| | |
| | | 大单成交数据解析器 |
| | | """ |
| | | import os |
| | | import re |
| | | from multiprocessing import Pool |
| | | |
| | | import pandas as pd |
| | |
| | | """ |
| | | combined_path = os.path.join(dir_path, 'combined.csv') |
| | | if os.path.exists(combined_path): |
| | | print("合并的目标文件已存在") |
| | | return |
| | | file_list = os.listdir(dir_path) |
| | | file_list.sort(key=lambda x: int(x.split(".")[0])) |
| | | file_list.sort(key=lambda x: int(re.findall(r'\d+', x)[0])) |
| | | df_list = [] |
| | | for file in file_list: |
| | | df = pd.read_csv(os.path.join(dir_path, file)) |
| | |
| | | continue |
| | | df["SecurityID"] = df["SecurityID"].apply(BigOrderDealParser.code_format) |
| | | df_list.append(df) |
| | | print("准备合并的文件数量:", len(df_list)) |
| | | |
| | | combined_df = pd.concat(df_list, ignore_index=True) |
| | | |
| | | print("合并完成,准备写入文件!") |
| | | # 保存结果 |
| | | combined_df.to_csv(combined_path, index=False) |
| | | print("写入文件完成!") |
| | | |
| | | |
| | | def concat_pre_transactions(dir_path): |
| | | __concat_pre_datas(dir_path) |
| | | |
| | | def concat_pre_ngtsticks(dir_path): |
| | | __concat_pre_datas(dir_path) |
| | | |
| | | if __name__ == "__main__": |
| | | # pre_process_transactions("E:/测试数据/Transaction_Test.csv") |
| | | pre_process_transactions("E:/测试数据/Transaction_Test.csv") |
| | | # pre_process_ngtsticks("E:/测试数据/NGTSTick_Test.csv") |
| | | concat_pre_transactions("E:/测试数据/Transaction_Test") |