updated endpoint definitions/names and reformatted some files and code

This commit is contained in:
Kikimanox
2022-09-14 16:40:29 +02:00
parent 0b90b6555b
commit 9e82f3b93a
32 changed files with 988 additions and 742 deletions
+2 -2
View File
@@ -177,8 +177,8 @@ def get_files_by_keywords(kljucnebesede):
ngrams_path = "classla_OS2022/ngrams/" if is_docker() else "../mnt/ssd/ds_ftp/classla_OS2022/ngrams/"
print("Looping trough ngrams")
for path, dirs, files, in os.walk(ngrams_path):
for i, _file in enumerate(files[:200]):
if i % 200 == 0: print(f"{i}/{len(files)}")
for i, _file in enumerate(files[:100]):
if i % 500 == 0: print(f"{i}/{len(files)}")
file = f'{ngrams_path}{_file}'
data = pd.read_csv(file, sep='\t')
amount = len(data[data['ngram_len'] == 1 & data['gram_text'].str.lower().isin(kljucnebesede)])