update reproduce

This commit is contained in:
LarFii
2024-10-11 15:16:43 +08:00
parent 52d51f6293
commit c51b2b38b6
5 changed files with 346 additions and 1 deletions

63
reproduce/Step_0.py Normal file
View File

@@ -0,0 +1,63 @@
import os
import json
import glob
import argparse
def extract_unique_contexts(input_directory, output_directory):
os.makedirs(output_directory, exist_ok=True)
jsonl_files = glob.glob(os.path.join(input_directory, '*.jsonl'))
print(f"Found {len(jsonl_files)} JSONL files.")
for file_path in jsonl_files:
filename = os.path.basename(file_path)
name, ext = os.path.splitext(filename)
output_filename = f"{name}_unique_contexts.json"
output_path = os.path.join(output_directory, output_filename)
unique_contexts_dict = {}
print(f"Processing file: {filename}")
try:
with open(file_path, 'r', encoding='utf-8') as infile:
for line_number, line in enumerate(infile, start=1):
line = line.strip()
if not line:
continue
try:
json_obj = json.loads(line)
context = json_obj.get('context')
if context and context not in unique_contexts_dict:
unique_contexts_dict[context] = None
except json.JSONDecodeError as e:
print(f"JSON decoding error in file {filename} at line {line_number}: {e}")
except FileNotFoundError:
print(f"File not found: {filename}")
continue
except Exception as e:
print(f"An error occurred while processing file {filename}: {e}")
continue
unique_contexts_list = list(unique_contexts_dict.keys())
print(f"There are {len(unique_contexts_list)} unique `context` entries in the file {filename}.")
try:
with open(output_path, 'w', encoding='utf-8') as outfile:
json.dump(unique_contexts_list, outfile, ensure_ascii=False, indent=4)
print(f"Unique `context` entries have been saved to: {output_filename}")
except Exception as e:
print(f"An error occurred while saving to the file {output_filename}: {e}")
print("All files have been processed.")
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--input_dir', type=str, default='../datasets')
parser.add_argument('-o', '--output_dir', type=str, default='../datasets/unique_contexts')
args = parser.parse_args()
extract_unique_contexts(args.input_dir, args.output_dir)