def word_count()->list:
lines = mecab(file)
longest_N_list = []
word_list = []
for line in lines:
for word in line:
word_list.append(word['surface'])
return(Counter(word_list))
def get_v_sur():
lines = mecab(file)
t = 0
V_sur = []
for line in lines:
for word in line:
if word['pos'] == '動詞':
surface = word['surface']
V_sur.append(surface)
t += 1
if t == 5:
break
return (V_sur)
def get_v_base():
lines = mecab(file)
t = 0
V_base = []
for line in lines:
for word in line:
if word['pos'] == '動詞':
base = word['base']
V_base.append(base)
t += 1
if t == 5:
break
return (V_base)
def get_greedy_n():
lines = mecab(file)
t = 0
longest_N_list = []
Name_phrase = []
for line in lines:
for word in line:
if word['pos'] == '名詞':
Name_phrase.append(word['surface'])
else:
if len(Name_phrase) > 1:
longest_N_list.append("".join(Name_phrase))
Name_phrase = []
t += 1
if t == 10:
break
return (longest_N_list)
def co_occ(target) -> list:
lines = mecab(file)
co_list = []
nouns = []
tar_sen = []
find_tar = 0
for line in lines:
for word in line:
if word['surface'] == '猫': find_tar = 1
else: nouns.append(word['surface'])
if word['surface'] == "。":
if find_tar == 1:
for noun in nouns:
co_list.append(noun)
nouns = []
find_tar = 0
return (co_list)