def main():
hound = text_to_string('hound.txt')
tokens = nltk.word_tokenize(hound)
texts = Text(tokens)
plt.ion()
plt.figure(figsize=(12, 9))
targets = [
'Holmes', 'Watson', 'Mortimer', 'Henry', 'Barrymore', 'Stapleton',
'Seldon', 'hound'
]
dispersion_plot(texts,
targets,
ignore_case=True,
title='Lexical Dispersion Plot')
plt.show(block=True)
def plot():
import nltk
import matplotlib.pyplot as plt
f = open("egghunt.txt")
raw = f.read()
tokens = nltk.word_tokenize(raw)
text = nltk.Text(tokens)
from nltk.draw.dispersion import dispersion_plot
plt.figure(figsize=(20, 3))
targets = ['creative', "egg", "hunt", 'happy', 'easter', 'yall']
dispersion_plot(text,
targets,
ignore_case=True,
title='Lexical Dispersion Plot')
# explore other concordances in different texts
print(text6.concordance('rabbit'))
print(lb1)
print(text3.concordance('lived'))
print(lb2)
print(text5.concordance('f**k'))
# print similarities to monstrous in Moby Dick and S & S
print(text1.similar('monstrous'))
print(lb1)
print(text2.similar('monstrous'))
print(lb2)
# print common contexts for very and monstrous in S & S
print(text2.common_contexts(['monstrous', 'very']))
print(lb1)
# explore similar and common_contexts
print(text6.similar('king'))
print(lb2)
print(text3.similar('king'))
print(lb1)
print(text5.common_contexts(['love', 'f**k']))
# print dispersion plot
dispersion_plot(text4,
['citizens', 'democracy', 'freedom', 'duties', 'America'])
# expolore dispersion_plot
dispersion_plot(text6, ['spam', 'king', 'grail', 'rabbit', 'ni'])
def wordhomogenity():
dispersion_plot(data2.Translated_Review,["good","awesome","usefull","love",
"brilliant","great","amazing","best"])
import nltk
from nltk.draw.dispersion import dispersion_plot
import matplotlib
ww = open("Moana.txt", "r")
raw = ww.read()
# process
pattern = r'''(?x) # set flag to allow verbose regexps
([A-Z]\.)+ # abbreviations, e.g. U.S.A.
| \w+(-\w+)* # words with optional internal hyphens
| \$?\d+(\.\d+)?%? # currency and percentages, e.g. $12.40, 82%
| \.\.\. # ellipsis
| [][.,;"'?():-_`] # these are separate tokens; includes ], [
'''
tokens = nltk.regexp_tokenize(raw, pattern)
lctokens = [w.lower() for w in tokens]
# ordered by frequency
from collections import Counter
c = Counter(tokens)
c.most_common(100)
#plot
dispersion_plot(lctokens, [
'maui', 'hook', 'heart', 'te', 'fiti', 'ka', 'ocean', 'island', 'reef',
'moana', 'boat', 'gramma', 'tattoo', 'cheeeehoooo', 'crab', 'shiny'
])
from nltk.draw.dispersion import dispersion_plot
#ww = open("Wonder.Woman.2017.txt","r")
ww = open("Black.Panther.dialogue.txt","r")
raw = ww.read()
# process
pattern = r'''(?x) # set flag to allow verbose regexps
([A-Z]\.)+ # abbreviations, e.g. U.S.A.
| \w+(-\w+)* # words with optional internal hyphens
| \$?\d+(\.\d+)?%? # currency and percentages, e.g. $12.40, 82%
| \.\.\. # ellipsis
| [][.,;"'?():-_`] # these are separate tokens; includes ], [
'''
tokens = nltk.regexp_tokenize(raw,pattern)
tokens = nltk.word_tokenize(raw)
lctokens = [w.lower() for w in tokens]
# ordered by frequency
from collections import Counter
c = Counter(lctokens)
for (i,j) in c.most_common(300):
if len(i) > 4:
print (i,j)
dispersion_plot(lctokens,['wakanda','oakland','korea','t\'challa','black','panther','nakia', 'shuri', 'okoye', 'klaue',
'jabari','n\'jobu','killmonger','ancestors','lab','challenge','herb',
'vibranium','weapons','freeze','beads','suit','heal','technology'])
# 1.3 Searching Text
text1.concordance('monstrous')
text1.concordance('live')
# Similar words, these are like synonym but derived from the context.
text1.similar('monstrous')
text2.similar('monstrous')
text1.similar('live')
# We can also obtain the shared context between multiple phrases.
text2.common_contexts(["monstrous", "very"])
# Dispersion plot, this plot displayes the location of occurence within a text.
from nltk.draw.dispersion import dispersion_plot
dispersion_plot(text4,
["citizens", "democracy", "freedom", "duties", "America"])
# We can also generate text based on the article.
#
# NOTE(Michael): This feature does not work in NLTK 3.0.
# text3.generate()
# 1.4 Counting Volcabulary
len(text3)
# We can also obtain the unique words (or token) in the text.
#
# Esentially, what we are doing is convert the text to a set, which
# contains only unique entries.
sorted(set(text3))
ww = open("Labyrinth.txt", "r")
raw = ww.read()
# process
pattern = r'''(?x) # set flag to allow verbose regexps
([A-Z]\.)+ # abbreviations, e.g. U.S.A.
| \w+(-\w+)* # words with optional internal hyphens
| \$?\d+(\.\d+)?%? # currency and percentages, e.g. $12.40, 82%
| \.\.\. # ellipsis
| [][.,;"'?():-_`] # these are separate tokens; includes ], [
'''
tokens = nltk.regexp_tokenize(raw, pattern)
#tokens = nltk.word_tokenize(raw)
# squash capitalization to combine words at beginning of sentences with others
lctokens = [w.lower() for w in tokens]
# ordered by frequency
from collections import Counter
c = Counter(tokens)
c.most_common(100)
#plot
dispersion_plot(lctokens, [
'ludo', 'hoggle', 'labyrinth', 'sarah', 'ambrosius', 'castle', 'toby',
'baby', 'friend', 'magic', 'solve', 'goblin', 'fair'
])
'''
tokens = nltk.regexp_tokenize(raw, pattern)
tokens = nltk.word_tokenize(raw)
lctokens = [w.lower() for w in tokens]
# ordered by frequency
from collections import Counter
c = Counter(text6)
c.most_common(50)
#plot
dispersion_plot(lctokens, [
'diana', 'wonder', 'woman', 'hippolyta', 'zeus', 'steve', 'ares', 'war',
'men', 'evil', 'ludendorff', 'german', 'gas', 'love', 'ice', 'cream',
'sleep', 'dance'
])
