from knock30 import conll_read
from knock31 import extract_postag
if __name__ == "__main__":
print(extract_postag(conll_read(), 'lemma', 'VB'))
import matplotlib.pyplot as plt
import operator
from knock35 import word_freqs
from knock30 import conll_read
def freqs_chart(count_freq, top):
words = []
freqs = []
for x, y in sorted(count_freq.items(),
key=operator.itemgetter(1),
reverse=True)[:top]:
words.append(str(x))
freqs.append(int(y))
x = range(1, top + 1)
y = freqs
plt.bar(x, y)
plt.xticks(x, words)
plt.xlabel('Words')
plt.ylabel('Frequency')
plt.show()
if __name__ == "__main__":
texts = conll_read()
counts = word_freqs(texts)
freqs_chart(counts, 10)
from knock30 import conll_read
def aofb_long(sentence):
seqs = []
seq = []
for sent in sentence:
for w in sent:
if w['pos'] == 'NN':
seq.append(w['text'])
else:
if len(seq) > 1:
seqs.append(seq)
seq = []
return seqs
if __name__ == "__main__":
phrase = aofb_long(conll_read())
for w in phrase:
print(' '.join(w) + '\n')
from knock30 import conll_read
def extract_postag(sentence, type, pos_tag):
res = []
for sent in sentence:
for token in sent:
if token['pos'] == pos_tag:
res.append(token[type])
return res
if __name__ == "__main__":
print(extract_postag(conll_read(), 'text', 'VB'))
from knock30 import conll_read
from knock31 import extract_postag
def extract_aofb(sentence):
res = []
for sent in sentence:
for w in range(len(sent) - 3):
phrase = sent[w:w + 3]
w1 = phrase[0]['pos'] == 'NN'
w2 = phrase[1]['text'] == 'of'
w3 = phrase[2]['pos'] == 'NN'
if w1 and w2 and w3:
res.append(word['text'] for word in phrase)
return res
if __name__ == "__main__":
phrase = extract_aofb(conll_read())
for w in phrase:
print(' '.join(w) + '\n')
from knock30 import conll_read
import operator
def word_freqs(sentence):
word_count = {}
for sent in sentence:
for w in sent:
if w['text'] in word_count:
word_count[w['text']] += 1
else:
word_count[w['text']] = 1
return word_count
if __name__ == "__main__":
text = conll_read()
counts = word_freqs(text)
for x, y in sorted(counts.items(),
key=operator.itemgetter(1),
reverse=True):
print('%s: %r' % (x, y))