克隆策略

In [ ]:

# 本代码由可视化策略环境自动生成 2021年10月31日 10:49
# 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。


# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m10_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    from sklearn.model_selection import train_test_split
    data = input_1.read()
    x_train, x_val, y_train, y_val = train_test_split(data["x"], data['y'])
    data_1 = DataSource.write_pickle({'x': x_train, 'y': y_train})
    data_2 = DataSource.write_pickle({'x': x_val, 'y': y_val})
    return Outputs(data_1=data_1, data_2=data_2, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m10_post_run_bigquant_run(outputs):
    return outputs

from tensorflow.keras.callbacks import EarlyStopping
m5_earlystop_bigquant_run=EarlyStopping(monitor='val_mse', min_delta=0.0001, patience=3)
# 用户的自定义层需要写到字典中，比如
# {
#   "MyLayer": MyLayer
# }
m5_custom_objects_bigquant_run = {
 
}

# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m24_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    pred_label = input_1.read_pickle()
    df = input_2.read_df()
    df = pd.DataFrame({'pred_label':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})
    df.sort_values(['date','pred_label'],inplace=True, ascending=[True,False])
    return Outputs(data_1=DataSource.write_df(df), data_2=None, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m24_post_run_bigquant_run(outputs):
    return outputs

# 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=0.001, sell_cost=0.001, 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 = 20
    # 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.perf_tracker.position_tracker.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.perf_tracker.position_tracker.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        # print('rank order for sell %s' % instruments)
        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': '2010-01-01',
    'm1.end_date': '2017-12-31',
    '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/data_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/big_expr.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)-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))

# 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.SHA',
    'm2.drop_na_label': True,
    'm2.cast_label_int': False,

    'm29': 'M.standardlize.v8',
    'm29.input_1': T.Graph.OutputPort('m2.data'),
    'm29.columns_input': 'label',

    'm3': 'M.input_features.v1',
    'm3.features': """close_0
open_0
high_0
low_0 
amount_0
turn_0 
return_0
 
close_1
open_1
high_1
low_1
return_1
amount_1
turn_1
 
close_2
open_2
high_2
low_2
amount_2
turn_2
return_2
 
close_3
open_3
high_3
low_3
amount_3
turn_3
return_3
 
close_4
open_4
high_4
low_4
amount_4
turn_4
return_4
 
mean(close_0, 5)
mean(low_0, 5)
mean(open_0, 5)
mean(high_0, 5)
mean(turn_0, 5)
mean(amount_0, 5)
mean(return_0, 5)
 
ts_max(close_0, 5)
ts_max(low_0, 5)
ts_max(open_0, 5)
ts_max(high_0, 5)
ts_max(turn_0, 5)
ts_max(amount_0, 5)
ts_max(return_0, 5)
 
ts_min(close_0, 5)
ts_min(low_0, 5)
ts_min(open_0, 5)
ts_min(high_0, 5)
ts_min(turn_0, 5)
ts_min(amount_0, 5)
ts_min(return_0, 5) 
 
std(close_0, 5)
std(low_0, 5)
std(open_0, 5)
std(high_0, 5)
std(turn_0, 5)
std(amount_0, 5)
std(return_0, 5)
 
ts_rank(close_0, 5)
ts_rank(low_0, 5)
ts_rank(open_0, 5)
ts_rank(high_0, 5)
ts_rank(turn_0, 5)
ts_rank(amount_0, 5)
ts_rank(return_0, 5)
 
decay_linear(close_0, 5)
decay_linear(low_0, 5)
decay_linear(open_0, 5)
decay_linear(high_0, 5)
decay_linear(turn_0, 5)
decay_linear(amount_0, 5)
decay_linear(return_0, 5)
 
correlation(volume_0, return_0, 5)
correlation(volume_0, high_0, 5)
correlation(volume_0, low_0, 5)
correlation(volume_0, close_0, 5)
correlation(volume_0, open_0, 5)
correlation(volume_0, turn_0, 5)
  
correlation(return_0, high_0, 5)
correlation(return_0, low_0, 5)
correlation(return_0, close_0, 5)
correlation(return_0, open_0, 5)
correlation(return_0, turn_0, 5)
 
correlation(high_0, low_0, 5)
correlation(high_0, close_0, 5)
correlation(high_0, open_0, 5)
correlation(high_0, turn_0, 5)
 
correlation(low_0, close_0, 5)
correlation(low_0, open_0, 5)
correlation(low_0, turn_0, 5)
 
correlation(close_0, open_0, 5)
correlation(close_0, turn_0, 5)

correlation(open_0, turn_0, 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': 0,

