克隆策略

TabNet量化选股策略¶

策略思想¶

根据TabNet的预测结果，选择20支股票买入进行持有，每5日换仓。

In [13]:

# 本代码由可视化策略环境自动生成 2021年9月23日 14:19
# 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=0.2)
    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

import tensorflow as tf
from tensorflow.keras.layers import Layer

def glu(x, n_units=None):
    """Generalized linear unit nonlinear activation."""
    if n_units is None:
        n_units = tf.shape(x)[-1] // 2

    return x[..., :n_units] * tf.nn.sigmoid(x[..., n_units:])


def sparsemax(logits, axis):
    logits = tf.convert_to_tensor(logits, name="logits")

    # We need its original shape for shape inference.
    shape = logits.get_shape()
    rank = shape.rank
    is_last_axis = (axis == -1) or (axis == rank - 1)

    if is_last_axis:
        output = _compute_2d_sparsemax(logits)
        output.set_shape(shape)
        return output

    # Swap logits' dimension of dim and its last dimension.
    rank_op = tf.rank(logits)
    axis_norm = axis % rank
    logits = _swap_axis(logits, axis_norm, tf.math.subtract(rank_op, 1))

    # Do the actual softmax on its last dimension.
    output = _compute_2d_sparsemax(logits)
    output = _swap_axis(output, axis_norm, tf.math.subtract(rank_op, 1))

    # Make shape inference work since transpose may erase its static shape.
    output.set_shape(shape)
    return output


def _swap_axis(logits, dim_index, last_index, **kwargs):
    return tf.transpose(
        logits,
        tf.concat(
            [
                tf.range(dim_index),
                [last_index],
                tf.range(dim_index + 1, last_index),
                [dim_index],
            ],
            0,
        ),
        **kwargs,
    )


def _compute_2d_sparsemax(logits):
    """Performs the sparsemax operation when axis=-1."""
    shape_op = tf.shape(logits)
    obs = tf.math.reduce_prod(shape_op[:-1])
    dims = shape_op[-1]

    # In the paper, they call the logits z.
    # The mean(logits) can be substracted from logits to make the algorithm
    # more numerically stable. the instability in this algorithm comes mostly
    # from the z_cumsum. Substacting the mean will cause z_cumsum to be close
    # to zero. However, in practise the numerical instability issues are very
    # minor and substacting the mean causes extra issues with inf and nan
    # input.
    # Reshape to [obs, dims] as it is almost free and means the remanining
    # code doesn't need to worry about the rank.
    z = tf.reshape(logits, [obs, dims])

    # sort z
    z_sorted, _ = tf.nn.top_k(z, k=dims)

    # calculate k(z)
    z_cumsum = tf.math.cumsum(z_sorted, axis=-1)
    k = tf.range(1, tf.cast(dims, logits.dtype) + 1) #, dtype=logits.dtype)
    z_check = 1 + k * z_sorted > z_cumsum
    # because the z_check vector is always [1,1,...1,0,0,...0] finding the
    # (index + 1) of the last `1` is the same as just summing the number of 1.
    k_z = tf.math.reduce_sum(tf.cast(z_check, tf.int32), axis=-1)

    # calculate tau(z)
    # If there are inf values or all values are -inf, the k_z will be zero,
    # this is mathematically invalid and will also cause the gather_nd to fail.
    # Prevent this issue for now by setting k_z = 1 if k_z = 0, this is then
    # fixed later (see p_safe) by returning p = nan. This results in the same
    # behavior as softmax.
    k_z_safe = tf.math.maximum(k_z, 1)
    indices = tf.stack([tf.range(0, obs), tf.reshape(k_z_safe, [-1]) - 1], axis=1)
    tau_sum = tf.gather_nd(z_cumsum, indices)
    tau_z = (tau_sum - 1) / tf.cast(k_z, logits.dtype)

    # calculate p
    p = tf.math.maximum(tf.cast(0, logits.dtype), z - tf.expand_dims(tau_z, -1))
    # If k_z = 0 or if z = nan, then the input is invalid
    p_safe = tf.where(
        tf.expand_dims(
            tf.math.logical_or(tf.math.equal(k_z, 0), tf.math.is_nan(z_cumsum[:, -1])),
            axis=-1,
        ),
        tf.fill([obs, dims], tf.cast(float("nan"), logits.dtype)),
        p,
    )

    # Reshape back to original size
    p_safe = tf.reshape(p_safe, shape_op)
    return p_safe


"""
Code replicated from https://github.com/tensorflow/addons/blob/master/tensorflow_addons/layers/normalizations.py
"""
class GroupNormalization(tf.keras.layers.Layer):
    def __init__(
            self,
            groups: int = 2,
            axis: int = -1,
            epsilon: float = 1e-3,
            center: bool = True,
            scale: bool = True,
            beta_initializer="zeros",
            gamma_initializer="ones",
            beta_regularizer=None,
            gamma_regularizer=None,
            beta_constraint=None,
            gamma_constraint=None,
            **kwargs
    ):
        super().__init__(**kwargs)
        self.supports_masking = True
        self.groups = groups
        self.axis = axis
        self.epsilon = epsilon
        self.center = center
        self.scale = scale
        self.beta_initializer = tf.keras.initializers.get(beta_initializer)
        self.gamma_initializer = tf.keras.initializers.get(gamma_initializer)
        self.beta_regularizer = tf.keras.regularizers.get(beta_regularizer)
        self.gamma_regularizer = tf.keras.regularizers.get(gamma_regularizer)
        self.beta_constraint = tf.keras.constraints.get(beta_constraint)
        self.gamma_constraint = tf.keras.constraints.get(gamma_constraint)
        self._check_axis()

    def build(self, input_shape):

        self._check_if_input_shape_is_none(input_shape)
        self._set_number_of_groups_for_instance_norm(input_shape)
        self._check_size_of_dimensions(input_shape)
        self._create_input_spec(input_shape)

        self._add_gamma_weight(input_shape)
        self._add_beta_weight(input_shape)
        self.built = True
        super().build(input_shape)

    def call(self, inputs, training=None):
        # Training=none is just for compat with batchnorm signature call
        input_shape = tf.keras.backend.int_shape(inputs)
        tensor_input_shape = tf.shape(inputs)

        reshaped_inputs, group_shape = self._reshape_into_groups(
            inputs, input_shape, tensor_input_shape
        )

        normalized_inputs = self._apply_normalization(reshaped_inputs, input_shape)

        outputs = tf.reshape(normalized_inputs, tensor_input_shape)

        return outputs

    def get_config(self):
        config = {
            "groups": self.groups,
            "axis": self.axis,
            "epsilon": self.epsilon,
            "center": self.center,
            "scale": self.scale,
            "beta_initializer": tf.keras.initializers.serialize(self.beta_initializer),
            "gamma_initializer": tf.keras.initializers.serialize(
                self.gamma_initializer
            ),
            "beta_regularizer": tf.keras.regularizers.serialize(self.beta_regularizer),
            "gamma_regularizer": tf.keras.regularizers.serialize(
                self.gamma_regularizer
            ),
            "beta_constraint": tf.keras.constraints.serialize(self.beta_constraint),
            "gamma_constraint": tf.keras.constraints.serialize(self.gamma_constraint),
        }
        base_config = super().get_config()
        return {**base_config, **config}

    def compute_output_shape(self, input_shape):
        return input_shape

    def _reshape_into_groups(self, inputs, input_shape, tensor_input_shape):

        group_shape = [tensor_input_shape[i] for i in range(len(input_shape))]
        group_shape[self.axis] = input_shape[self.axis] // self.groups
        group_shape.insert(self.axis, self.groups)
        group_shape = tf.stack(group_shape)
        reshaped_inputs = tf.reshape(inputs, group_shape)
        return reshaped_inputs, group_shape

    def _apply_normalization(self, reshaped_inputs, input_shape):

        group_shape = tf.keras.backend.int_shape(reshaped_inputs)
        group_reduction_axes = list(range(1, len(group_shape)))
        axis = -2 if self.axis == -1 else self.axis - 1
        group_reduction_axes.pop(axis)

        mean, variance = tf.nn.moments(
            reshaped_inputs, group_reduction_axes, keepdims=True
        )

        gamma, beta = self._get_reshaped_weights(input_shape)
        normalized_inputs = tf.nn.batch_normalization(
            reshaped_inputs,
            mean=mean,
            variance=variance,
            scale=gamma,
            offset=beta,
            variance_epsilon=self.epsilon,
        )
        return normalized_inputs

    def _get_reshaped_weights(self, input_shape):
        broadcast_shape = self._create_broadcast_shape(input_shape)
        gamma = None
        beta = None
        if self.scale:
            gamma = tf.reshape(self.gamma, broadcast_shape)

        if self.center:
            beta = tf.reshape(self.beta, broadcast_shape)
        return gamma, beta

    def _check_if_input_shape_is_none(self, input_shape):
        dim = input_shape[self.axis]
        if dim is None:
            raise ValueError(
                "Axis " + str(self.axis) + " of "
                                           "input tensor should have a defined dimension "
                                           "but the layer received an input with shape " + str(input_shape) + "."
            )

    def _set_number_of_groups_for_instance_norm(self, input_shape):
        dim = input_shape[self.axis]

