def write_content_for_tweet_id():
corpus_path = "C:\\Users\\ASUS\\Desktop\\Data"
config = ConfigClass(corpus_path)
r = ReadFile(corpus_path=config.get__corpusPath())
names = r.get_files_names_in_dir()
with open("text.csv", "w", newline='', encoding='utf-8') as f:
writer = csv.writer(f)
for name in names:
documents_list = r.read_file_by_name(file_name=str(name))
for doc in documents_list:
if doc[0] in tweet_ids:
writer.writerow([doc[0], doc[2]])
def run_engine(corpus_path, output_path, stemming, queries,
num_docs_to_retrieve, word2vec):
"""
:return:
"""
# print("start: ", time.asctime(time.localtime(time.time())))
number_of_documents = 0
num_of_writes = 1
config = ConfigClass(corpus_path)
r = ReadFile(corpus_path=config.get__corpusPath())
p = Parse(stemming)
indexer = Indexer(config, word2vec)
# documents_list = r.read_file(file_name='covid19_07-30.snappy.parquet') # TODO - handel all files ~50 (can do with from multiprocessing.pool import ThreadPool)
# Iterate over every document in the file
counter = 0
names = r.get_files_names_in_dir()
for name in names:
documents_list = r.read_file_by_name(file_name=str(name))
for idx, document in enumerate(documents_list):
parsed_document = p.parse_doc(document) # parse the document
if parsed_document == {}: # RT
continue
number_of_documents += 1
indexer.add_new_doc(parsed_document,
num_of_writes) # index the document data
counter += 1
if counter >= 500000:
write_and_clean_buffer(indexer, num_of_writes, stemming,
config, output_path)
counter = 0
# print("finish parser & index number: ", num_of_writes, " At: ", time.asctime(time.localtime(time.time())))
num_of_writes += 1
# print('Finished parsing and indexing. Starting to export files')
write_and_clean_buffer(indexer, num_of_writes, stemming, config,
output_path)
# print("finish parser & index: ", time.asctime(time.localtime(time.time())))
indexer.inverted_idx = {
key: val
for key, val in indexer.inverted_idx.items() if val != 1
}
utils.save_obj(indexer.inverted_idx, "inverted_idx")
# print("finish save index: ", time.asctime(time.localtime(time.time())))
return num_of_writes