复制链接

克隆策略

In [17]:

Out[17]:

In [18]:

# 本代码由可视化策略环境自动生成 2023年3月24日 09:50
# 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 m34_run_bigquant_run(input_1, input_2, input_3, SW_type):
    basic_data = input_1.read()
    start_date = str(basic_data.date.min())
    end_date = str(basic_data.date.max())
    SW_data = DataSource('basic_info_IndustrySw').read()
    SW_data['code'] = SW_data.code.astype('int')

    SW_data_2014_2 = SW_data[(SW_data.version==2014)&(SW_data.industry_sw_level==2)][['code','name']].rename(columns={'code':'industry_sw_level2_0','name':'name_SW2'})

    SW_data_2021_2 = SW_data[(SW_data.version==2021)&(SW_data.industry_sw_level==2)][['code','name']].rename(columns={'code':'industry_sw_level2_0','name':'name_SW2'})

    basic_data['daily_return_0'] = basic_data['daily_return_0']-1

    if end_date < '2021-12-13':

        basic_data = basic_data.merge(SW_data_2014_2,how='left',on='industry_sw_level2_0')

    else:
        basic_data_2014 = basic_data[basic_data.date < '2021-12-13']

        basic_data_2014 = basic_data_2014.merge(SW_data_2014_2,how='left',on='industry_sw_level2_0')

        basic_data_2021 = basic_data[basic_data.date >= '2021-12-13']

        basic_data_2021 = basic_data_2021.merge(SW_data_2021_2,how='left',on='industry_sw_level2_0')

        basic_data = pd.concat([basic_data_2014,basic_data_2021])
        
    block_data = basic_data.groupby(['name_SW2','date']).agg({'daily_return_0':'sum','market_cap_float_0':'sum'}).reset_index()
    block_data.columns = ['name_SW2','date','daily_return_0_block_sum','market_cap_float_0_block_sum']
    rst = pd.merge(basic_data[['date','name_SW2','instrument','daily_return_0','market_cap_float_0']],block_data,on=['date','name_SW2'],how='left').dropna()
    
    rst['板块流通收益率'] = rst['daily_return_0']*rst['market_cap_float_0']/rst['market_cap_float_0_block_sum']
    data_1 = DataSource.write_df(rst)
    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 m34_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 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'],shuffle=True)
    data_1 = DataSource.write_pickle({'x': x_train, 'y': y_train})
    data_2 = DataSource.write_pickle({'x': x_val, 'y': y_val})
    return Outputs(data_1=data_1, data_2=data_2, data_3=None)

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

from tensorflow.keras import losses 
m5_user_loss_bigquant_run=losses.huber
from tensorflow.keras.callbacks import EarlyStopping
m5_earlystop_bigquant_run=EarlyStopping(monitor='val_mse', 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 = {
 
}

# 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 = 1
    # 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='2020-01-01',
    end_date='2022-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m36 = M.use_datasource.v1(
    instruments=m1.data,
    datasource_id='bar1d_CN_STOCK_A',
    start_date='',
    end_date=''
)

m3 = M.input_features.v1(
    features="""return_0
return_5
rank_return_0
rank_return_5
rank_return_20
rank_return_0/rank_return_20
rank_return_5/rank_return_20
rank_amount_5/rank_amount_20
rank_turn_5/rank_turn_20
avg_turn_5
turn_20
avg_turn_5/turn_20

shift(close_0,20)/shift(close_0, 30)
shift(close_0,20)/shift(close_0, 35)
shift(close_0,20)/shift(close_0, 40)
delta(rank_return_0, 20)
avg_turn_3/((turn_18+turn_19+turn_20)/3)



"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=10
)

m32 = M.chinaa_stock_filter.v1(
    input_data=m15.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板', '创业板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['全部'],
    output_left_data=False
)

m16 = M.derived_feature_extractor.v3(
    input_data=m32.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m28 = M.standardlize.v12(
    input_1=m16.data,
    input_2=m3.data,
    standard_func='ZScoreNorm',
    columns_input='[]'
)

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

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2023-03-15'),
    end_date=T.live_run_param('trading_date', '2023-03-15'),
    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=10
)

m2 = M.chinaa_stock_filter.v1(
    input_data=m17.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板', '创业板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['全部'],
    output_left_data=False
)

m18 = M.derived_feature_extractor.v3(
    input_data=m2.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m25 = M.standardlize.v12(
    input_1=m18.data,
    input_2=m3.data,
    standard_func='ZScoreNorm',
    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='17',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

m8 = M.dl_layer_dense.v1(
    inputs=m6.data,
    units=512,
    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=''
)

m21 = M.dl_layer_dropout.v1(
    inputs=m8.data,
    rate=0.1,
    noise_shape='',
    name=''
)

m20 = M.dl_layer_dense.v1(
    inputs=m21.data,
    units=128,
    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=''
)

m22 = M.dl_layer_dropout.v1(
    inputs=m20.data,
    rate=0.1,
    noise_shape='',
    name=''
)

m23 = M.dl_layer_dense.v1(
    inputs=m22.data,
    units=1,
    activation='linear',
    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=''
)

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

m29 = M.input_features.v1(
    features="""industry_sw_level2_0
market_cap_float_0
daily_return_0
"""
)

m31 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m29.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m34 = M.cached.v3(
    input_1=m31.data,
    run=m34_run_bigquant_run,
    post_run=m34_post_run_bigquant_run,
    input_ports='',
    params="""{
    'SW_type':'name_SW2'
}""",
    output_ports='data_1,data_2'
)

m35 = M.join.v3(
    data1=m34.data_1,
    data2=m36.data,
    on='date,instrument',
    how='inner',
    sort=True
)

m37 = M.filter.v3(
    input_data=m35.data,
    expr='rank(板块流通收益率)>0.95',
    output_left_data=False
)

m38 = M.auto_labeler_on_datasource.v1(
    input_data=m37.data,
    label_expr="""

# 计算收益：3日最高价(作为卖出价格)      除以明日开盘价(作为买入价格)   /  未来3日 的板块流通收益率
-1*(shift(high, -3)/shift(open, -1))/shift(板块流通收益率, -3) -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))

# 将分数映射到分类，这里使用20个分类
all_wbins(label, 20)

# 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)""",
    drop_na_label=True,
    cast_label_int=False,
    date_col='date',
    instrument_col='instrument',
    user_functions={}
)

m12 = M.standardlize.v12(
    input_1=m38.data,
    standard_func='ZScoreNorm',
    columns_input='label'
)

m7 = M.join.v3(
    data1=m12.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='',
    m_cached=False
)

m5 = M.dl_model_train.v1(
    input_model=m4.data,
    training_data=m10.data_1,
    validation_data=m10.data_2,
    optimizer='Adam',
    loss='自定义',
    user_loss=m5_user_loss_bigquant_run,
    metrics='mse',
    batch_size=1024,
    epochs=30,
    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'
)

[2023-03-24 09:49:27.008020] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-03-24 09:49:27.015099] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.017313] INFO: moduleinvoker: instruments.v2 运行完成[0.009303s].

[2023-03-24 09:49:27.023290] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2023-03-24 09:49:27.029672] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.031492] INFO: moduleinvoker: use_datasource.v1 运行完成[0.008214s].

[2023-03-24 09:49:27.036217] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-03-24 09:49:27.042174] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.043980] INFO: moduleinvoker: input_features.v1 运行完成[0.007766s].

[2023-03-24 09:49:27.058405] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-03-24 09:49:27.065359] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.068355] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.009945s].

[2023-03-24 09:49:27.078977] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2023-03-24 09:49:27.086056] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.088663] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[0.009689s].

[2023-03-24 09:49:27.099018] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-03-24 09:49:27.106884] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.109255] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010241s].

[2023-03-24 09:49:27.114975] INFO: moduleinvoker: standardlize.v12 开始运行..

[2023-03-24 09:49:27.121307] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.123135] INFO: moduleinvoker: standardlize.v12 运行完成[0.008156s].

[2023-03-24 09:49:27.131969] INFO: moduleinvoker: fillnan.v1 开始运行..

[2023-03-24 09:49:27.138335] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.140366] INFO: moduleinvoker: fillnan.v1 运行完成[0.008397s].

[2023-03-24 09:49:27.147438] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-03-24 09:49:27.154434] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.156287] INFO: moduleinvoker: instruments.v2 运行完成[0.008864s].

[2023-03-24 09:49:27.169726] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-03-24 09:49:27.177464] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.180943] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011241s].

[2023-03-24 09:49:27.199877] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2023-03-24 09:49:27.208691] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.211246] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[0.011376s].

[2023-03-24 09:49:27.220158] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-03-24 09:49:27.227488] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.229316] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009187s].

[2023-03-24 09:49:27.235568] INFO: moduleinvoker: standardlize.v12 开始运行..

[2023-03-24 09:49:27.242178] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.244261] INFO: moduleinvoker: standardlize.v12 运行完成[0.008692s].

[2023-03-24 09:49:27.254425] INFO: moduleinvoker: fillnan.v1 开始运行..

[2023-03-24 09:49:27.261428] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.263194] INFO: moduleinvoker: fillnan.v1 运行完成[0.008778s].

[2023-03-24 09:49:27.276620] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2023-03-24 09:49:27.282711] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.284632] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.008044s].

[2023-03-24 09:49:27.305357] INFO: moduleinvoker: dl_layer_input.v1 运行完成[0.002s].

[2023-03-24 09:49:27.330039] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.015931s].

[2023-03-24 09:49:27.344374] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.004848s].

[2023-03-24 09:49:27.365254] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.011827s].

[2023-03-24 09:49:27.377825] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.005243s].

[2023-03-24 09:49:27.398676] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.0124s].

[2023-03-24 09:49:27.438676] INFO: moduleinvoker: cached.v3 开始运行..

[2023-03-24 09:49:27.450258] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.456791] INFO: moduleinvoker: cached.v3 运行完成[0.018125s].

[2023-03-24 09:49:27.459846] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.053151s].

[2023-03-24 09:49:27.466228] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-03-24 09:49:27.473001] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.478164] INFO: moduleinvoker: input_features.v1 运行完成[0.011918s].

[2023-03-24 09:49:27.496137] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-03-24 09:49:27.503246] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.505687] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.009593s].

[2023-03-24 09:49:27.525372] INFO: moduleinvoker: cached.v3 开始运行..

[2023-03-24 09:49:27.532743] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.535034] INFO: moduleinvoker: cached.v3 运行完成[0.009718s].

[2023-03-24 09:49:27.545529] INFO: moduleinvoker: join.v3 开始运行..

[2023-03-24 09:49:27.552115] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.554461] INFO: moduleinvoker: join.v3 运行完成[0.008932s].

[2023-03-24 09:49:27.566477] INFO: moduleinvoker: filter.v3 开始运行..

[2023-03-24 09:49:27.573003] INFO: moduleinvoker: 命中缓存

[2023-03-24 09:49:27.575469] INFO: moduleinvoker: filter.v3 运行完成[0.009002s].

[2023-03-24 09:49:27.596524] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2023-03-24 09:49:28.191066] INFO: 自动标注(任意数据源): 开始标注 ..

[2023-03-24 09:49:28.624785] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[1.028263s].

[2023-03-24 09:49:28.634846] INFO: moduleinvoker: standardlize.v12 开始运行..

[2023-03-24 09:49:31.568048] INFO: moduleinvoker: standardlize.v12 运行完成[2.933209s].

[2023-03-24 09:49:31.582034] INFO: moduleinvoker: join.v3 开始运行..

[2023-03-24 09:49:40.098598] INFO: join: /data, 行数=134796/2663402, 耗时=7.150793s

[2023-03-24 09:49:40.176852] INFO: join: 最终行数: 134796

[2023-03-24 09:49:40.188821] INFO: moduleinvoker: join.v3 运行完成[8.606781s].

[2023-03-24 09:49:40.205101] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2023-03-24 09:49:40.912300] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.707187s].

[2023-03-24 09:49:40.925119] INFO: moduleinvoker: cached.v3 开始运行..

[2023-03-24 09:49:41.100624] INFO: moduleinvoker: cached.v3 运行完成[0.175512s].

[2023-03-24 09:49:41.106175] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2023-03-24 09:49:41.211304] INFO: dl_model_train: 准备训练，训练样本个数：101097，迭代次数：30

[2023-03-24 09:49:57.391763] INFO: dl_model_train: 训练结束，耗时：16.18s

[2023-03-24 09:49:57.415266] INFO: moduleinvoker: dl_model_train.v1 运行完成[16.309087s].

[2023-03-24 09:49:57.421620] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2023-03-24 09:49:57.552354] ERROR: moduleinvoker: module name: dl_model_predict, module version: v1, trackeback: AttributeError: 'int' object has no attribute 'assign'

During handling of the above exception, another exception occurred:

AttributeError: 'int' object has no attribute 'assign'

Epoch 1/30
99/99 - 4s - loss: 0.3281 - mse: 0.9329 - val_loss: 0.3267 - val_mse: 0.9428
Epoch 2/30
99/99 - 2s - loss: 0.3232 - mse: 0.9208 - val_loss: 0.3269 - val_mse: 0.9379
Epoch 3/30
99/99 - 2s - loss: 0.3224 - mse: 0.9188 - val_loss: 0.3258 - val_mse: 0.9487
Epoch 4/30
99/99 - 2s - loss: 0.3222 - mse: 0.9186 - val_loss: 0.3259 - val_mse: 0.9383
Epoch 5/30
99/99 - 2s - loss: 0.3216 - mse: 0.9162 - val_loss: 0.3259 - val_mse: 0.9439
Epoch 6/30
99/99 - 2s - loss: 0.3210 - mse: 0.9141 - val_loss: 0.3256 - val_mse: 0.9391
Epoch 7/30
99/99 - 2s - loss: 0.3212 - mse: 0.9150 - val_loss: 0.3252 - val_mse: 0.9420

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
AttributeError: 'int' object has no attribute 'assign'

During handling of the above exception, another exception occurred:

AttributeError                            Traceback (most recent call last)
<ipython-input-18-136799157770> in <module>
    481 )
    482 
--> 483 m11 = M.dl_model_predict.v1(
    484     trained_model=m5.data,
    485     input_data=m27.data,

AttributeError: 'int' object has no attribute 'assign'

In [ ]:

ds = m5.data
pd.DataFrame([DataSource(ds.id).read()]).to_pickle('/home/bigquant/work/userlib/model-dnn.csv')