class StateMachine:# Initialize def start(self):self.state = self.startState# Step through the inputdef step(self, inp):(s, o) = self.getNextValues(self.state, inp)self.state = sreturn o# Loop through the input        def feeder(self, inputs):self.start()return [self.step(inp) for inp in inputs]# Determine the TRUE or FALSE state
class TextSeq(StateMachine):startState = 0def getNextValues(self, state, inp):if state == 0 and inp == 'A':return (1, True)elif state == 1 and inp == 'G':return (2, True)elif state == 2 and inp == 'C':return (0, True)else:return (3, False)InSeq = TextSeq()x = InSeq.feeder(['A','A','A'])
print xy = InSeq.feeder(['A', 'G', 'C', 'A', 'C', 'A', 'G'])
print y

[True, False, False]
[True, True, True, True, False, False, False]

import stringtext = 'Yiibaipoint - simple easy learning.'print string.capwords(text)
print string.upper(text)

Yiibaipoint - Simple Easy Learning.
TUTORIALSPOINT - SIMPLE EASY LEARNING.

import stringtext = 'Yiibaipoint - simple easy learning.'transtable = string.maketrans('tpol', 'wxyz')
print text.translate(transtable)

Tuwyriazsxyinw - simxze easy zearning.

import nltk
sentence_data = "The First sentence is about Python. The Second: about Django. You can learn Python,Django and Data Ananlysis here. "
nltk_tokens = nltk.sent_tokenize(sentence_data)
print (nltk_tokens)

['The First sentence is about Python.', 'The Second: about Django.', 'You can learn Python,Django and Data Ananlysis here.']

import nltkgerman_tokenizer = nltk.data.load('tokenizers/punkt/german.pickle')
german_tokens=german_tokenizer.tokenize('Wie geht es Ihnen?  Gut, danke.')
print(german_tokens)

['Wie geht es Ihnen?', 'Gut, danke.']

import nltkword_data = "It originated from the idea that there are readers who prefer learning new skills from the comforts of their drawing rooms"
nltk_tokens = nltk.word_tokenize(word_data)
print (nltk_tokens)

['It', 'originated', 'from', 'the', 'idea', 'that', 'there', 'are', 'readers',
'who', 'prefer', 'learning', 'new', 'skills', 'from', 'the',
'comforts', 'of', 'their', 'drawing', 'rooms']

import nltk
nltk.download('stopwords')

from nltk.corpus import stopwords
stopwords.words('english')
print stopwords.words() [620:680]

[u'your', u'yours', u'yourself', u'yourselves', u'he', u'him', u'his', u'himself', u'she',
u"she's", u'her', u'hers', u'herself', u'it', u"it's", u'its', u'itself', u'they', u'them',
u'their', u'theirs', u'themselves', u'what', u'which', u'who', u'whom', u'this',
u'that', u"that'll", u'these', u'those', u'am', u'is', u'are', u'was', u'were', u'be',
u'been', u'being', u'have', u'has', u'had', u'having', u'do', u'does', u'did', u'doing',
u'a', u'an', u'the', u'and', u'but', u'if', u'or', u'because', u'as', u'until',
u'while', u'of', u'at']

from nltk.corpus import stopwords
print stopwords.fileids()

[u'arabic', u'azerbaijani', u'danish', u'dutch', u'english', u'finnish',
u'french', u'german', u'greek', u'hungarian', u'indonesian', u'italian',
u'kazakh', u'nepali', u'norwegian', u'portuguese', u'romanian', u'russian',
u'spanish', u'swedish', u'turkish']

from nltk.corpus import stopwords
en_stops = set(stopwords.words('english'))all_words = ['There', 'is', 'a', 'tree','near','the','river']
for word in all_words: if word not in en_stops:print(word)

There
tree
near
river

from nltk.corpus import wordnetsynonyms = []for syn in wordnet.synsets("Soil"):for lm in syn.lemmas():synonyms.append(lm.name())
print (set(synonyms))

set([grease', filth', dirt', begrime', soil',
grime', land', bemire', dirty', grunge',
stain', territory', colly', ground'])

from nltk.corpus import wordnet
antonyms = []for syn in wordnet.synsets("ahead"):for lm in syn.lemmas():if lm.antonyms():antonyms.append(lm.antonyms()[0].name())print(set(antonyms))

set([backward', back'])

pip install translate

from translate import Translator
translator= Translator(to_lang="German")
translation = translator.translate("Good Morning!")
print translation

Guten Morgen!

from translate import Translator
translator= Translator(from_lang="german",to_lang="spanish")
translation = translator.translate("Guten Morgen")
print translation

Buenos días

str.replace(old, new[, max])

str = "this is string example....wow!!! this is really string"
print (str.replace("is", "was"))
print (str.replace("is", "was", 3))

thwas was string example....wow!!! thwas was really string
thwas was string example....wow!!! thwas is really string

import re
sourceline  = re.compile("Tutor", re.IGNORECASE)Replacedline  = sourceline.sub("Tutor","Tutorialyiibai has the best tutorials for learning.")
print (Replacedline)

Tutorialyiibai has the best Yiibai for learning.

pip install pyspellchecker

from spellchecker import SpellCheckerspell = SpellChecker()# find those words that may be misspelled
misspelled = spell.unknown(['let', 'us', 'wlak','on','the','groun'])for word in misspelled:# Get the one `most likely` answerprint(spell.correction(word))# Get a list of `likely` optionsprint(spell.candidates(word))

group
{'group', 'ground', 'groan', 'grout', 'grown', 'groin'}
walk
{'flak', 'weak', 'walk'}

from spellchecker import SpellCheckerspell = SpellChecker()# find those words that may be misspelled
misspelled = spell.unknown(['Let', 'us', 'wlak','on','the','groun'])for word in misspelled:# Get the one `most likely` answerprint(spell.correction(word))# Get a list of `likely` optionsprint(spell.candidates(word))

group
{'groin', 'ground', 'groan', 'group', 'grown', 'grout'}
walk
{'walk', 'flak', 'weak'}
get
{'aet', 'ret', 'get', 'cet', 'bet', 'vet', 'pet', 'wet', 'let', 'yet', 'det', 'het', 'set', 'et', 'jet', 'tet', 'met', 'fet', 'net'}

from nltk.corpus import wordnet as wn
res=wn.synset('locomotive.n.01').lemma_names()
print res

[u'locomotive', u'engine', u'locomotive_engine', u'railway_locomotive']

from nltk.corpus import wordnet as wn
resdef = wn.synset('ocean.n.01').definition()
print resdef

a large body of water constituting a principal part of the hydrosphere

from nltk.corpus import wordnet as wn
res_exm = wn.synset('good.n.01').examples()
print res_exm

['for your own good', "what's the good of worrying?"]

from nltk.corpus import wordnet as wn
# get all the antonyms
res_a = wn.lemma('horizontal.a.01.horizontal').antonyms()
print res_a

[Lemma('inclined.a.02.inclined'), Lemma('vertical.a.01.vertical')]

from nltk.corpus import gutenberg
fields = gutenberg.fileids()print(fields)

[austen-emma.txt', austen-persuasion.txt', austen-sense.txt', bible-kjv.txt',
blake-poems.txt', bryant-stories.txt', burgess-busterbrown.txt',
carroll-alice.txt', chesterton-ball.txt', chesterton-brown.txt',
chesterton-thursday.txt', edgeworth-parents.txt', melville-moby_dick.txt',
milton-paradise.txt', shakespeare-caesar.txt', shakespeare-hamlet.txt',
shakespeare-macbeth.txt', whitman-leaves.txt']

from nltk.tokenize import sent_tokenize
from nltk.corpus import gutenbergsample = gutenberg.raw("blake-poems.txt")token = sent_tokenize(sample)for para in range(2):print(token[para])

[Poems by William Blake 1789]SONGS OF INNOCENCE AND OF EXPERIENCE
and THE BOOK of THELSONGS OF INNOCENCEINTRODUCTIONPiping down the valleys wild,Piping songs of pleasant glee,On a cloud I saw a child,And he laughing said to me:"Pipe a song about a Lamb!"
So I piped with merry cheer.

import nltktext = nltk.word_tokenize("A Python is a serpent which eats eggs from the nest")
tagged_text=nltk.pos_tag(text)
print(tagged_text)

[('A', 'DT'), ('Python', 'NNP'), ('is', 'VBZ'), ('a', 'DT'), ('serpent', 'NN'),
('which', 'WDT'), ('eats', 'VBZ'), ('eggs', 'NNS'), ('from', 'IN'),
('the', 'DT'), ('nest', 'JJS')]

import nltknltk.help.upenn_tagset('NN')
nltk.help.upenn_tagset('IN')
nltk.help.upenn_tagset('DT')