    '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': True,
    'm16.remove_extra_columns': False,

    'm28': 'M.standardlize.v8',
    'm28.input_1': T.Graph.OutputPort('m16.data'),
    'm28.input_2': T.Graph.OutputPort('m3.data'),
    'm28.columns_input': '[]',

    'm13': 'M.fillnan.v1',
    'm13.input_data': T.Graph.OutputPort('m28.data'),
    'm13.features': T.Graph.OutputPort('m3.data'),
    'm13.fill_value': '0.0',

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m29.data'),
    'm7.data2': T.Graph.OutputPort('m13.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm26': 'M.dl_convert_to_bin.v2',
    'm26.input_data': T.Graph.OutputPort('m7.data'),
    'm26.features': T.Graph.OutputPort('m3.data'),
    'm26.window_size': 1,
    'm26.feature_clip': 3,
    'm26.flatten': True,
    'm26.window_along_col': 'instrument',

    'm10': 'M.cached.v3',
    'm10.input_1': T.Graph.OutputPort('m26.data'),
    'm10.run': m10_run_bigquant_run,
    'm10.post_run': m10_post_run_bigquant_run,
    'm10.input_ports': '',
    'm10.params': '{}',
    'm10.output_ports': '',

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2018-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2021-09-01'),
    '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': 0,

    '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': True,
    'm18.remove_extra_columns': False,

    'm25': 'M.standardlize.v8',
    'm25.input_1': T.Graph.OutputPort('m18.data'),
    'm25.input_2': T.Graph.OutputPort('m3.data'),
    'm25.columns_input': '[]',

    'm14': 'M.fillnan.v1',
    'm14.input_data': T.Graph.OutputPort('m25.data'),
    'm14.features': T.Graph.OutputPort('m3.data'),
    'm14.fill_value': '0.0',

    'm27': 'M.dl_convert_to_bin.v2',
    'm27.input_data': T.Graph.OutputPort('m14.data'),
    'm27.features': T.Graph.OutputPort('m3.data'),
    'm27.window_size': 1,
    'm27.feature_clip': 3,
    'm27.flatten': True,
    'm27.window_along_col': 'instrument',

    'm6': 'M.dl_layer_input.v1',
    'm6.shape': '98',
    'm6.batch_shape': '',
    'm6.dtype': 'float32',
    'm6.sparse': False,
    'm6.name': '',

    'm8': 'M.dl_layer_dense.v1',
    'm8.inputs': T.Graph.OutputPort('m6.data'),
    'm8.units': 256,
    'm8.activation': 'relu',
    'm8.use_bias': True,
    'm8.kernel_initializer': 'glorot_uniform',
    'm8.bias_initializer': 'Zeros',
    'm8.kernel_regularizer': 'None',
    'm8.kernel_regularizer_l1': 0,
    'm8.kernel_regularizer_l2': 0,
    'm8.bias_regularizer': 'None',
    'm8.bias_regularizer_l1': 0,
    'm8.bias_regularizer_l2': 0,
    'm8.activity_regularizer': 'None',
    'm8.activity_regularizer_l1': 0,
    'm8.activity_regularizer_l2': 0,
    'm8.kernel_constraint': 'None',
    'm8.bias_constraint': 'None',
    'm8.name': '',

    'm21': 'M.dl_layer_dropout.v1',
    'm21.inputs': T.Graph.OutputPort('m8.data'),
    'm21.rate': 0.1,
    'm21.noise_shape': '',
    'm21.name': '',

    'm20': 'M.dl_layer_dense.v1',
    'm20.inputs': T.Graph.OutputPort('m21.data'),
    'm20.units': 128,
    'm20.activation': 'relu',
    'm20.use_bias': True,
    'm20.kernel_initializer': 'glorot_uniform',
    'm20.bias_initializer': 'Zeros',
    'm20.kernel_regularizer': 'None',
    'm20.kernel_regularizer_l1': 0,
    'm20.kernel_regularizer_l2': 0,
    'm20.bias_regularizer': 'None',
    'm20.bias_regularizer_l1': 0,
    'm20.bias_regularizer_l2': 0,
    'm20.activity_regularizer': 'None',
    'm20.activity_regularizer_l1': 0,
    'm20.activity_regularizer_l2': 0,
    'm20.kernel_constraint': 'None',
    'm20.bias_constraint': 'None',
    'm20.name': '',

    'm22': 'M.dl_layer_dropout.v1',
    'm22.inputs': T.Graph.OutputPort('m20.data'),
    'm22.rate': 0.1,
    'm22.noise_shape': '',
    'm22.name': '',

