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12月28日 14:18
# 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 = 1
    # 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 = [1 / stock_count] * stock_count  #T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])#[1 / stock_count] * stock_count 
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.7
    context.options['hold_days'] = 2

# 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')]
    today = 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()}
#     print(today,"cash_avg=",cash_avg,"context.portfolio.cash=",context.portfolio.cash,"cash_for_buy=",cash_for_buy,"cash_for_sell=",cash_for_sell)
    # 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


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2019-01-01',
    'm1.end_date': '2021-12-31',
    'm1.market': 'CN_STOCK_A',
    'm1.instrument_list': '',
    'm1.max_count': 0,

    'm2': 'M.advanced_auto_labeler.v2',
    'm2.instruments': T.Graph.OutputPort('m1.data'),
    'm2.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)
""",
    'm2.start_date': '',
    'm2.end_date': '',
    'm2.benchmark': '000300.HIX',
    'm2.drop_na_label': True,
    'm2.cast_label_int': True,

    'm3': 'M.input_features.v1',
    'm3.features': """std(close_0, 5)
std(low_0, 5)
std(turn_0, 5)
std(return_0, 5)
return_5
avg_turn_5
avg_amount_0/avg_amount_5
rank_avg_amount_0/rank_avg_amount_5
rank_return_0
rank_return_5
rank_return_0/rank_return_5
pe_ttm_0
rank_fs_roe_0
mf_net_amount_5""",

    'm15': 'M.general_feature_extractor.v7',
    'm15.instruments': T.Graph.OutputPort('m1.data'),
    'm15.features': T.Graph.OutputPort('m3.data'),
    'm15.start_date': '',
    'm15.end_date': '',
    'm15.before_start_days': 90,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m15.data'),
    'm16.features': T.Graph.OutputPort('m3.data'),
    'm16.date_col': 'date',
    'm16.instrument_col': 'instrument',
    'm16.drop_na': False,
    'm16.remove_extra_columns': False,

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m2.data'),
    'm7.data2': T.Graph.OutputPort('m16.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm13': 'M.dropnan.v1',
    'm13.input_data': T.Graph.OutputPort('m7.data'),

    'm4': 'M.chinaa_stock_filter.v1',
    'm4.input_data': T.Graph.OutputPort('m13.data'),
    'm4.index_constituent_cond': ['全部'],
    'm4.board_cond': ['上证主板', '深证主板', '创业板'],
    'm4.industry_cond': ['全部'],
    'm4.st_cond': ['全部'],
    'm4.delist_cond': ['非退市'],
    'm4.output_left_data': False,

    'm6': 'M.stock_ranker_train.v6',
    'm6.training_ds': T.Graph.OutputPort('m4.data'),
    'm6.features': T.Graph.OutputPort('m3.data'),
    'm6.learning_algorithm': '排序',
    'm6.number_of_leaves': 30,
    'm6.minimum_docs_per_leaf': 1000,
    'm6.number_of_trees': 20,
    'm6.learning_rate': 0.1,
    'm6.max_bins': 1023,
    'm6.feature_fraction': 1,
    'm6.data_row_fraction': 1,
    'm6.plot_charts': True,
    'm6.ndcg_discount_base': 1,
    'm6.m_lazy_run': False,

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2022-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2022-08-26'),
    'm9.market': 'CN_STOCK_A',
    'm9.instrument_list': '',
    'm9.max_count': 0,

    'm17': 'M.general_feature_extractor.v7',
    'm17.instruments': T.Graph.OutputPort('m9.data'),
    'm17.features': T.Graph.OutputPort('m3.data'),
    'm17.start_date': '',
    'm17.end_date': '',
    'm17.before_start_days': 90,

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m17.data'),
    'm18.features': T.Graph.OutputPort('m3.data'),
    'm18.date_col': 'date',
    'm18.instrument_col': 'instrument',
    'm18.drop_na': False,
    'm18.remove_extra_columns': False,

