126 lines
4.3 KiB
Python
126 lines
4.3 KiB
Python
"""
|
|
Script Name:
|
|
Description: 根据yahoo提供的不复权数据，和分红及拆股数据，来计算前复权和后复权数据。
|
|
注意：
|
|
结果对不上！
|
|
按照yahoo规则，不复权数据已经处理了拆股，所以只要把分红加上去就行，但处理结果与它返回的前复权数据，仍然对不对上！
|
|
有些比如AAPL，差不多可以对得上；但对于KDP等，差异甚大，找不到原因。。
|
|
所以，这个程序暂时无法使用。。。
|
|
|
|
Author: [Your Name]
|
|
Created Date: YYYY-MM-DD
|
|
Last Modified: YYYY-MM-DD
|
|
Version: 1.0
|
|
|
|
Modification History:
|
|
- YYYY-MM-DD [Your Name]:
|
|
- YYYY-MM-DD [Your Name]:
|
|
- YYYY-MM-DD [Your Name]:
|
|
"""
|
|
|
|
|
|
import pymysql
|
|
import pandas as pd
|
|
import logging
|
|
import os
|
|
import time
|
|
import config
|
|
|
|
# 设置日志
|
|
filename = os.path.splitext(os.path.basename(__file__))[0]
|
|
config.setup_logging(f"./log/{filename}.log")
|
|
logger = logging.getLogger()
|
|
|
|
# 数据库连接函数
|
|
def connect_to_db():
|
|
return pymysql.connect(**config.db_config)
|
|
|
|
# 读取 sp500 表中的所有行，获取 code 和 name
|
|
def fetch_sp500_codes(connection):
|
|
query = "SELECT code, code_name as name FROM sp500 "
|
|
return pd.read_sql(query, connection)
|
|
|
|
# 读取 sp500_his_kline_none 表中的数据并按 time_key 降序排列
|
|
def fetch_sp500_his_kline_none(connection, code):
|
|
query = f"SELECT * FROM sp500_his_kline_none WHERE code = '{code}' ORDER BY time_key DESC"
|
|
return pd.read_sql(query, connection)
|
|
|
|
# 将计算结果插入到 sp500_ajust_kline_202410 表中
|
|
def insert_adjusted_kline_data(connection, data):
|
|
try:
|
|
with connection.cursor() as cursor:
|
|
insert_query = """
|
|
INSERT INTO sp500_ajust_kline_202410 (code, name, time_key, hfq_open, hfq_close, qfq_open, qfq_close, none_open, none_close)
|
|
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
|
|
ON DUPLICATE KEY UPDATE
|
|
hfq_open = VALUES(hfq_open),
|
|
hfq_close = VALUES(hfq_close),
|
|
qfq_open = VALUES(qfq_open),
|
|
qfq_close = VALUES(qfq_close),
|
|
none_open = VALUES(none_open),
|
|
none_close = VALUES(none_close)
|
|
"""
|
|
cursor.executemany(insert_query, data)
|
|
connection.commit()
|
|
except Exception as e:
|
|
logger.error(f"Error inserting data: {e}")
|
|
|
|
# 计算前复权和后复权的价格，并插入到 sp500_ajust_kline_202410
|
|
def process_and_insert_adjusted_kline(connection, code, name, result_none):
|
|
dividends_qfq = 0
|
|
dividends_hfq = 0
|
|
dividends_total = result_none['dividends'].sum()
|
|
|
|
adjusted_data = []
|
|
|
|
for index, row in result_none.iterrows():
|
|
# 计算前复权和后复权的开盘价和收盘价
|
|
qfq_close = row['close'] - dividends_qfq
|
|
qfq_open = row['open'] - dividends_qfq
|
|
hfq_close = row['close'] + dividends_hfq
|
|
hfq_open = row['open'] + dividends_hfq
|
|
|
|
adjusted_data.append((
|
|
row['code'], row['name'], row['time_key'],
|
|
hfq_open, hfq_close, qfq_open, qfq_close,
|
|
row['open'], row['close']
|
|
))
|
|
|
|
dividends_qfq += row['dividends']
|
|
dividends_hfq = dividends_total - dividends_qfq
|
|
|
|
# 插入到 sp500_ajust_kline_202410 表中
|
|
insert_adjusted_kline_data(connection, adjusted_data)
|
|
logger.info(f"Successfully processed and inserted data for code {code}")
|
|
|
|
# 主函数
|
|
def main():
|
|
try:
|
|
connection = connect_to_db()
|
|
|
|
# 读取 sp500 表中的所有行，得到 code 和 name 字段
|
|
sp500_codes = fetch_sp500_codes(connection)
|
|
|
|
for index, row in sp500_codes.iterrows():
|
|
code = row['code']
|
|
name = row['name']
|
|
logger.info(f"Processing data for code: {code}, name: {name}")
|
|
|
|
# 读取 sp500_his_kline_none 表中的数据并按 time_key 降序排列
|
|
result_none = fetch_sp500_his_kline_none(connection, code)
|
|
|
|
if result_none.empty:
|
|
logger.warning(f"No data found for code: {code}")
|
|
continue
|
|
|
|
# 处理并插入调整后的 K 线数据
|
|
process_and_insert_adjusted_kline(connection, code, name, result_none)
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error occurred: {e}")
|
|
finally:
|
|
if connection:
|
|
connection.close()
|
|
|
|
if __name__ == "__main__":
|
|
main() |