复制链接

克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2022年6月18日 11:47
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# 回测引擎：初始化函数，只执行一次
def m19_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()

    # 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
    context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
    # 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
    stock_count = 5
    # 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]
    context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.2
    context.options['hold_days'] = 5

# 回测引擎：每日数据处理函数，每天执行一次
def m19_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]

    # 1. 资金分配
    # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金
    # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）
    is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
    cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
    cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.portfolio.positions.items()}

    # 2. 生成卖出订单：hold_days天之后才开始卖出；对持仓的股票，按机器学习算法预测的排序末位淘汰
    if not is_staging and cash_for_sell > 0:
        equities = {e.symbol: e for e, p in context.portfolio.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities)])))

        for instrument in instruments:
            context.order_target(context.symbol(instrument), 0)
            cash_for_sell -= positions[instrument]
            if cash_for_sell <= 0:
                break

    # 3. 生成买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票
    buy_cash_weights = context.stock_weights
    buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    for i, instrument in enumerate(buy_instruments):
        cash = cash_for_buy * buy_cash_weights[i]
        if cash > max_cash_per_instrument - positions.get(instrument, 0):
            # 确保股票持仓量不会超过每次股票最大的占用资金量
            cash = max_cash_per_instrument - positions.get(instrument, 0)
        if cash > 0:
            context.order_value(context.symbol(instrument), cash)

# 回测引擎：准备数据，只执行一次
def m19_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2018-01-01',
    end_date='2020-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -5) / shift(open, -1)

# 极值处理：用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))

# 将分数映射到分类，这里使用20个分类
all_wbins(label, 20)

# 过滤掉一字涨停的情况 (设置label为NaN，在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
    start_date='',
    end_date='',
    benchmark='000300.HIX',
    drop_na_label=True,
    cast_label_int=True
)

m3 = M.input_features.v1(
    features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
return_5
return_10
return_20
avg_amount_0/avg_amount_5
avg_amount_5/avg_amount_20
rank_avg_amount_0/rank_avg_amount_5
rank_avg_amount_5/rank_avg_amount_10
rank_return_0
rank_return_5
rank_return_10
rank_return_0/rank_return_5
rank_return_5/rank_return_10
pe_ttm_0
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m13 = M.dropnan.v1(
    input_data=m7.data
)

m6 = M.stock_ranker_train.v6(
    training_ds=m13.data,
    features=m3.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    data_row_fraction=1,
    plot_charts=True,
    ndcg_discount_base=1,
    m_lazy_run=False
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-01-01'),
    end_date=T.live_run_param('trading_date', '2021-12-31'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m14 = M.dropnan.v1(
    input_data=m18.data
)

m8 = M.stock_ranker_predict.v5(
    model=m6.model,
    data=m14.data,
    m_lazy_run=False
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m8.predictions,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2022-06-18 11:10:27.705041] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-06-18 11:10:27.734789] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:27.743733] INFO: moduleinvoker: instruments.v2 运行完成[0.038693s].

[2022-06-18 11:10:27.760062] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-06-18 11:10:27.771580] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:27.971279] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.211206s].

[2022-06-18 11:10:27.980752] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-06-18 11:10:27.988398] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:27.991515] INFO: moduleinvoker: input_features.v1 运行完成[0.010771s].

[2022-06-18 11:10:28.026301] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-06-18 11:10:28.037943] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.040393] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.014133s].

[2022-06-18 11:10:28.062011] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-06-18 11:10:28.068115] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.070133] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.00812s].

[2022-06-18 11:10:28.090532] INFO: moduleinvoker: join.v3 开始运行..

[2022-06-18 11:10:28.114971] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.119135] INFO: moduleinvoker: join.v3 运行完成[0.028562s].

[2022-06-18 11:10:28.154425] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-06-18 11:10:28.164571] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.166940] INFO: moduleinvoker: dropnan.v1 运行完成[0.012534s].

[2022-06-18 11:10:28.184710] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-06-18 11:10:28.195909] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.469520] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.284805s].

[2022-06-18 11:10:28.479438] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-06-18 11:10:28.486993] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.489649] INFO: moduleinvoker: instruments.v2 运行完成[0.010214s].

[2022-06-18 11:10:28.503916] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-06-18 11:10:28.514069] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.517864] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.014021s].

[2022-06-18 11:10:28.531928] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-06-18 11:10:28.542520] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.545783] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.013876s].