        if self.groups == -1:
            self.groups = dim

    def _check_size_of_dimensions(self, input_shape):

        dim = input_shape[self.axis]
        if dim < self.groups:
            raise ValueError(
                "Number of groups (" + str(self.groups) + ") cannot be "
                                                          "more than the number of channels (" + str(dim) + ")."
            )

        if dim % self.groups != 0:
            raise ValueError(
                "Number of groups (" + str(self.groups) + ") must be a "
                                                          "multiple of the number of channels (" + str(dim) + ")."
            )

    def _check_axis(self):

        if self.axis == 0:
            raise ValueError(
                "You are trying to normalize your batch axis. Do you want to "
                "use tf.layer.batch_normalization instead"
            )

    def _create_input_spec(self, input_shape):

        dim = input_shape[self.axis]
        self.input_spec = tf.keras.layers.InputSpec(
            ndim=len(input_shape), axes={self.axis: dim}
        )

    def _add_gamma_weight(self, input_shape):

        dim = input_shape[self.axis]
        shape = (dim,)

        if self.scale:
            self.gamma = self.add_weight(
                shape=shape,
                name="gamma",
                initializer=self.gamma_initializer,
                regularizer=self.gamma_regularizer,
                constraint=self.gamma_constraint,
            )
        else:
            self.gamma = None

    def _add_beta_weight(self, input_shape):

        dim = input_shape[self.axis]
        shape = (dim,)

        if self.center:
            self.beta = self.add_weight(
                shape=shape,
                name="beta",
                initializer=self.beta_initializer,
                regularizer=self.beta_regularizer,
                constraint=self.beta_constraint,
            )
        else:
            self.beta = None

    def _create_broadcast_shape(self, input_shape):
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis] // self.groups
        broadcast_shape.insert(self.axis, self.groups)
        return broadcast_shape

    
class TransformBlock(tf.keras.layers.Layer):

    def __init__(self, features,
                 norm_type,
                 momentum=0.9,
                 virtual_batch_size=None,
                 groups=2,
                 block_name='',
                 **kwargs):
        super(TransformBlock, self).__init__(**kwargs)

        self.features = features
        self.norm_type = norm_type
        self.momentum = momentum
        self.groups = groups
        self.virtual_batch_size = virtual_batch_size
        self.block_name = block_name
    
    def build(self, input_shape):
        self.transform = tf.keras.layers.Dense(self.features, use_bias=False, name=f'transformblock_dense_{self.block_name}')
        if self.norm_type == 'batch':
            self.bn = tf.keras.layers.BatchNormalization(axis=-1, momentum=momentum,
                                                         virtual_batch_size=virtual_batch_size,
                                                         name=f'transformblock_bn_{self.block_name}')
        else:
            self.bn = GroupNormalization(axis=-1, groups=self.groups, name=f'transformblock_gn_{self.block_name}')
            
        self.built = True
        super().build(input_shape)
        
    def call(self, inputs, training=None):
        x = self.transform(inputs)
        x = self.bn(x, training=training)
        return x
    
    def get_config(self):
        config = {
            "features": self.features,
            "norm_type": self.norm_type,
            "virtual_batch_size": self.virtual_batch_size,
            "groups": self.groups,
            "block_name": self.block_name
        }
        base_config = super().get_config()
        return {**base_config, **config}
    
    def compute_output_shape(self, input_shape):
        return input_shape


class TabNetEncoderLayer(tf.keras.layers.Layer):

    def __init__(self, feature_columns,
                 feature_dim=16,
                 output_dim=8,
                 num_features=None,
                 num_decision_steps=3,
                 relaxation_factor=1.5,
                 sparsity_coefficient=1e-5,
                 norm_type='group',
                 batch_momentum=0.98,
                 virtual_batch_size=1024,
                 num_groups=2,
                 epsilon=1e-5,
                 **kwargs):

        super(TabNetEncoderLayer, self).__init__(**kwargs)

        # Input checks
        if feature_columns is not None:
            if type(feature_columns) not in (list, tuple):
                raise ValueError("`feature_columns` must be a list or a tuple.")

            if len(feature_columns) == 0:
                raise ValueError("`feature_columns` must be contain at least 1 tf.feature_column !")

            if num_features is None:
                num_features = len(feature_columns)
            else:
                num_features = int(num_features)

        else:
            if num_features is None:
                raise ValueError("If `feature_columns` is None, then `num_features` cannot be None.")

        if num_decision_steps < 1:
            raise ValueError("Num decision steps must be greater than 0.")
        