# Who is WW really about?
dispersion_plot(lctokens, [
'diana',
'wonder',
'woman',
'hippolyta',
'zeus',
'steve',
'ares',
'ludendorff',
'german',
plt.axis('off')
plt.show()
import nltk
from nltk.draw.dispersion import dispersion_plot
from nltk.corpus import stopwords
stopwords = stopwords.words('english')
wordlist = nltk.word_tokenize(text)
topics = ['government','country','states','citizen','power']
dispersion_plot(wordlist,topics)
wordlist = [x.lower() for x in nltk.word_tokenize(text) if x.lower() not in stopwords and x.isalpha()]
freq = nltk.FreqDist(wordlist)
plt.figure(figsize=(12,12))
freq.plot(50)
# lexical diversity
# text is a list of words
def ld(text):
return len(set(text))/len(text)
# -*-coding:UTF-8-*-
import codecs
import nltk
#import numpy, matplotlib
from nltk.draw.dispersion import dispersion_plot
text = codecs.open('quranic.txt', 'r', 'utf-8')
text4 = text.read()
text.close()
#text4=nltk.Text(text4)
text4 = text4.split()
#text4=u"بسم الله الرحمن الرحيم"
dispersion_plot(text4, ["LEM:{ll~ah"])
length = 0
print('Total usage of words: ', total, '\n')
print('Usage of the word men: ', men, '\n')
print('Usage of the word women: ', women, '\n')
print('Usage of the word people: ', people, '\n')
#Extra: Producing a dispersion plot to see the usages of the words over time
cfd = nltk.ConditionalFreqDist(
(genre, word) for genre in su.fileids() for word in su.words(genre)
if word.lower() == 'women' or word.lower() == 'men'
or word.lower() == 'people')
from nltk.draw.dispersion import dispersion_plot
words_watch = ['men', 'women', 'people']
dispersion_plot(su.words(), words_watch, ignore_case=True)
#Number 2 (2.13) in HW3
print('################ Number 2 ################')
from nltk.corpus import wordnet as wn
nnw = wn.all_synsets('n')
nouns = list(nnw)
print('Length of synsets', len(nouns))
yes = []
for w in nouns:
if len(w.hyponyms()) != 0:
yes.append(w)
print('Length of synsets with hyponyms', len(yes))
print('Percentage of noun synsets with no hypnoyms',
# Show tf-idf feature matrix tfidf.get_feature_names() # Create data frame #pd.DataFrame(feature_matrix.toarray(), columns=tfidf.get_feature_names()) # ## 2. Lexical dispersion plot # This is the plot of a word vs the offset of the word in the text corpus.The y-axis represents the word. Each word has a strip representing entire text in terms of offset, and a mark on the strip indicates the occurrence of the word at that offset, a strip is an x-axis. The positional information can indicate the focus of discussion in the text. topics = ['projection', 'federal', 'percent', 'tealbook', 'economic'] from nltk.draw.dispersion import dispersion_plot dispersion_plot(allwords, topics) # ## 3. Frequency distribution plot import nltk from nltk.probability import FreqDist fqdist = FreqDist(allwords) freqdist = nltk.FreqDist(allwords) plt.figure(figsize=(16, 5)) freqdist.plot(50) # Most Frequent 10 words in all Text freqdist.most_common(10)
from nltk.book import *
import nltk
# problem 1
from nltk.draw.dispersion import dispersion_plot
p1_words = ['Elinor', 'Marianne', 'Edward', 'Willoughby']
dispersion_plot(text2, p1_words)
# problem 2
V = set(text5)
wordsBeginWithT = [w for w in V if (len(w) == 5) and ((w[0] == 't') or (w[0] == 'T'))]
print(sorted(wordsBeginWithT))
from nltk import FreqDist
fdist = FreqDist(w for w in text5 if len(w) == 5)
print(fdist.most_common())
# problem 3
lista = sorted(w for w in set(text2) if w.endswith('er'))
listb = sorted(w for w in set(text2) if 'm' in w)
listc = sorted(w for w in set(text2) if 'ph' in w)
listd = sorted(w for w in set(text2) if w.istitle())
listall = lista + listb + listc + listd
print(listall)
text1.concordance("monstrous")
# What other words appear in a similar range of contexts?
text1.similar("monstrous")
# Examine contexts shared by two or more words
text2.common_contexts(["monstrous", "very"])
# Determine location of a word in the context, or how many words from the beginning it appears
# Note: As of November 13, 2016, the book's example code does not work.
# http://stackoverflow.com/questions/25182140/dispersion-plot-not-working-inspite-of-installing-matplotlib
from nltk.draw.dispersion import dispersion_plot
words = ["citizens", "democracy", "freedom", "duties", "America"]
dispersion_plot(text4, words)
# Find out the length of a text, in terms of words and punctuation
len(text3)
# len() returns a number of tokens, or a sequence of characters to be treated as a group
# Obtain vocabulary of a text, or the set of tokens used
sorted(set(text3))
len(set(text3))
# Compute lexical richness defined as percentage of unique words
len(set(text3)) / len(text3)
# Count how often a word occurs
