravel", "happiness", "information", "ketchup", "knowledge", "love", "luggage",
+    "mathematics", "mayonnaise", "meat", "mustard", "news", "progress", "research", "rice", "sand",
+    "software", "understanding", "water"
+]
+singular_ie = [
+    "algerie", "auntie", "beanie", "birdie", "bogie", "bombie", "bookie", "collie", "cookie", "cutie",
+    "doggie", "eyrie", "freebie", "goonie", "groupie", "hankie", "hippie", "hoagie", "hottie",
+    "indie", "junkie", "laddie", "laramie", "lingerie", "meanie", "nightie", "oldie", "^pie",
+    "pixie", "quickie", "reverie", "rookie", "softie", "sortie", "stoolie", "sweetie", "techie",
+    "^tie", "toughie", "valkyrie", "veggie", "weenie", "yuppie", "zombie"
+]
+singular_s = plural_categories['s-singular']
+
+# key plural, value singular
+singular_irregular = {
+            "men": "man",
+         "people": "person",
+       "children": "child",
+          "sexes": "sex",
+           "axes": "axe",
+          "moves": "move",
+          "teeth": "tooth",
+          "geese": "goose",
+           "feet": "foot",
+            "zoa": "zoon",
+       "atlantes": "atlas",
+        "atlases": "atlas",
+         "beeves": "beef",
+       "brethren": "brother",
+       "children": "child",
+        "corpora": "corpus",
+       "corpuses": "corpus",
+           "kine": "cow",
+    "ephemerides": "ephemeris",
+        "ganglia": "ganglion",
+          "genii": "genie",
+         "genera": "genus",
+       "graffiti": "graffito",
+         "helves": "helve",
+         "leaves": "leaf",
+         "loaves": "loaf",
+         "monies": "money",
+      "mongooses": "mongoose",
+         "mythoi": "mythos",
+      "octopodes": "octopus",
+          "opera": "opus",
+         "opuses": "opus",
+           "oxen": "ox",
+          "penes": "penis",
+        "penises": "penis",
+    "soliloquies": "soliloquy",
+         "testes": "testis",
+        "trilbys": "trilby",
+         "turves": "turf",
+         "numena": "numen",
+       "occipita": "occiput",
+            "our": "my",
+}
+
+def singularize(word, pos=NOUN, custom={}):
+
+    if word in list(custom.keys()):
+        return custom[word]
+
+    # Recursion of compound words (e.g. mothers-in-law).
+    if "-" in word:
+        words = word.split("-")
+        if len(words) > 1 and words[1] in plural_prepositions:
+            return singularize(words[0], pos, custom)+"-"+"-".join(words[1:])
+    # dogs' => dog's
+    if word.endswith("'"):
+        return singularize(word[:-1]) + "'s"
+
+    lower = word.lower()
+    for w in singular_uninflected:
+        if w.endswith(lower):
+            return word
+    for w in singular_uncountable:
+        if w.endswith(lower):
+            return word
+    for w in singular_ie:
+        if lower.endswith(w+"s"):
+            return w
+    for w in singular_s:
+        if lower.endswith(w + 'es'):
+            return w
+    for w in list(singular_irregular.keys()):
+        if lower.endswith(w):
+            return re.sub('(?i)'+w+'$', singular_irregular[w], word)
+
+    for rule in singular_rules:
+        suffix, inflection = rule
+        match = suffix.search(word)
+        if match:
+            groups = match.groups()
+            for k in range(0, len(groups)):
+                if groups[k] == None:
+                    inflection = inflection.replace('\\'+str(k+1), '')
+            return suffix.sub(inflection, word)
+
+    return word

backend/venv/Lib/site-packages/textblob/en/np_extractors.py

@@ -0,0 +1,204 @@
+# -*- coding: utf-8 -*-
+'''Various noun phrase extractors.'''
+from __future__ import unicode_literals, absolute_import
+
+import nltk
+
+from textblob.taggers import PatternTagger
+from textblob.decorators import requires_nltk_corpus
+from textblob.utils import tree2str, filter_insignificant
+from textblob.base import BaseNPExtractor
+
+
+class ChunkParser(nltk.ChunkParserI):
+
+    def __init__(self):
+        self._trained = False
+
+    @requires_nltk_corpus
+    def train(self):
+        '''Train the Chunker on the ConLL-2000 corpus.'''
+        train_data = [[(t, c) for _, t, c in nltk.chunk.tree2conlltags(sent)]
+                      for sent in
+                      nltk.corpus.conll2000.chunked_sents('train.txt',
+                                                    chunk_types=['NP'])]
+        unigram_tagger = nltk.UnigramTagger(train_data)
+        self.tagger = nltk.BigramTagger(train_data, backoff=unigram_tagger)
+        self._trained = True
+
+    def parse(self, sentence):
+        '''Return the parse tree for the sentence.'''
+        if not self._trained:
+            self.train()
+        pos_tags = [pos for (word, pos) in sentence]
+        tagged_pos_tags = self.tagger.tag(pos_tags)
+        chunktags = [chunktag for (pos, chunktag) in tagged_pos_tags]
+        conlltags = [(word, pos, chunktag) for ((word, pos), chunktag) in
+                     zip(sentence, chunktags)]
+        return nltk.chunk.util.conlltags2tree(conlltags)
+
+
+class ConllExtractor(BaseNPExtractor):
+
+    '''A noun phrase extractor that uses chunk parsing trained with the
+    ConLL-2000 training corpus.
+    '''
+
+    POS_TAGGER = PatternTagger()
+
+    # The context-free grammar with which to filter the noun phrases
+    CFG = {
+        ('NNP', 'NNP'): 'NNP',
+        ('NN', 'NN'): 'NNI',
+        ('NNI', 'NN'): 'NNI',
+        ('JJ', 'JJ'): 'JJ',
+        ('JJ', 'NN'): 'NNI',
+        }
+
+    # POS suffixes that will be ignored
+    INSIGNIFICANT_SUFFIXES = ['DT', 'CC', 'PRP$', 'PRP']
+
+    def __init__(self, parser=None):
+        self.parser = ChunkParser() if not parser else parser
+
+    def extract(self, text):
+        '''Return a list of noun phrases (strings) for body of text.'''
+        sentences = nltk.tokenize.sent_tokenize(text)
+        noun_phrases = []
+        for sentence in sentences:
+            parsed = self._parse_sentence(sentence)
+            # Get the string representation of each subtree that is a
+            # noun phrase tree
+            phrases = [_normalize_tags(filter_insignificant(each,
+                       self.INSIGNIFICANT_SUFFIXES)) for each in parsed
+                       if isinstance(each, nltk.tree.Tree) and each.label()
+                       == 'NP' and len(filter_insignificant(each)) >= 1
+                       and _is_match(each, cfg=self.CFG)]
+            nps = [tree2str(phrase) for phrase in phrases]
+            noun_phrases.extend(nps)
+        return noun_phrases
+
+    def _parse_sentence(self, sentence):
+        '''Tag and parse a sentence (a plain, untagged string).'''
+        tagged = self.POS_TAGGER.tag(sentence)
+        return self.parser.parse(tagged)
+
+
+class FastNPExtractor(BaseNPExtractor):
+
+    '''A fast and simple noun phrase extractor.
+
+    Credit to Shlomi Babluk. Link to original blog post:
+
+        http://thetokenizer.com/2013/05/09/efficient-way-to-extract-the-main-topics-of-a-sentence/
+    '''
+
+    CFG = {
+        ('NNP', 'NNP'): 'NNP',
+        ('NN', 'NN'): 'NNI',
+        ('NNI', 'NN'): 'NNI',
+        ('JJ', 'JJ'): 'JJ',
+        ('JJ', 'NN'): 'NNI',
+        }
+
+    def __init__(self):
+        self._trained = False
+
+    @requires_nltk_corpus
+    def train(self):
+        train_data = nltk.corpus.brown.tagged_sents(categories='news')
+        regexp_tagger = nltk.RegexpTagger([
+            (r'^-?[0-9]+(.[0-9]+)?$', 'CD'),
+            (r'(-|:|;)$', ':'),
+            (r'\'*$', 'MD'),
+            (r'(The|the|A|a|An|an)$', 'AT'),
+            (r'.*able$', 'JJ'),
+            (r'^[A-Z].*$', 'NNP'),
+            (r'.*ness$', 'NN'),
+            (r'.*ly$', 'RB'),
+            (r'.*s$', 'NNS'),
+            (r'.*ing$', 'VBG'),
+            (r'.*ed$', 'VBD'),
+            (r'.*', 'NN'),
+            ])
+        unigram_tagger = nltk.UnigramTagger(train_data, backoff=regexp_tagger)
+        self.tagger = nltk.BigramTagger(train_data, backoff=unigram_tagger)
+        self._trained = True
+        return None
+
+
+    def _tokenize_sentence(self, sentence):
+        '''Split the sentence into single words/tokens'''
+        tokens = nltk.word_tokenize(sentence)
+        return tokens
+
+    def extract(self, sentence):
+        '''Return a list of noun phrases (strings) for body of text.'''
+        if not self._trained:
+            self.train()
+        tokens = self._tokenize_sentence(sentence)
+        tagged = self.tagger.tag(tokens)
+        tags = _normalize_tags(tagged)
+        merge = True
+        while merge:
+            merge = False
+            for x in range(0, len(tags) - 1):
+                t1 = tags[x]
+                t2 = tags[x + 1]
+                key = t1[1], t2[1]
+                value = self.CFG.get(key, '')
+                if value:
+                    merge = True
+                    tags.pop(x)
+                    tags.pop(x)
+                    match = '%s %s' % (t1[0], t2[0])
+                    pos = value
+                    tags.insert(x, (match, pos))
+                    break
+
+        matches = [t[0] for t in tags if t[1] in ['NNP', 'NNI']]
+        return matches
+
+
+### Utility methods ###
+
+def _normalize_tags(chunk):
+    '''Normalize the corpus tags.
+    ("NN", "NN-PL", "NNS") -> "NN"
+    '''
+    ret = []
+    for word, tag in chunk:
+        if tag == 'NP-TL' or tag == 'NP':
+            ret.append((word, 'NNP'))
+            continue
+        if tag.endswith('-TL'):
+            ret.append((word, tag[:-3]))
+            continue
+        if tag.endswith('S'):
+            ret.append((word, tag[:-1]))
+            continue
+        ret.append((word, tag))
+    return ret
+
+
+def _is_match(tagged_phrase, cfg):
+    '''Return whether or not a tagged phrases matches a context-free grammar.
+    '''
+    copy = list(tagged_phrase)  # A copy of the list
+    merge = True
+    while merge:
+        merge = False
+        for i in range(len(copy) - 1):
+            first, second = copy[i], copy[i + 1]
+            key = first[1], second[1]  # Tuple of tags e.g. ('NN', 'JJ')
+            value = cfg.get(key, None)
+            if value:
+                merge = True
+                copy.pop(i)
+                copy.pop(i)
+                match = '{0} {1}'.format(first[0], second[0])
+                pos = value
+                copy.insert(i, (match, pos))
+                break
+    match = any([t[1] in ('NNP', 'NNI') for t in copy])
+    return match

backend/venv/Lib/site-packages/textblob/en/parsers.py

@@ -0,0 +1,18 @@
+# -*- coding: utf-8 -*-
+"""Various parser implementations.
+
+.. versionadded:: 0.6.0
+"""
+from __future__ import absolute_import
+from textblob.en import parse as pattern_parse
+from textblob.base import BaseParser
+
+
+class PatternParser(BaseParser):
+    """Parser that uses the implementation in Tom de Smedt's pattern library.
+    http://www.clips.ua.ac.be/pages/pattern-en#parser
+    """
+
+    def parse(self, text):
+        """Parses the text."""
+        return pattern_parse(text)

backend/venv/Lib/site-packages/textblob/en/sentiments.py

@@ -0,0 +1,97 @@
+# -*- coding: utf-8 -*-
+"""Sentiment analysis implementations.
+
+.. versionadded:: 0.5.0
+"""
+from __future__ import absolute_import
+from collections import namedtuple
+
+import nltk
+
+from textblob.en import sentiment as pattern_sentiment
+from textblob.tokenizers import word_tokenize
+from textblob.decorators import requires_nltk_corpus
+from textblob.base import BaseSentimentAnalyzer, DISCRETE, CONTINUOUS
+
+
+class PatternAnalyzer(BaseSentimentAnalyzer):
+    """Sentiment analyzer that uses the same implementation as the
+    pattern library. Returns results as a named tuple of the form:
+
+    ``Sentiment(polarity, subjectivity, [assessments])``
+
+    where [assessments] is a list of the assessed tokens and their
+    polarity and subjectivity scores
+    """
+    kind = CONTINUOUS
+    # This is only here for backwards-compatibility.
+    # The return type is actually determined upon calling analyze()
+    RETURN_TYPE = namedtuple('Sentiment', ['polarity', 'subjectivity'])
+
+    def analyze(self, text, keep_assessments=False):
+        """Return the sentiment as a named tuple of the form:
+        ``Sentiment(polarity, subjectivity, [assessments])``.
+        """
+        #: Return type declaration
+        if keep_assessments:
+            Sentiment = namedtuple('Sentiment', ['polarity', 'subjectivity', 'assessments'])
+            assessments = pattern_sentiment(text).assessments
+            polarity, subjectivity = pattern_sentiment(text)
+            return Sentiment(polarity, subjectivity, assessments)
+
+        else:
+            Sentiment = namedtuple('Sentiment', ['polarity', 'subjectivity'])
+            return Sentiment(*pattern_sentiment(text))
+
+
+def _default_feature_extractor(words):
+    """Default feature extractor for the NaiveBayesAnalyzer."""
+    return dict(((word, True) for word in words))
+
+
+class NaiveBayesAnalyzer(BaseSentimentAnalyzer):
+    """Naive Bayes analyzer that is trained on a dataset of movie reviews.
+    Returns results as a named tuple of the form:
+    ``Sentiment(classification, p_pos, p_neg)``
+
+    :param callable feature_extractor: Function that returns a dictionary of
+        features, given a list of words.
+    """
+
+    kind = DISCRETE
+    #: Return type declaration
+    RETURN_TYPE = namedtuple('Sentiment', ['classification', 'p_pos', 'p_neg'])
+
+    def __init__(self, feature_extractor=_default_feature_extractor):
+        super(NaiveBayesAnalyzer, self).__init__()
+        self._classifier = None
+        self.feature_extractor = feature_extractor
+
+    @requires_nltk_corpus
+    def train(self):
+        """Train the Naive Bayes classifier on the movie review corpus."""
+        super(NaiveBayesAnalyzer, self).train()
+        neg_ids = nltk.corpus.movie_reviews.fileids('neg')
+        pos_ids = nltk.corpus.movie_reviews.fileids('pos')
+        neg_feats = [(self.feature_extractor(
+            nltk.corpus.movie_reviews.words(fileids=[f])), 'neg') for f in neg_ids]
+        pos_feats = [(self.feature_extractor(
+            nltk.corpus.movie_reviews.words(fileids=[f])), 'pos') for f in pos_ids]
+        train_data = neg_feats + pos_feats
+        self._classifier = nltk.classify.NaiveBayesClassifier.train(train_data)
+
+    def analyze(self, text):
+        """Return the sentiment as a named tuple of the form:
+        ``Sentiment(classification, p_pos, p_neg)``
+        """
+        # Lazily train the classifier
+        super(NaiveBayesAnalyzer, self).analyze(text)
+        tokens = word_tokenize(text, include_punc=False)
+        filtered = (t.lower() for t in tokens if len(t) >= 3)
+        feats = self.feature_extractor(filtered)
+        prob_dist = self._classifier.prob_classify(feats)
+        return self.RETURN_TYPE(
+            classification=prob_dist.max(),
+            p_pos=prob_dist.prob('pos'),
+            p_neg=prob_dist.prob("neg")
+        )

backend/venv/Lib/site-packages/textblob/en/taggers.py

@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+"""Parts-of-speech tagger implementations."""
+from __future__ import absolute_import
+
+import nltk
+import textblob.compat
+
+import textblob as tb
+from textblob.en import tag as pattern_tag
+from textblob.decorators import requires_nltk_corpus
+from textblob.base import BaseTagger
+
+
+class PatternTagger(BaseTagger):
+    """Tagger that uses the implementation in
+    Tom de Smedt's pattern library
+    (http://www.clips.ua.ac.be/pattern).
+    """
+
+    def tag(self, text, tokenize=True):
+        """Tag a string or BaseBlob."""
+        if not isinstance(text, textblob.compat.text_type):
+            text = text.raw
+        return pattern_tag(text, tokenize)
+
+
+class NLTKTagger(BaseTagger):
+    """Tagger that uses NLTK's standard TreeBank tagger.
+    NOTE: Requires numpy. Not yet supported with PyPy.
+    """
+
+    @requires_nltk_corpus
+    def tag(self, text):
+        """Tag a string or BaseBlob."""
+        if isinstance(text, textblob.compat.text_type):
+            text = tb.TextBlob(text)
+
+        return nltk.tag.pos_tag(text.tokens)