    'm14': 'M.dropnan.v1',
    'm14.input_data': T.Graph.OutputPort('m18.data'),

    'm5': 'M.chinaa_stock_filter.v1',
    'm5.input_data': T.Graph.OutputPort('m14.data'),
    'm5.index_constituent_cond': ['全部'],
    'm5.board_cond': ['上证主板', '深证主板', '创业板'],
    'm5.industry_cond': ['全部'],
    'm5.st_cond': ['正常'],
    'm5.delist_cond': ['非退市'],
    'm5.output_left_data': False,

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m6.model'),
    'm8.data': T.Graph.OutputPort('m5.data'),
    'm8.m_lazy_run': False,

    'm19': 'M.trade.v4',
    'm19.instruments': T.Graph.OutputPort('m9.data'),
    'm19.options_data': T.Graph.OutputPort('m8.predictions'),
    'm19.start_date': '',
    'm19.end_date': '',
    'm19.initialize': m19_initialize_bigquant_run,
    'm19.handle_data': m19_handle_data_bigquant_run,
    'm19.prepare': m19_prepare_bigquant_run,
    'm19.volume_limit': 0.025,
    'm19.order_price_field_buy': 'open',
    'm19.order_price_field_sell': 'close',
    'm19.capital_base': 1000000,
    'm19.auto_cancel_non_tradable_orders': True,
    'm19.data_frequency': 'daily',
    'm19.price_type': '真实价格',
    'm19.product_type': '股票',
    'm19.plot_charts': True,
    'm19.backtest_only': False,
    'm19.benchmark': '000300.HIX',
})

# g.run({})


def m10_run_bigquant_run(bq_graph, inputs):
     
    test_years = ['2014','2015','2016','2017','2018','2019','2020','2021','2022']
    parameters_list = []
     
    for i in test_years:
        train_start_date =  str(int(i) -3)+'-01'+'-01'
        train_end_date =  str(int(i) - 1)+'-12'+'-31'
        test_start_date = i+'-01'+'-01'
        if i == test_years[-1]:
            test_end_date = i+'-11'+'-26'
        else:
            test_end_date  =  i+'-12'+'-31'
        
        parameters = {'m1.start_date':train_start_date,
                      'm1.end_date':train_end_date,
                      'm9.start_date':test_start_date,
                      'm9.end_date':test_end_date,
                     }
        
        parameters_list.append({'parameters': parameters})
    print(len(parameters_list), parameters_list)

    def run(parameters):
        try:
            print(parameters)
            return g.run(parameters)
        except Exception as e:
            print('ERROR --------', e)
            return None
        
    results = T.parallel_map(run, parameters_list, max_workers=4, remote_run=True, silent=True, backend="threading")

    return results


m10 = M.hyper_run.v1(
    run=m10_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2022-12-27 21:37:31.182075] WARNING: AI: 当前可运行1个高级AI任务，购买资源获取更多高级AI任务位[url="https://bigquant.com/account/big_member/?from=navigation" style="display: inline-block;padding: 5px 7px;border-radius: 2px;background: #F0BC41;color: white"]购买高级AI任务位[/url]

[2022-12-27 21:37:31.189779] INFO: AI: 开始并行运算, remote_run=True, workers=1 ..

[2022-12-27 21:37:31.192141] INFO: AI: [ParallelEx(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.

[2022-12-27 21:37:33.503874] INFO: cached.v2.9e0b6dc4: 任务状态: Pending

[2022-12-27 21:37:43.537140] INFO: cached.v2.9e0b6dc4: 任务状态: Running

[2022-12-27 21:38:03.600205] INFO: cached.v2.9e0b6dc4: 任务状态: Succeeded

[2022-12-27 21:38:03.663949] INFO: AI: [ParallelEx(n_jobs=1)]: Done   1 out of   1 | elapsed:   32.5s remaining:    0.0s

[2022-12-27 21:38:03.851725] INFO: cached.v2.b02308aa: 任务状态: Pending

[2022-12-27 21:38:13.884666] INFO: cached.v2.b02308aa: 任务状态: Running

[2022-12-27 21:38:33.950496] INFO: cached.v2.b02308aa: 任务状态: Succeeded

[2022-12-27 21:38:33.957603] INFO: AI: [ParallelEx(n_jobs=1)]: Done   2 out of   2 | elapsed:  1.0min remaining:    0.0s

