def answer_four():
from nltk.book import FreqDist
token_dict = FreqDist(moby_tokens)
new_list = []
for val in token_dict.keys():
if len(val) > 5 and token_dict[val] > 150:
new_list.append(val)
new_list.sort()
return new_list # Your answer here
def answer_four():
from nltk.book import FreqDist
token_dict = FreqDist(moby_tokens)
res_lis = []
for w in token_dict.keys():
if len(w) > 5 and token_dict[w] > 150:
res_lis.append(w)
res_lis.sort()
return res_lis
def answer_five():
from nltk.book import FreqDist
token_dict = FreqDist(moby_tokens)
max_len = 0
for w in token_dict.keys():
if len(w) > max_len:
max_word = w
max_len = len(w)
tups = (max_word, max_len)
return tups # Your answer here
def answer_six():
import operator
from nltk.book import FreqDist
token_dict = FreqDist(moby_tokens)
liss = {}
for w in token_dict.keys():
if w.isalpha() and token_dict[w] > 2000:
liss[w] = token_dict[w]
sortedlist = sorted(liss.items(), key=operator.itemgetter(1), reverse=True)
finale = [(f, w) for w, f in sortedlist]
return finale # Your answer here
def answer_six():
import operator
from nltk.book import FreqDist
token_dict = FreqDist(moby_tokens)
res_lis = {}
for w in token_dict.keys():
if w.isalpha() and token_dict[w] > 2000:
res_lis[w] = token_dict[w]
sorted_res_list = sorted(res_lis.items(), key=operator.itemgetter(1))
sorted_res_list.reverse()
result = [(f, w) for w, f in sorted_res_list]
return result
freq_150 = sorted([key for key in freq if len(key) > 5 and freq[key] > 150])
freq_150
#ANSWER 5
words = list(set(text1))
longest = ''
for word in words:
if len(word) > len(longest):
longest = word
(longest, len(longest))
#ANSWER6
freq = FreqDist(text1)
freq_2000 = sorted(
[(freq[word], word)
for word in freq.keys() if freq[word] > 2000 and word.isalpha()],
reverse=True)
freq_2000
#ANSWER7
sents = nltk.sent_tokenize(moby_raw)
ratio = len(text1) / len(sents)
ratio
#ANSWER8
tags = nltk.pos_tag(text1)
tag_dict = dict()
for tag in tags:
def question_six():
dist = FreqDist(text1)
frequentwords = [
w for w in list(dist.keys()) if w.isalpha() and dist[w] > 2000
]
return sorted([(dist[w], w) for w in frequentwords], reverse=True)
def question_four():
dist = FreqDist(text1)
frequentwords = [
w for w in list(dist.keys()) if len(w) > 5 and dist[w] > 150
]
return sorted(frequentwords)