        if feature_dim <= output_dim:
            raise ValueError("To compute `features_for_coef`, feature_dim must be larger than output dim")

        feature_dim = int(feature_dim)
        output_dim = int(output_dim)
        num_decision_steps = int(num_decision_steps)
        relaxation_factor = float(relaxation_factor)
        sparsity_coefficient = float(sparsity_coefficient)
        batch_momentum = float(batch_momentum)
        num_groups = max(1, int(num_groups))
        epsilon = float(epsilon)

        if relaxation_factor < 0.:
            raise ValueError("`relaxation_factor` cannot be negative !")

        if sparsity_coefficient < 0.:
            raise ValueError("`sparsity_coefficient` cannot be negative !")

        if virtual_batch_size is not None:
            virtual_batch_size = int(virtual_batch_size)

        if norm_type not in ['batch', 'group']:
            raise ValueError("`norm_type` must be either `batch` or `group`")

        self.feature_columns = feature_columns
        self.num_features = num_features
        self.feature_dim = feature_dim
        self.output_dim = output_dim

        self.num_decision_steps = num_decision_steps
        self.relaxation_factor = relaxation_factor
        self.sparsity_coefficient = sparsity_coefficient
        self.norm_type = norm_type
        self.batch_momentum = batch_momentum
        self.virtual_batch_size = virtual_batch_size
        self.num_groups = num_groups
        self.epsilon = epsilon

        if num_decision_steps > 1:
            features_for_coeff = feature_dim - output_dim
            print(f"[TabNet]: {features_for_coeff} features will be used for decision steps.")

        if self.feature_columns is not None:
            self.input_features = tf.keras.layers.DenseFeatures(feature_columns, trainable=True)

            if self.norm_type == 'batch':
                self.input_bn = tf.keras.layers.BatchNormalization(axis=-1, momentum=batch_momentum, name='input_bn')
            else:
                self.input_bn = GroupNormalization(axis=-1, groups=self.num_groups, name='input_gn')

        else:
            self.input_features = None
            self.input_bn = None
    
    def build(self, input_shape):
        self.transform_f1 = TransformBlock(2 * self.feature_dim, self.norm_type,
                                           self.batch_momentum, self.virtual_batch_size, self.num_groups,
                                           block_name='f1')

        self.transform_f2 = TransformBlock(2 * self.feature_dim, self.norm_type,
                                           self.batch_momentum, self.virtual_batch_size, self.num_groups,
                                           block_name='f2')

        self.transform_f3_list = [
            TransformBlock(2 * self.feature_dim, self.norm_type,
                           self.batch_momentum, self.virtual_batch_size, self.num_groups, block_name=f'f3_{i}')
            for i in range(self.num_decision_steps)
        ]

        self.transform_f4_list = [
            TransformBlock(2 * self.feature_dim, self.norm_type,
                           self.batch_momentum, self.virtual_batch_size, self.num_groups, block_name=f'f4_{i}')
            for i in range(self.num_decision_steps)
        ]

        self.transform_coef_list = [
            TransformBlock(self.num_features, self.norm_type,
                           self.batch_momentum, self.virtual_batch_size, self.num_groups, block_name=f'coef_{i}')
            for i in range(self.num_decision_steps - 1)
        ]

        self._step_feature_selection_masks = None
        self._step_aggregate_feature_selection_mask = None
        self.built = True
        super(TabNetEncoderLayer, self).build(input_shape)

    def call(self, inputs, training=None):
        if self.input_features is not None:
            features = self.input_features(inputs)
            features = self.input_bn(features, training=training)

        else:
            features = inputs

        batch_size = tf.shape(features)[0]
        self._step_feature_selection_masks = []
        self._step_aggregate_feature_selection_mask = None

        # Initializes decision-step dependent variables.
        output_aggregated = tf.zeros([batch_size, self.output_dim])
        masked_features = features
        mask_values = tf.zeros([batch_size, self.num_features])
        aggregated_mask_values = tf.zeros([batch_size, self.num_features])
        complementary_aggregated_mask_values = tf.ones(
            [batch_size, self.num_features])

        total_entropy = 0.0
        entropy_loss = 0.

        for ni in range(self.num_decision_steps):
            # Feature transformer with two shared and two decision step dependent
            # blocks is used below.=
            transform_f1 = self.transform_f1(masked_features, training=training)
            transform_f1 = glu(transform_f1, self.feature_dim)

            transform_f2 = self.transform_f2(transform_f1, training=training)
            transform_f2 = (glu(transform_f2, self.feature_dim) +
                            transform_f1) * tf.math.sqrt(0.5)

            transform_f3 = self.transform_f3_list[ni](transform_f2, training=training)
            transform_f3 = (glu(transform_f3, self.feature_dim) +
                            transform_f2) * tf.math.sqrt(0.5)

            transform_f4 = self.transform_f4_list[ni](transform_f3, training=training)
            transform_f4 = (glu(transform_f4, self.feature_dim) +
                            transform_f3) * tf.math.sqrt(0.5)

            if (ni > 0 or self.num_decision_steps == 1):
                decision_out = tf.nn.relu(transform_f4[:, :self.output_dim])

                # Decision aggregation.
                output_aggregated += decision_out

                # Aggregated masks are used for visualization of the
                # feature importance attributes.
                scale_agg = tf.reduce_sum(decision_out, axis=1, keepdims=True)

                if self.num_decision_steps > 1:
                    scale_agg = scale_agg / tf.cast(self.num_decision_steps - 1, tf.float32)

                aggregated_mask_values += mask_values * scale_agg

            features_for_coef = transform_f4[:, self.output_dim:]

            if ni < (self.num_decision_steps - 1):
                # Determines the feature masks via linear and nonlinear
                # transformations, taking into account of aggregated feature use.
                mask_values = self.transform_coef_list[ni](features_for_coef, training=training)
                mask_values *= complementary_aggregated_mask_values
                mask_values = sparsemax(mask_values, axis=-1)

                # Relaxation factor controls the amount of reuse of features between
                # different decision blocks and updated with the values of
                # coefficients.
                complementary_aggregated_mask_values *= (
                        self.relaxation_factor - mask_values)

                # Entropy is used to penalize the amount of sparsity in feature
                # selection.
                total_entropy += tf.reduce_mean(
                    tf.reduce_sum(
                        -mask_values * tf.math.log(mask_values + self.epsilon), axis=1)) / (
                                     tf.cast(self.num_decision_steps - 1, tf.float32))

                # Add entropy loss
                entropy_loss = total_entropy

                # Feature selection.
                masked_features = tf.multiply(mask_values, features)

                # Visualization of the feature selection mask at decision step ni
                # tf.summary.image(
                #     "Mask for step" + str(ni),
                #     tf.expand_dims(tf.expand_dims(mask_values, 0), 3),
                #     max_outputs=1)
                mask_at_step_i = tf.expand_dims(tf.expand_dims(mask_values, 0), 3)
                self._step_feature_selection_masks.append(mask_at_step_i)

            else:
                # This branch is needed for correct compilation by tf.autograph
                entropy_loss = 0.

        # Adds the loss automatically
        self.add_loss(self.sparsity_coefficient * entropy_loss)

        # Visualization of the aggregated feature importances
        # tf.summary.image(
        #     "Aggregated mask",
        #     tf.expand_dims(tf.expand_dims(aggregated_mask_values, 0), 3),
        #     max_outputs=1)

        agg_mask = tf.expand_dims(tf.expand_dims(aggregated_mask_values, 0), 3)
        self._step_aggregate_feature_selection_mask = agg_mask
        return output_aggregated

    def feature_selection_masks(self):
        return self._step_feature_selection_masks

    def aggregate_feature_selection_mask(self):
        return self._step_aggregate_feature_selection_mask
    
    def compute_output_shape(self, input_shape):
        return self.output_dim
    
    def get_config(self):
        config = {
            "feature_columns": self.feature_columns,
            "num_features": self.num_features,
            "feature_dim": self.feature_dim,
            "output_dim": self.output_dim,
            "num_decision_steps": self.num_decision_steps,
            "relaxation_factor": self.relaxation_factor,
            "sparsity_coefficient": self.sparsity_coefficient,
            "norm_type": self.norm_type,
            "batch_momentum": self.batch_momentum,
            "virtual_batch_size": self.virtual_batch_size,
            "num_groups": self.num_groups,
            "epsilon": self.epsilon,
        }
        base_config = super().get_config()
        return {**base_config, **config}
    
    
# 必须也将 UserLayer 赋值给 m12_layer_class_bigquant_run
m12_layer_class_bigquant_run = TabNetEncoderLayer

from tensorflow.keras.optimizers import Adam, schedules

lr = schedules.ExponentialDecay(0.02, decay_steps=2000, decay_rate=0.9, staircase=False)

m5_user_optimizer_bigquant_run=Adam(lr)
from tensorflow.keras.callbacks import EarlyStopping

m5_earlystop_bigquant_run=EarlyStopping(monitor='val_loss', min_delta=0.0001, patience=5)
# 用户的自定义层需要写到字典中，比如
# {
#   "MyLayer": MyLayer
# }
m5_custom_objects_bigquant_run = {
    "GroupNormalization": GroupNormalization,
    "TransformBlock": TransformBlock,
    "TabNetEncoderLayer": TabNetEncoderLayer
}

