复制链接
克隆策略

DeepAlpha短周期因子系列研究：LSTM

回测

  • 策略思想：基于模型的预测结果进行选股，选择当日排名靠前的50只股票买入，卖出其他持有的股票。
  • 调仓周期：日频，每日换仓
  • 资金管理：每只股票最大资金占用20%
  • 手续费：买入0.0003，卖出0.0013
In [17]:
import tensorflow as tf

gpus = tf.config.list_physical_devices('GPU')
if gpus:
    try:
        # Currently, memory growth needs to be the same across GPUs
        for gpu in gpus:
            tf.config.experimental.set_memory_growth(gpu, True)
        
        logical_gpus = tf.config.list_logical_devices('GPU')
        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
    except RuntimeError as e:
        # Memory growth must be set before GPUs have been initialized
        print(e)

1 Physical GPUs, 1 Logical GPUs

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"-106:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"-2469:input_1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"to_node_id":"-106:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-113:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-122:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-129:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-243:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-251:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-266:input_2","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-288:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-298:input_2","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-293:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-243:input_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"-122:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-141:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-113:input_data","from_node_id":"-106:data"},{"to_node_id":"-266:input_1","from_node_id":"-113:data"},{"to_node_id":"-129:input_data","from_node_id":"-122:data"},{"to_node_id":"-2431:input_2","from_node_id":"-129:data"},{"to_node_id":"-298:input_1","from_node_id":"-129:data"},{"to_node_id":"-682:inputs","from_node_id":"-160:data"},{"to_node_id":"-4111:inputs","from_node_id":"-160:data"},{"to_node_id":"-231:inputs","from_node_id":"-196:data"},{"to_node_id":"-196:inputs","from_node_id":"-224:data"},{"to_node_id":"-238:inputs","from_node_id":"-231:data"},{"to_node_id":"-682:outputs","from_node_id":"-238:data"},{"to_node_id":"-1098:input_model","from_node_id":"-682:data"},{"to_node_id":"-1540:trained_model","from_node_id":"-1098:data"},{"to_node_id":"-2431:input_1","from_node_id":"-1540:data"},{"to_node_id":"-141:options_data","from_node_id":"-2431:data_1"},{"to_node_id":"-436:input_1","from_node_id":"-243:data"},{"to_node_id":"-1540:input_data","from_node_id":"-251:data"},{"to_node_id":"-1098:training_data","from_node_id":"-436:data_1"},{"to_node_id":"-1098:validation_data","from_node_id":"-436:data_2"},{"to_node_id":"-288:input_data","from_node_id":"-266:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-288:data"},{"to_node_id":"-251:input_data","from_node_id":"-293:data"},{"to_node_id":"-293:input_data","from_node_id":"-298:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","from_node_id":"-2469:data"},{"to_node_id":"-224:inputs","from_node_id":"-4111:data"}],"nodes":[{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2018-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2020-12-31","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":"0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"cacheable":true,"seq_num":1,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","module_id":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","parameters":[{"name":"label_expr","value":"# #号开始的表示注释\n# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html\n# 添加benchmark_前缀，可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_\n\n# 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)\nshift(close, -5) / shift(open, -1) - 1\n\n# 极值处理：用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 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)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","type":"Literal","bound_global_parameter":null},{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.SHA","type":"Literal","bound_global_parameter":null},{"name":"drop_na_label","value":"True","type":"Literal","bound_global_parameter":null},{"name":"cast_label_int","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"cacheable":true,"seq_num":2,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"close_0\nopen_0\nhigh_0\nlow_0 \namount_0\nturn_0 \nreturn_0\n \nclose_1\nopen_1\nhigh_1\nlow_1\nreturn_1\namount_1\nturn_1\n \nclose_2\nopen_2\nhigh_2\nlow_2\namount_2\nturn_2\nreturn_2\n \nclose_3\nopen_3\nhigh_3\nlow_3\namount_3\nturn_3\nreturn_3\n \nclose_4\nopen_4\nhigh_4\nlow_4\namount_4\nturn_4\nreturn_4\n \nmean(close_0, 5)\nmean(low_0, 5)\nmean(open_0, 5)\nmean(high_0, 5)\nmean(turn_0, 5)\nmean(amount_0, 5)\nmean(return_0, 5)\n \nts_max(close_0, 5)\nts_max(low_0, 5)\nts_max(open_0, 5)\nts_max(high_0, 5)\nts_max(turn_0, 5)\nts_max(amount_0, 5)\nts_max(return_0, 5)\n \nts_min(close_0, 5)\nts_min(low_0, 5)\nts_min(open_0, 5)\nts_min(high_0, 5)\nts_min(turn_0, 5)\nts_min(amount_0, 5)\nts_min(return_0, 5) \n \nstd(close_0, 5)\nstd(low_0, 5)\nstd(open_0, 5)\nstd(high_0, 5)\nstd(turn_0, 5)\nstd(amount_0, 5)\nstd(return_0, 5)\n \nts_rank(close_0, 5)\nts_rank(low_0, 5)\nts_rank(open_0, 5)\nts_rank(high_0, 5)\nts_rank(turn_0, 5)\nts_rank(amount_0, 5)\nts_rank(return_0, 5)\n \ndecay_linear(close_0, 5)\ndecay_linear(low_0, 5)\ndecay_linear(open_0, 5)\ndecay_linear(high_0, 5)\ndecay_linear(turn_0, 5)\ndecay_linear(amount_0, 5)\ndecay_linear(return_0, 5)\n \ncorrelation(volume_0, return_0, 5)\ncorrelation(volume_0, high_0, 5)\ncorrelation(volume_0, low_0, 5)\ncorrelation(volume_0, close_0, 5)\ncorrelation(volume_0, open_0, 5)\ncorrelation(volume_0, turn_0, 5)\n \ncorrelation(return_0, high_0, 5)\ncorrelation(return_0, low_0, 5)\ncorrelation(return_0, close_0, 5)\ncorrelation(return_0, open_0, 5)\ncorrelation(return_0, turn_0, 5)\n \ncorrelation(high_0, low_0, 5)\ncorrelation(high_0, close_0, 5)\ncorrelation(high_0, open_0, 5)\ncorrelation(high_0, turn_0, 5)\n \ncorrelation(low_0, close_0, 5)\ncorrelation(low_0, open_0, 5)\ncorrelation(low_0, turn_0, 5)\n \ncorrelation(close_0, open_0, 5)\ncorrelation(close_0, turn_0, 5)\n\ncorrelation(open_0, turn_0, 5)","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"cacheable":true,"seq_num":3,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","module_id":"BigQuantSpace.join.join-v3","parameters":[{"name":"on","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"how","value":"inner","type":"Literal","bound_global_parameter":null},{"name":"sort","value":"True","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"data1","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"name":"data2","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2021-12-31","type":"Literal","bound_global_parameter":"交易日期"},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":"0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"cacheable":true,"seq_num":9,"comment":"预测数据，用于回测和模拟","comment_collapsed":false},{"node_id":"-106","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":"10","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-106"},{"name":"features","node_id":"-106"}],"output_ports":[{"name":"data","node_id":"-106"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true},{"node_id":"-113","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"True","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-113"},{"name":"features","node_id":"-113"}],"output_ports":[{"name":"data","node_id":"-113"}],"cacheable":true,"seq_num":16,"comment":"","comment_collapsed":true},{"node_id":"-122","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":"10","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-122"},{"name":"features","node_id":"-122"}],"output_ports":[{"name":"data","node_id":"-122"}],"cacheable":true,"seq_num":17,"comment":"","comment_collapsed":true},{"node_id":"-129","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"True","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-129"},{"name":"features","node_id":"-129"}],"output_ports":[{"name":"data","node_id":"-129"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true},{"node_id":"-141","module_id":"BigQuantSpace.trade.trade-v4","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"initialize","value":"# 回测引擎：初始化函数，只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 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\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)\n # 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\n stock_count = 50\n # 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, ..]\n context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])\n # 设置每只股票占用的最大资金比例\n context.max_cash_per_instrument = 0.2\n context.options['hold_days'] = 5\n","type":"Literal","bound_global_parameter":null},{"name":"handle_data","value":"# 回测引擎：每日数据处理函数，每天执行一次\ndef bigquant_run(context, data):\n # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n\n # 1. 资金分配\n # 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\n # 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）\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 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\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))\n # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 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\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","type":"Literal","bound_global_parameter":null},{"name":"prepare","value":"# 回测引擎：准备数据，只执行一次\ndef bigquant_run(context):\n pass\n","type":"Literal","bound_global_parameter":null},{"name":"before_trading_start","value":"","type":"Literal","bound_global_parameter":null},{"name":"volume_limit","value":0.025,"type":"Literal","bound_global_parameter":null},{"name":"order_price_field_buy","value":"open","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_sell","value":"close","type":"Literal","bound_global_parameter":null},{"name":"capital_base","value":1000000,"type":"Literal","bound_global_parameter":null},{"name":"auto_cancel_non_tradable_orders","value":"True","type":"Literal","bound_global_parameter":null},{"name":"data_frequency","value":"daily","type":"Literal","bound_global_parameter":null},{"name":"price_type","value":"后复权","type":"Literal","bound_global_parameter":null},{"name":"product_type","value":"股票","type":"Literal","bound_global_parameter":null},{"name":"plot_charts","value":"True","type":"Literal","bound_global_parameter":null},{"name":"backtest_only","value":"False","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.SHA","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-141"},{"name":"options_data","node_id":"-141"},{"name":"history_ds","node_id":"-141"},{"name":"benchmark_ds","node_id":"-141"},{"name":"trading_calendar","node_id":"-141"}],"output_ports":[{"name":"raw_perf","node_id":"-141"}],"cacheable":false,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-160","module_id":"BigQuantSpace.dl_layer_input.dl_layer_input-v1","parameters":[{"name":"shape","value":"5,98","type":"Literal","bound_global_parameter":null},{"name":"batch_shape","value":"","type":"Literal","bound_global_parameter":null},{"name":"dtype","value":"float32","type":"Literal","bound_global_parameter":null},{"name":"sparse","value":"False","type":"Literal","bound_global_parameter":null},{"name":"name","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"inputs","node_id":"-160"}],"output_ports":[{"name":"data","node_id":"-160"}],"cacheable":false,"seq_num":6,"comment":"","comment_collapsed":true},{"node_id":"-196","module_id":"BigQuantSpace.dl_layer_dense.dl_layer_dense-v1","parameters":[{"name":"units","value":"128","type":"Literal","bound_global_parameter":null},{"name":"activation","value":"relu","type":"Literal","bound_global_parameter":null},{"name":"user_activation","value":"","type":"Literal","bound_global_parameter":null},{"name":"use_bias","value":"True","type":"Literal","bound_global_parameter":null},{"name":"kernel_initializer","value":"glorot_uniform","type":"Literal","bound_global_parameter":null},{"name":"user_kernel_initializer","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_initializer","value":"Zeros","type":"Literal","bound_global_parameter":null},{"name":"user_bias_initializer","value":"","type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_kernel_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_bias_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_activity_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"kernel_constraint","value":"None","type":"Literal","bound_global_parameter":null},{"name":"user_kernel_constraint","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_constraint","value":"None","type":"Literal","bound_global_parameter":null},{"name":"user_bias_constraint","value":"","type":"Literal","bound_global_parameter":null},{"name":"name","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"inputs","node_id":"-196"}],"output_ports":[{"name":"data","node_id":"-196"}],"cacheable":false,"seq_num":20,"comment":"","comment_collapsed":true},{"node_id":"-224","module_id":"BigQuantSpace.dl_layer_dropout.dl_layer_dropout-v1","parameters":[{"name":"rate","value":"0.1","type":"Literal","bound_global_parameter":null},{"name":"noise_shape","value":"","type":"Literal","bound_global_parameter":null},{"name":"seed","value":"","type":"Literal","bound_global_parameter":null},{"name":"name","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"inputs","node_id":"-224"}],"output_ports":[{"name":"data","node_id":"-224"}],"cacheable":false,"seq_num":21,"comment":"","comment_collapsed":true},{"node_id":"-231","module_id":"BigQuantSpace.dl_layer_dropout.dl_layer_dropout-v1","parameters":[{"name":"rate","value":"0.1","type":"Literal","bound_global_parameter":null},{"name":"noise_shape","value":"","type":"Literal","bound_global_parameter":null},{"name":"seed","value":"","type":"Literal","bound_global_parameter":null},{"name":"name","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"inputs","node_id":"-231"}],"output_ports":[{"name":"data","node_id":"-231"}],"cacheable":false,"seq_num":22,"comment":"","comment_collapsed":true},{"node_id":"-238","module_id":"BigQuantSpace.dl_layer_dense.dl_layer_dense-v1","parameters":[{"name":"units","value":"1","type":"Literal","bound_global_parameter":null},{"name":"activation","value":"linear","type":"Literal","bound_global_parameter":null},{"name":"user_activation","value":"","type":"Literal","bound_global_parameter":null},{"name":"use_bias","value":"True","type":"Literal","bound_global_parameter":null},{"name":"kernel_initializer","value":"glorot_uniform","type":"Literal","bound_global_parameter":null},{"name":"user_kernel_initializer","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_initializer","value":"Zeros","type":"Literal","bound_global_parameter":null},{"name":"user_bias_initializer","value":"","type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_kernel_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_bias_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_activity_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"kernel_constraint","value":"None","type":"Literal","bound_global_parameter":null},{"name":"user_kernel_constraint","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_constraint","value":"None","type":"Literal","bound_global_parameter":null},{"name":"user_bias_constraint","value":"","type":"Literal","bound_global_parameter":null},{"name":"name","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"inputs","node_id":"-238"}],"output_ports":[{"name":"data","node_id":"-238"}],"cacheable":false,"seq_num":23,"comment":"","comment_collapsed":true},{"node_id":"-682","module_id":"BigQuantSpace.dl_model_init.dl_model_init-v1","parameters":[],"input_ports":[{"name":"inputs","node_id":"-682"},{"name":"outputs","node_id":"-682"}],"output_ports":[{"name":"data","node_id":"-682"}],"cacheable":false,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-1098","module_id":"BigQuantSpace.dl_model_train.dl_model_train-v1","parameters":[{"name":"optimizer","value":"Adam","type":"Literal","bound_global_parameter":null},{"name":"user_optimizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"loss","value":"mean_squared_error","type":"Literal","bound_global_parameter":null},{"name":"user_loss","value":"","type":"Literal","bound_global_parameter":null},{"name":"metrics","value":"mse","type":"Literal","bound_global_parameter":null},{"name":"batch_size","value":"1024","type":"Literal","bound_global_parameter":null},{"name":"epochs","value":"10","type":"Literal","bound_global_parameter":null},{"name":"earlystop","value":"from tensorflow.keras.callbacks import EarlyStopping\nbigquant_run=EarlyStopping(monitor='val_mse', min_delta=0.0001, patience=3)","type":"Literal","bound_global_parameter":null},{"name":"custom_objects","value":"# 用户的自定义层需要写到字典中，比如\n# {\n# \"MyLayer\": MyLayer\n# }\nbigquant_run = {\n \n}\n","type":"Literal","bound_global_parameter":null},{"name":"n_gpus","value":"0","type":"Literal","bound_global_parameter":null},{"name":"verbose","value":"2:每个epoch输出一行记录","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_model","node_id":"-1098"},{"name":"training_data","node_id":"-1098"},{"name":"validation_data","node_id":"-1098"}],"output_ports":[{"name":"data","node_id":"-1098"}],"cacheable":true,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-1540","module_id":"BigQuantSpace.dl_model_predict.dl_model_predict-v1","parameters":[{"name":"batch_size","value":"1024","type":"Literal","bound_global_parameter":null},{"name":"n_gpus","value":0,"type":"Literal","bound_global_parameter":null},{"name":"verbose","value":"2:每个epoch输出一行记录","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"trained_model","node_id":"-1540"},{"name":"input_data","node_id":"-1540"}],"output_ports":[{"name":"data","node_id":"-1540"}],"cacheable":true,"seq_num":11,"comment":"","comment_collapsed":true},{"node_id":"-2431","module_id":"BigQuantSpace.cached.cached-v3","parameters":[{"name":"run","value":"# 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\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n pred_label = input_1.read_pickle()\n df = input_2.read_df()\n df = pd.DataFrame({'pred_label':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})\n df.sort_values(['date','pred_label'],inplace=True, ascending=[True,False])\n return Outputs(data_1=DataSource.write_df(df), data_2=None, data_3=None)\n","type":"Literal","bound_global_parameter":null},{"name":"post_run","value":"# 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。\ndef bigquant_run(outputs):\n return outputs\n","type":"Literal","bound_global_parameter":null},{"name":"input_ports","value":"","type":"Literal","bound_global_parameter":null},{"name":"params","value":"{}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-2431"},{"name":"input_2","node_id":"-2431"},{"name":"input_3","node_id":"-2431"}],"output_ports":[{"name":"data_1","node_id":"-2431"},{"name":"data_2","node_id":"-2431"},{"name":"data_3","node_id":"-2431"}],"cacheable":true,"seq_num":24,"comment":"","comment_collapsed":true},{"node_id":"-243","module_id":"BigQuantSpace.dl_convert_to_bin.dl_convert_to_bin-v2","parameters":[{"name":"window_size","value":"5","type":"Literal","bound_global_parameter":null},{"name":"feature_clip","value":"3","type":"Literal","bound_global_parameter":null},{"name":"flatten","value":"False","type":"Literal","bound_global_parameter":null},{"name":"window_along_col","value":"instrument","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-243"},{"name":"features","node_id":"-243"}],"output_ports":[{"name":"data","node_id":"-243"}],"cacheable":true,"seq_num":26,"comment":"","comment_collapsed":true},{"node_id":"-251","module_id":"BigQuantSpace.dl_convert_to_bin.dl_convert_to_bin-v2","parameters":[{"name":"window_size","value":"5","type":"Literal","bound_global_parameter":null},{"name":"feature_clip","value":"3","type":"Literal","bound_global_parameter":null},{"name":"flatten","value":"False","type":"Literal","bound_global_parameter":null},{"name":"window_along_col","value":"instrument","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-251"},{"name":"features","node_id":"-251"}],"output_ports":[{"name":"data","node_id":"-251"}],"cacheable":true,"seq_num":27,"comment":"","comment_collapsed":true},{"node_id":"-436","module_id":"BigQuantSpace.cached.cached-v3","parameters":[{"name":"run","value":"# 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\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n from sklearn.model_selection import train_test_split\n data = input_1.read()\n x_train, x_val, y_train, y_val = train_test_split(data[\"x\"], data['y'], test_size=0.1)\n data_1 = DataSource.write_pickle({'x': x_train, 'y': y_train})\n data_2 = DataSource.write_pickle({'x': x_val, 'y': y_val})\n return Outputs(data_1=data_1, data_2=data_2, data_3=None)\n","type":"Literal","bound_global_parameter":null},{"name":"post_run","value":"# 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。\ndef bigquant_run(outputs):\n return outputs\n","type":"Literal","bound_global_parameter":null},{"name":"input_ports","value":"","type":"Literal","bound_global_parameter":null},{"name":"params","value":"{}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-436"},{"name":"input_2","node_id":"-436"},{"name":"input_3","node_id":"-436"}],"output_ports":[{"name":"data_1","node_id":"-436"},{"name":"data_2","node_id":"-436"},{"name":"data_3","node_id":"-436"}],"cacheable":true,"seq_num":10,"comment":"","comment_collapsed":true},{"node_id":"-266","module_id":"BigQuantSpace.standardlize.standardlize-v8","parameters":[{"name":"columns_input","value":"[]","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-266"},{"name":"input_2","node_id":"-266"}],"output_ports":[{"name":"data","node_id":"-266"}],"cacheable":true,"seq_num":28,"comment":"","comment_collapsed":true},{"node_id":"-288","module_id":"BigQuantSpace.fillnan.fillnan-v1","parameters":[{"name":"fill_value","value":"0.0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-288"},{"name":"features","node_id":"-288"}],"output_ports":[{"name":"data","node_id":"-288"}],"cacheable":true,"seq_num":13,"comment":"","comment_collapsed":true},{"node_id":"-293","module_id":"BigQuantSpace.fillnan.fillnan-v1","parameters":[{"name":"fill_value","value":"0.0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-293"},{"name":"features","node_id":"-293"}],"output_ports":[{"name":"data","node_id":"-293"}],"cacheable":true,"seq_num":14,"comment":"","comment_collapsed":true},{"node_id":"-298","module_id":"BigQuantSpace.standardlize.standardlize-v8","parameters":[{"name":"columns_input","value":"[]","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-298"},{"name":"input_2","node_id":"-298"}],"output_ports":[{"name":"data","node_id":"-298"}],"cacheable":true,"seq_num":25,"comment":"","comment_collapsed":true},{"node_id":"-2469","module_id":"BigQuantSpace.standardlize.standardlize-v9","parameters":[{"name":"standard_func","value":"ZScoreNorm","type":"Literal","bound_global_parameter":null},{"name":"columns_input","value":"label","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-2469"},{"name":"input_2","node_id":"-2469"}],"output_ports":[{"name":"data","node_id":"-2469"}],"cacheable":true,"seq_num":12,"comment":"","comment_collapsed":true},{"node_id":"-306","module_id":"BigQuantSpace.hyper_run.hyper_run-v1","parameters":[{"name":"run","value":"def bigquant_run(bq_graph, inputs):\n \n test_years = ['2015', '2016','2017','2018','2019','2020','2021']\n parameters_list = []\n \n for i in test_years:\n train_start_date = str(int(i) -4)+'-01'+'-01'\n train_end_date = str(int(i) - 1)+'-12'+'-31'\n test_start_date = i+'-01'+'-01'\n# if i == test_years[-1]:\n# test_end_date = i+'-08'+'-01'\n# else:\n# test_end_date = i+'-12'+'-31'\n test_end_date = i+'-12'+'-31'\n parameters = {'m1.start_date':train_start_date,\n 'm1.end_date':train_end_date,\n 'm9.start_date':test_start_date,\n 'm9.end_date':test_end_date,\n }\n \n parameters_list.append({'parameters': parameters})\n print(len(parameters_list), parameters_list)\n\n def run(parameters):\n try:\n print(parameters)\n return g.run(parameters)\n except Exception as e:\n print('ERROR --------', e)\n return None\n \n results = T.parallel_map(run, parameters_list, max_workers=1, remote_run=False, silent=True)\n\n return results\n","type":"Literal","bound_global_parameter":null},{"name":"run_now","value":"True","type":"Literal","bound_global_parameter":null},{"name":"bq_graph","value":"True","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"bq_graph_port","node_id":"-306"},{"name":"input_1","node_id":"-306"},{"name":"input_2","node_id":"-306"},{"name":"input_3","node_id":"-306"}],"output_ports":[{"name":"result","node_id":"-306"}],"cacheable":false,"seq_num":29,"comment":"","comment_collapsed":true},{"node_id":"-4111","module_id":"BigQuantSpace.dl_layer_lstm.dl_layer_lstm-v1","parameters":[{"name":"units","value":"64","type":"Literal","bound_global_parameter":null},{"name":"activation","value":"tanh","type":"Literal","bound_global_parameter":null},{"name":"user_activation","value":"","type":"Literal","bound_global_parameter":null},{"name":"recurrent_activation","value":"sigmoid","type":"Literal","bound_global_parameter":null},{"name":"user_recurrent_activation","value":"","type":"Literal","bound_global_parameter":null},{"name":"use_bias","value":"True","type":"Literal","bound_global_parameter":null},{"name":"kernel_initializer","value":"glorot_uniform","type":"Literal","bound_global_parameter":null},{"name":"user_kernel_initializer","value":"","type":"Literal","bound_global_parameter":null},{"name":"recurrent_initializer","value":"Orthogonal","type":"Literal","bound_global_parameter":null},{"name":"user_recurrent_initializer","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_initializer","value":"Zeros","type":"Literal","bound_global_parameter":null},{"name":"user_bias_initializer","value":"","type":"Literal","bound_global_parameter":null},{"name":"unit_forget_bias","value":"True","type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"kernel_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_kernel_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"recurrent_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"recurrent_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"recurrent_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_recurrent_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"bias_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_bias_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer","value":"None","type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer_l1","value":0,"type":"Literal","bound_global_parameter":null},{"name":"activity_regularizer_l2","value":0,"type":"Literal","bound_global_parameter":null},{"name":"user_activity_regularizer","value":"","type":"Literal","bound_global_parameter":null},{"name":"kernel_constraint","value":"None","type":"Literal","bound_global_parameter":null},{"name":"user_kernel_constraint","value":"","type":"Literal","bound_global_parameter":null},{"name":"recurrent_constraint","value":"None","type":"Literal","bound_global_parameter":null},{"name":"user_recurrent_constraint","value":"","type":"Literal","bound_global_parameter":null},{"name":"bias_constraint","value":"None","type":"Literal","bound_global_parameter":null},{"name":"user_bias_constraint","value":"","type":"Literal","bound_global_parameter":null},{"name":"dropout","value":0,"type":"Literal","bound_global_parameter":null},{"name":"recurrent_dropout","value":0,"type":"Literal","bound_global_parameter":null},{"name":"return_sequences","value":"False","type":"Literal","bound_global_parameter":null},{"name":"implementation","value":"2","type":"Literal","bound_global_parameter":null},{"name":"name","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"inputs","node_id":"-4111"}],"output_ports":[{"name":"data","node_id":"-4111"}],"cacheable":false,"seq_num":8,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='323,60,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='101,168,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='772,-47,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='291,505,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1145,129,200,200'/><node_position Node='-106' Position='441,156,200,200'/><node_position Node='-113' Position='441,235,200,200'/><node_position Node='-122' Position='1146,284,200,200'/><node_position Node='-129' Position='1156,392,200,200'/><node_position Node='-141' Position='349,1021,200,200'/><node_position Node='-160' Position='-202,35,200,200'/><node_position Node='-196' Position='-203,311,200,200'/><node_position Node='-224' Position='-203,240,200,200'/><node_position Node='-231' Position='-201,395,200,200'/><node_position Node='-238' Position='-195,470,200,200'/><node_position Node='-682' Position='-195,560,200,200'/><node_position Node='-1098' Position='28,745,200,200'/><node_position Node='-1540' Position='221,833,200,200'/><node_position Node='-2431' Position='438,934,200,200'/><node_position Node='-243' Position='294,579,200,200'/><node_position Node='-251' Position='1147,690,200,200'/><node_position Node='-436' Position='282,662,200,200'/><node_position Node='-266' Position='446,303,200,200'/><node_position Node='-288' Position='448,374,200,200'/><node_position Node='-293' Position='1150,600,200,200'/><node_position Node='-298' Position='1155,500,200,200'/><node_position Node='-2469' Position='110,312,200,200'/><node_position Node='-306' Position='-176,1000,200,200'/><node_position Node='-4111' Position='-201.02820873260498,128,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [18]:
    # 本代码由可视化策略环境自动生成 2022年4月25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'], test_size=0.1)
    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=0.0003, 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 = 50
    # 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': '2018-01-01',
    'm1.end_date': '2020-12-31',
    '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,

    'm12': 'M.standardlize.v9',
    'm12.input_1': T.Graph.OutputPort('m2.data'),
    'm12.standard_func': 'ZScoreNorm',
    'm12.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': 10,

    '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('m12.data'),
    'm7.data2': T.Graph.OutputPort('m13.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': True,

    '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': 5,
    'm26.feature_clip': 3,
    'm26.flatten': False,
    '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', '2021-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2021-12-31'),
    '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': 10,

    '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': 5,
    'm27.feature_clip': 3,
    'm27.flatten': False,
    'm27.window_along_col': 'instrument',

    'm6': 'M.dl_layer_input.v1',
    'm6.shape': '5,98',
    'm6.batch_shape': '',
    'm6.dtype': 'float32',
    'm6.sparse': False,
    'm6.name': '',

    'm8': 'M.dl_layer_lstm.v1',
    'm8.inputs': T.Graph.OutputPort('m6.data'),
    'm8.units': 64,
    'm8.activation': 'tanh',
    'm8.recurrent_activation': 'sigmoid',
    'm8.use_bias': True,
    'm8.kernel_initializer': 'glorot_uniform',
    'm8.recurrent_initializer': 'Orthogonal',
    'm8.bias_initializer': 'Zeros',
    'm8.unit_forget_bias': True,
    'm8.kernel_regularizer': 'None',
    'm8.kernel_regularizer_l1': 0,
    'm8.kernel_regularizer_l2': 0,
    'm8.recurrent_regularizer': 'None',
    'm8.recurrent_regularizer_l1': 0,
    'm8.recurrent_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.recurrent_constraint': 'None',
    'm8.bias_constraint': 'None',
    'm8.dropout': 0,
    'm8.recurrent_dropout': 0,
    'm8.return_sequences': False,
    'm8.implementation': '2',
    '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': 'Adam',
    'm5.loss': 'mean_squared_error',
    'm5.metrics': 'mse',
    'm5.batch_size': 1024,
    'm5.epochs': 10,
    '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',

    '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 m29_run_bigquant_run(bq_graph, inputs):
     
    test_years = ['2015', '2016','2017','2018','2019','2020','2021']
    parameters_list = []
     
    for i in test_years:
        train_start_date =  str(int(i) -4)+'-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+'-08'+'-01'
#         else:
#             test_end_date  =  i+'-12'+'-31'
        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=1, remote_run=False, silent=True)

    return results


m29 = M.hyper_run.v1(
    run=m29_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

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

    {'m1.start_date': '2011-01-01', 'm1.end_date': '2014-12-31', 'm9.start_date': '2015-01-01', 'm9.end_date': '2015-12-31'}

    Epoch 1/10
1926/1926 - 89s - loss: 0.9862 - mse: 0.9862 - val_loss: 0.9751 - val_mse: 0.9751
Epoch 2/10
1926/1926 - 12s - loss: 0.9793 - mse: 0.9793 - val_loss: 0.9714 - val_mse: 0.9714
Epoch 3/10
1926/1926 - 9s - loss: 0.9756 - mse: 0.9756 - val_loss: 0.9685 - val_mse: 0.9685
Epoch 4/10
1926/1926 - 8s - loss: 0.9722 - mse: 0.9722 - val_loss: 0.9668 - val_mse: 0.9668
Epoch 5/10
1926/1926 - 8s - loss: 0.9693 - mse: 0.9693 - val_loss: 0.9645 - val_mse: 0.9645
Epoch 6/10
1926/1926 - 8s - loss: 0.9665 - mse: 0.9665 - val_loss: 0.9659 - val_mse: 0.9659
Epoch 7/10
1926/1926 - 9s - loss: 0.9639 - mse: 0.9639 - val_loss: 0.9636 - val_mse: 0.9636
Epoch 8/10
1926/1926 - 14s - loss: 0.9615 - mse: 0.9615 - val_loss: 0.9618 - val_mse: 0.9618
Epoch 9/10
1926/1926 - 11s - loss: 0.9593 - mse: 0.9593 - val_loss: 0.9607 - val_mse: 0.9607
Epoch 10/10
1926/1926 - 8s - loss: 0.9572 - mse: 0.9572 - val_loss: 0.9592 - val_mse: 0.9592

    564/564 - 3s
DataSource(add03031016b43d88858110b974bf9f1T)
    • 收益率232.86%
    • 年化收益率246.24%
    • 基准收益率5.58%
    • 阿尔法2.48
    • 贝塔0.92
    • 夏普比率2.64
    • 胜率0.65
    • 盈亏比0.95
    • 收益波动率51.05%
    • 信息比率0.22
    • 最大回撤51.15%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-0685b70c03444534be396452fd8aa7f8"}/bigcharts-data-end
    {'m1.start_date': '2012-01-01', 'm1.end_date': '2015-12-31', 'm9.start_date': '2016-01-01', 'm9.end_date': '2016-12-31'}

    Epoch 1/10
1970/1970 - 54s - loss: 0.9837 - mse: 0.9837 - val_loss: 0.9741 - val_mse: 0.9741
Epoch 2/10
1970/1970 - 16s - loss: 0.9762 - mse: 0.9762 - val_loss: 0.9699 - val_mse: 0.9699
Epoch 3/10
1970/1970 - 17s - loss: 0.9710 - mse: 0.9710 - val_loss: 0.9670 - val_mse: 0.9670
Epoch 4/10
1970/1970 - 15s - loss: 0.9671 - mse: 0.9671 - val_loss: 0.9632 - val_mse: 0.9632
Epoch 5/10
1970/1970 - 14s - loss: 0.9632 - mse: 0.9632 - val_loss: 0.9596 - val_mse: 0.9596
Epoch 6/10
1970/1970 - 17s - loss: 0.9603 - mse: 0.9603 - val_loss: 0.9585 - val_mse: 0.9585
Epoch 7/10
1970/1970 - 12s - loss: 0.9569 - mse: 0.9569 - val_loss: 0.9569 - val_mse: 0.9569
Epoch 8/10
1970/1970 - 11s - loss: 0.9545 - mse: 0.9545 - val_loss: 0.9575 - val_mse: 0.9575
Epoch 9/10
1970/1970 - 14s - loss: 0.9518 - mse: 0.9518 - val_loss: 0.9569 - val_mse: 0.9569
Epoch 10/10
1970/1970 - 14s - loss: 0.9498 - mse: 0.9498 - val_loss: 0.9555 - val_mse: 0.9555

    635/635 - 4s
DataSource(b5898bb690e54560b40759a209838a3eT)
    • 收益率50.71%
    • 年化收益率52.75%
    • 基准收益率-11.28%
    • 阿尔法0.79
    • 贝塔1.08
    • 夏普比率1.41
    • 胜率0.57
    • 盈亏比1.17
    • 收益波动率31.37%
    • 信息比率0.18
    • 最大回撤16.05%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-ea853549ea9740acbe29debc6517492d"}/bigcharts-data-end
    {'m1.start_date': '2013-01-01', 'm1.end_date': '2016-12-31', 'm9.start_date': '2017-01-01', 'm9.end_date': '2017-12-31'}

    Epoch 1/10
2034/2034 - 16s - loss: 0.9835 - mse: 0.9835 - val_loss: 0.9807 - val_mse: 0.9807
Epoch 2/10
2034/2034 - 10s - loss: 0.9761 - mse: 0.9761 - val_loss: 0.9755 - val_mse: 0.9755
Epoch 3/10
2034/2034 - 10s - loss: 0.9711 - mse: 0.9711 - val_loss: 0.9725 - val_mse: 0.9725
Epoch 4/10
2034/2034 - 9s - loss: 0.9671 - mse: 0.9671 - val_loss: 0.9692 - val_mse: 0.9692
Epoch 5/10
2034/2034 - 9s - loss: 0.9636 - mse: 0.9636 - val_loss: 0.9687 - val_mse: 0.9687
Epoch 6/10
2034/2034 - 9s - loss: 0.9603 - mse: 0.9603 - val_loss: 0.9659 - val_mse: 0.9659
Epoch 7/10
2034/2034 - 9s - loss: 0.9575 - mse: 0.9575 - val_loss: 0.9628 - val_mse: 0.9628
Epoch 8/10
2034/2034 - 9s - loss: 0.9546 - mse: 0.9546 - val_loss: 0.9629 - val_mse: 0.9629
Epoch 9/10
2034/2034 - 8s - loss: 0.9524 - mse: 0.9524 - val_loss: 0.9610 - val_mse: 0.9610
Epoch 10/10
2034/2034 - 9s - loss: 0.9499 - mse: 0.9499 - val_loss: 0.9594 - val_mse: 0.9594

    731/731 - 2s
DataSource(03e3e0ae72624d40a42aa5394cc21952T)
    • 收益率21.13%
    • 年化收益率21.89%
    • 基准收益率21.78%
    • 阿尔法0.03
    • 贝塔1.01
    • 夏普比率0.75
    • 胜率0.54
    • 盈亏比1.06
    • 收益波动率27.81%
    • 信息比率0.01
    • 最大回撤15.67%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-c2296dd019bc476ea80d4f0fd5daefa0"}/bigcharts-data-end
    {'m1.start_date': '2014-01-01', 'm1.end_date': '2017-12-31', 'm9.start_date': '2018-01-01', 'm9.end_date': '2018-12-31'}

    Epoch 1/10
2185/2185 - 20s - loss: 0.9864 - mse: 0.9864 - val_loss: 0.9795 - val_mse: 0.9795
Epoch 2/10
2185/2185 - 10s - loss: 0.9792 - mse: 0.9792 - val_loss: 0.9741 - val_mse: 0.9741
Epoch 3/10
2185/2185 - 10s - loss: 0.9744 - mse: 0.9744 - val_loss: 0.9702 - val_mse: 0.9702
Epoch 4/10
2185/2185 - 12s - loss: 0.9703 - mse: 0.9703 - val_loss: 0.9691 - val_mse: 0.9691
Epoch 5/10
2185/2185 - 13s - loss: 0.9664 - mse: 0.9664 - val_loss: 0.9654 - val_mse: 0.9654
Epoch 6/10
2185/2185 - 10s - loss: 0.9630 - mse: 0.9630 - val_loss: 0.9642 - val_mse: 0.9642
Epoch 7/10
2185/2185 - 11s - loss: 0.9601 - mse: 0.9601 - val_loss: 0.9617 - val_mse: 0.9617
Epoch 8/10
2185/2185 - 12s - loss: 0.9570 - mse: 0.9570 - val_loss: 0.9608 - val_mse: 0.9608
Epoch 9/10
2185/2185 - 13s - loss: 0.9545 - mse: 0.9545 - val_loss: 0.9594 - val_mse: 0.9594
Epoch 10/10
2185/2185 - 12s - loss: 0.9518 - mse: 0.9518 - val_loss: 0.9576 - val_mse: 0.9576

    803/803 - 3s
DataSource(a0e4a718186d4f0f875f7f412890c3e8T)
    • 收益率25.75%
    • 年化收益率26.83%
    • 基准收益率-25.31%
    • 阿尔法0.74
    • 贝塔0.98
    • 夏普比率0.83
    • 胜率0.52
    • 盈亏比1.17
    • 收益波动率30.6%
    • 信息比率0.16
    • 最大回撤22.91%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-ca6e22cd5afc4d7b8b4708e9aa22db3f"}/bigcharts-data-end
    {'m1.start_date': '2015-01-01', 'm1.end_date': '2018-12-31', 'm9.start_date': '2019-01-01', 'm9.end_date': '2019-12-31'}

    Epoch 1/10
2401/2401 - 21s - loss: 0.9847 - mse: 0.9847 - val_loss: 0.9809 - val_mse: 0.9809
Epoch 2/10
2401/2401 - 12s - loss: 0.9770 - mse: 0.9770 - val_loss: 0.9754 - val_mse: 0.9754
Epoch 3/10
2401/2401 - 12s - loss: 0.9724 - mse: 0.9724 - val_loss: 0.9714 - val_mse: 0.9714
Epoch 4/10
2401/2401 - 11s - loss: 0.9685 - mse: 0.9685 - val_loss: 0.9690 - val_mse: 0.9690
Epoch 5/10
2401/2401 - 13s - loss: 0.9649 - mse: 0.9649 - val_loss: 0.9674 - val_mse: 0.9674
Epoch 6/10
2401/2401 - 12s - loss: 0.9618 - mse: 0.9618 - val_loss: 0.9641 - val_mse: 0.9641
Epoch 7/10
2401/2401 - 12s - loss: 0.9590 - mse: 0.9590 - val_loss: 0.9627 - val_mse: 0.9627
Epoch 8/10
2401/2401 - 11s - loss: 0.9562 - mse: 0.9562 - val_loss: 0.9619 - val_mse: 0.9619
Epoch 9/10
2401/2401 - 11s - loss: 0.9540 - mse: 0.9540 - val_loss: 0.9614 - val_mse: 0.9614
Epoch 10/10
2401/2401 - 11s - loss: 0.9515 - mse: 0.9515 - val_loss: 0.9597 - val_mse: 0.9597

    867/867 - 3s
DataSource(b92d4cf44307411cbfd71ad8884bacbaT)
    • 收益率16.04%
    • 年化收益率16.61%
    • 基准收益率36.07%
    • 阿尔法-0.1
    • 贝塔0.84
    • 夏普比率0.65
    • 胜率0.54
    • 盈亏比1.04
    • 收益波动率23.05%
    • 信息比率-0.06
    • 最大回撤27.32%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-9fef1d4985bd4853af364e64b675a043"}/bigcharts-data-end
    {'m1.start_date': '2016-01-01', 'm1.end_date': '2019-12-31', 'm9.start_date': '2020-01-01', 'm9.end_date': '2020-12-31'}

    Epoch 1/10
2681/2681 - 44s - loss: 0.9866 - mse: 0.9866 - val_loss: 0.9841 - val_mse: 0.9841
Epoch 2/10
2681/2681 - 20s - loss: 0.9807 - mse: 0.9807 - val_loss: 0.9815 - val_mse: 0.9815
Epoch 3/10
2681/2681 - 22s - loss: 0.9773 - mse: 0.9773 - val_loss: 0.9785 - val_mse: 0.9785
Epoch 4/10
2681/2681 - 22s - loss: 0.9742 - mse: 0.9742 - val_loss: 0.9768 - val_mse: 0.9768
Epoch 5/10
2681/2681 - 23s - loss: 0.9713 - mse: 0.9713 - val_loss: 0.9735 - val_mse: 0.9735
Epoch 6/10
2681/2681 - 19s - loss: 0.9687 - mse: 0.9687 - val_loss: 0.9730 - val_mse: 0.9730
Epoch 7/10
2681/2681 - 22s - loss: 0.9660 - mse: 0.9660 - val_loss: 0.9710 - val_mse: 0.9710
Epoch 8/10
2681/2681 - 20s - loss: 0.9635 - mse: 0.9635 - val_loss: 0.9710 - val_mse: 0.9710
Epoch 9/10
2681/2681 - 24s - loss: 0.9615 - mse: 0.9615 - val_loss: 0.9703 - val_mse: 0.9703
Epoch 10/10
2681/2681 - 24s - loss: 0.9593 - mse: 0.9593 - val_loss: 0.9698 - val_mse: 0.9698

    933/933 - 6s
DataSource(213018c699934fe4ab54fedffe3eceb6T)
    • 收益率42.56%
    • 年化收益率44.44%
    • 基准收益率27.21%
    • 阿尔法0.15
    • 贝塔0.96
    • 夏普比率1.32
    • 胜率0.51
    • 盈亏比1.29
    • 收益波动率28.68%
    • 信息比率0.05
    • 最大回撤11.96%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-ac2839f1b76e4dc38547d4e54c8eebc3"}/bigcharts-data-end
    {'m1.start_date': '2017-01-01', 'm1.end_date': '2020-12-31', 'm9.start_date': '2021-01-01', 'm9.end_date': '2021-12-31'}

    Epoch 1/10
2944/2944 - 24s - loss: 0.9879 - mse: 0.9879 - val_loss: 0.9807 - val_mse: 0.9807
Epoch 2/10
2944/2944 - 14s - loss: 0.9825 - mse: 0.9825 - val_loss: 0.9771 - val_mse: 0.9771
Epoch 3/10
2944/2944 - 13s - loss: 0.9791 - mse: 0.9791 - val_loss: 0.9741 - val_mse: 0.9741
Epoch 4/10
2944/2944 - 16s - loss: 0.9762 - mse: 0.9762 - val_loss: 0.9730 - val_mse: 0.9730
Epoch 5/10
2944/2944 - 14s - loss: 0.9738 - mse: 0.9738 - val_loss: 0.9716 - val_mse: 0.9716
Epoch 6/10
2944/2944 - 14s - loss: 0.9713 - mse: 0.9713 - val_loss: 0.9705 - val_mse: 0.9705
Epoch 7/10
2944/2944 - 14s - loss: 0.9689 - mse: 0.9689 - val_loss: 0.9682 - val_mse: 0.9682
Epoch 8/10
2944/2944 - 15s - loss: 0.9667 - mse: 0.9667 - val_loss: 0.9688 - val_mse: 0.9688
Epoch 9/10
2944/2944 - 13s - loss: 0.9646 - mse: 0.9646 - val_loss: 0.9670 - val_mse: 0.9670
Epoch 10/10
2944/2944 - 15s - loss: 0.9628 - mse: 0.9628 - val_loss: 0.9675 - val_mse: 0.9675

    1050/1050 - 3s
DataSource(f5ae613a18ac4b84a0a6b373345a9112T)
    • 收益率46.38%
    • 年化收益率48.46%
    • 基准收益率-5.2%
    • 阿尔法0.52
    • 贝塔0.26
    • 夏普比率1.49
    • 胜率0.48
    • 盈亏比1.44
    • 收益波动率26.98%
    • 信息比率0.1
    • 最大回撤18.13%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-cc8d5caad41348cdb6c2535b66073258"}/bigcharts-data-end
    In [20]:
    df = pd.DataFrame() 
for i in range(len(m29.result)):
    tmp = m29.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': return_ratio,
      'annual_return_ratio': annual_return_ratio,
      'beta': beta,
      'alpha': alpha,
      'sharp_ratio': sharp_ratio,
      'return_volatility': return_volatility,
      'max_drawdown': max_drawdown,
      '收益回测比': abs(annual_return_ratio / max_drawdown)
    }
d=get_stats(df['returns'], df['benchmark_period_return'])
df1=pd.DataFrame.from_dict(d,orient='index')
df1.T
    Out[20]:
    return_ratio annual_return_ratio beta alpha sharp_ratio return_volatility max_drawdown 收益回测比
    0 17.50279 0.539212 0.519747 0.59379 1.383448 0.32508 -0.511487 1.054205
    In [21]:
    T.plot((df['returns']+1).cumprod())
    In [ ]: