def analysis(directory: str = './zip',
aggregate=False,
key_file='keys.csv',
res_file='res.xlsx'):
if aggregate:
aggregate_files(directory, key_file)
groups = group(key_file, threshold=0.8)
write_excel(groups, res_file)
return True
def analysis(directory: str = "./zip",
aggregate=False,
clusters_count=2,
key_file="keys.csv",
res_file="res.xlsx"):
""" 对所有的 zip 文件进行分析，输出为到 res.xlsx 文件中"""
if aggregate:
aggregate_files(directory, key_file)
file_path = get_path("keys.csv")
groups = group(file_path, clusters_count=clusters_count)
write_excel(groups, res_file)
return True
def analysis(
directory: str = './zip',
aggregate=False,
clusters_count=2,
file_count: int = 10,
calc_times: bool = False,
key_file='keys.csv',
res_file='res.xlsx',
):
""" 对所有的 zip 文件进行分析，输出为到 res.xlsx 文件中"""
if aggregate:
aggregate_files(directory, key_file)
file_path = get_path('keys.csv')
groups = group(file_path, clusters_count=clusters_count, calc_times=calc_times)
if file_count > clusters_count:
file_count = clusters_count
each = clusters_count // file_count
for i in range(file_count):
subgroup = {t: groups.get(t) for t in range(i * each, (i + 1) * each)}
write_excel(subgroup, f'res/{i + 1}_{res_file}')
return True
def __init__(
self,
directory: str = './zip',
aggregate: bool = True,
key_file='keys.csv',
res_file: str = 'res.xmind',
depth: int = 4,
width: int = 5,
):
self.index = {}
self.invert_index = {}
self.ignore_topics = {}
self.key_file = key_file
self.res_file = res_file
self.depth = depth
self.width = width
if aggregate:
texts = aggregate_files(directory,
file_name='keys.csv',
to_csv=False)
else:
texts = pd.read_csv(key_file, encoding='UTF_8_SIG')
self._build_index(texts, get_stop_words())
def analysis(directory: str = "./zip", aggregate=False, key_file="keys.csv", res_file="res.xlsx"):
if aggregate:
aggregate_files(directory, key_file)
groups = group(key_file, threshold=0.8)
write_excel(groups, res_file)
return True