saved_models/codesearch_simp/simplify.py

import numpy as np
import json

# file_path = "/home/yiming/ContrastDebugger/EXP/codesearch_simp/Model/Epoch_1/train_data.npy"

# # 读取 ndarray 数据
# data = np.load(file_path)

# print(len(data))
# # # 选择前 50000 条数据
# # selected_data = data[:50000]

# # # 重新保存到文件中
# # np.save(file_path, selected_data)

# idxs = [i for i in range(len(data))]

# idxs_path = "/home/yiming/ContrastDebugger/EXP/codesearch_simp/Model/Epoch_1/index.json"
# json_file = open(idxs_path, mode='w')
# json.dump(idxs, json_file, indent=4)

input_file = "/home/yiming/ContrastDebugger/EXP/codesearch_query_simp/Model/label_list.json"
output_file = "/home/yiming/ContrastDebugger/EXP/codesearch_query_simp/Model/label.txt"

# 读取输入文件
with open(input_file, "r") as f:
    data = json.load(f)

# 选择前 50000 条数据
selected_data = data[:50000]

# 将每条数据作为一行存储到输出文件
with open(output_file, "w") as f:
    for item in selected_data:
        f.write(item + "\n")