    'm23': 'M.dl_layer_dense.v1',
    'm23.inputs': T.Graph.OutputPort('m22.data'),
    'm23.units': 1,
    'm23.activation': 'linear',
    'm23.use_bias': True,
    'm23.kernel_initializer': 'glorot_uniform',
    'm23.bias_initializer': 'Zeros',
    'm23.kernel_regularizer': 'None',
    'm23.kernel_regularizer_l1': 0,
    'm23.kernel_regularizer_l2': 0,
    'm23.bias_regularizer': 'None',
    'm23.bias_regularizer_l1': 0,
    'm23.bias_regularizer_l2': 0,
    'm23.activity_regularizer': 'None',
    'm23.activity_regularizer_l1': 0,
    'm23.activity_regularizer_l2': 0,
    'm23.kernel_constraint': 'None',
    'm23.bias_constraint': 'None',
    'm23.name': '',

    'm4': 'M.dl_model_init.v1',
    'm4.inputs': T.Graph.OutputPort('m6.data'),
    'm4.outputs': T.Graph.OutputPort('m23.data'),

    'm5': 'M.dl_model_train.v1',
    'm5.input_model': T.Graph.OutputPort('m4.data'),
    'm5.training_data': T.Graph.OutputPort('m10.data_1'),
    'm5.validation_data': T.Graph.OutputPort('m10.data_2'),
    'm5.optimizer': 'RMSprop',
    'm5.loss': 'mean_squared_error',
    'm5.metrics': 'mse',
    'm5.batch_size': 1024,
    'm5.epochs': 20,
    'm5.earlystop': m5_earlystop_bigquant_run,
    'm5.custom_objects': m5_custom_objects_bigquant_run,
    'm5.n_gpus': 0,
    'm5.verbose': '2:每个epoch输出一行记录',
    'm5.m_cached': False,

    'm11': 'M.dl_model_predict.v1',
    'm11.trained_model': T.Graph.OutputPort('m5.data'),
    'm11.input_data': T.Graph.OutputPort('m27.data'),
    'm11.batch_size': 1024,
    'm11.n_gpus': 0,
    'm11.verbose': '2:每个epoch输出一行记录',

    'm24': 'M.cached.v3',
    'm24.input_1': T.Graph.OutputPort('m11.data'),
    'm24.input_2': T.Graph.OutputPort('m18.data'),
    'm24.run': m24_run_bigquant_run,
    'm24.post_run': m24_post_run_bigquant_run,
    'm24.input_ports': '',
    'm24.params': '{}',
    'm24.output_ports': '',

    'm19': 'M.trade.v4',
    'm19.instruments': T.Graph.OutputPort('m9.data'),
    'm19.options_data': T.Graph.OutputPort('m24.data_1'),
    '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': '后复权',
    'm19.product_type': '股票',
    'm19.plot_charts': True,
    'm19.backtest_only': False,
    'm19.benchmark': '000300.SHA',
})

# g.run({})


def m31_run_bigquant_run(bq_graph, inputs):
     
    test_years = ['2014','2015','2016','2017','2018','2019','2020','2021']
    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+'-09'+'-01'
        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=8, remote_run=True, silent=True)

    return results


m31 = M.hyper_run.v1(
    run=m31_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

In [ ]:

print(len(m31.result))
for i in range(len(m31.result)):
    print('==='*15, i)
    perf = m31.result[i]['m19'].raw_perf.read()
    T.render_perf(perf, buy_moment="buy", sell_moment="sell")

In [3]:

# T.render_perf(m31.result[0]['m19'].raw_perf.read(), buy_moment = "buy", sell_moment = "sell")
df = pd.DataFrame() 
for i in range(len(m31.result)):
    tmp = m31.result[i]['m19'].raw_perf.read()
    df = df.append(tmp[['returns','benchmark_period_return']])

In [4]:

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': return_ratio,
      'annual_return_ratio': annual_return_ratio,
      'beta': beta,
      'alpha': alpha,
      'sharp_ratio': sharp_ratio,
      'return_volatility': return_volatility,
      'max_drawdown': max_drawdown,
    }
get_stats(df['returns'], df['benchmark_period_return'])

Out[4]:

{'return_ratio': 63.120698592428724,
 'annual_return_ratio': 0.7519024660961879,
 'beta': 0.48546565304668354,
 'alpha': 0.8158119966625121,
 'sharp_ratio': 1.7219246312810157,
 'return_volatility': 0.3392824400837007,
 'max_drawdown': -0.5532899611410996}

In [5]:

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