[2022-06-18 11:10:28.559728] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-06-18 11:10:28.570909] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.572841] INFO: moduleinvoker: dropnan.v1 运行完成[0.013087s].

[2022-06-18 11:10:28.588560] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-06-18 11:10:28.600249] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:28.602805] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.01425s].

[2022-06-18 11:10:34.100505] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-06-18 11:10:34.115005] INFO: moduleinvoker: 命中缓存

[2022-06-18 11:10:35.777054] INFO: moduleinvoker: backtest.v8 运行完成[1.676551s].

[2022-06-18 11:10:35.780133] INFO: moduleinvoker: trade.v4 运行完成[7.167482s].

设置评估测试数据集，查看训练曲线
[视频教程]StockRanker训练曲线

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-9b65806197c645a3bcc1eeb268f633e5"}/bigcharts-data-end

收益率67.67%
年化收益率70.91%
基准收益率-6.21%
阿尔法0.78
贝塔0.42
夏普比率1.99
胜率0.53
盈亏比1.42
收益波动率27.29%
信息比率0.14
最大回撤15.12%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-85aba33bf3b441be8066f4819e72ed8f"}/bigcharts-data-end

'date'：交易日期

'trading_days'：交易日序列

'portfolio_value'：期末总资产

'starting_value'：期初持仓市值

'ending_value'：期末持仓市值

'starting_cash'：期初可用资金

'ending_cash'：期末可用资金

'returns'：收益率

'algorithm_period_return'：策略收益

'benchmark_period_return'：基准收益

'realized_pnl'：平仓盈亏

'pnl'：累计盈亏

'long_value'：多头市值

'short_value'：空头市值

'long_margin'：多头保证金

'short_margin'：空头保证金

'cancel_times'：撤单次数

'trade_times'：交易次数

'profit_count'：盈利次数

'loss_count'：亏损次数

'win_percent'：胜率

'pnl_ratio'：盈亏比

'longs_count'：多头开仓次数（累计）

'shorts_count'：空头开仓次数（累计）

'net_leverage'：净杠杆率

'gross_leverage'：总杠杆率

'max_leverage'：最大杠杆率

'capital_used'：资金使用金额

'today_buy_balance'：买入总金额

'today_sell_balance'：卖出总金额

'commission'：手续费

'capital_changed'：总资金变化率

'orders'：计划单信息

'transactions'：出入金信息

'positions'：持仓信息

In [6]:

result = m19
print(result)

{'version': 'v3', '__end_date': '2021-12-31', '__start_date': '2021-01-01', 'benchmark': '000300.HIX', 'capital_base': 1000000, 'context_outputs': {'version': 'v3'}, 'data_frequency': 'daily', 'data_panel': DataSource(9326777b939742229bdadd4e3c32eddeT), 'end_date': '2021-12-31', 'market': 'CN_Stock', 'order_price_field_buy': 'open', 'order_price_field_sell': 'close', 'perf_raw_object': 0, 'plot_charts': True, 'price_type': 'real', 'product_type': 'stock', 'raw_perf': DataSource(f1450703462a4b87a4a660a84e93f622T), 'start_date': '2021-01-01', 'volume_limit': 0.025, 'display': <bound method display of {...}>, 'read_raw_perf': <bound method read_raw_perf of {...}>, 'read_data_panel': <bound method read_data_panel of {...}>}

In [13]:

df = result.raw_perf.read()
df.head()

Out[13]:

	ending_value	ending_exposure	capital_used	starting_value	starting_exposure	starting_cash	ending_cash	portfolio_value	pnl	returns	...	sharpe	sortino	information	max_drawdown	max_leverage	period_label
2021-01-04 15:00:00+00:00	0.000000	0.000000	0.000000	0.000000	0.000000	1000000.000000	1000000.000000	1000000.000000	0.000000	0.000000	...	0.000000	0.000000	0.000000	0.000000	0.000000	2021-01
2021-01-05 15:00:00+00:00	196144.996548	196144.996548	-198881.940114	0.000000	0.000000	1000000.000000	801118.059886	997263.056434	-2736.943566	-0.002737	...	-12.187132	-11.224972	-0.707107	-0.002737	0.196683	2021-01
2021-01-06 15:00:00+00:00	386116.995144	386116.995144	-196493.203048	196144.996548	196144.996548	801118.059886	604624.856838	990741.851982	-6521.204452	-0.006539	...	-15.513587	-11.993098	-1.110592	-0.009258	0.389725	2021-01
2021-01-07 15:00:00+00:00	556533.996820	556533.996820	-193586.070472	386116.995144	386116.995144	604624.856838	411038.786366	967572.783187	-23169.068795	-0.023386	...	-12.528136	-10.608926	-1.156958	-0.032427	0.575186	2021-01
2021-01-08 15:00:00+00:00	759730.015349	759730.015349	-191312.395440	556533.996820	556533.996820	411038.786366	219726.390927	979456.406276	11883.623089	0.012282	...	-5.162949	-5.920755	-0.584877	-0.032427	0.775665	2021-01

5 rows × 45 columns

In [14]:

df.columns

Out[14]:

Index(['ending_value', 'ending_exposure', 'capital_used', 'starting_value',
       'starting_exposure', 'starting_cash', 'ending_cash', 'portfolio_value',
       'pnl', 'returns', 'period_open', 'period_close', 'gross_leverage',
       'net_leverage', 'short_exposure', 'long_exposure', 'short_value',
       'long_value', 'longs_count', 'shorts_count', 'need_settle', 'positions',
       'transactions', 'orders', 'LOG', 'TRA_FAC', 'POS_FAC', 'trading_days',
       'benchmark_volatility', 'algo_volatility', 'treasury_period_return',
       'algorithm_period_return', 'benchmark_period_return', 'beta', 'alpha',
       'sharpe', 'sortino', 'information', 'excess_return', 'max_drawdown',
       'max_leverage', 'period_label', 'trade_times', 'win_percent',
       'pnl_ratio'],
      dtype='object')

In [45]:

# 交易情况分析
from collections import defaultdict

stock_earn = defaultdict(float)
hold_stock = defaultdict(float)
for i in range(df.shape[0]):
    row = df.iloc[i]
    transactions = row["transactions"]
    
    for trans in transactions:
        mony = trans["transaction_money"]
        stock_name = trans["name"]
        
        if mony > 0:
            # 买入
            hold_stock[stock_name] = mony
        if mony < 0:
            # 卖出
            stock_earn[stock_name] += (mony + hold_stock[stock_name])
            del hold_stock[stock_name]

earn_df = pd.DataFrame([{"stock": k, "盈利": stock_earn[k]} for k in stock_earn])
earn_df.sort_values("盈利", ascending=False).reset_index(drop=True)

Out[45]:

	stock	盈利
0	ST凯乐	18196.295109
1	盈康生命	13782.998961
2	诚迈科技	11244.999098
3	德固特	11076.008782
4	*ST西发	10881.024411
...	...	...
666	开立医疗	-277795.799589
667	青松股份	-279985.649575
668	惠发食品	-297468.210339
669	理工光科	-312136.596929
670	东方银星	-466227.782601

671 rows × 2 columns

In [18]:

# 盈利最大的一天
df[df['returns'] == df['returns'].max()]

Out[18]:

	ending_value	ending_exposure	capital_used	starting_value	starting_exposure	starting_cash	ending_cash	portfolio_value	pnl	returns	...	sharpe	sortino	information	excess_return	max_drawdown	max_leverage	period_label	trade_times	win_percent	pnl_ratio
2021-01-15 15:00:00+00:00	744368.029976	744368.029976	30542.166358	706276.010084	706276.010084	201030.750571	231572.91693	975940.946905	68634.18625	0.075646	...	-1.063603	-1.794277	-0.155295	0	-0.093563	0.973955	2021-01	21	0.285714	-0.156068

1 rows × 45 columns

In [19]:

# 盈利最小的一天
df[df['returns'] == df['returns'].min()]

Out[19]:

	ending_value	ending_exposure	capital_used	starting_value	starting_exposure	starting_cash	ending_cash	portfolio_value	pnl	returns	...	sharpe	sortino	information	excess_return	max_drawdown	max_leverage	period_label	trade_times	win_percent	pnl_ratio
2021-03-15 15:00:00+00:00	605761.011004	605761.011004	79003.310303	730436.004066	730436.004066	290264.251353	369267.561656	975028.57266	-45671.682759	-0.044745	...	-0.319028	-0.353973	0.020106	0	-0.151221	0.973955	2021-03	157	0.452229	-1.260746

1 rows × 45 columns

In [ ]: