【其他】提问：基础特征抽取 (v7)日期不匹配问题

由bq2sr4ov创建，最终由small_q更新于2025-02-16 02:39 被浏览 20 用户

下面的m16是基础特征抽取 (v7)，我想了解一下这个数据输出的格式是如何定义的。为什么前面几行是有0,0 1,1, 2,2这样的index的，但最后几行是连续的

猜测前几行和输入参数before_start_days有关，但是参数设置before_start_days为90天时，打印出来的数据中2018-11-13到2019-01-02之间似乎只有60天左右。

下面是策略的代码：

# 本代码由可视化策略环境自动生成 2024年1月8日 14:47
# 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。
 
# 显式导入 BigQuant 相关 SDK 模块
from bigdatasource.api import DataSource
from bigdata.api.datareader import D
from biglearning.api import M
from biglearning.api import tools as T
from biglearning.module2.common.data import Outputs
 
import pandas as pd
import numpy as np
import math
import warnings
import datetime
 
from zipline.finance.commission import PerOrder
from zipline.api import get_open_orders
from zipline.api import symbol
 
from bigtrader.sdk import *
from bigtrader.utils.my_collections import NumPyDeque
from bigtrader.constant import OrderType
from bigtrader.constant import Direction

# <aistudiograph>

# @param(id="m6", name="custom_objects")
# 用户的自定义层需要写到字典中，比如
# {
#   "MyLayer": MyLayer
# }
m6_custom_objects_bigquant_run = {
    
}

# @param(id="m2", name="run")
# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m2_run_bigquant_run(input_1, input_2, input_3):

    test_data = input_2.read_pickle()
    pred_label = input_1.read_pickle()
    pred_result = pred_label.reshape(pred_label.shape[0]) 
    dt = input_3.read_df()['date'][-1*len(pred_result):]
    pred_df = pd.Series(pred_result, index=dt)
    ds = DataSource.write_df(pred_df)
    
    return Outputs(data_1=ds)

# @param(id="m2", name="post_run")
# 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 m2_post_run_bigquant_run(outputs):
    return outputs

# @param(id="m1", name="initialize")
# 回测引擎：初始化函数，只执行一次
def m1_initialize_bigquant_run(context):
    # 加载预测数据
    context.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))
# @param(id="m1", name="handle_data")
# 回测引擎：每日数据处理函数，每天执行一次
def m1_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    try:
        prediction = context.prediction[data.current_dt.strftime('%Y-%m-%d')]
    except KeyError as e:
        return
    
    instrument = context.instruments[0]
    sid = context.symbol(instrument)
    cur_position = context.portfolio.positions[sid].amount
    
    # 交易逻辑
    if prediction > 0.5 and cur_position == 0:
        context.order_target_percent(context.symbol(instrument), 1)
        print(data.current_dt, '买入！')
        
    elif prediction < 0.5 and cur_position > 0:
        context.order_target_percent(context.symbol(instrument), 0)
        print(data.current_dt, '卖出！')
    
# @param(id="m1", name="prepare")
# 回测引擎：准备数据，只执行一次
def m1_prepare_bigquant_run(context):
    pass

# @param(id="m1", name="before_trading_start")
# 回测引擎：每个单位时间开始前调用一次，即每日开盘前调用一次。
def m1_before_trading_start_bigquant_run(context, data):
    pass


# @module(position="346,-367", comment='', comment_collapsed=True)
m3 = M.dl_layer_input.v1(
    shape='50,5',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

# @module(position="279,-194", comment='', comment_collapsed=True)
m13 = M.dl_layer_reshape.v1(
    inputs=m3.data,
    target_shape='50,5,1',
    name=''
)

# @module(position="280,-107", comment='', comment_collapsed=True)
m14 = M.dl_layer_conv2d.v1(
    inputs=m13.data,
    filters=32,
    kernel_size='3,5',
    strides='1,1',
    padding='valid',
    data_format='channels_last',
    dilation_rate='1,1',
    activation='relu',
    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=''
)

# @module(position="275,-29", comment='', comment_collapsed=True)
m19 = M.dl_layer_reshape.v1(
    inputs=m14.data,
    target_shape='1536',
    name=''
)

# @module(position="276,57", comment='', comment_collapsed=True)
m29 = M.dl_layer_dense.v1(
    inputs=m19.data,
    units=128,
    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=''
)

# @module(position="279,146", comment='', comment_collapsed=True)
m11 = M.dl_layer_dropout.v1(
    inputs=m29.data,
    rate=0.4,
    noise_shape='',
    name=''
)

# @module(position="279,218", comment='', comment_collapsed=True)
m10 = M.dl_layer_dense.v1(
    inputs=m11.data,
    units=32,
    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=''
)

# @module(position="282,301", comment='', comment_collapsed=True)
m12 = M.dl_layer_dropout.v1(
    inputs=m10.data,
    rate=0.8,
    noise_shape='',
    name=''
)

# @module(position="281,387", comment='', comment_collapsed=True)
m9 = M.dl_layer_dense.v1(
    inputs=m12.data,
    units=1,
    activation='sigmoid',
    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=''
)

# @module(position="474,466", comment='', comment_collapsed=True)
m5 = M.dl_model_init.v1(
    inputs=m3.data,
    outputs=m9.data
)

# @module(position="1063,-225", comment='', comment_collapsed=True)
m8 = M.input_features.v1(
    features="""(close_0/close_1-1)*10
(high_0/high_1-1)*10
(low_0/low_1-1)*10
(open_0/open_1-1)*10
(volume_0/volume_1-1)*10"""
)

# @module(position="708,-325", comment='', comment_collapsed=True)
m24 = M.instruments.v2(
    start_date='2017-06-02',
    end_date='2017-10-30',
    market='CN_STOCK_A',
    instrument_list='600009.SHA',
    max_count=0
)

# @module(position="561,-48", comment='', comment_collapsed=True)
m21 = M.advanced_auto_labeler.v2(
    instruments=m24.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/develop/datasource/deprecated/history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
where(shift(close, -10) / close -1>0,1,0)

# 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=True,
    user_functions={}
)

# @module(position="860,-82", comment='', comment_collapsed=True)
m22 = M.general_feature_extractor.v7(
    instruments=m24.data,
    features=m8.data,
    start_date='',
    end_date='',
    before_start_days=90
)

# @module(position="871,10", comment='', comment_collapsed=True)
m23 = M.derived_feature_extractor.v3(
    input_data=m22.data,
    features=m8.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

# @module(position="735,138", comment='标注特征连接', comment_collapsed=False)
m17 = M.join.v3(
    data1=m21.data,
    data2=m23.data,
    on='date',
    how='inner',
    sort=True
)

# @module(position="725,247", comment='去掉为nan的数据', comment_collapsed=True)
m18 = M.dropnan.v1(
    input_data=m17.data
)

# @module(position="753,329", comment='', comment_collapsed=True)
m25 = M.dl_convert_to_bin.v2(
    input_data=m18.data,
    features=m8.data,
    window_size=50,
    feature_clip=5,
    flatten=False,
    window_along_col=''
)

# @module(position="633,537", comment='', comment_collapsed=True)
m6 = M.dl_model_train.v1(
    input_model=m5.data,
    training_data=m25.data,
    optimizer='Adam',
    loss='binary_crossentropy',
    metrics='accuracy',
    batch_size=2048,
    epochs=10,
    custom_objects=m6_custom_objects_bigquant_run,
    n_gpus=1,
    verbose='1:输出进度条记录'
)

# @module(position="1257,-312", comment='', comment_collapsed=True)
m28 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2019-02-11'),
    end_date=T.live_run_param('trading_date', '2019-08-01'),
    market='CN_STOCK_A',
    instrument_list='600009.SHA',
    max_count=0
)

# @module(position="1229,-86", comment='', comment_collapsed=True)
m16 = M.general_feature_extractor.v7(
    instruments=m28.data,
    features=m8.data,
    start_date='',
    end_date='',
    before_start_days=90
)

\