import pandas as pd import os from datetime import time as s_time from datetime import datetime import chardet # 日盘商品期货交易品种 commodity_day_dict = {'bb': s_time(15,00), 'jd': s_time(15,00), 'lh': s_time(15,00), 'l': s_time(15,00), 'fb': s_time(15,00), 'ec': s_time(15,00), 'AP': s_time(15,00), 'CJ': s_time(15,00), 'JR': s_time(15,00), 'LR': s_time(15,00), 'RS': s_time(15,00), 'PK': s_time(15,00), 'PM': s_time(15,00), 'PX': s_time(15,00), 'RI': s_time(15,00), 'ao': s_time(15,00), 'br': s_time(15,00), 'wr': s_time(15,00),} # 夜盘商品期货交易品种 commodity_night_dict = {'sc': s_time(2,30), 'bc': s_time(1,0), 'lu': s_time(23,0), 'nr': s_time(23,0),'au': s_time(2,30), 'ag': s_time(2,30), 'ss': s_time(1,0), 'sn': s_time(1,0), 'ni': s_time(1,0), 'pb': s_time(1,0),'zn': s_time(1,0), 'al': s_time(1,0), 'cu': s_time(1,0), 'ru': s_time(23,0), 'rb': s_time(23,0), 'hc': s_time(23,0), 'fu': s_time(23,0), 'bu': s_time(23,0), 'sp': s_time(23,0), 'PF': s_time(23,0), 'SR': s_time(23,0), 'CF': s_time(23,0), 'CY': s_time(23,0), 'RM': s_time(23,0), 'MA': s_time(23,0), 'TA': s_time(23,0), 'ZC': s_time(23,0), 'FG': s_time(23,0), 'OI': s_time(23,0), 'SA': s_time(23,0), 'p': s_time(23,0), 'j': s_time(23,0), 'jm': s_time(23,0), 'i': s_time(23,0), 'l': s_time(23,0), 'v': s_time(23,0), 'pp': s_time(23,0), 'eg': s_time(23,0), 'c': s_time(23,0), 'cs': s_time(23,0), 'y': s_time(23,0), 'm': s_time(23,0), 'a': s_time(23,0), 'b': s_time(23,0), 'rr': s_time(23,0), 'eb': s_time(23,0), 'pg': s_time(23,0)} # 金融期货交易品种 financial_time_dict = {'IH': s_time(15,00), 'IF': s_time(15,00), 'IC': s_time(15,00), 'IM': s_time(15,00),'T': s_time(15,00), 'TS': s_time(15,00), 'TF': s_time(15,00), 'TL': s_time(15,00)} # 所有已列入的筛选品种 all_dict = {k: v for d in [commodity_day_dict, commodity_night_dict, financial_time_dict] for k, v in d.items()} # def has_common_keys(*dicts): # keys_union = set().union(*dicts) # 计算所有字典键的并集 # keys_intersection = set().intersection(*dicts) # 计算所有字典键的交集 # return len(keys_intersection) > 0 # has_common_keys(commodity_day_dict, commodity_night_dict,financial_time_dict) # import chardet # # 假设file_path是你要读取的文件路径 # with open(file_path, 'rb') as file: # data = file.read() # # 使用chardet检测编码 # detected_encoding = chardet.detect(data)['encoding'] # # 如果检测到的编码不是gbk，可以尝试转换编码后再读取 # if detected_encoding and detected_encoding != 'gbk': # with open(file_path, 'rb') as file: # data = file.read().decode(detected_encoding) def split_alpha_numeric(string): alpha_chars = "" numeric_chars = "" for char in string: if char.isalpha(): alpha_chars += char elif char.isdigit(): numeric_chars += char return alpha_chars, numeric_chars def find_files(all_csv_files): all_csv_files = sorted(all_csv_files) sp_old_chars = ['_2019','_2020','_2021'] sp_old_chars = sorted(sp_old_chars) sp_new_chars = ['_2022','_2023'] sp_new_chars = sorted(sp_new_chars) csv_old_files = [file for file in all_csv_files if any(sp_char in file for sp_char in sp_old_chars)] csv_new_files = [file for file in all_csv_files if any(sp_char in file for sp_char in sp_new_chars)] return csv_old_files, csv_new_files def merged_old_tickdata(all_csv_files, sp_char): merged_up_df = pd.DataFrame() merged_up_df = merged_old_unprocessed_tickdata(all_csv_files, sp_char) # 获取当前目录下的所有文件名包含sp_char的csv文件 # 添加主力连续的合约代码，主力连续为888，指数连续可以用999，次主力连续可以使用889，表头用“统一代码” alpha_chars, numeric_chars = split_alpha_numeric(merged_up_df.loc[0,'合约代码']) code_value = alpha_chars + "888" print("code_value characters:", code_value) merged_up_df.insert(loc=0,column="统一代码", value=code_value) while alpha_chars not in all_dict.keys(): print("%s期货品种未列入所有筛选条件中!!!"%(code_value)) continue # merged_df['时间'] = pd.to_datetime(merged_df['时间']) merged_df =pd.DataFrame({'main_contract':merged_df['统一代码'],'symbol':merged_df['合约代码'],'datetime':merged_df['时间'],'lastprice':merged_df['最新'],'volume':merged_df['成交量'], 'bid_p':merged_df['买一价'],'ask_p':merged_df['卖一价'],'bid_v':merged_df['买一量'],'ask_v':merged_df['卖一量']}) merged_df['tmp_time'] = merged_df['datetime'].dt.strftime('%H:%M:%S.%f') merged_df['time'] = merged_df['tmp_time'].apply(lambda x: datetime.strptime(x, '%H:%M:%S.%f')).dt.time del merged_df['tmp_time'] if alpha_chars in financial_time_dict.keys(): drop_index1 = pd.DataFrame().index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 0, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) | (merged_df['time'] < s_time(9, 30, 0, 000000))].index drop_index4 = pd.DataFrame().index print("按照中金所交易时间筛选金融期货品种") # else: elif alpha_chars in commodity_night_dict.keys(): if commodity_night_dict[alpha_chars] == s_time(23,00): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) & (merged_df['time'] < s_time(21, 0, 0, 000000))].index drop_index4 = merged_df.loc[(merged_df['time'] > s_time(23, 0, 0, 000000)) | (merged_df['time'] < s_time(9, 0, 0, 000000))].index print("按照夜盘截止交易时间为23:00筛选商品期货品种") elif commodity_night_dict[alpha_chars] == s_time(1,00): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) & (merged_df['time'] < s_time(21, 0, 0, 000000))].index drop_index4 = merged_df.loc[(merged_df['time'] > s_time(1, 0, 0, 000000)) & (merged_df['time'] < s_time(9, 0, 0, 000000))].index print("按照夜盘截止交易时间为1:00筛选商品期货品种") elif commodity_night_dict[alpha_chars] == s_time(2,30): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) & (merged_df['time'] < s_time(21, 0, 0, 000000))].index drop_index4 = merged_df.loc[(merged_df['time'] > s_time(2, 30, 0, 000000)) & (merged_df['time'] < s_time(9, 0, 0, 000000))].index print("按照夜盘截止交易时间为2:30筛选商品期货品种") else: print("夜盘截止交易时间未设置或者设置错误！！！") elif alpha_chars in commodity_day_dict.keys(): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) | (merged_df['time'] < s_time(9, 0, 0, 000000))].index drop_index4 = pd.DataFrame().index print("按照无夜盘筛选商品期货品种") else: print("%s期货品种未列入筛选条件中!!!"%(code_value)) # 清理不在交易时间段的数据 merged_df.drop(labels=drop_index1, axis=0, inplace=True) merged_df.drop(drop_index2, axis=0, inplace=True) merged_df.drop(drop_index3, axis=0, inplace=True) merged_df.drop(drop_index4, axis=0, inplace=True) del merged_df['time'] # sorted_merged_df = merged_df.sort_values(by = ['datetime'], ascending=True) # merged_df['datetime'] = pd.to_datetime(merged_df['datetime']) merged_df['datetime'] = sorted(merged_df['datetime']) print("%s%s数据生成成功!"%(code_value,sp_char)) return merged_df, code_value def merged_new_tickdata(all_csv_files, sp_char): # 获取当前目录下的所有文件名包含sp_char的csv文件 csv_files = [sp_file for sp_file in all_csv_files if sp_char in sp_file] print("csv_files:", csv_files) merged_df = pd.DataFrame() dir = os.getcwd() # 循环遍历每个csv文件 for file in csv_files: # 读取csv文件，并使用第一行为列标题，编译不通过可以改为gbk try: df = pd.read_csv( file, header=0, usecols=[0, 1, 4, 11, 20, 21, 22, 23, 24, 25, 43], names=[ "交易日", "合约代码", "最新价", "数量", "最后修改时间", "最后修改毫秒", "申买价一", "申买量一", "申卖价一", "申卖量一", "业务日期", ], encoding='gbk', # skiprows=0, parse_dates=['业务日期','最后修改时间','最后修改毫秒'])#注意此处增加的排序，为了后面按时间排序 except: # 假设file_path是你要读取的文件路径 file_path = os.path.join(dir, file) with open(file_path, 'rb') as file: data = file.read() # 使用chardet检测编码 detected_encoding = chardet.detect(data)['encoding'] print("当前读取文件读取错误：", file) print("当前读取文件正确解码格式", detected_encoding) # 删除重复行 df.drop_duplicates(inplace=True) # 将数据合并到新的DataFrame中 merged_df = pd.concat([merged_df, df], ignore_index=True) # 删除重复列 merged_df.drop_duplicates(subset = merged_df.columns.tolist(), inplace=True) # 重置行索引 merged_df.reset_index(inplace=True, drop=True) #print("合约代码:", merged_df["合约代码"]) # 插入新的数据 alpha_chars, numeric_chars = split_alpha_numeric(merged_df.loc[0,'合约代码']) # print("Alphabetical characters:", alpha_chars) # 添加主力连续的合约代码，主力连续为888，指数连续可以用999，次主力连续可以使用889，表头用“统一代码” code_value = alpha_chars + "888" print("code_value characters:", code_value) merged_df.insert(loc=1, column="统一代码", value=code_value) while alpha_chars not in all_dict.keys(): print("%s期货品种未列入所有筛选条件中!!!"%(code_value)) continue #日期修正 #merged_df['业务日期'] = pd.to_datetime(merged_df['业务日期']) merged_df['业务日期'] = merged_df['业务日期'].dt.strftime('%Y-%m-%d') merged_df['datetime'] = merged_df['业务日期'] + ' '+merged_df['最后修改时间'].dt.time.astype(str) + '.' + merged_df['最后修改毫秒'].astype(str) # 将'datetime' 列的数据类型更改为 datetime 格式，如果数据转换少8个小时，可以用timedelta处理 merged_df['datetime'] = pd.to_datetime(merged_df['datetime'], errors='coerce', format='%Y-%m-%d %H:%M:%S.%f') #计算瞬时成交量 merged_df['volume'] = merged_df['数量'] - merged_df['数量'].shift(1) merged_df['volume'] = merged_df['volume'].fillna(0) merged_df =pd.DataFrame({'main_contract':merged_df['统一代码'],'symbol':merged_df['合约代码'],'datetime':merged_df['datetime'],'lastprice':merged_df['最新价'],'volume':merged_df['volume'], 'bid_p':merged_df['申买价一'],'ask_p':merged_df['申卖价一'],'bid_v':merged_df['申买量一'],'ask_v':merged_df['申卖量一']}) merged_df['tmp_time'] = merged_df['datetime'].dt.strftime('%H:%M:%S.%f') merged_df['time'] = merged_df['tmp_time'].apply(lambda x: datetime.strptime(x, '%H:%M:%S.%f')).dt.time del merged_df['tmp_time'] if alpha_chars in financial_time_dict.keys(): drop_index1 = pd.DataFrame().index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 0, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) | (merged_df['time'] < s_time(9, 30, 0, 000000))].index drop_index4 = pd.DataFrame().index print("按照中金所交易时间筛选金融期货品种") # else: elif alpha_chars in commodity_night_dict.keys(): if commodity_night_dict[alpha_chars] == s_time(23,00): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) & (merged_df['time'] < s_time(21, 0, 0, 000000))].index drop_index4 = merged_df.loc[(merged_df['time'] > s_time(23, 0, 0, 000000)) | (merged_df['time'] < s_time(9, 0, 0, 000000))].index print("按照夜盘截止交易时间为23:00筛选商品期货品种") elif commodity_night_dict[alpha_chars] == s_time(1,00): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) & (merged_df['time'] < s_time(21, 0, 0, 000000))].index drop_index4 = merged_df.loc[(merged_df['time'] > s_time(1, 0, 0, 000000)) & (merged_df['time'] < s_time(9, 0, 0, 000000))].index print("按照夜盘截止交易时间为1:00筛选商品期货品种") elif commodity_night_dict[alpha_chars] == s_time(2,30): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) & (merged_df['time'] < s_time(21, 0, 0, 000000))].index drop_index4 = merged_df.loc[(merged_df['time'] > s_time(2, 30, 0, 000000)) & (merged_df['time'] < s_time(9, 0, 0, 000000))].index print("按照夜盘截止交易时间为2:30筛选商品期货品种") else: print("夜盘截止交易时间未设置或者设置错误！！！") elif alpha_chars in commodity_day_dict.keys(): drop_index1 = merged_df.loc[(merged_df['time'] > s_time(10, 15, 0, 000000)) & (merged_df['time'] < s_time(10, 30, 0, 000000))].index drop_index2 = merged_df.loc[(merged_df['time'] > s_time(11, 30, 0, 000000)) & (merged_df['time'] < s_time(13, 30, 0, 000000))].index drop_index3 = merged_df.loc[(merged_df['time'] > s_time(15, 0, 0, 000000)) | (merged_df['time'] < s_time(9, 0, 0, 000000))].index drop_index4 = pd.DataFrame().index print("按照无夜盘筛选商品期货品种") else: print("%s期货品种未列入筛选条件中!!!"%(code_value)) # 清理不在交易时间段的数据 merged_df.drop(labels=drop_index1, axis=0, inplace=True) merged_df.drop(drop_index2, axis=0, inplace=True) merged_df.drop(drop_index3, axis=0, inplace=True) merged_df.drop(drop_index4, axis=0, inplace=True) del merged_df['time'] # sorted_merged_df = merged_df.sort_values(by = ['datetime'], inplace=True) merged_df['datetime'] = sorted(merged_df['datetime']) print("%s%s数据生成成功!"%(code_value,sp_char)) return merged_df, code_value def merged_old_unprocessed_tickdata(all_csv_files, sp_char): csv_files = [sp_file for sp_file in all_csv_files if sp_char in sp_file] print("csv_files:", csv_files) merged_df = pd.DataFrame() dir = os.getcwd() # 循环遍历每个csv文件 for file in csv_files: try: # 读取csv文件，并使用第一行为列标题，编译不通过可以改为gbk df = pd.read_csv(file, header=0, encoding='gbk') except: file_path = os.path.join(dir, file) with open(file_path, 'rb') as file: data = file.read() # 使用chardet检测编码 detected_encoding = chardet.detect(data)['encoding'] print("当前读取文件读取错误：", file) print("当前读取文件正确解码格式", detected_encoding) # 删除重复行 df.drop_duplicates(inplace=True) # 将数据合并到新的DataFrame中 merged_df = pd.concat([merged_df, df], ignore_index=True) # 删除重复列 merged_df.drop_duplicates(subset=merged_df.columns.tolist(), inplace=True) # 重置行索引 merged_df.reset_index(inplace=True, drop=True) # 插入新的数据 alpha_chars, numeric_chars = split_alpha_numeric(merged_df.loc[0,'合约代码']) # 添加主力连续的合约代码，主力连续为888，指数连续可以用999，次主力连续可以使用889，表头用“统一代码” code_value = alpha_chars + "888" print("code_value characters:", code_value) merged_df.insert(loc=1,column="统一代码", value=code_value) # 将合并后的数据保存到csv文件中 folder_path = "合成tick数据2019-2021" if not os.path.exists(folder_path): os.mkdir('合成tick数据2019-2021') # sorted_merged_df = merged_df.sort_values(by= ['业务日期','最后修改时间','最后修改毫秒'], ascending=[True, True, True]) # sorted_merged_df.to_csv('./合成tick数据/%s.csv'%(code_value), index=False) merged_df['时间'] = pd.to_datetime(merged_df['时间']) sorted_merged_df = merged_df.sort_values(by = ['时间'], ascending=True) sorted_merged_df.to_csv('./合成tick数据2019-2021/%s%s.csv'%(code_value,sp_char), index=False) del merged_df del sorted_merged_df #merged_df.to_csv('./合成tick数据/%s.csv'%(code_value), index=False) #数据按照时间排序，前面文件夹按照时间修改好了可以直接用这里 # 打印提示信息 print("CSV文件合并成功！")