from knock30 import load_mecab
verb = set()
for line in load_mecab():
for morpheme in line:
if(morpheme['pos'] == '動詞'):
verb.add(morpheme['base'])
print(verb)
# -*- coding: utf-8 -*-
from knock30 import load_mecab
path = 'neko.txt.mecab'
ans = []
for sentence in load_mecab(path):
for morpheme in sentence:
if morpheme['pos'] == '動詞':
ans.append(morpheme['surface'])
print(ans)
# -*- coding: utf-8 -*-
from knock30 import load_mecab
from knock36 import morpheme_count
import matplotlib.pyplot as plt
def log_log_graph(rank):
x = []
y = []
for i, (morpheme, count) in enumerate(rank):
x.append(i + 1)
y.append(count)
plt.scatter(x, y, s=10, marker='.')
plt.yscale('log')
plt.xscale('log')
plt.show()
if __name__ == '__main__':
path = 'neko.txt.mecab'
rank = sorted(morpheme_count(load_mecab(path)).items(),
key=lambda x: -x[1])
log_log_graph(rank)
# -*- coding: utf-8 -*-
from knock30 import load_mecab
from collections import defaultdict
def morpheme_count(sentences):
count = defaultdict(lambda: 0)
for sentence in sentences:
for morpheme in sentence:
count[morpheme['surface']] += 1
return count
if __name__ == '__main__':
path = 'neko.txt.mecab'
for morpheme, count in sorted(morpheme_count(load_mecab(path)).items(),
key=lambda x: -x[1]):
print(f'{morpheme} {count}')
def word_counter(num):
word_count = Counter()
for line in load_mecab():
for morpheme in line:
word_count[morpheme['surface']]+=1
return word_count.most_common(num)
# -*- coding: utf-8 -*-
from knock30 import load_mecab
from knock36 import morpheme_count
import matplotlib.pyplot as plt
def histogram(data):
counts = []
for morpheme, count in data.items():
counts.append(count)
plt.hist(counts, bins=20, range=(1, 50))
plt.show()
if __name__ == '__main__':
path = 'neko.txt.mecab'
histogram(morpheme_count(load_mecab(path)))