In [3]:

# 本代码由可视化策略环境自动生成 2023年12月11日 11:21
# 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="m16", name="initialize")
# 回测引擎：初始化函数，只执行一次
def m16_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 = [1]
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 1
    context.options['hold_days'] = 5

# @param(id="m16", name="handle_data")
# 回测引擎：每日数据处理函数，每天执行一次
def m16_handle_data_bigquant_run(context, data):
    # 获取当前持仓
    positions = context.portfolio.positions
    today = data.current_dt.strftime('%Y-%m-%d')

    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == today]

    # 获取涨停状态
    status_df = context.status_df[context.status_df.date == today]

    # 今天涨停持有，不涨停卖出
    for instrument, position in positions.items():
        symbol = instrument.symbol
        if symbol in status_df.instrument.values:
            # 检查是否涨停
            price_limit_status = status_df[status_df.instrument == symbol]['price_limit_status_0'].iloc[0]
            if price_limit_status != 3:
                # 不涨停，卖出
                context.order_target(instrument, 0)

    # 买入逻辑保持不变
    cash_for_buy = context.portfolio.cash
    buy_instruments = list(ranker_prediction.instrument)
    sell_instruments = [instrument.symbol for instrument in positions.keys()]
    to_buy = set(buy_instruments[:1]) - set(sell_instruments) 

    # 如果没有持仓，则买入
    if len(positions) == 0:
        for instrument in to_buy:
            context.order_value(context.symbol(instrument), cash_for_buy)
# @param(id="m16", name="prepare")
def m16_prepare_bigquant_run(context):


     # 获取st状态和涨跌停状态
    
    context.status_df = D.features(instruments =context.instruments,start_date = context.start_date, end_date = context.end_date, 
                           fields=['st_status_0','price_limit_status_0','price_limit_status_1'])

# @param(id="m16", name="before_trading_start")
def m16_before_trading_start_bigquant_run(context, data):
    pass     
#     # 获取涨跌停状态数据
#     df_price_limit_status=context.status_df.set_index('date')
#     today=data.current_dt.strftime('%Y-%m-%d')
#     # 得到当前未完成订单
#     for orders in get_open_orders().values():
#         # 循环，撤销订单
#         for _order in orders:
#             ins=str(_order.sid.symbol)
#             try:
#                 #判断一下如果当日涨停，则取消卖单
#                 if  df_price_limit_status[df_price_limit_status.instrument==ins].price_limit_status_0.loc[today]>2 and _order.amount<0:
#                     cancel_order(_order)
#                     print(today,'尾盘涨停取消卖单',ins) 
#             except:
#                 continue
  
    
    

# @module(position="594,-80", comment='', comment_collapsed=True)
m1 = M.input_features.v1(
    features="""
# #号开始的表示注释，注释需单独一行
# 多个特征，每行一个，可以包含基础特征和衍生特征，特征须为本平台特征
rank_return_90<2
rank_return_5<2
rank_return_20<2
rank_return_10<2
price_limit_status_0
price_limit_status_1
price_limit_status_2
price_limit_status_3
price_limit_status_4
price_limit_status_5
price_limit_status_6
price_limit_status_7
price_limit_status_8
price_limit_status_9
price_limit_status_10
close_0<30
close_0<10
market_cap_float_0<28000000000
market_cap_float_0<10000000000
#avg_turn_5
#avg_turn_10
#turn_0
amount_0
avg_amount_5
#mf_net_pct_xl_0
#amount_0/avg_amount_5>4
#判断放量
#cj=turn_0/turn_1>3&amount_0>3000000000
#turn_0/turn_1>3 and amount_0>3000000000
# 计算过去n个交易日的复权收盘价与换手率的Pearson相关系数
#level_0
turn_0
close_0
correlation(close_0, turn_0, 10)
#10日涨停次数
s2=sum(price_limit_status_0==3, 15)
#5日涨停次数
s3=sum(price_limit_status_0==3, 5)
#涨停排名
s=rank(sum(where(price_limit_status_0 == 3, 1, 0), 5))
#连板次数排名
s1=rank(sum(where(price_limit_status_0 == 3, 1, 0), 15))
#成交额小于10亿
amount_0<1000000000
industry_sw_level1_0
myrank=rank_fs_roe_ttm_0+rank_fs_net_profit_qoq_0-rank_pb_lf_0
#超大单净额
mf_net_amount_xl_0
#15日平均换手率除以当日换手率，用于衡量股票的流动性和热度。
avg_turn_10/turn_0 

#表示相对收益率
#relative_ret=stockret-bmret 
#表示5日相对收益率，是指过去5个交易日的相对收益率之和，用于衡量股票的短期表现。
#relative_ret_5=sum(relative_ret,5)
"""
)

# @module(position="138,12", comment='', comment_collapsed=True)
m2 = M.instruments.v2(
    start_date='2019-01-01',
    end_date='2022-01-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

# @module(position="559,167", comment='', comment_collapsed=True)
m3 = M.general_feature_extractor.v7(
    instruments=m2.data,
    features=m1.data,
    start_date='',
    end_date='',
    before_start_days=90
)

# @module(position="559,267", comment='', comment_collapsed=True)
m4 = M.derived_feature_extractor.v3(
    input_data=m3.data,
    features=m1.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

# @module(position="155,176", comment='', comment_collapsed=True)
m5 = M.advanced_auto_labeler.v2(
    instruments=m2.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)
shift(close, -2) / shift(open, -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)

""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=True,
    user_functions={}
)

# @module(position="170,288", comment='', comment_collapsed=True)
m7 = M.chinaa_stock_filter.v1(
    input_data=m5.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['全部'],
    output_left_data=False
)

# @module(position="291,361", comment='', comment_collapsed=True)
m6 = M.join.v3(
    data1=m7.data,
    data2=m4.data,
    on='date,instrument',
    how='inner',
    sort=False
)

# @module(position="1013,23", comment='', comment_collapsed=True)
m11 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2022-01-02'),
    end_date=T.live_run_param('trading_date', '2023-12-30'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

# @module(position="1069,178", comment='', comment_collapsed=True)
m12 = M.general_feature_extractor.v7(
    instruments=m11.data,
    features=m1.data,
    start_date='',
    end_date='',
    before_start_days=90
)

# @module(position="1069,269", comment='', comment_collapsed=True)
m13 = M.derived_feature_extractor.v3(
    input_data=m12.data,
    features=m1.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=True,
    user_functions={}
)

# @module(position="991,386", comment='', comment_collapsed=True)
m17 = M.chinaa_stock_filter.v1(
    input_data=m13.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['全部'],
    output_left_data=False
)

# @module(position="872,514", comment='', comment_collapsed=True)
m15 = M.filter.v3(
    input_data=m17.data,
    expr='price_limit_status_0==3&price_limit_status_1==3',
    output_left_data=False
)

# @module(position="-131,-101", comment='', comment_collapsed=True)
m20 = M.input_features.v1(
    features="""operatedept_code=operatedept_code_0
operatedept_name
return
close
net
type=type_0
operatedept_code

"""
)

# @module(position="-484,-94", comment='', comment_collapsed=True)
m23 = M.instruments.v2(
    start_date='2022-01-02',
    end_date='2023-12-30',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

# @module(position="-380,97", comment='', comment_collapsed=True)
m18 = M.use_datasource.v2(
    instruments=m23.data,
    features=m20.data,
    datasource_id='dragon_detail_CN_STOCK_A',
    start_date='',
    end_date='',
    before_start_days=90
)

# @module(position="-106,48", comment='', comment_collapsed=True)
m24 = M.input_features.v1(
    features="""
# #号开始的表示注释，注释需单独一行
# 多个特征，每行一个，可以包含基础特征和衍生特征，特征须为本平台特征
type=type
operatedept_code=operatedept_code
zt=((type == '买入金额最大的前5名') & ((where(operatedept_code == '10428246', 1, 0)) + (where(operatedept_code == '10472087', 1, 0)) + (where(operatedept_code == '10484371', 1, 0)) + (where(operatedept_code == '10495103', 1, 0)) + (where(operatedept_code == '10708576', 1, 0))))"""
)

# @module(position="-225,210", comment='', comment_collapsed=True)
m19 = M.derived_feature_extractor.v3(
    input_data=m18.data,
    features=m24.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

# @module(position="39,456", comment='', comment_collapsed=True)
m21 = M.join.v3(
    data1=m19.data,
    data2=m6.data,
    on='date,instrument',
    how='inner',
    sort=False
)

# @module(position="281,536", comment='', comment_collapsed=True)
m14 = M.filter.v3(
    input_data=m21.data,
    expr='price_limit_status_0==3&price_limit_status_1==3',
    output_left_data=False
)

# @module(position="200,645", comment='', comment_collapsed=True)
m8 = M.dropnan.v2(
    input_data=m14.data
)

# @module(position="376,788", comment='', comment_collapsed=True)
m9 = M.stock_ranker_train.v6(
    training_ds=m8.data,
    features=m1.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.4,
    max_bins=1023,
    feature_fraction=1,
    data_row_fraction=1,
    plot_charts=True,
    ndcg_discount_base=1,
    m_lazy_run=False
)

# @module(position="685,907", comment='', comment_collapsed=True)
m10 = M.stock_ranker_predict.v5(
    model=m9.model,
    data=m15.data,
    m_lazy_run=False
)

# @module(position="593,1082", comment='', comment_collapsed=True)
m16 = M.trade.v4(
    instruments=m11.data,
    options_data=m10.predictions,
    start_date='',
    end_date='',
    initialize=m16_initialize_bigquant_run,
    handle_data=m16_handle_data_bigquant_run,
    prepare=m16_prepare_bigquant_run,
    before_trading_start=m16_before_trading_start_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=100000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.SHA'
)
# </aistudiograph>

[2023-12-11 11:10:46.323182] INFO: moduleinvoker:2572406930.py:111: input_features.v1 开始运行..
[2023-12-11 11:10:46.374313] INFO: moduleinvoker:2572406930.py:111: input_features.v1 运行完成[0.051071s].
[2023-12-11 11:10:46.390710] INFO: moduleinvoker:2572406930.py:174: instruments.v2 开始运行..
[2023-12-11 11:10:46.413874] INFO: moduleinvoker:2572406930.py:174: 命中缓存
[2023-12-11 11:10:46.417936] INFO: moduleinvoker:2572406930.py:174: instruments.v2 运行完成[0.027241s].
[2023-12-11 11:10:46.461067] INFO: moduleinvoker:2572406930.py:183: general_feature_extractor.v7 开始运行..

[2023-12-11 11:10:50.236512] INFO 基础特征抽取: 年份 2018, 特征行数=210561
[2023-12-11 11:10:58.044149] INFO 基础特征抽取: 年份 2019, 特征行数=884867
[2023-12-11 11:11:05.923772] INFO 基础特征抽取: 年份 2020, 特征行数=945961
[2023-12-11 11:11:15.003932] INFO 基础特征抽取: 年份 2021, 特征行数=1061527
[2023-12-11 11:11:16.353519] INFO 基础特征抽取: 年份 2022, 特征行数=0
[2023-12-11 11:11:16.826381] INFO 基础特征抽取: 总行数: 3102916

[2023-12-11 11:11:16.834671] INFO: moduleinvoker:2572406930.py:183: general_feature_extractor.v7 运行完成[30.373583s].
[2023-12-11 11:11:16.856246] INFO: moduleinvoker:2572406930.py:192: derived_feature_extractor.v3 开始运行..

[2023-12-11 11:11:36.372132] INFO derived_feature_extractor: 提取完成 rank_return_90<2, 0.007s
[2023-12-11 11:11:36.382938] INFO derived_feature_extractor: 提取完成 rank_return_5<2, 0.007s
[2023-12-11 11:11:36.392961] INFO derived_feature_extractor: 提取完成 rank_return_20<2, 0.006s
[2023-12-11 11:11:36.406923] INFO derived_feature_extractor: 提取完成 rank_return_10<2, 0.006s
[2023-12-11 11:11:36.416682] INFO derived_feature_extractor: 提取完成 close_0<30, 0.006s
[2023-12-11 11:11:36.427735] INFO derived_feature_extractor: 提取完成 close_0<10, 0.008s
[2023-12-11 11:11:36.438460] INFO derived_feature_extractor: 提取完成 market_cap_float_0<28000000000, 0.007s
[2023-12-11 11:11:36.449061] INFO derived_feature_extractor: 提取完成 market_cap_float_0<10000000000, 0.007s
[2023-12-11 11:12:47.033619] INFO derived_feature_extractor: 提取完成 correlation(close_0, turn_0, 10), 70.581s
[2023-12-11 11:12:51.472188] INFO derived_feature_extractor: 提取完成 s2=sum(price_limit_status_0==3, 15), 4.435s
[2023-12-11 11:12:55.321745] INFO derived_feature_extractor: 提取完成 s3=sum(price_limit_status_0==3, 5), 3.846s
[2023-12-11 11:13:00.825413] INFO derived_feature_extractor: 提取完成 s=rank(sum(where(price_limit_status_0 == 3, 1, 0), 5)), 5.500s
[2023-12-11 11:13:05.853612] INFO derived_feature_extractor: 提取完成 s1=rank(sum(where(price_limit_status_0 == 3, 1, 0), 15)), 5.025s
[2023-12-11 11:13:05.867238] INFO derived_feature_extractor: 提取完成 amount_0<1000000000, 0.010s
[2023-12-11 11:13:05.886249] INFO derived_feature_extractor: 提取完成 myrank=rank_fs_roe_ttm_0+rank_fs_net_profit_qoq_0-rank_pb_lf_0, 0.015s
[2023-12-11 11:13:05.901080] INFO derived_feature_extractor: 提取完成 avg_turn_10/turn_0, 0.011s
[2023-12-11 11:13:09.595359] INFO derived_feature_extractor: /y_2018, 210561
[2023-12-11 11:13:15.181441] INFO derived_feature_extractor: /y_2019, 884867
[2023-12-11 11:13:22.026643] INFO derived_feature_extractor: /y_2020, 945961
[2023-12-11 11:13:29.698105] INFO derived_feature_extractor: /y_2021, 1061527

[2023-12-11 11:13:31.739552] INFO: moduleinvoker:2572406930.py:192: derived_feature_extractor.v3 运行完成[134.883324s].
[2023-12-11 11:13:31.942303] INFO: moduleinvoker:2572406930.py:203: factorlens.v2 开始运行..
[2023-12-11 11:13:33.106605] ERROR: moduleinvoker:2572406930.py:203: module name: factorlens, module version: v2, trackeback: _pickle.UnpicklingError: invalid load key, 'H'.

---------------------------------------------------------------------------
UnpicklingError                           Traceback (most recent call last)
Cell In[3], line 203
    192 m4 = M.derived_feature_extractor.v3(
    193     input_data=m3.data,
    194     features=m1.data,
   (...)
    199     user_functions={}
    200 )
    202 # @module(position="554.5902404785156,387.44156646728516", comment='', comment_collapsed=True)
--> 203 m22 = M.factorlens.v2(
    204     features=m4.data,
    205     title='因子分析: {factor_name}',
    206     start_date='2019-01-01',
    207     end_date='2019-12-31',
    208     rebalance_period=22,
    209     delay_rebalance_days=0,
    210     rebalance_price='close_0',
    211     stock_pool='全市场',
    212     quantile_count=5,
    213     commission_rate=0.0016,
    214     returns_calculation_method='累乘',
    215     benchmark='无',
    216     drop_new_stocks=60,
    217     drop_price_limit_stocks=False,
    218     drop_st_stocks=False,
    219     drop_suspended_stocks=False,
    220     cutoutliers=True,
    221     normalization=True,
    222     neutralization=[],
    223     metrics=['因子表现概览', '因子分布', '因子行业分布', '因子市值分布', 'IC分析', '买入信号重合分析', '因子估值分析', '因子拥挤度分析', '因子值最大/最小股票', '表达式因子值', '多因子相关性分析'],
    224     factor_coverage=0.5,
    225     user_data_merge='left'
    226 )
    228 # @module(position="155,176", comment='', comment_collapsed=True)
    229 m5 = M.advanced_auto_labeler.v2(
    230     instruments=m2.data,
    231     label_expr="""# #号开始的表示注释
   (...)
    255     user_functions={}
    256 )

File module2/common/modulemanagerv2.py:88, in biglearning.module2.common.modulemanagerv2.BigQuantModuleVersion.__call__()

File module2/common/moduleinvoker.py:370, in biglearning.module2.common.moduleinvoker.module_invoke()

File module2/common/moduleinvoker.py:292, in biglearning.module2.common.moduleinvoker._invoke_with_cache()

File module2/common/moduleinvoker.py:253, in biglearning.module2.common.moduleinvoker._invoke_with_cache()

File module2/common/moduleinvoker.py:210, in biglearning.module2.common.moduleinvoker._module_run()

File module2/modules/factorlens/v2/__init__.py:220, in biglearning.module2.modules.factorlens.v2.__init__.bigquant_run()

File module2/common/utils.py:81, in biglearning.module2.common.utils.smart_list()

File module2/common/utils.py:50, in biglearning.module2.common.utils.smart_object()

File /var/app/enabled/bigdatasource/api/v6/__init__.py:70, in read_pickle(self, use_dill, return_use_dill)

File /var/app/enabled/bigdatasource/impl/dsimpl/pkl.py:50, in read_pickle(id, version, use_dill, return_use_dill)

UnpicklingError: invalid load key, 'H'.

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m19, column_name="date")

[2023-12-11 01:39:33.707704] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

	type	net	date	sell	reason	operatedept_code	instrument	close	operatedept_name	buy
Loading... (need help?)

date列数据统计值

行数：1000

列数：10

缺失值：0

唯一值：2

In [ ]:

m19.data.read()

Out[ ]:

	type	net	date	sell	reason	operatedept_code	instrument	close	operatedept_name	buy	return
0	卖出金额最大的前5名	-12124152.00	2021-12-28	14322851.00	日跌幅偏离值达到7%的前5只证券	10088113	000665.SZA	6.26	中国国际金融股份有限公司上海分公司	2198699.00	None
1	卖出金额最大的前5名	-15547779.32	2021-12-28	15547779.32	日跌幅偏离值达到7%的前5只证券	10442978	000665.SZA	6.26	华鑫证券有限责任公司江苏分公司	0.00	None
2	卖出金额最大的前5名	-32449164.68	2021-12-28	33655175.68	连续三个交易日内，跌幅偏离值累计达到20%的证券	10586323	000665.SZA	6.26	中信证券股份有限公司宁波和义路证券营业部	1206011.00	None
3	买入金额最大的前5名	17122248.15	2021-12-28	21613578.60	连续三个交易日内，跌幅偏离值累计达到20%的证券	10472087	000665.SZA	6.26	东方财富证券股份有限公司拉萨东环路第二证券营业部	38735826.75	None
4	卖出金额最大的前5名	-168588.73	2021-12-28	16011448.73	日跌幅偏离值达到7%的前5只证券	10428246	000665.SZA	6.26	东方财富证券股份有限公司拉萨东环路第一证券营业部	15842860.00	None
...	...	...	...	...	...	...	...	...	...	...	...
300412	卖出金额最大的前5名	-4620529.07	2023-12-08	4945459.26	当日换手率达到20%的前5只股票	10174510	873152.BJA	12.00	平安证券股份有限公司广西分公司	324930.19	None
300413	卖出金额最大的前5名	-1428626.34	2023-12-08	4913562.93	当日换手率达到20%的前5只股票	10472087	873152.BJA	12.00	东方财富证券股份有限公司拉萨东环路第二证券营业部	3484936.59	None
300414	卖出金额最大的前5名	-98887.31	2023-12-08	3990930.10	当日换手率达到20%的前5只股票	10495103	873152.BJA	12.00	东方财富证券股份有限公司拉萨团结路第二证券营业部	3892042.79	None
300415	卖出金额最大的前5名	-3567388.55	2023-12-08	3567388.55	当日换手率达到20%的前5只股票	10129981	873152.BJA	12.00	国信证券股份有限公司宁波宁穿路证券营业部	0.00	None
300416	卖出金额最大的前5名	-501581.21	2023-12-08	3537431.86	当日换手率达到20%的前5只股票	10428246	873152.BJA	12.00	东方财富证券股份有限公司拉萨东环路第一证券营业部	3035850.65	None

300417 rows × 11 columns

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m14, column_name="date")

[2023-12-10 21:51:53.033912] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

	amount_0	avg_amount_5	close_0	date	instrument	market_cap_float_0	price_limit_status_0	price_limit_status_1	price_limit_status_10	price_limit_status_2	price_limit_status_3	price_limit_status_4	price_limit_status_5	price_limit_status_6	price_limit_status_7	price_limit_status_8	price_limit_status_9	rank_return_10	rank_return_20	rank_return_5	rank_return_90	turn_0	rank_return_90<2	rank_return_5<2	rank_return_20<2	rank_return_10<2	close_0<30	close_0<10	market_cap_float_0<28000000000	market_cap_float_0<10000000000	correlation(close_0, turn_0, 10)	s2	s3	s	s1	amount_0<1000000000	m:amount	m:close	m:low	m:high	m:open	label
Loading... (need help?)

date列数据统计值

行数：1000

列数：42

缺失值：0

唯一值：491

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m19, column_name="date")

[2023-12-11 00:03:48.140249] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

	type	net	date	sell	reason	operatedept_code	instrument	close	operatedept_name	buy	return
Loading... (need help?)

date列数据统计值

行数：1000

列数：11

缺失值：0

唯一值：2

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m19, column_name="date")

[2023-12-11 00:12:31.630533] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

	type	net	date	sell	reason	operatedept_code	instrument	close	operatedept_name	buy	return
Loading... (need help?)

date列数据统计值

行数：1000

列数：11

缺失值：0

唯一值：2

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m14, column_name="date")

[2023-12-10 21:52:49.923785] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

	amount_0	avg_amount_5	close_0	date	instrument	market_cap_float_0	price_limit_status_0	price_limit_status_1	price_limit_status_10	price_limit_status_2	price_limit_status_3	price_limit_status_4	price_limit_status_5	price_limit_status_6	price_limit_status_7	price_limit_status_8	price_limit_status_9	rank_return_10	rank_return_20	rank_return_5	rank_return_90	turn_0	rank_return_90<2	rank_return_5<2	rank_return_20<2	rank_return_10<2	close_0<30	close_0<10	market_cap_float_0<28000000000	market_cap_float_0<10000000000	correlation(close_0, turn_0, 10)	s2	s3	s	s1	amount_0<1000000000	m:amount	m:close	m:low	m:high	m:open	label
Loading... (need help?)

date列数据统计值

行数：1000

列数：42

缺失值：0

唯一值：491

In [ ]:

m9.model_id

Out[ ]:

'70adc104976211ee8e7eaa055e4d0bac'

In [ ]:

m9.plot_model()

[2023-12-10 21:52:50.313820] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

Out[ ]:

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m4, column_name="date")

[2023-12-10 21:53:12.516765] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

	amount_0	avg_amount_5	close_0	date	instrument	market_cap_float_0	price_limit_status_0	price_limit_status_1	price_limit_status_10	price_limit_status_2	price_limit_status_3	price_limit_status_4	price_limit_status_5	price_limit_status_6	price_limit_status_7	price_limit_status_8	price_limit_status_9	rank_return_10	rank_return_20	rank_return_5	rank_return_90	turn_0	rank_return_90<2	rank_return_5<2	rank_return_20<2	rank_return_10<2	close_0<30	close_0<10	market_cap_float_0<28000000000	market_cap_float_0<10000000000	correlation(close_0, turn_0, 10)	s2	s3	s	s1	amount_0<1000000000
Loading... (need help?)

date列数据统计值

行数：1000

列数：36

缺失值：0

唯一值：60

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m9, column_name="date")

模块结果无法查看

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m6, column_name="date")

[2023-12-10 21:53:31.680921] INFO: bigcharts.impl.render:render.py:408:render_chart Data is None, skip loading it to chart.

	amount_0	avg_amount_5	close_0	date	instrument	market_cap_float_0	price_limit_status_0	price_limit_status_1	price_limit_status_10	price_limit_status_2	price_limit_status_3	price_limit_status_4	price_limit_status_5	price_limit_status_6	price_limit_status_7	price_limit_status_8	price_limit_status_9	rank_return_10	rank_return_20	rank_return_5	rank_return_90	turn_0	rank_return_90<2	rank_return_5<2	rank_return_20<2	rank_return_10<2	close_0<30	close_0<10	market_cap_float_0<28000000000	market_cap_float_0<10000000000	correlation(close_0, turn_0, 10)	s2	s3	s	s1	amount_0<1000000000	m:amount	m:close	m:low	m:high	m:open	label
Loading... (need help?)

date列数据统计值

行数：1000

列数：42

缺失值：0

唯一值：728

In [ ]:

from biglearning.api.tools import view_model_result 

# 查看模块运行结果,通过column_name指定需要统计的字段 
view_model_result(m10, column_name="date")

模块结果无法查看

In [ ]:

m10.predictions.read()

Out[ ]:

	date	instrument	score	position
0	2021-10-08	603978.SHA	0.256047	1
1	2021-10-08	605162.SHA	0.158742	2
2	2021-10-08	600268.SHA	0.061198	3
3	2021-10-08	001217.SZA	-0.058698	4
4	2021-10-08	600071.SHA	-0.064584	5
...	...	...	...	...
6182	2023-12-08	603038.SHA	0.001042	5
6183	2023-12-08	603189.SHA	-0.005783	6
6184	2023-12-08	603938.SHA	-0.034713	7
6185	2023-12-08	603660.SHA	-0.097266	8
6186	2023-12-08	002962.SZA	-0.162609	9

6187 rows × 4 columns