Untitled
Anonymous
plain_text
04/27/2023 10:33 AM
532 B
32
Indexable
class FilterImportantLogsDoFn(beam.DoFn):
def __init__(self, important_words_file):
self.important_words_file = important_words_file
def process(self, df):
with open(self.important_words_file, "r") as f:
important_words = f.read().splitlines()
filtered_df = df[df['log_text'].str.contains('|'.join(important_words))]
yield filtered_df
Editor is loading...