XPUB

You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

NLTK - Frequency Distribution¶

In [ ]:

import nltk
import random

In [ ]:

lines = open('txt/language.txt').readlines()
sentence = random.choice(lines)
print(sentence)

Tokens¶

In [ ]:

tokens = nltk.word_tokenize(sentence)
print(tokens)

In [ ]:

In [ ]:

# frequency of characters
fd = nltk.FreqDist(sentence)
print(fd)

In [ ]:

print(fd.most_common(50))

In [ ]:

# frequency of words
fd = nltk.FreqDist(tokens)
print(fd)

In [ ]:

print(fd.most_common(50))

In [ ]:

# frequency of a text
txt = open('txt/language.txt').read()
tokens = nltk.word_tokenize(txt)
fd = nltk.FreqDist(tokens)
print(fd)

In [ ]:

print(fd.most_common(50))

In [ ]:

# Requesting the frequency of a specific word
print(fd['language'])

In [ ]: