克隆策略

In [95]:

m8.predictions.read().head()

Out[95]:

	score	date	instrument	position
0	1.206727	2014-10-29	600035.SHA	1
1	0.970216	2014-10-29	600004.SHA	2
2	0.948796	2014-10-29	600486.SHA	3
3	0.939215	2014-10-29	601555.SHA	4
4	0.938887	2014-10-29	002598.SZA	5

In [100]:

m12.predictions.read().head()

Out[100]:

	classes_prob_0	classes_prob_1	date	instrument
2	0.640431	0.359569	2014-10-30	000001.SZA
21	0.679217	0.320783	2014-11-26	000001.SZA
35	0.571991	0.428009	2014-12-16	000001.SZA
39	0.699138	0.300862	2014-12-22	000001.SZA
46	0.650829	0.349171	2014-12-31	000001.SZA

In [103]:

df1 = m8.predictions.read_df()
df1_filter=df1.groupby('date',group_keys=False).apply(lambda x:x.sort_values('position')[:2]).reset_index(drop=True)
df1.head()

Out[103]:

	score	date	instrument	position
0	1.206727	2014-10-29	600035.SHA	1
1	0.970216	2014-10-29	600004.SHA	2
2	0.948796	2014-10-29	600486.SHA	3
3	0.939215	2014-10-29	601555.SHA	4
4	0.938887	2014-10-29	002598.SZA	5

In [121]:

df2 = m12.predictions.read_df()

df2_filter=df2.groupby('date',group_keys=False).apply(lambda x:x.sort_values('classes_prob_0')[:2]).reset_index(drop=True)
df2_filter.head()

Out[121]:

	classes_prob_0	classes_prob_1	date	instrument
0	0.522840	0.477160	2014-10-29	600834.SHA
1	0.526359	0.473641	2014-10-29	002682.SZA
2	0.549988	0.450012	2014-10-30	000657.SZA
3	0.566365	0.433635	2014-10-30	300093.SZA
4	0.563091	0.436909	2014-10-31	600259.SHA

In [125]:

df=pd.merge(df1_filter,df2_filter,left_on=['date','instrument'],right_on=['date','instrument']).sort_values(['date','position'])
df.head()

Out[125]:

	score	date	instrument	position	classes_prob_0	classes_prob_1
0	1.155616	2014-10-31	600259.SHA	1	0.563091	0.436909
1	0.787467	2014-11-04	600359.SHA	1	0.543182	0.456818
2	1.261694	2014-11-07	600446.SHA	1	0.519923	0.480077
3	1.308929	2014-11-13	002274.SZA	2	0.551363	0.448637
4	1.252863	2014-11-14	600100.SHA	2	0.533990	0.466010

In [132]:

# 本代码由可视化策略环境自动生成 2019年1月29日 17:15
# 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 m11_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    f1 = input_1.read_pickle()
    f2 = input_2.read_pickle()
    factors = [ k for k in set(f1 + f2)]
    data_1 = DataSource.write_pickle(factors)
    return Outputs(data_1=data_1, 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 m11_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 m35_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    f1 = input_1.read_pickle()
    f2 = input_2.read_pickle()
    factors = [ k for k in set(f1 + f2)]
    data_1 = DataSource.write_pickle(factors)
    return Outputs(data_1=data_1, 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 m35_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 m36_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    f1 = input_1.read_pickle()
    f2 = input_2.read_pickle()
    factors = [ k for k in set(f1 + f2)]
    data_1 = DataSource.write_pickle(factors)
    return Outputs(data_1=data_1, 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 m36_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 m25_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df1=input_1.read_df()
    df1_filter=df1.groupby('date',group_keys=False).apply(lambda x:x.sort_values('position')[:2]).reset_index(drop=True)
    df2=input_2.read_df()
    df2_filter=df2.groupby('date',group_keys=False).apply(lambda x:x.sort_values('classes_prob_0')[:2]).reset_index(drop=True)
    
    df=pd.merge(df1_filter,df2_filter,left_on=['date','instrument'],right_on=['date','instrument']).sort_values(['date','position'])
    
    data_1 = DataSource.write_df(df)
    return Outputs(data_1=data_1, 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 m25_post_run_bigquant_run(outputs):
    return outputs

# 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):

    # 获取今日的日期
    today = data.current_dt.strftime('%Y-%m-%d')  
    
    # 通过positions对象，使用列表生成式的方法获取目前持仓的股票列表
    stock_hold_now = [equity.symbol for equity in context.portfolio.positions ]      
    
    # 按日期过滤得到今日的预测数据,和买入备选股票列表
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
    stock_to_buy = list(ranker_prediction.instrument)
    
    # 需要卖出的股票:已有持仓中不在买入列表的股票
    stock_to_sell = [ i for i in stock_hold_now if i not in stock_to_buy]
    
    # 生成卖出订单：
    if len(stock_to_sell)>0:
        for instrument in stock_to_sell:
            sid = context.symbol(instrument) # 将标的转化为equity格式
            cur_position = context.portfolio.positions[sid].amount # 持仓
            if cur_position > 0 and data.can_trade(sid):
                context.order_target_percent(sid, 0) # 全部卖出   
    
    
    # 生成买入订单：买入每天两个策略前两名的股票
    if len(stock_to_buy)>0:
        if len(stock_to_buy)>0:
            weight = 1/4 # 每只股票的比重为等资金比例持有1/4仓位
            for instrument in stock_to_buy:
                sid = context.symbol(instrument) # 将标的转化为equity格式
                if  data.can_trade(sid):
                    context.order_target_percent(sid, weight) # 买入

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

# 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 = 4
    # 每只的股票等资金分配
    context.stock_weights = [1/stock_count for i in range(4)]


m1 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2015-01-01',
    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, -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
)

m3 = M.input_features.v1(
    features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
return_0
return_4
return_5"""
)

m26 = M.input_features.v1(
    features_ds=m3.data,
    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
st_status_0
return_90
return_10
return_80
return_0
high_0
low_0
close_0
open_0


"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m26.data,
    start_date='',
    end_date=''
)

m32 = M.input_features.v1(
    features_ds=m3.data,
    features="""
# 输入参与训练的自定义列

ret1
ret2
ret3
"""
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2015-01-01'),
    end_date=T.live_run_param('trading_date', '2019-01-01'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m4 = M.input_features.v1(
    features="""
# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
return_0
return_4
return_5"""
)

m27 = M.input_features.v1(
    features_ds=m4.data,
    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
st_status_0
return_90
return_10
return_80
high_0
low_0
close_0
open_0"""
)

m11 = M.cached.v3(
    input_1=m26.data,
    input_2=m27.data,
    run=m11_run_bigquant_run,
    post_run=m11_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m11.data_1,
    start_date='',
    end_date=''
)

m38 = M.input_features.v1(
    features_ds=m4.data,
    features="""
# 输入参与训练的自定义列

ret1
ret2
ret3
"""
)

m5 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2015-01-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m10 = M.advanced_auto_labeler.v2(
    instruments=m5.data,
    label_expr="""

# 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, -2) / shift(open, -1)-1>0.01, 1, 0)

# 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={}
)

m42 = M.general_feature_extractor.v7(
    instruments=m5.data,
    features=m27.data,
    start_date='',
    end_date=''
)

m28 = 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
mid=mean(close_0,14)
atr=ta_atr(high_0, low_0, close_0, 14)
ret1=return_90/return_10
ret2=return_80/return_10
ret3=return_5/return_0

"""
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m28.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m30 = 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
cond2=(close_0>atr+mid) & (shift(close_0, 1) < shift(atr+mid, 1))
"""
)

m29 = M.derived_feature_extractor.v3(
    input_data=m16.data,
    features=m30.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m29.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m39 = M.filter.v3(
    input_data=m7.data,
    expr='st_status_0 == 0 and cond2>0',
    output_left_data=False
)

m13 = M.dropnan.v1(
    input_data=m39.data
)

m6 = M.stock_ranker_train.v5(
    training_ds=m13.data,
    features=m32.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    m_lazy_run=False
)

m34 = 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
mid=mean(close_0,14)
atr=ta_atr(high_0, low_0, close_0, 14)
ret1=return_90/return_10
ret2=return_80/return_10
ret3=return_5/return_0

"""
)

m20 = M.derived_feature_extractor.v3(
    input_data=m42.data,
    features=m34.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False,
    user_functions={}
)

m35 = M.cached.v3(
    input_1=m28.data,
    input_2=m34.data,
    run=m35_run_bigquant_run,
    post_run=m35_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m35.data_1,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m37 = 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
cond2=(close_0>atr+mid) & (shift(close_0, 1) < shift(atr+mid, 1))


"""
)

m36 = M.cached.v3(
    input_1=m30.data,
    input_2=m37.data,
    run=m36_run_bigquant_run,
    post_run=m36_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m31 = M.derived_feature_extractor.v3(
    input_data=m18.data,
    features=m36.data_1,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m41 = M.filter.v3(
    input_data=m31.data,
    expr='st_status_0 == 0 and cond2>0',
    output_left_data=False
)

m14 = M.dropnan.v1(
    input_data=m41.data
)

m8 = M.stock_ranker_predict.v5(
    model=m6.model,
    data=m14.data,
    m_lazy_run=False
)

m33 = M.derived_feature_extractor.v3(
    input_data=m20.data,
    features=m37.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m21 = M.join.v3(
    data1=m33.data,
    data2=m10.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m40 = M.filter.v3(
    input_data=m21.data,
    expr='st_status_0 == 0 and cond2>0',
    output_left_data=False
)

m22 = M.dropnan.v1(
    input_data=m40.data
)

m12 = M.random_forest_classifier.v1(
    training_ds=m22.data,
    features=m38.data,
    predict_ds=m14.data,
    iterations=10,
    feature_fraction=1,
    max_depth=30,
    min_samples_per_leaf=200,
    key_cols='date,instrument',
    workers=2,
    other_train_parameters={}
)

m25 = M.cached.v3(
    input_1=m8.predictions,
    input_2=m12.predictions,
    run=m25_run_bigquant_run,
    post_run=m25_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m25.data_1,
    start_date='',
    end_date='',
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    initialize=m19_initialize_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=''
)

[2019-01-29 17:08:05.456702] INFO: bigquant: instruments.v2 开始运行..
[2019-01-29 17:08:05.463487] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.465099] INFO: bigquant: instruments.v2 运行完成[0.008419s].
[2019-01-29 17:08:05.468339] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
[2019-01-29 17:08:05.473832] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.475361] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.007017s].
[2019-01-29 17:08:05.478080] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:08:05.483138] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.484320] INFO: bigquant: input_features.v1 运行完成[0.006275s].
[2019-01-29 17:08:05.486660] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:08:05.491766] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.492765] INFO: bigquant: input_features.v1 运行完成[0.006078s].
[2019-01-29 17:08:05.500425] INFO: bigquant: general_feature_extractor.v7 开始运行..
[2019-01-29 17:08:05.505565] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.506614] INFO: bigquant: general_feature_extractor.v7 运行完成[0.006162s].
[2019-01-29 17:08:05.509472] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:08:05.514366] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.515247] INFO: bigquant: input_features.v1 运行完成[0.005764s].
[2019-01-29 17:08:05.518065] INFO: bigquant: instruments.v2 开始运行..
[2019-01-29 17:08:05.523972] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.524952] INFO: bigquant: instruments.v2 运行完成[0.006908s].
[2019-01-29 17:08:05.527103] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:08:05.531198] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.531925] INFO: bigquant: input_features.v1 运行完成[0.004821s].
[2019-01-29 17:08:05.534311] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:08:05.538189] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.538919] INFO: bigquant: input_features.v1 运行完成[0.004604s].
[2019-01-29 17:08:05.543024] INFO: bigquant: cached.v3 开始运行..
[2019-01-29 17:08:05.549438] INFO: bigquant: 命中缓存
[2019-01-29 17:08:05.551093] INFO: bigquant: cached.v3 运行完成[0.00808s].
[2019-01-29 17:08:05.557968] INFO: bigquant: general_feature_extractor.v7 开始运行..
[2019-01-29 17:08:52.258840] INFO: 基础特征抽取: 年份 2014, 特征行数=141569
[2019-01-29 17:09:35.642926] INFO: 基础特征抽取: 年份 2015, 特征行数=569698
[2019-01-29 17:10:13.367252] INFO: 基础特征抽取: 年份 2016, 特征行数=641546
[2019-01-29 17:11:32.565460] INFO: 基础特征抽取: 年份 2017, 特征行数=743233
[2019-01-29 17:11:44.714231] INFO: 基础特征抽取: 年份 2018, 特征行数=816977
[2019-01-29 17:11:47.276421] INFO: 基础特征抽取: 年份 2019, 特征行数=0
[2019-01-29 17:11:47.305215] INFO: 基础特征抽取: 总行数: 2913023
[2019-01-29 17:11:47.308502] INFO: bigquant: general_feature_extractor.v7 运行完成[221.750514s].
[2019-01-29 17:11:47.312266] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:11:47.325354] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.326730] INFO: bigquant: input_features.v1 运行完成[0.014477s].
[2019-01-29 17:11:47.329545] INFO: bigquant: instruments.v2 开始运行..
[2019-01-29 17:11:47.334760] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.335963] INFO: bigquant: instruments.v2 运行完成[0.006419s].
[2019-01-29 17:11:47.338829] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
[2019-01-29 17:11:47.345261] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.346888] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.008043s].
[2019-01-29 17:11:47.358525] INFO: bigquant: general_feature_extractor.v7 开始运行..
[2019-01-29 17:11:47.365145] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.366228] INFO: bigquant: general_feature_extractor.v7 运行完成[0.007696s].
[2019-01-29 17:11:47.369365] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:11:47.378227] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.379417] INFO: bigquant: input_features.v1 运行完成[0.01004s].
[2019-01-29 17:11:47.383103] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-01-29 17:11:47.388892] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.389915] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.006859s].
[2019-01-29 17:11:47.392943] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:11:47.399194] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.400186] INFO: bigquant: input_features.v1 运行完成[0.007238s].
[2019-01-29 17:11:47.403454] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-01-29 17:11:47.408570] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.409510] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.006062s].
[2019-01-29 17:11:47.412413] INFO: bigquant: join.v3 开始运行..
[2019-01-29 17:11:47.429635] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.430752] INFO: bigquant: join.v3 运行完成[0.018311s].
[2019-01-29 17:11:47.433516] INFO: bigquant: filter.v3 开始运行..
[2019-01-29 17:11:47.528756] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.529836] INFO: bigquant: filter.v3 运行完成[0.096307s].
[2019-01-29 17:11:47.532978] INFO: bigquant: dropnan.v1 开始运行..
[2019-01-29 17:11:47.538862] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.539921] INFO: bigquant: dropnan.v1 运行完成[0.006915s].
[2019-01-29 17:11:47.549994] INFO: bigquant: stock_ranker_train.v5 开始运行..
[2019-01-29 17:11:47.645773] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.648050] INFO: bigquant: stock_ranker_train.v5 运行完成[0.098022s].
[2019-01-29 17:11:47.651050] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:11:47.658371] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.659557] INFO: bigquant: input_features.v1 运行完成[0.00853s].
[2019-01-29 17:11:47.662536] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-01-29 17:11:47.668840] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.670248] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.00771s].
[2019-01-29 17:11:47.674402] INFO: bigquant: cached.v3 开始运行..
[2019-01-29 17:11:47.731124] INFO: bigquant: 命中缓存
[2019-01-29 17:11:47.732752] INFO: bigquant: cached.v3 运行完成[0.058339s].
[2019-01-29 17:11:47.735513] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-01-29 17:11:50.038413] INFO: derived_feature_extractor: 提取完成 ret1=return_90/return_10, 0.021s
[2019-01-29 17:11:50.061002] INFO: derived_feature_extractor: 提取完成 ret2=return_80/return_10, 0.021s
[2019-01-29 17:11:50.074692] INFO: derived_feature_extractor: 提取完成 ret3=return_5/return_0, 0.012s
[2019-01-29 17:11:54.244030] INFO: derived_feature_extractor: 提取完成 mid=mean(close_0,14), 4.168s
[2019-01-29 17:12:01.152997] INFO: derived_feature_extractor: 提取完成 atr=ta_atr(high_0, low_0, close_0, 14), 6.906s
[2019-01-29 17:12:02.297576] INFO: derived_feature_extractor: /y_2014, 141569
[2019-01-29 17:12:02.574686] INFO: derived_feature_extractor: /y_2015, 569698
[2019-01-29 17:12:03.463373] INFO: derived_feature_extractor: /y_2016, 641546
[2019-01-29 17:12:04.362990] INFO: derived_feature_extractor: /y_2017, 743233
[2019-01-29 17:12:05.877658] INFO: derived_feature_extractor: /y_2018, 816977
[2019-01-29 17:12:07.412928] INFO: bigquant: derived_feature_extractor.v3 运行完成[19.677385s].
[2019-01-29 17:12:07.416398] INFO: bigquant: input_features.v1 开始运行..
[2019-01-29 17:12:07.422133] INFO: bigquant: 命中缓存
[2019-01-29 17:12:07.423153] INFO: bigquant: input_features.v1 运行完成[0.006755s].
[2019-01-29 17:12:07.427898] INFO: bigquant: cached.v3 开始运行..
[2019-01-29 17:12:07.434072] INFO: bigquant: 命中缓存
[2019-01-29 17:12:07.434968] INFO: bigquant: cached.v3 运行完成[0.007081s].
[2019-01-29 17:12:07.438233] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-01-29 17:12:09.874992] INFO: derived_feature_extractor: 提取完成 cond2=(close_0>atr+mid) & (shift(close_0, 1) < shift(atr+mid, 1)), 1.286s
[2019-01-29 17:12:09.953130] INFO: derived_feature_extractor: /y_2014, 104572
[2019-01-29 17:12:10.424702] INFO: derived_feature_extractor: /y_2015, 547984
[2019-01-29 17:12:11.318960] INFO: derived_feature_extractor: /y_2016, 625475
[2019-01-29 17:12:12.269310] INFO: derived_feature_extractor: /y_2017, 702247
[2019-01-29 17:12:13.792519] INFO: derived_feature_extractor: /y_2018, 802730
[2019-01-29 17:12:15.355325] INFO: bigquant: derived_feature_extractor.v3 运行完成[7.917064s].
[2019-01-29 17:12:15.357993] INFO: bigquant: filter.v3 开始运行..
[2019-01-29 17:12:15.365446] INFO: filter: 使用表达式 st_status_0 == 0 and cond2>0 过滤
[2019-01-29 17:12:15.505925] INFO: filter: 过滤 /y_2014, 6130/0/104572
[2019-01-29 17:12:15.725592] INFO: filter: 过滤 /y_2015, 36187/0/547984
[2019-01-29 17:12:16.011539] INFO: filter: 过滤 /y_2016, 34463/0/625475
[2019-01-29 17:12:16.334279] INFO: filter: 过滤 /y_2017, 33863/0/702247
[2019-01-29 17:12:16.785000] INFO: filter: 过滤 /y_2018, 34973/0/802730
[2019-01-29 17:12:16.864148] INFO: bigquant: filter.v3 运行完成[1.506103s].
[2019-01-29 17:12:16.867888] INFO: bigquant: dropnan.v1 开始运行..
[2019-01-29 17:12:16.995810] INFO: dropnan: /y_2014, 6130/6130
[2019-01-29 17:12:17.074006] INFO: dropnan: /y_2015, 36187/36187
[2019-01-29 17:12:17.144360] INFO: dropnan: /y_2016, 34463/34463
[2019-01-29 17:12:17.231165] INFO: dropnan: /y_2017, 33863/33863
[2019-01-29 17:12:17.340479] INFO: dropnan: /y_2018, 34973/34973
[2019-01-29 17:12:17.364744] INFO: dropnan: 行数: 145616/145616
[2019-01-29 17:12:17.368467] INFO: bigquant: dropnan.v1 运行完成[0.500596s].
[2019-01-29 17:12:17.371480] INFO: bigquant: stock_ranker_predict.v5 开始运行..
[2019-01-29 17:12:17.771399] INFO: StockRanker: prepare data: prediction ..
[2019-01-29 17:12:21.054196] INFO: stock_ranker_predict: 准备预测: 145616 行
[2019-01-29 17:12:21.055395] INFO: stock_ranker_predict: 正在预测 ..
[2019-01-29 17:12:31.237077] INFO: bigquant: stock_ranker_predict.v5 运行完成[13.865554s].
[2019-01-29 17:12:31.239465] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-01-29 17:12:31.245102] INFO: bigquant: 命中缓存
[2019-01-29 17:12:31.246445] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.006961s].
[2019-01-29 17:12:31.249115] INFO: bigquant: join.v3 开始运行..
[2019-01-29 17:12:31.254464] INFO: bigquant: 命中缓存
[2019-01-29 17:12:31.255420] INFO: bigquant: join.v3 运行完成[0.006295s].
[2019-01-29 17:12:31.258163] INFO: bigquant: filter.v3 开始运行..
[2019-01-29 17:12:31.262993] INFO: bigquant: 命中缓存
[2019-01-29 17:12:31.263968] INFO: bigquant: filter.v3 运行完成[0.005798s].
[2019-01-29 17:12:31.266204] INFO: bigquant: dropnan.v1 开始运行..
[2019-01-29 17:12:31.270962] INFO: bigquant: 命中缓存
[2019-01-29 17:12:31.271786] INFO: bigquant: dropnan.v1 运行完成[0.005569s].
[2019-01-29 17:12:31.274915] INFO: bigquant: random_forest_classifier.v1 开始运行..
[2019-01-29 17:12:32.009287] INFO: bigquant: random_forest_classifier.v1 运行完成[0.734349s].
[2019-01-29 17:12:32.013537] INFO: bigquant: cached.v3 开始运行..
[2019-01-29 17:12:34.034605] INFO: bigquant: cached.v3 运行完成[2.021031s].
[2019-01-29 17:12:34.052695] INFO: bigquant: backtest.v8 开始运行..
[2019-01-29 17:12:34.055187] INFO: bigquant: biglearning backtest:V8.1.8
[2019-01-29 17:12:34.056415] INFO: bigquant: product_type:stock by specified
[2019-01-29 17:12:52.103332] INFO: bigquant: 读取股票行情完成:3646127
[2019-01-29 17:13:32.329825] INFO: algo: TradingAlgorithm V1.4.5
[2019-01-29 17:13:45.321664] INFO: algo: trading transform...
[2019-01-29 17:13:49.432240] INFO: Performance: Simulated 975 trading days out of 975.
[2019-01-29 17:13:49.433796] INFO: Performance: first open: 2015-01-05 09:30:00+00:00
[2019-01-29 17:13:49.434680] INFO: Performance: last close: 2018-12-28 15:00:00+00:00

收益率143.65%
年化收益率25.88%
基准收益率-14.8%
阿尔法0.22
贝塔0.21
夏普比率1.35
胜率0.58
盈亏比1.12
收益波动率15.81%
信息比率0.06
最大回撤21.77%

[2019-01-29 17:13:53.885310] INFO: bigquant: backtest.v8 运行完成[79.832587s].