[2022-12-27 21:38:34.145700] INFO: cached.v2.c230fa0c: 任务状态: Pending

[2022-12-27 21:38:44.186442] INFO: cached.v2.c230fa0c: 任务状态: Running

[2022-12-27 21:39:04.257319] INFO: cached.v2.c230fa0c: 任务状态: Succeeded

[2022-12-27 21:39:04.267804] INFO: AI: [ParallelEx(n_jobs=1)]: Done   3 out of   3 | elapsed:  1.6min remaining:    0.0s

[2022-12-27 21:39:04.453909] INFO: cached.v2.d440210a: 任务状态: Pending

[2022-12-27 21:39:14.503836] INFO: cached.v2.d440210a: 任务状态: Running

[2022-12-27 21:39:24.536917] INFO: cached.v2.d440210a: 任务状态: Succeeded

[2022-12-27 21:39:24.543266] INFO: AI: [ParallelEx(n_jobs=1)]: Done   4 out of   4 | elapsed:  1.9min remaining:    0.0s

[2022-12-27 21:39:24.734277] INFO: cached.v2.e0551b6c: 任务状态: Pending

[2022-12-27 21:39:34.765955] INFO: cached.v2.e0551b6c: 任务状态: Running

[2022-12-27 21:40:04.860665] INFO: cached.v2.e0551b6c: 任务状态: Succeeded

[2022-12-27 21:40:04.867064] INFO: AI: [ParallelEx(n_jobs=1)]: Done   5 out of   5 | elapsed:  2.6min remaining:    0.0s

[2022-12-27 21:40:05.068889] INFO: cached.v2.f85f38a0: 任务状态: Pending

[2022-12-27 21:40:15.101259] INFO: cached.v2.f85f38a0: 任务状态: Running

[2022-12-27 21:50:27.077831] INFO: cached.v2.f85f38a0: 任务状态: Succeeded

[2022-12-27 21:50:27.084665] INFO: AI: [ParallelEx(n_jobs=1)]: Done   6 out of   6 | elapsed: 12.9min remaining:    0.0s

[2022-12-27 21:50:27.262005] INFO: cached.v2.6b3c501e: 任务状态: Pending

[2022-12-27 21:50:37.290740] INFO: cached.v2.6b3c501e: 任务状态: Running

[2022-12-27 22:03:09.797537] INFO: cached.v2.6b3c501e: 任务状态: Succeeded

[2022-12-27 22:03:09.807681] INFO: AI: [ParallelEx(n_jobs=1)]: Done   7 out of   7 | elapsed: 25.6min remaining:    0.0s

[2022-12-27 22:03:09.979873] INFO: cached.v2.31dc1442: 任务状态: Pending

[2022-12-27 22:03:20.014143] INFO: cached.v2.31dc1442: 任务状态: Running

[2022-12-27 22:16:22.720007] INFO: cached.v2.31dc1442: 任务状态: Succeeded

[2022-12-27 22:16:22.726556] INFO: AI: [ParallelEx(n_jobs=1)]: Done   8 out of   8 | elapsed: 38.9min remaining:    0.0s

[2022-12-27 22:16:22.973484] INFO: cached.v2.0a7a7658: 任务状态: Pending

[2022-12-27 22:16:33.006507] INFO: cached.v2.0a7a7658: 任务状态: Running

[2022-12-27 22:29:45.513875] INFO: cached.v2.0a7a7658: 任务状态: Succeeded

[2022-12-27 22:29:45.520255] INFO: AI: [ParallelEx(n_jobs=1)]: Done   9 out of   9 | elapsed: 52.2min remaining:    0.0s

[2022-12-27 22:29:45.522360] INFO: AI: [ParallelEx(n_jobs=1)]: Done   9 out of   9 | elapsed: 52.2min finished

[2022-12-27 22:29:45.524292] INFO: moduleinvoker: hyper_run.v1 运行完成[3134.365917s].