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

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

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

    # 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
    context.set_commission(PerOrder(buy_cost=0.001, sell_cost=0.001, min_cost=5))
    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
    # 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
    stock_count = 20
    # 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]
    context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.2
    context.options['hold_days'] = 5

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

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

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

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

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


m1 = M.instruments.v2(
    start_date='2014-01-01',
    end_date='2017-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/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
)

m29 = M.standardlize.v8(
    input_1=m2.data,
    columns_input='label'
)

m3 = M.input_features.v1(
    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(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

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
)

m28 = M.standardlize.v8(
    input_1=m16.data,
    input_2=m3.data,
    columns_input='[]'
)

m13 = M.fillnan.v1(
    input_data=m28.data,
    features=m3.data,
    fill_value='0.0'
)

m7 = M.join.v3(
    data1=m29.data,
    data2=m13.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m26 = M.dl_convert_to_bin.v2(
    input_data=m7.data,
    features=m3.data,
    window_size=1,
    feature_clip=3,
    flatten=True,
    window_along_col='instrument'
)

m10 = M.cached.v3(
    input_1=m26.data,
    run=m10_run_bigquant_run,
    post_run=m10_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2018-01-01'),
    end_date=T.live_run_param('trading_date', '2021-07-01'),
    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=0
)

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='[]'
)

m14 = M.fillnan.v1(
    input_data=m25.data,
    features=m3.data,
    fill_value='0.0'
)

m27 = M.dl_convert_to_bin.v2(
    input_data=m14.data,
    features=m3.data,
    window_size=1,
    feature_clip=3,
    flatten=True,
    window_along_col='instrument'
)

m6 = M.dl_layer_input.v1(
    shape='98',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

m12 = M.dl_layer_userlayer.v1(
    input1=m6.data,
    layer_class=m12_layer_class_bigquant_run,
    params="""{
    "num_features": 98, 
    "feature_columns": None,
    "feature_dim": 64,
    "output_dim": 32,
    "num_decision_steps": 3,
    "relaxation_factor": 1.3,
    "sparsity_coefficient": 1e-5,
    "norm_type": "group",
    "batch_momentum": 0.9,
    "virtual_batch_size": 128,
    "num_groups": 2,
    "epsilon": 1e-5
}""",
    name=''
)

m23 = M.dl_layer_dense.v1(
    inputs=m12.data,
    units=1,
    activation='linear',
    use_bias=False,
    kernel_initializer='Zeros',
    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=''
)

m4 = M.dl_model_init.v1(
    inputs=m6.data,
    outputs=m23.data
)

m5 = M.dl_model_train.v1(
    input_model=m4.data,
    training_data=m10.data_1,
    validation_data=m10.data_2,
    optimizer='自定义',
    user_optimizer=m5_user_optimizer_bigquant_run,
    loss='mean_squared_error',
    metrics='mse',
    batch_size=10240,
    epochs=100,
    earlystop=m5_earlystop_bigquant_run,
    custom_objects=m5_custom_objects_bigquant_run,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录',
    m_cached=False
)

m11 = M.dl_model_predict.v1(
    trained_model=m5.data,
    input_data=m27.data,
    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'
)

[2021-09-23 14:10:14.903414] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-09-23 14:10:14.910403] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:14.912146] INFO: moduleinvoker: instruments.v2 运行完成[0.008744s].

[2021-09-23 14:10:14.919358] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-09-23 14:10:14.925039] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:14.926274] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.006921s].

[2021-09-23 14:10:14.930385] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-09-23 14:10:14.935966] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:14.937145] INFO: moduleinvoker: standardlize.v8 运行完成[0.00676s].

[2021-09-23 14:10:14.940444] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-09-23 14:10:14.946259] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:14.947482] INFO: moduleinvoker: input_features.v1 运行完成[0.007041s].

[2021-09-23 14:10:14.959182] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-09-23 14:10:14.964525] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:14.965688] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.00651s].

[2021-09-23 14:10:14.971554] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-09-23 14:10:14.976840] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:14.978009] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.006456s].

[2021-09-23 14:10:14.982112] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-09-23 14:10:14.986804] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:14.988039] INFO: moduleinvoker: standardlize.v8 运行完成[0.005926s].

[2021-09-23 14:10:14.995104] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-09-23 14:10:15.000262] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.002028] INFO: moduleinvoker: fillnan.v1 运行完成[0.006924s].

[2021-09-23 14:10:15.009454] INFO: moduleinvoker: join.v3 开始运行..

[2021-09-23 14:10:15.014301] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.015470] INFO: moduleinvoker: join.v3 运行完成[0.006016s].

[2021-09-23 14:10:15.027620] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-09-23 14:10:15.032541] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.033737] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.006123s].

