克隆策略

In [4]:

# 本代码由可视化策略环境自动生成 2021年10月16日 14:59
# 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。


# 回测引擎：每日数据处理函数，每天执行一次
def m6_handle_data_bigquant_run(context, data):
    # curr_data：用于当前handle_bar，各处理函数可以用 curr_data 传递数据
    context.curr_data = {}
    if 'handle_bar_functions' in context.options:
        for func in context.options['handle_bar_functions']:
            if not func(context, data):
                # 如果有处理函数返回False，则表示跳过后续执行
                return

# 回测引擎：准备数据，只执行一次
def m6_prepare_bigquant_run(context):
    pass

# 回测引擎：初始化函数，只执行一次
def m6_initialize_bigquant_run(context):
    if 'initialize_functions' in context.options:
        for func in context.options['initialize_functions']:
            if not func(context):
                # 如果有处理函数返回False，则表示跳过后续执行
                return

# 回测引擎：每个单位时间开始前调用一次，即每日开盘前调用一次。
def m6_before_trading_start_bigquant_run(context, data):
    pass


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2015-01-01',
    'm1.end_date': '2019-01-01',
    'm1.market': 'CN_STOCK_A',
    'm1.instrument_list': '',
    'm1.max_count': 0,

    'm2': 'M.advanced_auto_labeler.v2',
    'm2.instruments': T.Graph.OutputPort('m1.data'),
    'm2.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, -5) / 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)
""",
    'm2.start_date': '',
    'm2.end_date': '',
    'm2.benchmark': '000300.SHA',
    'm2.drop_na_label': True,
    'm2.cast_label_int': True,

    'm3': 'M.input_features.v1',
    'm3.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_5
return_10
return_20
avg_amount_0/avg_amount_5
avg_amount_5/avg_amount_20
rank_avg_amount_0/rank_avg_amount_5
rank_avg_amount_5/rank_avg_amount_10
rank_return_0
rank_return_5
rank_return_10
rank_return_0/rank_return_5
rank_return_5/rank_return_10
pe_ttm_0
avg_amount_60
mf_net_amount_l_0#大单净流入净额
mf_net_amount_m_0#中单净流入净额
mf_net_amount_main_0#主力净流入净额
mf_net_amount_xl_0#超大单净流入净额
mf_net_pct_l_0#大单净流入占比
mf_net_pct_m_0#中单净流入占比
mf_net_pct_main_0#主力净流入占比
mf_net_pct_xl_0#超大单净流入占比
volume_5#第前 5个交易日的交易量
volume_10#第前 10个交易日的交易量
ta_macd_macd_12_26_9_0#MACD
ta_stoch_slowd_5_3_0_3_0_0#指标D值
ta_stoch_slowk_5_3_0_3_0_0#指标K值
some_alias=ta_rsi_14_0#RSI指标，timeperiod=14
some_alias=ta_rsi_28_0#RSI指标，timeperiod=28
volume_5#第5前个交易日的交易量
volume_10#第10前个交易日的交易量
return_1


""",

    'm15': 'M.general_feature_extractor.v7',
    'm15.instruments': T.Graph.OutputPort('m1.data'),
    'm15.features': T.Graph.OutputPort('m3.data'),
    'm15.start_date': '',
    'm15.end_date': '',
    'm15.before_start_days': 90,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m15.data'),
    'm16.features': T.Graph.OutputPort('m3.data'),
    'm16.date_col': 'date',
    'm16.instrument_col': 'instrument',
    'm16.drop_na': False,
    'm16.remove_extra_columns': False,

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m2.data'),
    'm7.data2': T.Graph.OutputPort('m16.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm4': 'M.chinaa_stock_filter.v1',
    'm4.input_data': T.Graph.OutputPort('m7.data'),
    'm4.index_constituent_cond': ['全部'],
    'm4.board_cond': ['上证主板', '深证主板'],
    'm4.industry_cond': ['全部'],
    'm4.st_cond': ['正常'],
    'm4.delist_cond': ['非退市'],
    'm4.output_left_data': False,

    'm13': 'M.dropnan.v1',
    'm13.input_data': T.Graph.OutputPort('m4.data'),

    'm21': 'M.replace_inf_dropna.v1',
    'm21.input_1': T.Graph.OutputPort('m13.data'),

    'm19': 'M.stock_ranker_train.v6',
    'm19.training_ds': T.Graph.OutputPort('m21.data_1'),
    'm19.features': T.Graph.OutputPort('m3.data'),
    'm19.test_ds': T.Graph.OutputPort('m21.data_1'),
    'm19.learning_algorithm': '排序',
    'm19.number_of_leaves': 800,
    'm19.minimum_docs_per_leaf': 100000,
    'm19.number_of_trees': 400,
    'm19.learning_rate': 0.5,
    'm19.max_bins': 1023,
    'm19.feature_fraction': 1,
    'm19.data_row_fraction': 0.999,
    'm19.ndcg_discount_base': 1,
    'm19.m_lazy_run': False,

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2019-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2021-10-1'),
    'm9.market': 'CN_STOCK_A',
    'm9.instrument_list': '',
    'm9.max_count': 0,

    'm17': 'M.general_feature_extractor.v7',
    'm17.instruments': T.Graph.OutputPort('m9.data'),
    'm17.features': T.Graph.OutputPort('m3.data'),
    'm17.start_date': '',
    'm17.end_date': '',
    'm17.before_start_days': 90,

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m17.data'),
    'm18.features': T.Graph.OutputPort('m3.data'),
    'm18.date_col': 'date',
    'm18.instrument_col': 'instrument',
    'm18.drop_na': False,
    'm18.remove_extra_columns': False,

    'm5': 'M.chinaa_stock_filter.v1',
    'm5.input_data': T.Graph.OutputPort('m18.data'),
    'm5.index_constituent_cond': ['全部'],
    'm5.board_cond': ['上证主板', '深证主板'],
    'm5.industry_cond': ['全部'],
    'm5.st_cond': ['正常'],
    'm5.delist_cond': ['非退市'],
    'm5.output_left_data': False,

    'm14': 'M.dropnan.v1',
    'm14.input_data': T.Graph.OutputPort('m5.data'),

    'm22': 'M.replace_inf_dropna.v1',
    'm22.input_1': T.Graph.OutputPort('m14.data'),

    'm23': 'M.stock_ranker_predict.v5',
    'm23.model': T.Graph.OutputPort('m19.model'),
    'm23.data': T.Graph.OutputPort('m22.data_1'),
    'm23.m_lazy_run': False,

    'm10': 'M.input_features.v1',
    'm10.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
name""",

    'm11': 'M.use_datasource.v1',
    'm11.instruments': T.Graph.OutputPort('m9.data'),
    'm11.features': T.Graph.OutputPort('m10.data'),
    'm11.datasource_id': 'instruments_CN_STOCK_A',
    'm11.start_date': '',
    'm11.end_date': '',

    'm12': 'M.join.v3',
    'm12.data1': T.Graph.OutputPort('m23.predictions'),
    'm12.data2': T.Graph.OutputPort('m11.data'),
    'm12.on': 'date,instrument',
    'm12.how': 'inner',
    'm12.sort': False,

    'm20': 'M.sort.v4',
    'm20.input_ds': T.Graph.OutputPort('m12.data'),
    'm20.sort_by': 'position',
    'm20.group_by': 'date',
    'm20.keep_columns': '--',
    'm20.ascending': True,

    'm24': 'M.trade_func_set_commission.v1',
    'm24.mode': '订单/PerOrder',
    'm24.buy_cost': 0.0003,
    'm24.sell_cost': 0.0013,
    'm24.min_cost': 3,

    'm25': 'M.trade_func_rebalance_manage.v1',
    'm25.mode': '滚动',
    'm25.period': 5,

    'm26': 'M.trade_func_buy_by_rank.v1',
    'm26.input_functions': T.Graph.OutputPort('m25.functions'),
    'm26.mode': '对数权重',
    'm26.bias': 2,
    'm26.stock_count': 10,
    'm26.unit': 0,
    'm26.max_position_per_instrument': 1,

    'm27': 'M.trade_func_sell_by_rank.v1',
    'm27.input_functions': T.Graph.OutputPort('m26.functions'),

    'm6': 'M.tradex.v1',
    'm6.instruments': T.Graph.OutputPort('m9.data'),
    'm6.initialize_functions': T.Graph.OutputPort('m24.functions'),
    'm6.handle_bar_functions': T.Graph.OutputPort('m27.functions'),
    'm6.options_data': T.Graph.OutputPort('m20.sorted_data'),
    'm6.start_date': '',
    'm6.end_date': '',
    'm6.handle_data': m6_handle_data_bigquant_run,
    'm6.prepare': m6_prepare_bigquant_run,
    'm6.initialize': m6_initialize_bigquant_run,
    'm6.before_trading_start': m6_before_trading_start_bigquant_run,
    'm6.volume_limit': 0.025,
    'm6.order_price_field_buy': 'open',
    'm6.order_price_field_sell': 'close',
    'm6.capital_base': 100000,
    'm6.auto_cancel_non_tradable_orders': True,
    'm6.data_frequency': 'daily',
    'm6.price_type': '真实价格',
    'm6.product_type': '股票',
    'm6.plot_charts': True,
    'm6.backtest_only': False,
})

# g.run({})


def m8_param_grid_builder_bigquant_run():
    param_grid = {}

    # 在这里设置需要调优的参数备选
    param_grid['m3.features'] = ['close_1/close_0', 'close_2/close_0', 'close_3/close_0']
    param_grid['m19.number_of_trees'] = [5, 10, 20]

    return param_grid

def m8_scoring_bigquant_run(result):
    score = result.get('m6').read_raw_perf()['sharpe'].tail(1)[0]

    return {'score': score}


m8 = M.hyper_parameter_search.v1(
    param_grid_builder=m8_param_grid_builder_bigquant_run,
    scoring=m8_scoring_bigquant_run,
    search_algorithm='随机搜索',
    search_iterations=10,
    workers=1,
    worker_distributed_run=True,
    worker_silent=True,
    run_now=True,
    bq_graph=g
)

[2021-10-16 13:55:07.384981] INFO: cached.v3.9d24a1d6: 任务状态: Pending

[2021-10-16 13:55:17.432901] INFO: cached.v3.9d24a1d6: 任务状态: Running

[2021-10-16 14:00:18.316776] INFO: cached.v3.9d24a1d6: 任务状态: Failed

[2021-10-16 14:00:18.319656] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 9d24a1d62e4511ec8215c294a6a4b5c3 Failed

[2021-10-16 14:00:18.988645] INFO: cached.v3.56ffabc8: 任务状态: Pending

[2021-10-16 14:00:29.021132] INFO: cached.v3.56ffabc8: 任务状态: Running

[2021-10-16 14:07:40.350870] INFO: cached.v3.56ffabc8: 任务状态: Failed

[2021-10-16 14:07:40.353168] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 56ffabc82e4611ecb0f4c294a6a4b5c3 Failed

[2021-10-16 14:07:41.130100] INFO: cached.v3.5e762e3a: 任务状态: Pending

[2021-10-16 14:07:51.162119] INFO: cached.v3.5e762e3a: 任务状态: Running

[2021-10-16 14:13:02.059659] INFO: cached.v3.5e762e3a: 任务状态: Failed

[2021-10-16 14:13:02.061677] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 5e762e3a2e4711ec9d1cc294a6a4b5c3 Failed

[2021-10-16 14:13:03.174557] INFO: cached.v3.1e3871d8: 任务状态: Pending

[2021-10-16 14:13:13.300546] INFO: cached.v3.1e3871d8: 任务状态: Running

[2021-10-16 14:17:34.075869] INFO: cached.v3.1e3871d8: 任务状态: Failed

[2021-10-16 14:17:34.078263] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 1e3871d82e4811ecb2a6c294a6a4b5c3 Failed

[2021-10-16 14:17:34.885809] INFO: cached.v3.c05a0238: 任务状态: Pending

[2021-10-16 14:17:44.915288] INFO: cached.v3.c05a0238: 任务状态: Running

[2021-10-16 14:21:55.638093] INFO: cached.v3.c05a0238: 任务状态: Failed

[2021-10-16 14:21:55.640136] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, c05a02382e4811ecb2bec294a6a4b5c3 Failed

[2021-10-16 14:21:56.334111] INFO: cached.v3.5c3f48a2: 任务状态: Pending

[2021-10-16 14:22:06.363722] INFO: cached.v3.5c3f48a2: 任务状态: Running

[2021-10-16 14:28:07.414022] INFO: cached.v3.5c3f48a2: 任务状态: Failed

[2021-10-16 14:28:07.417646] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 5c3f48a22e4911eca61cc294a6a4b5c3 Failed

[2021-10-16 14:28:08.285378] INFO: cached.v3.39d9c750: 任务状态: Pending

[2021-10-16 14:28:18.314660] INFO: cached.v3.39d9c750: 任务状态: Running

[2021-10-16 14:35:39.595135] INFO: cached.v3.39d9c750: 任务状态: Failed

[2021-10-16 14:35:39.597086] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 39d9c7502e4a11ec8c61c294a6a4b5c3 Failed

[2021-10-16 14:35:40.251533] INFO: cached.v3.475f9318: 任务状态: Pending

[2021-10-16 14:35:50.285082] INFO: cached.v3.475f9318: 任务状态: Running

[2021-10-16 14:41:51.327571] INFO: cached.v3.475f9318: 任务状态: Failed

[2021-10-16 14:41:51.330494] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 475f93182e4b11ec96dec294a6a4b5c3 Failed

[2021-10-16 14:41:51.934031] INFO: cached.v3.24f091dc: 任务状态: Pending

[2021-10-16 14:42:01.964677] INFO: cached.v3.24f091dc: 任务状态: Running

[2021-10-16 14:48:24.563861] INFO: cached.v3.24f091dc: 任务状态: Failed

[2021-10-16 14:48:24.565861] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 24f091dc2e4c11ecab18c294a6a4b5c3 Failed

[2021-10-16 14:48:25.511142] INFO: cached.v3.0f540bf0: 任务状态: Pending

[2021-10-16 14:48:35.549157] INFO: cached.v3.0f540bf0: 任务状态: Running

[2021-10-16 14:48:45.580421] INFO: cached.v3.0f540bf0: 任务状态: Failed

[2021-10-16 14:48:45.582335] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: Exception: 任务运行失败, 0f540bf02e4d11ec9df9c294a6a4b5c3 Failed

[2021-10-16 14:48:45.585263] ERROR: moduleinvoker: module name: hyper_parameter_search, module version: v1, trackeback: Exception: 任务运行失败, 0f540bf02e4d11ec9df9c294a6a4b5c3 Failed

Fitting 1 folds for each of 9 candidates, totalling 9 fits
[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[CV 1/1; 1/9] START m19.number_of_trees=5, m3.features=close_1/close_0..........

[CV 1/1; 1/9] END m19.number_of_trees=5, m3.features=close_1/close_0; total time= 5.2min
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:  5.2min remaining:    0.0s
[CV 1/1; 2/9] START m19.number_of_trees=5, m3.features=close_2/close_0..........

[CV 1/1; 2/9] END m19.number_of_trees=5, m3.features=close_2/close_0; total time= 7.4min
[Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed: 12.6min remaining:    0.0s
[CV 1/1; 3/9] START m19.number_of_trees=5, m3.features=close_3/close_0..........

[CV 1/1; 3/9] END m19.number_of_trees=5, m3.features=close_3/close_0; total time= 5.4min
[Parallel(n_jobs=1)]: Done   3 out of   3 | elapsed: 17.9min remaining:    0.0s
[CV 1/1; 4/9] START m19.number_of_trees=10, m3.features=close_1/close_0.........

[CV 1/1; 4/9] END m19.number_of_trees=10, m3.features=close_1/close_0; total time= 4.5min
[Parallel(n_jobs=1)]: Done   4 out of   4 | elapsed: 22.5min remaining:    0.0s
[CV 1/1; 5/9] START m19.number_of_trees=10, m3.features=close_2/close_0.........

[CV 1/1; 5/9] END m19.number_of_trees=10, m3.features=close_2/close_0; total time= 4.4min
[Parallel(n_jobs=1)]: Done   5 out of   5 | elapsed: 26.8min remaining:    0.0s
[CV 1/1; 6/9] START m19.number_of_trees=10, m3.features=close_3/close_0.........

[CV 1/1; 6/9] END m19.number_of_trees=10, m3.features=close_3/close_0; total time= 6.2min
[Parallel(n_jobs=1)]: Done   6 out of   6 | elapsed: 33.0min remaining:    0.0s
[CV 1/1; 7/9] START m19.number_of_trees=20, m3.features=close_1/close_0.........

[CV 1/1; 7/9] END m19.number_of_trees=20, m3.features=close_1/close_0; total time= 7.5min
[Parallel(n_jobs=1)]: Done   7 out of   7 | elapsed: 40.6min remaining:    0.0s
[CV 1/1; 8/9] START m19.number_of_trees=20, m3.features=close_2/close_0.........

[CV 1/1; 8/9] END m19.number_of_trees=20, m3.features=close_2/close_0; total time= 6.2min
[Parallel(n_jobs=1)]: Done   8 out of   8 | elapsed: 46.7min remaining:    0.0s
[CV 1/1; 9/9] START m19.number_of_trees=20, m3.features=close_3/close_0.........

[CV 1/1; 9/9] END m19.number_of_trees=20, m3.features=close_3/close_0; total time= 6.6min
[Parallel(n_jobs=1)]: Done   9 out of   9 | elapsed: 53.3min remaining:    0.0s
[Parallel(n_jobs=1)]: Done   9 out of   9 | elapsed: 53.3min finished

---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-4-814bacea9a38> in <module>
    287 
    288 
--> 289 m8 = M.hyper_parameter_search.v1(
    290     param_grid_builder=m8_param_grid_builder_bigquant_run,
    291     scoring=m8_scoring_bigquant_run,

Exception: 任务运行失败, 0f540bf02e4d11ec9df9c294a6a4b5c3 Failed