9 [{'parameters': {'m1.start_date': '2011-01-01', 'm1.end_date': '2013-12-31', 'm9.start_date': '2014-01-01', 'm9.end_date': '2014-12-31'}}, {'parameters': {'m1.start_date': '2012-01-01', 'm1.end_date': '2014-12-31', 'm9.start_date': '2015-01-01', 'm9.end_date': '2015-12-31'}}, {'parameters': {'m1.start_date': '2013-01-01', 'm1.end_date': '2015-12-31', 'm9.start_date': '2016-01-01', 'm9.end_date': '2016-12-31'}}, {'parameters': {'m1.start_date': '2014-01-01', 'm1.end_date': '2016-12-31', 'm9.start_date': '2017-01-01', 'm9.end_date': '2017-12-31'}}, {'parameters': {'m1.start_date': '2015-01-01', 'm1.end_date': '2017-12-31', 'm9.start_date': '2018-01-01', 'm9.end_date': '2018-12-31'}}, {'parameters': {'m1.start_date': '2016-01-01', 'm1.end_date': '2018-12-31', 'm9.start_date': '2019-01-01', 'm9.end_date': '2019-12-31'}}, {'parameters': {'m1.start_date': '2017-01-01', 'm1.end_date': '2019-12-31', 'm9.start_date': '2020-01-01', 'm9.end_date': '2020-12-31'}}, {'parameters': {'m1.start_date': '2018-01-01', 'm1.end_date': '2020-12-31', 'm9.start_date': '2021-01-01', 'm9.end_date': '2021-12-31'}}, {'parameters': {'m1.start_date': '2019-01-01', 'm1.end_date': '2021-12-31', 'm9.start_date': '2022-01-01', 'm9.end_date': '2022-11-26'}}]

In [2]:

from datetime import datetime
print(datetime.now())
print(len(m10.result))
for i in range(len(m10.result)):
    try:
        print('==='*15, i)
        perf = m10.result[i]['m19'].raw_perf.read()
        T.render_perf(perf, buy_moment="buy", sell_moment="sell")
    except Exception as e:
        print(e)
        continue

2022-12-27 22:29:45.657812
9
============================================= 0
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 1
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 2
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 3
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 4
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 5
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 6
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 7
No module named 'biglearning.module2.modules.backtest.v7'
============================================= 8
No module named 'biglearning.module2.modules.backtest.v7'

In [3]:

df = pd.DataFrame() 
for i in range(len(m10.result)):
    tmp = m10.result[i]['m19'].raw_perf.read()
    df = df.append(tmp[['returns','benchmark_period_return']])
    
import empyrical
def get_stats(returns, benchmark_period_return):
    return_ratio  = empyrical.cum_returns_final(returns)
    annual_return_ratio  = empyrical.annual_return(returns)
    sharp_ratio = empyrical.sharpe_ratio(returns,0.035/252)
    return_volatility = empyrical.annual_volatility(returns)
    max_drawdown  = empyrical.max_drawdown(returns)
    benchmark_returns = (benchmark_period_return+1)/(benchmark_period_return+1).shift(1)-1
    alpha, beta =empyrical.alpha_beta_aligned(returns, benchmark_returns)
    
    return {
        'return_ratio': round(return_ratio,2),
        'annual_return_ratio': round(annual_return_ratio,2),
        'beta': round(beta,2),
        'alpha': round(alpha,2),
        'sharp_ratio': round(sharp_ratio,2),
        'return_volatility': round(return_volatility,2),
        'max_drawdown': round(max_drawdown,2),
        '收益回撤比': round(abs(annual_return_ratio / max_drawdown),2)
    }
d=get_stats(df['returns'], df['benchmark_period_return'])
df1=pd.DataFrame.from_dict(d,orient='index')
df1.T

Out[3]:

	return_ratio	annual_return_ratio	beta	alpha	sharp_ratio	return_volatility	max_drawdown	收益回撤比
0	68.44	0.64	0.44	0.75	1.38	0.39	-0.61	1.04

In [4]:

T.plot((df['returns']+1).cumprod())