[2021-09-23 14:10:15.043010] INFO: moduleinvoker: cached.v3 开始运行..

[2021-09-23 14:10:15.056273] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.057457] INFO: moduleinvoker: cached.v3 运行完成[0.014452s].

[2021-09-23 14:10:15.061782] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-09-23 14:10:15.080831] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.082071] INFO: moduleinvoker: instruments.v2 运行完成[0.020289s].

[2021-09-23 14:10:15.092861] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-09-23 14:10:15.097422] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.098666] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.005809s].

[2021-09-23 14:10:15.105193] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-09-23 14:10:15.110513] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.111962] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.006778s].

[2021-09-23 14:10:15.116681] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-09-23 14:10:15.121976] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.123264] INFO: moduleinvoker: standardlize.v8 运行完成[0.00658s].

[2021-09-23 14:10:15.130546] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-09-23 14:10:15.135347] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.136579] INFO: moduleinvoker: fillnan.v1 运行完成[0.006035s].

[2021-09-23 14:10:15.147338] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-09-23 14:10:15.152263] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:10:15.153425] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.006092s].

[2021-09-23 14:10:15.159386] INFO: moduleinvoker: dl_layer_input.v1 运行完成[0.00129s].

[2021-09-23 14:10:16.216359] INFO: moduleinvoker: dl_layer_userlayer.v1 运行完成[1.052319s].

[2021-09-23 14:10:16.227863] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.00555s].

[2021-09-23 14:10:16.249325] INFO: moduleinvoker: cached.v3 开始运行..

[2021-09-23 14:10:16.274649] INFO: moduleinvoker: cached.v3 运行完成[0.025327s].

[2021-09-23 14:10:16.276105] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.04396s].

[2021-09-23 14:10:16.279241] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2021-09-23 14:10:19.282089] INFO: dl_model_train: 准备训练，训练样本个数：1981139，迭代次数：100

[2021-09-23 14:16:04.177624] INFO: dl_model_train: 训练结束，耗时：344.89s

[2021-09-23 14:16:04.226533] INFO: moduleinvoker: dl_model_train.v1 运行完成[347.94725s].

[2021-09-23 14:16:04.232049] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2021-09-23 14:16:31.882920] INFO: moduleinvoker: dl_model_predict.v1 运行完成[27.65085s].

[2021-09-23 14:16:31.898251] INFO: moduleinvoker: cached.v3 开始运行..

[2021-09-23 14:16:56.989142] INFO: moduleinvoker: cached.v3 运行完成[25.090901s].

[2021-09-23 14:16:57.050966] INFO: moduleinvoker: backtest.v8 开始运行..

[2021-09-23 14:16:57.059589] INFO: backtest: biglearning backtest:V8.5.0

[2021-09-23 14:16:57.060668] INFO: backtest: product_type:stock by specified

[2021-09-23 14:16:58.017335] INFO: moduleinvoker: cached.v2 开始运行..

[2021-09-23 14:16:58.024620] INFO: moduleinvoker: 命中缓存

[2021-09-23 14:16:58.025982] INFO: moduleinvoker: cached.v2 运行完成[0.008665s].

[2021-09-23 14:17:03.854880] INFO: algo: TradingAlgorithm V1.8.5

[2021-09-23 14:17:06.055674] INFO: algo: trading transform...

[2021-09-23 14:18:09.990156] INFO: Performance: Simulated 849 trading days out of 849.

[2021-09-23 14:18:09.991732] INFO: Performance: first open: 2018-01-02 09:30:00+00:00

[2021-09-23 14:18:09.992849] INFO: Performance: last close: 2021-07-01 15:00:00+00:00

[2021-09-23 14:18:25.658874] INFO: moduleinvoker: backtest.v8 运行完成[88.607908s].

[2021-09-23 14:18:25.660410] INFO: moduleinvoker: trade.v4 运行完成[88.664626s].

[TabNet]: 32 features will be used for decision steps.

[TabNet]: 32 features will be used for decision steps.

Epoch 1/100
194/194 - 19s - loss: 0.9963 - mse: 0.9963 - val_loss: 0.9971 - val_mse: 0.9971
Epoch 2/100
194/194 - 10s - loss: 0.9944 - mse: 0.9944 - val_loss: 0.9956 - val_mse: 0.9956
Epoch 3/100
194/194 - 10s - loss: 0.9931 - mse: 0.9931 - val_loss: 0.9939 - val_mse: 0.9939
Epoch 4/100
194/194 - 10s - loss: 0.9918 - mse: 0.9918 - val_loss: 0.9926 - val_mse: 0.9926
Epoch 5/100
194/194 - 10s - loss: 0.9903 - mse: 0.9903 - val_loss: 0.9908 - val_mse: 0.9908
Epoch 6/100
194/194 - 10s - loss: 0.9888 - mse: 0.9888 - val_loss: 0.9894 - val_mse: 0.9894
Epoch 7/100
194/194 - 10s - loss: 0.9879 - mse: 0.9879 - val_loss: 0.9888 - val_mse: 0.9888
Epoch 8/100
194/194 - 10s - loss: 0.9873 - mse: 0.9873 - val_loss: 0.9884 - val_mse: 0.9884
Epoch 9/100
194/194 - 10s - loss: 0.9864 - mse: 0.9864 - val_loss: 0.9886 - val_mse: 0.9886
Epoch 10/100
194/194 - 10s - loss: 0.9859 - mse: 0.9859 - val_loss: 0.9876 - val_mse: 0.9876
Epoch 11/100
194/194 - 10s - loss: 0.9851 - mse: 0.9851 - val_loss: 0.9881 - val_mse: 0.9881
Epoch 12/100
194/194 - 10s - loss: 0.9846 - mse: 0.9846 - val_loss: 0.9866 - val_mse: 0.9866
Epoch 13/100
194/194 - 10s - loss: 0.9841 - mse: 0.9841 - val_loss: 0.9881 - val_mse: 0.9881
Epoch 14/100
194/194 - 10s - loss: 0.9834 - mse: 0.9834 - val_loss: 0.9876 - val_mse: 0.9876
Epoch 15/100
194/194 - 10s - loss: 0.9828 - mse: 0.9828 - val_loss: 0.9856 - val_mse: 0.9856
Epoch 16/100
194/194 - 10s - loss: 0.9821 - mse: 0.9821 - val_loss: 0.9850 - val_mse: 0.9850
Epoch 17/100
194/194 - 10s - loss: 0.9818 - mse: 0.9818 - val_loss: 0.9852 - val_mse: 0.9852
Epoch 18/100
194/194 - 10s - loss: 0.9810 - mse: 0.9810 - val_loss: 0.9863 - val_mse: 0.9863
Epoch 19/100
194/194 - 10s - loss: 0.9804 - mse: 0.9804 - val_loss: 0.9849 - val_mse: 0.9849
Epoch 20/100
194/194 - 10s - loss: 0.9800 - mse: 0.9800 - val_loss: 0.9844 - val_mse: 0.9844
Epoch 21/100
194/194 - 11s - loss: 0.9795 - mse: 0.9795 - val_loss: 0.9842 - val_mse: 0.9842
Epoch 22/100
194/194 - 11s - loss: 0.9785 - mse: 0.9785 - val_loss: 0.9846 - val_mse: 0.9846
Epoch 23/100
194/194 - 11s - loss: 0.9784 - mse: 0.9784 - val_loss: 0.9847 - val_mse: 0.9847
Epoch 24/100
194/194 - 11s - loss: 0.9781 - mse: 0.9781 - val_loss: 0.9838 - val_mse: 0.9838
Epoch 25/100
194/194 - 11s - loss: 0.9769 - mse: 0.9769 - val_loss: 0.9849 - val_mse: 0.9849
Epoch 26/100
194/194 - 11s - loss: 0.9764 - mse: 0.9764 - val_loss: 0.9853 - val_mse: 0.9853
Epoch 27/100
194/194 - 11s - loss: 0.9761 - mse: 0.9761 - val_loss: 0.9836 - val_mse: 0.9836
Epoch 28/100
194/194 - 11s - loss: 0.9751 - mse: 0.9751 - val_loss: 0.9840 - val_mse: 0.9840
Epoch 29/100
194/194 - 11s - loss: 0.9746 - mse: 0.9746 - val_loss: 0.9843 - val_mse: 0.9843
Epoch 30/100
194/194 - 11s - loss: 0.9742 - mse: 0.9742 - val_loss: 0.9840 - val_mse: 0.9840
Epoch 31/100
194/194 - 11s - loss: 0.9736 - mse: 0.9736 - val_loss: 0.9851 - val_mse: 0.9851
Epoch 32/100
194/194 - 11s - loss: 0.9730 - mse: 0.9730 - val_loss: 0.9844 - val_mse: 0.9844

[TabNet]: 32 features will be used for decision steps.
3059/3059 - 21s
DataSource(5d79c920ec4d4f0cb52d91863ccd5739T)

收益率61.36%
年化收益率15.26%
基准收益率29.74%
阿尔法0.1
贝塔0.82
夏普比率0.55
胜率0.5
盈亏比1.18
收益波动率27.64%
信息比率0.02
最大回撤28.54%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-a32aa386eb814a8eaab4a4d12999ac4f"}/bigcharts-data-end