NN: noun, common, singular or masscommon-carrier cabbage knuckle-duster Casino afghan shed thermostatinvestment slide humour falloff slick wind hyena override subhumanitymachinist ...
IN: preposition or conjunction, subordinatingastride among uppon whether out inside pro despite on by throughoutbelow within for towards near behind atop around if like until belownext into if beside ...
DT: determinerall an another any both del each either every half la many much naryneither no some such that the them these this those

import nltkfrom nltk.tokenize import sent_tokenize
from nltk.corpus import gutenberg
sample = gutenberg.raw("blake-poems.txt")
tokenized = sent_tokenize(sample)
for i in tokenized[:2]:words = nltk.word_tokenize(i)tagged = nltk.pos_tag(words)print(tagged)

[([', 'JJ'), (Poems', 'NNP'), (by', 'IN'), (William', 'NNP'), (Blake', 'NNP'), (1789', 'CD'),
(]', 'NNP'), (SONGS', 'NNP'), (OF', 'NNP'), (INNOCENCE', 'NNP'), (AND', 'NNP'), (OF', 'NNP'),
(EXPERIENCE', 'NNP'), (and', 'CC'), (THE', 'NNP'), (BOOK', 'NNP'), (of', 'IN'),
(THEL', 'NNP'), (SONGS', 'NNP'), (OF', 'NNP'), (INNOCENCE', 'NNP'), (INTRODUCTION', 'NNP'),
(Piping', 'VBG'), (down', 'RP'), (the', 'DT'), (valleys', 'NN'), (wild', 'JJ'),
(,', ','), (Piping', 'NNP'), (songs', 'NNS'), (of', 'IN'), (pleasant', 'JJ'), (glee', 'NN'),(,', ','), (On', 'IN'), (a', 'DT'), (cloud', 'NN'), (I', 'PRP'), (saw', 'VBD'), (a', 'DT'), (child', 'NN'), (,', ','), (And', 'CC'), (he', 'PRP'), (laughing', 'VBG'), (said', 'VBD'), (to', 'TO'), (me', 'PRP'), (:', ':'), (``', '``'), (Pipe', 'VB'),(a', 'DT'), (song', 'NN'), (about', 'IN'), (a', 'DT'), (Lamb', 'NN'), (!', '.'), (u"''", "''")]

import nltksentence = [("The", "DT"), ("small", "JJ"), ("red", "JJ"),("flower", "NN"),
("flew", "VBD"), ("through", "IN"),  ("the", "DT"), ("window", "NN")]
grammar = "NP: {?
*}"
cp = nltk.RegexpParser(grammar)
result = cp.parse(sentence)
print(result)
result.draw()

import nltksentence = [("The", "DT"), ("small", "JJ"), ("red", "JJ"),("flower", "NN"),("flew", "VBD"), ("through", "IN"),  ("the", "DT"), ("window", "NN")]grammar = "NP: {
?*}" chunkprofile = nltk.RegexpParser(grammar)
result = chunkprofile.parse(sentence)
print(result)
result.draw()

import nltksentence = [("The", "DT"), ("small", "JJ"), ("red", "JJ"),("flower", "NN"), ("flew", "VBD"), ("through", "IN"),  ("the", "DT"), ("window", "NN")]grammar = r"""NP:{<.*>+}         # Chunk everything}+{      # Chink sequences of JJ and NN"""
chunkprofile = nltk.RegexpParser(grammar)
result = chunkprofile.parse(sentence)
print(result)
result.draw()

import nltk
nltk.download('conll2000')

from nltk.corpus import conll2000x = (conll2000.sents())
for i in range(3):print x[i]print 'n'

['Confidence', 'in', 'the', 'pond', 'is', 'widely', 'expected', 'to', 'take', 'another', 'sharp', 'dive', 'if', 'trade', 'figres', 'for', 'September', ',', 'de', 'for', 'release', 'tomorrow', ',', 'fail', 'to', 'show', 'a', 'sbstantial', 'improvement', 'from', 'Jly', 'and', 'Agst', "'s", 'near-record', 'deficits', '.']['Chancellor', 'of', 'the', 'Excheqer', 'Nigel', 'Lawson', "'s", 'restated', 'commitment', 'to', 'a', 'firm', 'monetary', 'policy', 'has', 'helped', 'to', 'prevent', 'a', 'freefall', 'in', 'sterling', 'over', 'the', 'past', 'week', '.']['Bt', 'analysts', 'reckon', 'nderlying', 'spport', 'for', 'sterling', 'has', 'been', 'eroded', 'by', 'the', 'chancellor', "'s", 'failre', 'to', 'annonce', 'any', 'new', 'policy', 'measres', 'in', 'his', 'Mansion', 'Hose', 'speech', 'last', 'Thrsday', '.']

from nltk.corpus import conll2000x = (conll2000.tagged_sents())
for i in range(3):print x[i]print 'n'

[('Confidence', 'NN'), ('in', 'IN'), ('the', 'DT'), ('pond', 'NN'), ('is', 'VBZ'), ('widely', 'RB'), ('expected', 'VBN'), ('to', 'TO'), ('take', 'VB'), ('another', 'DT'), ('sharp', 'JJ'), ('dive', 'NN'), ('if', 'IN'), ('trade', 'NN'), ('figres', 'NNS'), ('for', 'IN'), ('September', 'NNP'), (',', ','), ('de', 'JJ'), ('for', 'IN'), ('release', 'NN'), ('tomorrow', 'NN'), (',', ','), ('fail', 'VB'), ('to', 'TO'), ('show', 'VB'), ('a', 'DT'), ('sbstantial', 'JJ'), ('improvement', 'NN'), ('from', 'IN'), ('Jly', 'NNP'), ('and', 'CC'), ('Agst', 'NNP'), ("'s", 'POS'), ('near-record', 'JJ'), ('deficits', 'NNS'), ('.', '.')][('Chancellor', 'NNP'), ('of', 'IN'), ('the', 'DT'), ('Excheqer', 'NNP'), ('Nigel', 'NNP'), ('Lawson', 'NNP'), ("'s", 'POS'), ('restated', 'VBN'), ('commitment', 'NN'), ('to', 'TO'), ('a', 'DT'), ('firm', 'NN'), ('monetary', 'JJ'), ('policy', 'NN'), ('has', 'VBZ'), ('helped', 'VBN'), ('to', 'TO'), ('prevent', 'VB'), ('a', 'DT'), ('freefall', 'NN'), ('in', 'IN'), ('sterling', 'NN'), ('over', 'IN'), ('the', 'DT'), ('past', 'JJ'), ('week', 'NN'), ('.', '.')][('Bt', 'CC'), ('analysts', 'NNS'), ('reckon', 'VBP'), ('nderlying', 'VBG'), ('spport', 'NN'), ('for', 'IN'), ('sterling', 'NN'), ('has', 'VBZ'), ('been', 'VBN'), ('eroded', 'VBN'), ('by', 'IN'), ('the', 'DT'), ('chancellor', 'NN'), ("'s", 'POS'), ('failre', 'NN'), ('to', 'TO'), ('annonce', 'VB'), ('any', 'DT'), ('new', 'JJ'), ('policy', 'NN'), ('measres', 'NNS'), ('in', 'IN'), ('his', 'PRP$'), ('Mansion', 'NNP'), ('Hose', 'NNP'), ('speech', 'NN'), ('last', 'JJ'), ('Thrsday', 'NNP'), ('.', '.')]

# Lets See how the movies are classified
from nltk.corpus import movie_reviewsall_cats = []
for w in movie_reviews.categories():all_cats.append(w.lower())
print(all_cats)

['neg', 'pos']

from nltk.corpus import movie_reviews
from nltk.tokenize import sent_tokenize
fields = movie_reviews.fileids()sample = movie_reviews.raw("pos/cv944_13521.txt")token = sent_tokenize(sample)
for lines in range(4):print(token[lines])

meteor threat set to blow away all volcanoes & twisters !
summer is here again !
this season could probably be the most ambitious = season this decade with hollywood churning out films
like deep impact , = godzilla , the x-files , armageddon , the truman show ,
all of which has but = one main aim , to rock the box office .
leading the pack this summer is = deep impact , one of the first few film
releases from the = spielberg-katzenberg-geffen's dreamworks production company .

import nltk
from nltk.corpus import movie_reviews
fields = movie_reviews.fileids()all_words = []
for w in movie_reviews.words():all_words.append(w.lower())all_words = nltk.FreqDist(all_words)
print(all_words.most_common(10))

[(,', 77717), (the', 76529), (.', 65876), (a', 38106), (and', 35576),
(of', 34123), (to', 31937), (u"'", 30585), (is', 25195), (in', 21822)]

import nltkword_data = "The best performance can bring in sky high success."
nltk_tokens = nltk.word_tokenize(word_data)      print(list(nltk.bigrams(nltk_tokens)))

[('The', 'best'), ('best', 'performance'), ('performance', 'can'), ('can', 'bring'),
('bring', 'in'), ('in', 'sky'), ('sky', 'high'), ('high', 'success'), ('success', '.')]