From dfee6963a1839366b3b5307b72f866c6e5529c3e Mon Sep 17 00:00:00 2001 From: Zach Nussbaum Date: Sun, 26 Mar 2023 18:15:22 +0000 Subject: [PATCH] fix: don't rewrite clean file if exists! --- clean.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/clean.py b/clean.py index 9cf8bf57..324b99fd 100644 --- a/clean.py +++ b/clean.py @@ -6,8 +6,10 @@ import jsonlines import pandas as pd -prompt_generation_dir = "prompts-reponses" +prompt_generation_dir = "raw_data_sanity_cleaned_delobotomized" for file in glob.glob(os.path.join(prompt_generation_dir, "*.jsonl")): + if "clean" in file: + continue data = [] print(file) with open(file) as f: