【专题研究】基于LSTM模型的智能选股策略

机器学习
策略分享
lstm
专题报告
标签: #<Tag:0x00007f4cd38a7218> #<Tag:0x00007f4cd38a70d8> #<Tag:0x00007f4cd38a6f98> #<Tag:0x00007f4cd38a6e58>

(iQuant) #1

这是本系列专题研究的第五篇:基于长短期记忆网络LSTM的深度学习因子选股模型。LSTM作为改进的RNN(循环神经网络),是一种非常成熟的能够处理变化的序列数据的神经网络。此算法在keras, tensorflow上都有可以直接调用的api,在BigQuant平台中也有封装好的可视化模块。本文首先大致介绍了RNN和LSTM的原理,然后以一个可视化实例展示LSTM模型在因子选股方面的应用。


$$目录$$
1、LSTM原理介绍
1.1 什么是RNN
1.2 什么是LSTM
1.3 LSTM V.S. RNN
1.4 LSTM的单元结构
1.5 LSTM小结
2、实例:LSTM模型选股


1、LSTM原理介绍

1.1 什么是RNN

RNN,顾名思义,是包含循环的神经网络。它与传统神经网络模型最大不同之处是加入了对时序数据的处理。以股票多因子为例,传统神经网络在某一时间截面的输入因子数据,输出下期超额收益预测;而RNN是将某支股票的长期因子数据作为时间序列,取过去一段时间内的数据作为输入值。资本市场的信息有着一定持久性,使用RNN可以充分把握“历史重演”的机会。

如图表1 左侧所示,RNN读取某个输入$x$,并输出一个值$o$,循环可以使得信息从当前步传递到下一步。从表面看,这样的网络结构较难理解,因此将其展开为图表1 右侧。对于从序列索引1 到T 的时间序列数据,如果关注$t $时刻附近的网络结构,$𝑥_𝑡$代表了在序列索引号t 时刻训练样本的输入,同理$𝑥_{𝑡−1}$和$𝑥_{𝑡+1}$代表了在序列索引号$t-1$ 时刻和$t+1$ 时刻训练样本的输入;$ℎ_𝑡$代表在t 时刻模型的隐藏状态,不仅由$𝑥_𝑡$决定,也受到$h_{𝑡−1}$的影响;$𝑜_𝑡$代表在t 时刻模型的输出,$𝑜_𝑡$只由模型当前的隐藏状态$ℎ_𝑡$决定;$𝑦_𝑡$是$t$ 时刻样本序列的真实值;$𝐿_𝑡$是$t$ 时刻模型的损失函数,通过$𝑜_𝑡$和$y_𝑡$计算得出;$U$、$V$、$W$ 这三个矩阵是模型的参数,它们在整个模型中是共享的。

RNN 模型本质上也是采用BP(Back Propagation)算法进行权值和阈值的调整优化,只是增加了时间序列,叫做BPTT(Back Propagation Through Time)。公式如下:
%E6%8D%95%E8%8E%B7

其中$C_t$表示$t$时刻模型输出与真实值之间的交叉熵。对于上述公式中,如果$\sigma$为sigmoid 函数或者 tanh 函数,根据$\delta$的递推式,当时间跨度较大时,$\delta$就会很小,从而使 BP 的梯度很小,产生“梯度消失”。

另外,对于参数$W_{hh}$:由于RNN 中$W_{hh}$在每个时刻都是指的相同参数,所以$\delta$中会出现$W_{hh}$的累乘。而多次累乘后,数值的分布有明显的趋势:要么趋近于0,要么趋近于绝对值很大的值。而这两种情况,就很可能会分别造成“梯度消失”和“梯度爆炸”。

1.2 什么是LSTM

传统RNN 模型容易产生梯度消失的问题,难以处理长序列的数据。因此Hochreater 和Schmidhuber 在1997 年提出了长短期记忆网络LSTM,通过用精心设计的隐藏层神经元缓解了传统RNN的梯度消失问题。

1.3 LSTM V.S. RNN

在RNN 模型中,在每个序列索引位置都有一个隐藏状态$ℎ_𝑡$,如果我们略去每层都有的$o_𝑡$,$𝑦_𝑡$和 $𝐿_𝑡$,那么模型可以简化为如图表4 的形式,通过线条指示的路径可以清晰地看出隐藏状态$ℎ_𝑡$由$ℎ_{𝑡−1}$和$𝑥_𝑡$共同决定。$ℎ_𝑡$将一方面用于计算当前层模型的损失,另一方面用于计算下一层的$ℎ_{𝑡+1}$。

LSTM 模型中,每个序列索引位置$t$时刻被向前传播的,除了和RNN 一样的隐藏状态$ℎ_𝑡$,还多了另一个隐藏状态,如图表6中的标黑横线。这个隐藏状态被我们称为细胞状态$𝐶_𝑡$(Cell State),细胞也就是LSTM的一个单元。$𝐶_𝑡$在LSTM 中实质上起到了RNN 中隐层状态$ℎ_𝑡$的作用。

1.4 LSTM的单元结构

除了细胞状态,LSTM的单元还有其他许多结构,这些结构一般称之为门控结构(Gate)。LSTM 模型在每个序列索引位置$t$的门控结构一般包括输入门(Input Gate), 输出门(Output Gate), 忘记门(Forget Gate):这三个 Gate 本质上就是权值,形象地说,类似电路中用于控制电流的开关。当值为1,表示开关闭合,流量无损耗流过;当值为0,表示开关打开,完全阻塞流量;当值介于(0,1),则表示流量通过的程度。而这种[0,1]的取值,其实就是通过激活函数实现的。

由上述的结构分析可知,LSTM 只能避免RNN 的“梯度消失”。“梯度膨胀”虽然不是个严重的问题,但它会导致参数会被修改的非常远离当前值,使得大量已完成的优化工作成为无用功。当然,“梯度膨胀”可以采用梯度裁剪(gradient clipping)来优化(如果梯度的范数大于某个给定值,将梯度同比收缩)。

1.5 LSTM小结

总结而言,LSTM内部主要有三个阶段:

  1. 忘记阶段。这个阶段主要是对上一个节点传进来的输入进行 选择性 忘记。简单来说就是会 “忘记不重要的,记住重要的”。通过忘记门进行判断。

  2. 选择记忆阶段。这个阶段将对输入有选择性地进行“记忆”。哪些重要则着重记录下来,哪些不重要,则少记一些。通过输入门控制。

  3. 输出阶段。将上面两步得到的结果相加,即可得到传输给下一个状态的$h_t$。这个阶段将决定哪些将会被当成当前状态的输出。主要是通过输出门控制。

2、实例:LSTM模型选股

LSTM的底层逻辑确实比较复杂,但是在实际使用中,只要能够理解其大致原理和关键参数,通过调用平台上的深度学习相关的各种可视化模块,便能省时省力地构建深度学习网络,从而将精力更多地放在策略逻辑优化上。下面,我们将以一个可视化实例展现如何通过LSTM模型进行选股。

如图所示,LSTM选股策略构建包含下列步骤:

  • 获取数据 :A股所有股票。
  • 特征和标签提取 :计算7个因子作为样本特征;计算5日个股收益率,极值处理。
  • 特征预处理 :进行缺失值处理;去掉特征异常的股票,比如某个特征值高于99.5%或低于0.5%的;标准化处理,去除特征量纲/数量级差异的影响。
  • 序列窗口滚动 :窗口大小设置为5,滚动切割。这里的意思是使用过去5天的因子数据作为输入。窗口大小可调整,在“序列窗口滚动”模块中进行。
  • 搭建LSTM模型 :构建两个隐含层的LSTM长短期记忆神经网络预测股票收益率(回归模型)。在可视化策略中表现为1个输入层;一个LSTM和一个全连接层作为隐藏层,每构建一层进行dropout断开一些神经元防止过拟合;最后一个全连接层作为输出层(输出维度调整为1)。
  • 模型训练与预测 :使用LSTM模型进行训练和预测;可以尝试多种激活函数,策略默认为tanh。
  • 策略回测 :利用2010到2016年数据进行训练,预测2016到2019年的股票表现。每日买入预测排名最靠前的30只股票,至少持有5日,同时淘汰排名靠后的股票。具体而言,预测排名越靠前,分配到的资金越多且最大资金占用比例不超过20%;初始5日平均分配资金,之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)。
  • 模型评价 :查看模型回测结果。

LSTM模型的参数如下:

  • 输入数据:7个因子,使用了过去5天的因子数据,因此输入7*5的一个矩阵。
    %E8%BE%93%E5%85%A5

  • LSTM层:激活函数采用tanh,recurrent激活函数采用hard_sigmoid。循环核初始化方法Orthogonal,权值使用glorot_uniform初始化方法,偏置向量使用Zeros初始化方法。

  • 全连接层:激活函数tanh。权重使用glorot_uniform初始化方法,偏置向量使用Zeros初始化方法。

  • 输出层:最后一个全连接层。需要选择“输出空间维度”为1,因为要得到个股的收益率预测结果,这是一个值。
    %E8%BE%93%E5%87%BA

  • 随机断开输入神经元比例dropout:0.2。在不同隐藏层之间使用dropout可以让网络更耐用并且避免过拟合

  • 训练次数率:epochs值为5,共训练5轮,以mae作为评估指标。

  • 优化器:RMSProp。

  • 损失函数:均方误差MSE。

预测个股下五日的收益率,排序后得到结果如下:
%E9%A2%84%E6%B5%8B

回测结果如下:

可以看到,LSTM的回测结果比较突出,相比于基准收益有着非常突出的表现。在本次的策略中,我们运用了两层的LSTM模型,具体的循环层数、模型参数有非常大的调整空间,欢迎大家尝试。

克隆策略

策略简介

因子:样例因子(7个)

因子是否标准化:是

标注:未来5日收益(不做离散化)

算法:LSTM

类型:回归问题

训练集:10-16年

测试集:16-19年

选股依据:根据预测值降序排序买入

持股数:30

持仓天数:5

    {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-106:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-773:input_1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"-106:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-113:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-122:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-129:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-768:input_2","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-778:input_2","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-243:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-251:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-3895:input_2","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-3907:input_2","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-243:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-122:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-141:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-113:input_data","SourceOutputPortId":"-106:data"},{"DestinationInputPortId":"-768:input_1","SourceOutputPortId":"-113:data"},{"DestinationInputPortId":"-129:input_data","SourceOutputPortId":"-122:data"},{"DestinationInputPortId":"-2431:input_2","SourceOutputPortId":"-129:data"},{"DestinationInputPortId":"-778:input_1","SourceOutputPortId":"-129:data"},{"DestinationInputPortId":"-3880:inputs","SourceOutputPortId":"-160:data"},{"DestinationInputPortId":"-356:inputs","SourceOutputPortId":"-160:data"},{"DestinationInputPortId":"-1540:trained_model","SourceOutputPortId":"-1098:data"},{"DestinationInputPortId":"-2431:input_1","SourceOutputPortId":"-1540:data"},{"DestinationInputPortId":"-141:options_data","SourceOutputPortId":"-2431:data_1"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-768:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"-773:data"},{"DestinationInputPortId":"-251:input_data","SourceOutputPortId":"-778:data"},{"DestinationInputPortId":"-3895:input_1","SourceOutputPortId":"-243:data"},{"DestinationInputPortId":"-3907:input_1","SourceOutputPortId":"-251:data"},{"DestinationInputPortId":"-1098:input_model","SourceOutputPortId":"-3880:data"},{"DestinationInputPortId":"-1098:training_data","SourceOutputPortId":"-3895:data_1"},{"DestinationInputPortId":"-1540:input_data","SourceOutputPortId":"-3907:data_1"},{"DestinationInputPortId":"-567:inputs","SourceOutputPortId":"-356:data"},{"DestinationInputPortId":"-412:inputs","SourceOutputPortId":"-567:data"},{"DestinationInputPortId":"-574:inputs","SourceOutputPortId":"-412:data"},{"DestinationInputPortId":"-440:inputs","SourceOutputPortId":"-574:data"},{"DestinationInputPortId":"-3880:outputs","SourceOutputPortId":"-440:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2016-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":" ","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","ModuleId":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","ModuleParameters":[{"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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na_label","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"cast_label_int","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"close_0/mean(close_0,5)\nclose_0/mean(close_0,10)\nclose_0/mean(close_0,20)\nclose_0/open_0\nopen_0/mean(close_0,5)\nopen_0/mean(close_0,10)\nopen_0/mean(close_0,20)","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2016-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2019-04-16","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"Id":"-106","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":"30","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-106"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-106"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-106","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"Comment":"","CommentCollapsed":true},{"Id":"-113","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-113"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-113"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-113","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"Comment":"","CommentCollapsed":true},{"Id":"-122","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":"30","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-122"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-122"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-122","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"Comment":"","CommentCollapsed":true},{"Id":"-129","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-129"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-129"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-129","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"Comment":"","CommentCollapsed":true},{"Id":"-141","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":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 = 30\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 = 0.9\n context.options['hold_days'] = 5","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"prepare","Value":"# 回测引擎:准备数据,只执行一次\ndef bigquant_run(context):\n pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":0.025,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"close","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"capital_base","Value":1000000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"股票","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-141"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-141"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-141"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-141"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-141"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-141","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":19,"Comment":"","CommentCollapsed":true},{"Id":"-160","ModuleId":"BigQuantSpace.dl_layer_input.dl_layer_input-v1","ModuleParameters":[{"Name":"shape","Value":"7,5","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"batch_shape","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"dtype","Value":"float32","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sparse","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"name","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"inputs","NodeId":"-160"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-160","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":6,"Comment":"","CommentCollapsed":true},{"Id":"-1098","ModuleId":"BigQuantSpace.dl_model_train.dl_model_train-v1","ModuleParameters":[{"Name":"optimizer","Value":"RMSprop","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_optimizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"loss","Value":"mean_squared_error","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_loss","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"metrics","Value":"mae","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"batch_size","Value":"256","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"epochs","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"n_gpus","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"verbose","Value":"2:每个epoch输出一行记录","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_model","NodeId":"-1098"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_data","NodeId":"-1098"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"validation_data","NodeId":"-1098"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-1098","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"Comment":"","CommentCollapsed":true},{"Id":"-1540","ModuleId":"BigQuantSpace.dl_model_predict.dl_model_predict-v1","ModuleParameters":[{"Name":"batch_size","Value":"1024","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"n_gpus","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"verbose","Value":"2:每个epoch输出一行记录","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trained_model","NodeId":"-1540"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-1540"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-1540","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"Comment":"","CommentCollapsed":true},{"Id":"-2431","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"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","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-2431"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-2431"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-2431"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-2431","OutputType":null},{"Name":"data_2","NodeId":"-2431","OutputType":null},{"Name":"data_3","NodeId":"-2431","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":24,"Comment":"","CommentCollapsed":true},{"Id":"-768","ModuleId":"BigQuantSpace.standardlize.standardlize-v8","ModuleParameters":[{"Name":"columns_input","Value":"[]","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-768"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-768"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-768","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"Comment":"","CommentCollapsed":true},{"Id":"-773","ModuleId":"BigQuantSpace.standardlize.standardlize-v8","ModuleParameters":[{"Name":"columns_input","Value":"label","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-773"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-773"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-773","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":13,"Comment":"","CommentCollapsed":true},{"Id":"-778","ModuleId":"BigQuantSpace.standardlize.standardlize-v8","ModuleParameters":[{"Name":"columns_input","Value":"[]","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-778"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-778"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-778","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":25,"Comment":"","CommentCollapsed":true},{"Id":"-243","ModuleId":"BigQuantSpace.dl_convert_to_bin.dl_convert_to_bin-v2","ModuleParameters":[{"Name":"window_size","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_clip","Value":5,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"flatten","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"window_along_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-243"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-243"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-243","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":26,"Comment":"","CommentCollapsed":true},{"Id":"-251","ModuleId":"BigQuantSpace.dl_convert_to_bin.dl_convert_to_bin-v2","ModuleParameters":[{"Name":"window_size","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_clip","Value":5,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"flatten","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"window_along_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-251"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-251"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-251","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":27,"Comment":"","CommentCollapsed":true},{"Id":"-3880","ModuleId":"BigQuantSpace.dl_model_init.dl_model_init-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"inputs","NodeId":"-3880"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"outputs","NodeId":"-3880"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-3880","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":34,"Comment":"","CommentCollapsed":true},{"Id":"-3895","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"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 df = input_1.read_pickle()\n feature_len = len(input_2.read_pickle())\n \n \n df['x'] = df['x'].reshape(df['x'].shape[0], int(feature_len), int(df['x'].shape[1]/feature_len))\n \n data_1 = DataSource.write_pickle(df)\n return Outputs(data_1=data_1)\n","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-3895"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-3895"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-3895"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-3895","OutputType":null},{"Name":"data_2","NodeId":"-3895","OutputType":null},{"Name":"data_3","NodeId":"-3895","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"Comment":"","CommentCollapsed":true},{"Id":"-3907","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"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 df = input_1.read_pickle()\n feature_len = len(input_2.read_pickle())\n \n \n df['x'] = df['x'].reshape(df['x'].shape[0], int(feature_len), int(df['x'].shape[1]/feature_len))\n \n data_1 = DataSource.write_pickle(df)\n return Outputs(data_1=data_1)\n","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-3907"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-3907"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-3907"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-3907","OutputType":null},{"Name":"data_2","NodeId":"-3907","OutputType":null},{"Name":"data_3","NodeId":"-3907","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"Comment":"","CommentCollapsed":true},{"Id":"-356","ModuleId":"BigQuantSpace.dl_layer_lstm.dl_layer_lstm-v1","ModuleParameters":[{"Name":"units","Value":"32","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activation","Value":"tanh","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_activation","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"recurrent_activation","Value":"hard_sigmoid","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_recurrent_activation","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"use_bias","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_initializer","Value":"glorot_uniform","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_initializer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"recurrent_initializer","Value":"Orthogonal","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_recurrent_initializer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_initializer","Value":"Zeros","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_initializer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"unit_forget_bias","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"recurrent_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"recurrent_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"recurrent_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_recurrent_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_activity_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_constraint","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_constraint","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"recurrent_constraint","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_recurrent_constraint","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_constraint","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_constraint","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"dropout","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"recurrent_dropout","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"return_sequences","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"implementation","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"name","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"inputs","NodeId":"-356"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-356","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":10,"Comment":"","CommentCollapsed":true},{"Id":"-567","ModuleId":"BigQuantSpace.dl_layer_dropout.dl_layer_dropout-v1","ModuleParameters":[{"Name":"rate","Value":"0.2","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"noise_shape","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"seed","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"name","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"inputs","NodeId":"-567"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-567","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":12,"Comment":"","CommentCollapsed":true},{"Id":"-412","ModuleId":"BigQuantSpace.dl_layer_dense.dl_layer_dense-v1","ModuleParameters":[{"Name":"units","Value":"30","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activation","Value":"tanh","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_activation","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"use_bias","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_initializer","Value":"glorot_uniform","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_initializer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_initializer","Value":"Zeros","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_initializer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_activity_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_constraint","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_constraint","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_constraint","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_constraint","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"name","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"inputs","NodeId":"-412"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-412","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":20,"Comment":"","CommentCollapsed":true},{"Id":"-574","ModuleId":"BigQuantSpace.dl_layer_dropout.dl_layer_dropout-v1","ModuleParameters":[{"Name":"rate","Value":"0.2","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"noise_shape","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"seed","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"name","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"inputs","NodeId":"-574"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-574","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":21,"Comment":"","CommentCollapsed":true},{"Id":"-440","ModuleId":"BigQuantSpace.dl_layer_dense.dl_layer_dense-v1","ModuleParameters":[{"Name":"units","Value":"1","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activation","Value":"tanh","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_activation","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"use_bias","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_initializer","Value":"glorot_uniform","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_initializer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_initializer","Value":"Zeros","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_initializer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer_l1","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"activity_regularizer_l2","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_activity_regularizer","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"kernel_constraint","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_kernel_constraint","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bias_constraint","Value":"None","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_bias_constraint","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"name","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"inputs","NodeId":"-440"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-440","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":22,"Comment":"","CommentCollapsed":true}],"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='394,23,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='208,220,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='757,-113,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='379,435,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1074,139,200,200'/><NodePosition Node='-106' Position='547,173,200,200'/><NodePosition Node='-113' Position='548,275,200,200'/><NodePosition Node='-122' Position='1078,236,200,200'/><NodePosition Node='-129' Position='1081,327,200,200'/><NodePosition Node='-141' Position='568,1031,200,200'/><NodePosition Node='-160' Position='-279,-153,200,200'/><NodePosition Node='-1098' Position='137,642,200,200'/><NodePosition Node='-1540' Position='203,733,200,200'/><NodePosition Node='-2431' Position='345,826,200,200'/><NodePosition Node='-768' Position='683,355,200,200'/><NodePosition Node='-773' Position='200,329,200,200'/><NodePosition Node='-778' Position='1067,432,200,200'/><NodePosition Node='-243' Position='381,513,200,200'/><NodePosition Node='-251' Position='1061,508,200,200'/><NodePosition Node='-3880' Position='-135,516,200,200'/><NodePosition Node='-3895' Position='385,585,200,200'/><NodePosition Node='-3907' Position='1056,590,200,200'/><NodePosition Node='-356' Position='-281,-31,200,200'/><NodePosition Node='-567' Position='-279,65,200,200'/><NodePosition Node='-412' Position='-277,154,200,200'/><NodePosition Node='-574' Position='-276,242,200,200'/><NodePosition Node='-440' Position='-280,332,200,200'/></NodePositions><NodeGroups /></DataV1>"},"IsDraft":true,"ParentExperimentId":null,"WebService":{"IsWebServiceExperiment":false,"Inputs":[],"Outputs":[],"Parameters":[{"Name":"交易日期","Value":"","ParameterDefinition":{"Name":"交易日期","FriendlyName":"交易日期","DefaultValue":"","ParameterType":"String","HasDefaultValue":true,"IsOptional":true,"ParameterRules":[],"HasRules":false,"MarkupType":0,"CredentialDescriptor":null}}],"WebServiceGroupId":null,"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions></NodePositions><NodeGroups /></DataV1>"},"DisableNodesUpdate":false,"Category":"user","Tags":[],"IsPartialRun":true}
    In [1]:
    # 本代码由可视化策略环境自动生成 2019年8月28日 11:39
    # 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 m4_run_bigquant_run(input_1, input_2, input_3):
        # 示例代码如下。在这里编写您的代码
        df =  input_1.read_pickle()
        feature_len = len(input_2.read_pickle())
        
        
        df['x'] = df['x'].reshape(df['x'].shape[0], int(feature_len), int(df['x'].shape[1]/feature_len))
        
        data_1 = DataSource.write_pickle(df)
        return Outputs(data_1=data_1)
    
    # 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 m4_post_run_bigquant_run(outputs):
        return outputs
    
    # 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 m8_run_bigquant_run(input_1, input_2, input_3):
        # 示例代码如下。在这里编写您的代码
        df =  input_1.read_pickle()
        feature_len = len(input_2.read_pickle())
        
        
        df['x'] = df['x'].reshape(df['x'].shape[0], int(feature_len), int(df['x'].shape[1]/feature_len))
        
        data_1 = DataSource.write_pickle(df)
        return Outputs(data_1=data_1)
    
    # 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 m8_post_run_bigquant_run(outputs):
        return outputs
    
    # 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 = 30
        # 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 = 0.9
        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
    
    
    m1 = M.instruments.v2(
        start_date='2010-01-01',
        end_date='2016-01-01',
        market='CN_STOCK_A',
        instrument_list=' ',
        max_count=0
    )
    
    m2 = M.advanced_auto_labeler.v2(
        instruments=m1.data,
        label_expr="""# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/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)
    """,
        start_date='',
        end_date='',
        benchmark='000300.SHA',
        drop_na_label=True,
        cast_label_int=False
    )
    
    m13 = M.standardlize.v8(
        input_1=m2.data,
        columns_input='label'
    )
    
    m3 = M.input_features.v1(
        features="""close_0/mean(close_0,5)
    close_0/mean(close_0,10)
    close_0/mean(close_0,20)
    close_0/open_0
    open_0/mean(close_0,5)
    open_0/mean(close_0,10)
    open_0/mean(close_0,20)"""
    )
    
    m15 = M.general_feature_extractor.v7(
        instruments=m1.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=30
    )
    
    m16 = M.derived_feature_extractor.v3(
        input_data=m15.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=True,
        remove_extra_columns=False
    )
    
    m14 = M.standardlize.v8(
        input_1=m16.data,
        input_2=m3.data,
        columns_input='[]'
    )
    
    m7 = M.join.v3(
        data1=m13.data,
        data2=m14.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m26 = M.dl_convert_to_bin.v2(
        input_data=m7.data,
        features=m3.data,
        window_size=5,
        feature_clip=5,
        flatten=True,
        window_along_col='instrument'
    )
    
    m4 = M.cached.v3(
        input_1=m26.data,
        input_2=m3.data,
        run=m4_run_bigquant_run,
        post_run=m4_post_run_bigquant_run,
        input_ports='',
        params='{}',
        output_ports=''
    )
    
    m9 = M.instruments.v2(
        start_date=T.live_run_param('trading_date', '2016-01-01'),
        end_date=T.live_run_param('trading_date', '2019-04-16'),
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m17 = M.general_feature_extractor.v7(
        instruments=m9.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=30
    )
    
    m18 = M.derived_feature_extractor.v3(
        input_data=m17.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=True,
        remove_extra_columns=False
    )
    
    m25 = M.standardlize.v8(
        input_1=m18.data,
        input_2=m3.data,
        columns_input='[]'
    )
    
    m27 = M.dl_convert_to_bin.v2(
        input_data=m25.data,
        features=m3.data,
        window_size=5,
        feature_clip=5,
        flatten=True,
        window_along_col='instrument'
    )
    
    m8 = M.cached.v3(
        input_1=m27.data,
        input_2=m3.data,
        run=m8_run_bigquant_run,
        post_run=m8_post_run_bigquant_run,
        input_ports='',
        params='{}',
        output_ports=''
    )
    
    m6 = M.dl_layer_input.v1(
        shape='7,5',
        batch_shape='',
        dtype='float32',
        sparse=False,
        name=''
    )
    
    m10 = M.dl_layer_lstm.v1(
        inputs=m6.data,
        units=32,
        activation='tanh',
        recurrent_activation='hard_sigmoid',
        use_bias=True,
        kernel_initializer='glorot_uniform',
        recurrent_initializer='Orthogonal',
        bias_initializer='Zeros',
        unit_forget_bias=True,
        kernel_regularizer='None',
        kernel_regularizer_l1=0,
        kernel_regularizer_l2=0,
        recurrent_regularizer='None',
        recurrent_regularizer_l1=0,
        recurrent_regularizer_l2=0,
        bias_regularizer='None',
        bias_regularizer_l1=0,
        bias_regularizer_l2=0,
        activity_regularizer='None',
        activity_regularizer_l1=0,
        activity_regularizer_l2=0,
        kernel_constraint='None',
        recurrent_constraint='None',
        bias_constraint='None',
        dropout=0,
        recurrent_dropout=0,
        return_sequences=False,
        implementation='0',
        name=''
    )
    
    m12 = M.dl_layer_dropout.v1(
        inputs=m10.data,
        rate=0.2,
        noise_shape='',
        name=''
    )
    
    m20 = M.dl_layer_dense.v1(
        inputs=m12.data,
        units=30,
        activation='tanh',
        use_bias=True,
        kernel_initializer='glorot_uniform',
        bias_initializer='Zeros',
        kernel_regularizer='None',
        kernel_regularizer_l1=0,
        kernel_regularizer_l2=0,
        bias_regularizer='None',
        bias_regularizer_l1=0,
        bias_regularizer_l2=0,
        activity_regularizer='None',
        activity_regularizer_l1=0,
        activity_regularizer_l2=0,
        kernel_constraint='None',
        bias_constraint='None',
        name=''
    )
    
    m21 = M.dl_layer_dropout.v1(
        inputs=m20.data,
        rate=0.2,
        noise_shape='',
        name=''
    )
    
    m22 = M.dl_layer_dense.v1(
        inputs=m21.data,
        units=1,
        activation='tanh',
        use_bias=True,
        kernel_initializer='glorot_uniform',
        bias_initializer='Zeros',
        kernel_regularizer='None',
        kernel_regularizer_l1=0,
        kernel_regularizer_l2=0,
        bias_regularizer='None',
        bias_regularizer_l1=0,
        bias_regularizer_l2=0,
        activity_regularizer='None',
        activity_regularizer_l1=0,
        activity_regularizer_l2=0,
        kernel_constraint='None',
        bias_constraint='None',
        name=''
    )
    
    m34 = M.dl_model_init.v1(
        inputs=m6.data,
        outputs=m22.data
    )
    
    m5 = M.dl_model_train.v1(
        input_model=m34.data,
        training_data=m4.data_1,
        optimizer='RMSprop',
        loss='mean_squared_error',
        metrics='mae',
        batch_size=256,
        epochs=5,
        n_gpus=0,
        verbose='2:每个epoch输出一行记录'
    )
    
    m11 = M.dl_model_predict.v1(
        trained_model=m5.data,
        input_data=m8.data_1,
        batch_size=1024,
        n_gpus=0,
        verbose='2:每个epoch输出一行记录'
    )
    
    m24 = M.cached.v3(
        input_1=m11.data,
        input_2=m18.data,
        run=m24_run_bigquant_run,
        post_run=m24_post_run_bigquant_run,
        input_ports='',
        params='{}',
        output_ports=''
    )
    
    m19 = M.trade.v4(
        instruments=m9.data,
        options_data=m24.data_1,
        start_date='',
        end_date='',
        initialize=m19_initialize_bigquant_run,
        handle_data=m19_handle_data_bigquant_run,
        prepare=m19_prepare_bigquant_run,
        volume_limit=0.025,
        order_price_field_buy='open',
        order_price_field_sell='close',
        capital_base=1000000,
        auto_cancel_non_tradable_orders=True,
        data_frequency='daily',
        price_type='后复权',
        product_type='股票',
        plot_charts=True,
        backtest_only=False,
        benchmark='000300.SHA'
    )
    
    Using TensorFlow backend.
    
    Epoch 1/5
     - 281s - loss: 0.9905 - mean_absolute_error: 0.7246
    Epoch 2/5
     - 264s - loss: 0.9885 - mean_absolute_error: 0.7238
    Epoch 3/5
     - 291s - loss: 0.9874 - mean_absolute_error: 0.7232
    Epoch 4/5
     - 280s - loss: 0.9867 - mean_absolute_error: 0.7229
    Epoch 5/5
     - 268s - loss: 0.9862 - mean_absolute_error: 0.7227
    
    DataSource(180333cae60f45d087bff20434a1df53T, v3)
    
    • 收益率139.61%
    • 年化收益率31.69%
    • 基准收益率9.51%
    • 阿尔法0.28
    • 贝塔1.01
    • 夏普比率0.95
    • 胜率0.6
    • 盈亏比0.87
    • 收益波动率31.15%
    • 信息比率0.07
    • 最大回撤34.37%
    bigcharts-data-start/{"__id":"bigchart-f27ea542ae0b4e72b0c0a941cd4485b8","__type":"tabs"}/bigcharts-data-end

    参考文献

    • 华泰证券 《人工智能选股之循环神经网络》2018-12-13
    • 国信证券 《递归神经网络RNN——长短期记忆细胞LSTM的分行业多因子预测》2018-12-28
    • 知乎《人人都能看懂的LSTM

    (oversky2003) #2

    之前还运行正常的,今天再跑报错

    TypeError Traceback (most recent call last)
    in ()
    142 m13 = M.standardlize.v8(
    143 input_1=m2.data,
    –> 144 columns_input=’[‘label’]’
    145 )
    146

    TypeError: bigquant_run() takes at least 1 positional argument (0 given)


    (iQuant) #3

    收到,我们来看下哈


    (达达) #4

    模块升级,原来的标准化模块代码框的方括号去掉了

    https://i.bigquant.com/user/qhdxlgd/lab/share/LSTM-AI%E9%80%89%E8%82%A1-demo%20-Clone2.ipynb