复制链接

克隆策略

TabNet在量化选股中的应用¶

TabNet: Attentive Interpretable Tabular Learning

基于Tabnet模型的量化选股方案。抽取了98个量价因子，2010到2018年为数据训练TabNet模型，并将模型的预测结果应用在2018到2021年9月的数据上进行了回测。

TabNet核心参数

input_dim: 输入的特征数
n_steps: 决策的步数，通常为{3 ~ 10}
n_d: 预测阶段的特征数，通常为{8 ~ 64}
n_a: Attentive阶段的特征数，通常为{8 ~ 64}
gamma: Attentive中注意力更新的比例，通常为{1.0 ~ 2.0}
momentum: BN层的动量，通常为{0.0 ~ 1.0}

In [ ]:

# 本代码由可视化策略环境自动生成 2023年2月6日 17:00
# 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 m12_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'], random_state=2021)
    data_1 = DataSource.write_pickle({'x': x_train, 'y': y_train.reshape(-1, 1)})
    data_2 = DataSource.write_pickle({'x': x_val, 'y': y_val.reshape(-1, 1)})
    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 m12_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 m20_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 m20_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m21_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 m21_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 m21_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2010-01-01',
    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
)

m17 = 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)"""
)

m6 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=10
)

m7 = M.derived_feature_extractor.v3(
    input_data=m6.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m13 = M.standardlize.v8(
    input_1=m7.data,
    input_2=m3.data,
    columns_input='[]'
)

m14 = M.fillnan.v1(
    input_data=m13.data,
    features=m3.data,
    fill_value='0.0'
)

m4 = M.join.v3(
    data1=m17.data,
    data2=m14.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m10 = M.dl_convert_to_bin.v2(
    input_data=m4.data,
    features=m3.data,
    window_size=1,
    feature_clip=3,
    flatten=True,
    window_along_col='instrument'
)

m12 = M.cached.v3(
    input_1=m10.data,
    run=m12_run_bigquant_run,
    post_run=m12_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m18 = M.dl_models_tabnet_train.v1(
    training_data=m12.data_1,
    validation_data=m12.data_2,
    input_dim=98,
    n_steps=3,
    n_d=32,
    n_a=32,
    gamma=1.3,
    momentum=0.02,
    batch_size=5120,
    virtual_batch_size=512,
    epochs=100,
    num_workers=4,
    device_name='auto:自动调用GPU',
    verbose='1:输出进度条记录'
)

m5 = M.instruments.v2(
    start_date='2018-01-01',
    end_date='2021-09-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m8 = M.general_feature_extractor.v7(
    instruments=m5.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=10
)

m9 = M.derived_feature_extractor.v3(
    input_data=m8.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m16 = M.standardlize.v8(
    input_1=m9.data,
    input_2=m3.data,
    columns_input='[]'
)

m15 = M.fillnan.v1(
    input_data=m16.data,
    features=m3.data,
    fill_value='0.0'
)

m11 = M.dl_convert_to_bin.v2(
    input_data=m15.data,
    features=m3.data,
    window_size=1,
    feature_clip=3,
    flatten=True,
    window_along_col='instrument'
)

m19 = M.dl_models_tabnet_predict.v1(
    trained_model=m18.data,
    input_data=m11.data,
    m_cached=False
)

m20 = M.cached.v3(
    input_1=m19.data,
    input_2=m9.data,
    run=m20_run_bigquant_run,
    post_run=m20_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m21 = M.trade.v4(
    instruments=m5.data,
    options_data=m20.data_1,
    start_date='',
    end_date='',
    initialize=m21_initialize_bigquant_run,
    handle_data=m21_handle_data_bigquant_run,
    prepare=m21_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'
)

m22 = M.strategy_turn_analysis.v1(
    raw_perf=m21.raw_perf
)

[2023-02-06 16:37:57.336251] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-02-06 16:37:57.352452] INFO: moduleinvoker: 命中缓存

[2023-02-06 16:37:57.354889] INFO: moduleinvoker: instruments.v2 运行完成[0.018633s].

[2023-02-06 16:37:57.369811] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-02-06 16:38:20.492282] INFO: 自动标注(股票): 加载历史数据: 4597290 行

[2023-02-06 16:38:20.494755] INFO: 自动标注(股票): 开始标注 ..

[2023-02-06 16:38:39.696554] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[42.3267s].

[2023-02-06 16:38:39.722611] INFO: moduleinvoker: standardlize.v8 开始运行..

[2023-02-06 16:39:33.963236] INFO: moduleinvoker: standardlize.v8 运行完成[54.2406s].

[2023-02-06 16:39:33.978601] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-02-06 16:39:33.989988] INFO: moduleinvoker: 命中缓存

[2023-02-06 16:39:33.991618] INFO: moduleinvoker: input_features.v1 运行完成[0.013036s].

[2023-02-06 16:39:34.021812] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-02-06 16:39:34.554094] INFO: 基础特征抽取: 年份 2009, 特征行数=12795

[2023-02-06 16:39:36.172050] INFO: 基础特征抽取: 年份 2010, 特征行数=431567

[2023-02-06 16:39:38.278423] INFO: 基础特征抽取: 年份 2011, 特征行数=511455

[2023-02-06 16:39:40.375428] INFO: 基础特征抽取: 年份 2012, 特征行数=565675

[2023-02-06 16:39:42.438953] INFO: 基础特征抽取: 年份 2013, 特征行数=564168

[2023-02-06 16:39:44.683353] INFO: 基础特征抽取: 年份 2014, 特征行数=569948

[2023-02-06 16:39:46.749629] INFO: 基础特征抽取: 年份 2015, 特征行数=569698

[2023-02-06 16:39:49.161167] INFO: 基础特征抽取: 年份 2016, 特征行数=641546

[2023-02-06 16:39:51.920496] INFO: 基础特征抽取: 年份 2017, 特征行数=743233

[2023-02-06 16:39:52.211382] INFO: 基础特征抽取: 总行数: 4610085

[2023-02-06 16:39:52.224517] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[18.202683s].

[2023-02-06 16:39:52.238909] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-02-06 16:40:07.981329] INFO: derived_feature_extractor: 提取完成 mean(close_0, 5), 3.434s

[2023-02-06 16:40:11.503450] INFO: derived_feature_extractor: 提取完成 mean(low_0, 5), 3.520s

[2023-02-06 16:40:15.259763] INFO: derived_feature_extractor: 提取完成 mean(open_0, 5), 3.755s

[2023-02-06 16:40:18.878552] INFO: derived_feature_extractor: 提取完成 mean(high_0, 5), 3.617s

[2023-02-06 16:40:22.596895] INFO: derived_feature_extractor: 提取完成 mean(turn_0, 5), 3.717s

[2023-02-06 16:40:26.115930] INFO: derived_feature_extractor: 提取完成 mean(amount_0, 5), 3.517s

[2023-02-06 16:40:29.836563] INFO: derived_feature_extractor: 提取完成 mean(return_0, 5), 3.719s

[2023-02-06 16:40:33.714054] INFO: derived_feature_extractor: 提取完成 ts_max(close_0, 5), 3.876s

[2023-02-06 16:40:37.540503] INFO: derived_feature_extractor: 提取完成 ts_max(low_0, 5), 3.823s

[2023-02-06 16:40:41.295402] INFO: derived_feature_extractor: 提取完成 ts_max(open_0, 5), 3.753s

[2023-02-06 16:40:44.961536] INFO: derived_feature_extractor: 提取完成 ts_max(high_0, 5), 3.664s

[2023-02-06 16:40:49.239124] INFO: derived_feature_extractor: 提取完成 ts_max(turn_0, 5), 4.276s

[2023-02-06 16:40:53.082962] INFO: derived_feature_extractor: 提取完成 ts_max(amount_0, 5), 3.842s

[2023-02-06 16:40:56.928948] INFO: derived_feature_extractor: 提取完成 ts_max(return_0, 5), 3.844s

[2023-02-06 16:41:00.841566] INFO: derived_feature_extractor: 提取完成 ts_min(close_0, 5), 3.911s

[2023-02-06 16:41:04.605869] INFO: derived_feature_extractor: 提取完成 ts_min(low_0, 5), 3.763s

[2023-02-06 16:41:08.459554] INFO: derived_feature_extractor: 提取完成 ts_min(open_0, 5), 3.852s

[2023-02-06 16:41:12.164385] INFO: derived_feature_extractor: 提取完成 ts_min(high_0, 5), 3.703s

[2023-02-06 16:41:15.853189] INFO: derived_feature_extractor: 提取完成 ts_min(turn_0, 5), 3.687s

[2023-02-06 16:41:19.803632] INFO: derived_feature_extractor: 提取完成 ts_min(amount_0, 5), 3.944s

[2023-02-06 16:41:23.459307] INFO: derived_feature_extractor: 提取完成 ts_min(return_0, 5), 3.654s

[2023-02-06 16:41:27.253483] INFO: derived_feature_extractor: 提取完成 std(close_0, 5), 3.792s

[2023-02-06 16:41:30.996103] INFO: derived_feature_extractor: 提取完成 std(low_0, 5), 3.741s

[2023-02-06 16:41:34.720316] INFO: derived_feature_extractor: 提取完成 std(open_0, 5), 3.723s

[2023-02-06 16:41:38.366487] INFO: derived_feature_extractor: 提取完成 std(high_0, 5), 3.644s

[2023-02-06 16:41:42.113912] INFO: derived_feature_extractor: 提取完成 std(turn_0, 5), 3.745s

[2023-02-06 16:41:45.903676] INFO: derived_feature_extractor: 提取完成 std(amount_0, 5), 3.788s

[2023-02-06 16:41:49.756957] INFO: derived_feature_extractor: 提取完成 std(return_0, 5), 3.851s

[2023-02-06 16:42:04.406071] INFO: derived_feature_extractor: 提取完成 ts_rank(close_0, 5), 14.646s

[2023-02-06 16:42:18.779127] INFO: derived_feature_extractor: 提取完成 ts_rank(low_0, 5), 14.371s

[2023-02-06 16:42:33.167217] INFO: derived_feature_extractor: 提取完成 ts_rank(open_0, 5), 14.386s

[2023-02-06 16:42:47.890220] INFO: derived_feature_extractor: 提取完成 ts_rank(high_0, 5), 14.721s

[2023-02-06 16:43:02.702455] INFO: derived_feature_extractor: 提取完成 ts_rank(turn_0, 5), 14.810s

[2023-02-06 16:43:17.167617] INFO: derived_feature_extractor: 提取完成 ts_rank(amount_0, 5), 14.463s

[2023-02-06 16:43:31.676192] INFO: derived_feature_extractor: 提取完成 ts_rank(return_0, 5), 14.506s

[2023-02-06 16:43:41.159677] INFO: derived_feature_extractor: 提取完成 decay_linear(close_0, 5), 9.482s

[2023-02-06 16:43:51.650427] INFO: derived_feature_extractor: 提取完成 decay_linear(low_0, 5), 10.489s

[2023-02-06 16:44:02.584390] INFO: derived_feature_extractor: 提取完成 decay_linear(open_0, 5), 10.932s

[2023-02-06 16:44:12.802596] INFO: derived_feature_extractor: 提取完成 decay_linear(high_0, 5), 10.216s

[2023-02-06 16:44:22.761476] INFO: derived_feature_extractor: 提取完成 decay_linear(turn_0, 5), 9.957s

[2023-02-06 16:44:32.519604] INFO: derived_feature_extractor: 提取完成 decay_linear(amount_0, 5), 9.756s

[2023-02-06 16:44:42.181734] INFO: derived_feature_extractor: 提取完成 decay_linear(return_0, 5), 9.660s

[2023-02-06 16:45:08.300387] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, return_0, 5), 26.117s

[2023-02-06 16:45:33.838024] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, high_0, 5), 25.535s

[2023-02-06 16:46:00.181543] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, low_0, 5), 26.342s

[2023-02-06 16:46:26.259549] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, close_0, 5), 26.076s

[2023-02-06 16:46:52.100702] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, open_0, 5), 25.839s

[2023-02-06 16:47:20.074399] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, turn_0, 5), 27.971s

[2023-02-06 16:47:48.500996] INFO: derived_feature_extractor: 提取完成 correlation(return_0, high_0, 5), 28.425s

[2023-02-06 16:48:14.161572] INFO: derived_feature_extractor: 提取完成 correlation(return_0, low_0, 5), 25.659s

[2023-02-06 16:48:39.544091] INFO: derived_feature_extractor: 提取完成 correlation(return_0, close_0, 5), 25.380s

[2023-02-06 16:49:04.768786] INFO: derived_feature_extractor: 提取完成 correlation(return_0, open_0, 5), 25.223s

[2023-02-06 16:49:31.236453] INFO: derived_feature_extractor: 提取完成 correlation(return_0, turn_0, 5), 26.466s

[2023-02-06 16:49:58.010757] INFO: derived_feature_extractor: 提取完成 correlation(high_0, low_0, 5), 26.772s

[2023-02-06 16:50:22.989153] INFO: derived_feature_extractor: 提取完成 correlation(high_0, close_0, 5), 24.977s

[2023-02-06 16:50:48.433728] INFO: derived_feature_extractor: 提取完成 correlation(high_0, open_0, 5), 25.443s

[2023-02-06 16:51:15.464583] INFO: derived_feature_extractor: 提取完成 correlation(high_0, turn_0, 5), 27.029s

[2023-02-06 16:51:43.802066] INFO: derived_feature_extractor: 提取完成 correlation(low_0, close_0, 5), 28.335s

[2023-02-06 16:52:11.512977] INFO: derived_feature_extractor: 提取完成 correlation(low_0, open_0, 5), 27.709s

[2023-02-06 16:52:40.152028] INFO: derived_feature_extractor: 提取完成 correlation(low_0, turn_0, 5), 28.637s

[2023-02-06 16:53:07.370211] INFO: derived_feature_extractor: 提取完成 correlation(close_0, open_0, 5), 27.216s

[2023-02-06 16:53:34.106387] INFO: derived_feature_extractor: 提取完成 correlation(close_0, turn_0, 5), 26.734s

[2023-02-06 16:54:01.725587] INFO: derived_feature_extractor: 提取完成 correlation(open_0, turn_0, 5), 27.617s

/usr/local/python3/lib/python3.8/site-packages/matplotlib/__init__.py:169: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  if LooseVersion(module.__version__) < minver:
/usr/local/python3/lib/python3.8/site-packages/setuptools/_distutils/version.py:351: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  other = LooseVersion(other)
/var/app/data/python_lib/tensorflow_probability/python/__init__.py:61: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  if (distutils.version.LooseVersion(tf.__version__) <
/var/app/data/python_lib/tensorflow_probability/python/__init__.py:61: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  if (distutils.version.LooseVersion(tf.__version__) <
/usr/local/python3/lib/python3.8/site-packages/ray/air/util/tensor_extensions/pandas.py:169: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  if LooseVersion("1.1.0") <= LooseVersion(pd.__version__) < LooseVersion("1.3.0"):

/usr/local/python3/lib/python3.8/site-packages/pandas/compat/_optional.py:116: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  if distutils.version.LooseVersion(version) < minimum_version:
/usr/local/python3/lib/python3.8/site-packages/setuptools/_distutils/version.py:351: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  other = LooseVersion(other)
/usr/local/python3/lib/python3.8/site-packages/tables/atom.py:1224: DeprecationWarning: tostring() is deprecated. Use tobytes() instead.
  return pickle.loads(array.tostring())

In [1]:

# 输出predict
predict_df = m20.data_1.read()
predict_df.head()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-1-01310d04a4de> in <module>
      1 # 输出predict
----> 2 predict_df = m20.data_1.read()
      3 predict_df.head()

NameError: name 'm20' is not defined

In [4]:

predict_df.to_csv("tabnet_predict.csv")

In [ ]: