def save_corpus_one_extracted_feature_by_name(self,
feature_name,
left=0,
right=0):
filenames = tp.get_filenames_from_dir(self._file_dir)
for filename in filenames:
save_extracted_feature_by_name(self._file_dir + filename,
feature_name, left, right)
def save_corpus_one_extracted_feature_by_regex(self,
regex,
left=0,
right=0,
feature_name=None):
filenames = tp.get_filenames_from_dir(self._file_dir)
for filename in filenames:
save_extracted_feature_by_regex(self._file_dir + filename, regex,
left, right, feature_name)
def save_corpus_extracted_features(self, left=0, right=0):
other_feature_patterns = [v for v in fs.FEATURE_DICT.values()]
filenames = tp.get_filenames_from_dir(self._file_dir)
for filename in filenames:
raw_text = str(open(self._file_dir + filename, 'rb').read())
tagged_text = tp.get_modified_pos_tagged_text(raw_text)
for pattern in other_feature_patterns:
results = fs.feature_finder(pattern, tagged_text)
feature_name = get_feature_name_by_regex(pattern)
file_p = self._file_dir + filename
save_extracted_feature_by_res(file_p, results, feature_name,
tagged_text, left, right)
print('The extracted features of the corpus saved!')
def corpus_feature_fre_extraction(self,
normalized_rate=100,
save_tagged_corpus=True,
save_extracted_features=True,
left=0,
right=0):
freq_data = [[
'Filename', 'Words', 'Mean word length', 'Type-token ratio'
]]
feature_names = [k for k in fs.FEATURE_DICT.keys()]
freq_data[0].extend(feature_names)
filenames = tp.get_filenames_from_dir(self._file_dir)
for filename in filenames:
sub_data = get_single_file_feature_fre(self._file_dir + filename,
normalized_rate,
save_tagged_corpus,
save_extracted_features,
left, right)
freq_data.append(sub_data)
pd.DataFrame(freq_data).to_excel('Feature_Fre_Extracted.xlsx')
return freq_data
def save_cleaned_corpus(self):
filenames = tp.get_filenames_from_dir(self._file_dir)
for filename in filenames:
save_single_cleaned_text(self._file_dir + filename)
print('Cleaned corpus saved!')
def get_filepath_list(self):
filenames = tp.get_filenames_from_dir(self._file_dir)
path_list = []
for filename in filenames:
path_list.append(self._file_dir + filename)
return '\n'.join(path_list)