From e6cbb6c96b6576da5eaf089cfa3dd6098cc6baf9 Mon Sep 17 00:00:00 2001
From: Administrator <admin@example.com>
Date: 星期二, 27 五月 2025 15:40:30 +0800
Subject: [PATCH] 人为修改大单阈值
---
data_parser/transaction_big_order_parser.py | 70 ++++++++++++++++++++++++++++-------
1 files changed, 56 insertions(+), 14 deletions(-)
diff --git a/data_parser/transaction_big_order_parser.py b/data_parser/transaction_big_order_parser.py
index e986684..42aa437 100644
--- a/data_parser/transaction_big_order_parser.py
+++ b/data_parser/transaction_big_order_parser.py
@@ -194,9 +194,60 @@
))
-def extract_big_order_of_code(dir_path, code):
+def extract_big_order_of_code(dir_path, code=None):
"""
鎻愬彇浠ｇ爜鐨勫ぇ鍗�
+ @param dir_path: 鏁版嵁鐩綍
+ @param code: 涓虹┖琛ㄧず瀵煎嚭鍏ㄩ儴
+ @return:
+ """
+
+ def first_last(group):
+ """
+ 鑾峰彇绗竴鏉℃暟鎹笌鏈�鍚庝竴鏉�
+ @param group:
+ @return:
+ """
+ return pd.Series({
+ 'SecurityID': group['SecurityID'].iloc[0],
+ 'BuyNo': group['BuyNo'].iloc[0],
+ 'TotalVolume': group['TotalVolume'].sum(),
+ 'TotalAmount': group['TotalAmount'].sum(),
+ 'EndTime': group['EndTime'].iloc[-1],
+ 'EndPrice': group['EndPrice'].iloc[-1],
+ 'StartTime': group['StartTime'].iloc[0],
+ 'StartPrice': group['StartPrice'].iloc[0]
+ })
+
+ combined_path = os.path.join(dir_path, 'combined.csv')
+ if not os.path.exists(combined_path):
+ print("鎷兼帴鏁版嵁涓嶅瓨鍦�")
+ return
+ df = pd.read_csv(combined_path)
+ df_copy = df.copy()
+ if code:
+ df_copy = df_copy[df_copy["SecurityID"] == int(code)]
+ if df_copy.empty:
+ print("鐩爣浠ｇ爜瀵瑰簲鎴愪氦鏁版嵁涓虹┖")
+ return
+ df_copy["SecurityID"] = df_copy["SecurityID"].apply(BigOrderDealParser.code_format)
+ # 鎸塖ecurityID鍜孊uyNo鍒嗙粍
+ grouped = df_copy.groupby(['SecurityID', 'BuyNo'])
+ grouped_result = grouped.apply(first_last)
+ grouped_result = grouped_result[grouped_result["TotalAmount"] > 500000]
+ # print(grouped_result)
+ # 閬嶅巻鍐呭
+ if code:
+ grouped_result.to_csv(os.path.join(dir_path, f"big_buy_{code}.csv"), index=False)
+ else:
+ grouped_result.to_csv(os.path.join(dir_path, f"big_buy.csv"), index=False)
+ print("淇濆瓨鎴愬姛")
+
+
+def extract_big_order_codes(dir_path):
+ """
+ 瀵煎嚭澶у崟浠ｇ爜
+ @param dir_path: 鏁版嵁鐩綍
@param code:
@return:
"""
@@ -208,12 +259,6 @@
@return:
"""
return pd.Series({
- 'TotalAmount': group['TotalAmount'].sum(),
- 'TotalVolume': group['TotalVolume'].sum(),
- 'StartTime': group['StartTime'].iloc[0],
- 'StartPrice': group['StartPrice'].iloc[0],
- 'EndTime': group['EndTime'].iloc[-1],
- 'EndPrice': group['EndPrice'].iloc[-1]
})
combined_path = os.path.join(dir_path, 'combined.csv')
@@ -222,21 +267,18 @@
return
df = pd.read_csv(combined_path)
df_copy = df.copy()
- df_copy = df_copy[df_copy["SecurityID"] == int(code)]
if df_copy.empty:
print("鐩爣浠ｇ爜瀵瑰簲鎴愪氦鏁版嵁涓虹┖")
return
df_copy["SecurityID"] = df_copy["SecurityID"].apply(BigOrderDealParser.code_format)
# 鎸塖ecurityID鍜孊uyNo鍒嗙粍
- grouped = df_copy.groupby(['SecurityID', 'BuyNo'])
- grouped_result = grouped.apply(first_last)
- grouped_result = grouped_result[grouped_result["TotalAmount"] > 500000]
- grouped_result.to_csv(os.path.join(dir_path, f"{code}.csv"))
- print("淇濆瓨鎴愬姛")
+ grouped = df_copy.groupby(['SecurityID'])
+ return set(grouped.groups.keys())
if __name__ == "__main__":
# pre_process_transactions("E:/娴嬭瘯鏁版嵁/Transaction_Test.csv")
# pre_process_ngtsticks("E:/娴嬭瘯鏁版嵁/NGTSTick_Test.csv")
# concat_pre_transactions("E:/娴嬭瘯鏁版嵁/Transaction_Test")
- extract_big_order_of_code("E:/娴嬭瘯鏁版嵁/Transaction_Test", "000017")
+ # extract_big_order_codes("E:/娴嬭瘯鏁版嵁/Transaction_Test")
+ extract_big_order_of_code("E:/娴嬭瘯鏁版嵁/Transaction_Test")
--
Gitblit v1.8.0