排名做多和做空信号

在本文档中，你将学习如何对各股票代码的多头和空头信号进行排名。

[1]:

import pybroker
from pybroker import Strategy, YFinance

pybroker.enable_data_source_cache("ranking")

[1]:

<pybroker.cache._L1Cache at 0x7f5f881bb290>

多头信号

让我们从一个示例开始，说明如何在下买单时根据成交量对股票代码进行排名：

[2]:

def buy_highest_volume(ctx):
    # If there are no long positions across all tickers being traded:
    if not ctx.has_long_positions():
        ctx.buy_shares = ctx.calc_target_shares(1)
        ctx.long_score = ctx.volume[-1]
        ctx.hold_bars = 2

buy_highest_volume 函数分配 100% 的投资组合并持有 2 个 Bar。它将 ctx.long_score 设置为 ctx.volume[-1]，因此 PyBroker 会根据成交量对买入信号进行排名。

[3]:

strategy = Strategy(YFinance(), "6/1/2021", "6/1/2022")
strategy.add_execution(buy_highest_volume, ["T", "F", "GM", "PFE"])
strategy.set_max_long_positions(1)

要将同一时间可持有的多头仓位数量限制为 1，我们调用 set_max_long_positions。这实际上会买入成交量最高的股票代码。

[4]:

result = strategy.backtest()
result.trades

Backtesting: 2021-06-01 00:00:00 to 2022-06-01 00:00:00

Loading bar data...

[*********************100%***********************]  4 of 4 completed

Loaded bar data: 0:00:01

Test split: 2021-06-01 00:00:00 to 2022-05-31 00:00:00

100% (253 of 253) |######################| Elapsed Time: 0:00:00 Time:  0:00:00


Finished backtest: 0:00:01

[4]:

	type	symbol	entry_date	exit_date	entry	exit	shares	pnl	return_pct	agg_pnl	bars	pnl_per_bar	stop	mae	mfe
id
1	long	F	2021-06-02	2021-06-04	14.85	16.13	6734	8619.52	8.62	8619.52	2	4309.76	bar	-0.17	1.28
2	long	F	2021-06-07	2021-06-09	15.93	15.51	6801	-2856.42	-2.64	5763.10	2	-1428.21	bar	-0.60	0.27
3	long	F	2021-06-10	2021-06-14	15.43	15.06	6832	-2527.84	-2.40	3235.26	2	-1263.92	bar	-0.37	0.35
4	long	F	2021-06-15	2021-06-17	14.96	14.99	6900	207.00	0.20	3442.26	2	103.50	bar	-0.20	0.33
5	long	F	2021-06-18	2021-06-22	14.61	14.96	7003	2451.05	2.40	5893.31	2	1225.53	bar	-0.17	0.35
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
80	long	F	2022-05-10	2022-05-12	13.43	12.47	7258	-6967.68	-7.15	-9482.76	2	-3483.84	bar	-0.96	0.41
81	long	F	2022-05-13	2022-05-17	13.25	13.34	6831	614.79	0.68	-8867.97	2	307.40	bar	-0.38	0.38
82	long	F	2022-05-18	2022-05-20	13.03	12.59	6735	-2963.40	-3.38	-11831.37	2	-1481.70	bar	-0.44	0.33
83	long	F	2022-05-23	2022-05-25	12.72	12.57	6931	-1039.65	-1.18	-12871.02	2	-519.83	bar	-0.45	0.23
84	long	F	2022-05-26	2022-05-31	12.99	13.59	6707	4024.20	4.62	-8846.82	2	2012.10	bar	-0.20	0.64

84 rows × 15 columns

空头信号

PyBroker 还可以使用 short_score 对空头信号进行排名，空头订单会下给 short_score 值最高的股票代码。以下示例买入 5 日变化率（ROC）最高的股票代码，同时卖空 5 日 ROC 最负的股票代码：

[5]:

def long_high_short_low(ctx):
    # Wait for 6 bars of data and skip symbols with an open position:
    if ctx.bars < 6 or ctx.long_pos() or ctx.short_pos():
        return
    # Calculate the 5-day rate of change (ROC):
    roc = (ctx.close[-1] - ctx.close[-6]) / ctx.close[-6]
    if roc > 0 and not ctx.has_long_positions():
        ctx.buy_shares = ctx.calc_target_shares(0.5)
        # Hold the long position for 2 bars
        ctx.hold_bars = 2
        ctx.long_score = roc
    elif roc < 0 and not ctx.has_short_positions():
        ctx.sell_shares = ctx.calc_target_shares(0.5)
        # Hold the short position for 2 bars
        ctx.hold_bars = 2
        ctx.short_score = -roc


strategy = Strategy(YFinance(), "1/1/2025", "1/1/2026")
strategy.add_execution(long_high_short_low, ["T", "F", "GM", "PFE"])
strategy.set_max_long_positions(1)
strategy.set_max_short_positions(1)
result = strategy.backtest()
result.trades

Backtesting: 2025-01-01 00:00:00 to 2026-01-01 00:00:00

Loading bar data...

[*********************100%***********************]  4 of 4 completed

Loaded bar data: 0:00:00

Test split: 2025-01-02 00:00:00 to 2025-12-31 00:00:00

100% (250 of 250) |######################| Elapsed Time: 0:00:00 Time:  0:00:00


Finished backtest: 0:00:00

[5]:

	type	symbol	entry_date	exit_date	entry	exit	shares	pnl	return_pct	agg_pnl	bars	pnl_per_bar	stop	mae	mfe
id
1	long	PFE	2025-01-13	2025-01-15	26.59	26.43	1871	-299.36	-0.60	-299.36	2	-149.68	bar	-0.32	0.28
2	short	T	2025-01-13	2025-01-15	21.54	21.98	2305	-1014.20	-2.00	-1313.56	2	-507.10	bar	-0.44	0.16
3	long	F	2025-01-16	2025-01-21	9.98	10.34	4939	1778.04	3.61	464.48	2	889.02	bar	-0.09	0.36
4	short	PFE	2025-01-16	2025-01-21	26.26	26.51	1881	-470.25	-0.94	-5.77	2	-235.13	bar	-0.31	0.30
5	long	GM	2025-01-22	2025-01-24	52.94	54.15	927	1121.67	2.29	1115.90	2	560.84	bar	-0.51	1.41
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
142	short	PFE	2025-12-18	2025-12-22	25.10	25.26	1650	-264.00	-0.63	-17237.70	2	-132.00	bar	-0.42	0.12
143	long	GM	2025-12-19	2025-12-23	81.89	83.05	508	589.28	1.42	-16648.42	2	294.64	bar	-0.80	1.79
144	short	PFE	2025-12-23	2025-12-26	25.09	25.02	1652	115.64	0.28	-16532.78	2	57.82	bar	-0.25	0.26
145	long	T	2025-12-24	2025-12-29	24.54	24.81	1703	459.81	1.10	-16072.97	2	229.91	bar	-0.17	0.27
146	short	F	2025-12-29	2025-12-31	13.28	13.17	3142	345.62	0.84	-15727.35	2	172.81	bar	-0.03	0.11

146 rows × 15 columns

在下一篇文档中，我们将讨论如何在 PyBroker 中实现自定义指标。