def word_count() -> list:
lines = data_mapping(analysis_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 = data_mapping(analysis_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 = data_mapping(analysis_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_n_phrase():
lines = data_mapping(analysis_file)
t = 0
N_phrase = []
for line in lines:
for i in range(1, len(line) - 1):
if line[i]['surface'] == 'の' \
and line[i - 1]['pos'] == '名詞' \
and line[i + 1]['pos'] == '名詞':
phrase = line[i-1]['surface'] + line[i]['surface'] + line[i+1]['surface']
N_phrase.append(phrase)
t += 1
if t == 10:
break
return(N_phrase)
def co_occ(target) -> list:
lines = data_mapping(analysis_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)