146 lines
5.4 KiB
Python
146 lines
5.4 KiB
Python
|
||
import pandas as pd
|
||
import pymysql
|
||
import backtrader as bt
|
||
import config
|
||
|
||
# 从 MySQL 提取数据
|
||
def fetch_data_from_mysql():
|
||
connection = pymysql.connect(**config.db_config)
|
||
# ['datetime', 'open', 'high', 'low', 'close', 'volume', 'openinterest']]
|
||
#query = "SELECT code, time_key, qfq_close as close FROM hs300_ajust_kline_202410 where time_key>='2023-01-01 00:00:00' "
|
||
query = "SELECT code, time_key, open, high, low, close, volume FROM hs300_his_kline_none where time_key>='2023-01-01 00:00:00' "
|
||
data = pd.read_sql(query, connection)
|
||
data['time_key'] = pd.to_datetime(data['time_key'], errors='coerce') # 确保为datetime格式
|
||
data['openinterest'] = 0 # 添加 openinterest 列并赋值为 0
|
||
connection.close()
|
||
return data
|
||
|
||
# 格式化数据为Backtrader兼容的格式
|
||
data = fetch_data_from_mysql()
|
||
data_by_code = {code: df for code, df in data.groupby('code')}
|
||
|
||
|
||
class BestPortfolioStrategy(bt.Strategy):
|
||
params = dict(
|
||
max_stocks=30,
|
||
rebalance_monthly=True,
|
||
commission=0.0003,
|
||
slippage=0.005,
|
||
maperiod = 15,
|
||
printlog = False
|
||
)
|
||
def __init__(self):
|
||
self.stocks = [] # 持有的股票
|
||
self.rebalance_date = None
|
||
|
||
def next(self):
|
||
# 判断是否是月初
|
||
if self.rebalance_date and self.data.datetime.date(0) < self.rebalance_date.date():
|
||
return
|
||
|
||
print(f"rebalance date: {self.rebalance_date}")
|
||
# 设置下次调仓日
|
||
self.rebalance_date = self.data.datetime.date(0).replace(day=1) + pd.DateOffset(months=1)
|
||
|
||
# 选股逻辑：计算过去一段时间的收益率，选取最高的30只股票
|
||
returns = {}
|
||
for data in self.datas:
|
||
returns[data._name] = (data.close[0] / data.close[-20]) - 1 # 上个月的收益率
|
||
|
||
# 按收益率排序并选择最佳组合
|
||
sorted_stocks = sorted(returns, key=returns.get, reverse=True)[:self.params.max_stocks]
|
||
print(sorted_stocks)
|
||
|
||
# 调仓：卖出非选中股票，买入新选股票
|
||
self.rebalance(sorted_stocks)
|
||
|
||
def rebalance(self, selected_stocks):
|
||
for stock in self.stocks:
|
||
if stock not in selected_stocks:
|
||
self.close(self.getdatabyname(stock))
|
||
|
||
for stock in selected_stocks:
|
||
if stock not in self.stocks:
|
||
self.buy(self.getdatabyname(stock), size=100)
|
||
|
||
self.stocks = selected_stocks
|
||
|
||
|
||
# 交易记录日志（可省略，默认不输出结果）
|
||
|
||
def log(self, txt, dt=None, doprint=False):
|
||
if self.params.printlog or doprint:
|
||
dt = dt or self.datas[0].datetime.date(0)
|
||
print(f'{dt.isoformat()},{txt}')
|
||
|
||
def notify_order(self, order):
|
||
# 未被处理的订单
|
||
if order.status in [order.Submitted, order.Accepted]:
|
||
return
|
||
# 已经处理的订单
|
||
if order.status in [order.Completed, order.Canceled, order.Margin]:
|
||
if order.isbuy():
|
||
self.log(
|
||
'BUY EXECUTED, ref:%.0f，Price: %.2f, Cost: %.2f, Comm %.2f, Size: %.2f, Stock: %s' %
|
||
(order.ref, # 订单编号
|
||
order.executed.price, # 成交价
|
||
order.executed.value, # 成交额
|
||
order.executed.comm, # 佣金
|
||
order.executed.size, # 成交量
|
||
order.data._name)) # 股票名称
|
||
else: # Sell
|
||
self.log('SELL EXECUTED, ref:%.0f, Price: %.2f, Cost: %.2f, Comm %.2f, Size: %.2f, Stock: %s' %
|
||
(order.ref,
|
||
order.executed.price,
|
||
order.executed.value,
|
||
order.executed.comm,
|
||
order.executed.size,
|
||
order.data._name))
|
||
|
||
|
||
cerebro = bt.Cerebro()
|
||
cerebro.broker.setcash(1_000_000) # 初始资金 100万
|
||
cerebro.broker.setcommission(commission=0.0003) # 设置交易费率 万分之三
|
||
cerebro.broker.set_slippage_perc(0.005) # 设置滑点 0.005
|
||
|
||
# 加载数据
|
||
for code, df in data_by_code.items():
|
||
# 删除缺失值
|
||
df = df.dropna(subset=['time_key'])
|
||
|
||
# 设置DataFrame为Backtrader的数据格式
|
||
data_feed = bt.feeds.PandasData(
|
||
dataname=df,
|
||
datetime='time_key',
|
||
openinterest=None # 如果没有openinterest列，则为None
|
||
)
|
||
#bt_data = bt.feeds.PandasData(dataname=df)
|
||
cerebro.adddata(data_feed, name=code)
|
||
|
||
|
||
cerebro.addanalyzer(bt.analyzers.TimeReturn, _name='pnl') # 返回收益率时序数据
|
||
cerebro.addanalyzer(bt.analyzers.AnnualReturn, _name='_AnnualReturn') # 年化收益率
|
||
cerebro.addanalyzer(bt.analyzers.SharpeRatio, _name='_SharpeRatio') # 夏普比率
|
||
cerebro.addanalyzer(bt.analyzers.DrawDown, _name='_DrawDown') # 回撤
|
||
|
||
# 加载策略
|
||
cerebro.addstrategy(BestPortfolioStrategy, printlog=True)
|
||
# 运行回测
|
||
results = cerebro.run()
|
||
|
||
|
||
# 获取分析结果
|
||
results = cerebro.run()
|
||
strat = results[0]
|
||
|
||
# 返回日度收益率序列
|
||
daily_return = pd.Series(strat.analyzers.pnl.get_analysis())
|
||
# 打印评价指标
|
||
print("--------------- AnnualReturn -----------------")
|
||
print(strat.analyzers._AnnualReturn.get_analysis())
|
||
print("--------------- SharpeRatio -----------------")
|
||
print(strat.analyzers._SharpeRatio.get_analysis())
|
||
print("--------------- DrawDown -----------------")
|
||
print(strat.analyzers._DrawDown.get_analysis())
|