def load_files_not_first(self, path='static/outfile'):
files = utilities.load_file(path)
return files
# # this function is extracting the content of an uncleaned txt file
# # for example the content of the file that user uploaded
# def extract_fromTXT(path):
#
# #all_files = filenames(path)
# files_content = []
#
# for filename in all_files:
# with open(os.path.join(path, filename)) as file:
# content = file.read()
# content = re.sub(r"<.*?>", "", content)
# content = re.sub(r"\n", " " , content)
# content = re.sub(r"\t", " ", content)
#
# content = re.sub(r"[0-9]", " ", content)
# content = re.sub(r"\[|\]", " ", content)
# content = re.sub(r"[\.\(\)\:\|]"," ", content)
# content = re.sub(r"[\.\(\)\:\|\/\$\;\"\"\&\#\,]", " ", content)
# #content = re.sub(r" *+ *"," ",content)
# content = re.sub(r" +", " ", content)
# content = content.lower()
#
# files_content.append(content)
#
# return files_content, filename
def keyword_content(keyword):
all_files = 'static/outfiles'
all_names = 'static/filenames'
all_contents = utilities.load_file(all_files)
all_names = hp.load_filenames_not_first(all_names)
results = []
for i in range(len(all_contents)):
if keyword.lower() in all_contents[i].lower():
results.append(all_names[i])
return results
def load_reduced_vectors(self, path='static/reduced_vectors'):
reduced_vectors = utilities.load_file(path)
return reduced_vectors
def load_dim_red_model(self, path='static/PCA'):
reducer = utilities.load_file(path)
return reducer
def load_vector(self, path='static/vectors'):
vectors = utilities.load_file(path)
return vectors
def load_vectorizer(self, path="static/vectorizer"):
vectorizer = utilities.load_file(path)
return vectorizer
def load_all_top_words_not_first(self, path="static/all_file_topwords"):
top_words = utilities.load_file(path)
return top_words
def load_filenames_not_first(self, path="static/filenames"):
filenames = utilities.load_file(path)
return filenames