克隆策略

In [11]:

# 本代码由可视化策略环境自动生成 2021年10月27日 16:05
# 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：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 = 5
    # 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 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.portfolio.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.portfolio.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities)])))

        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


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2010-01-01',
    'm1.end_date': '2015-01-01',
    '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
""",

    '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,

    'm13': 'M.dropnan.v1',
    'm13.input_data': T.Graph.OutputPort('m7.data'),

    'm6': 'M.stock_ranker_train.v5',
    'm6.training_ds': T.Graph.OutputPort('m13.data'),
    'm6.features': T.Graph.OutputPort('m3.data'),
    'm6.learning_algorithm': '排序',
    'm6.number_of_leaves': 30,
    'm6.minimum_docs_per_leaf': 1000,
    'm6.number_of_trees': 20,
    'm6.learning_rate': 0.1,
    'm6.max_bins': 1023,
    'm6.feature_fraction': 1,
    'm6.m_lazy_run': False,

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2015-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2017-01-01'),
    '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,

    'm14': 'M.dropnan.v1',
    'm14.input_data': T.Graph.OutputPort('m18.data'),

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m6.model'),
    'm8.data': T.Graph.OutputPort('m14.data'),
    'm8.m_lazy_run': False,

    'm19': 'M.trade.v4',
    'm19.instruments': T.Graph.OutputPort('m9.data'),
    'm19.options_data': T.Graph.OutputPort('m8.predictions'),
    'm19.start_date': '',
    'm19.end_date': '',
    'm19.initialize': m19_initialize_bigquant_run,
    'm19.handle_data': m19_handle_data_bigquant_run,
    'm19.prepare': m19_prepare_bigquant_run,
    'm19.volume_limit': 0.025,
    'm19.order_price_field_buy': 'open',
    'm19.order_price_field_sell': 'close',
    'm19.capital_base': 1000000,
    'm19.auto_cancel_non_tradable_orders': True,
    'm19.data_frequency': 'daily',
    'm19.price_type': '真实价格',
    'm19.product_type': '股票',
    'm19.plot_charts': True,
    'm19.backtest_only': False,
    'm19.benchmark': '000300.SHA',
})

# g.run({})


def m4_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\nclose_3/close_0']
    param_grid['m6.number_of_trees'] = [5, 20]
    param_grid['m6.learning_rate'] = [0.1, 0.01]


    return param_grid

def m4_scoring_bigquant_run(result):
    score = result.get('m19').read_raw_perf()['sharpe'].tail(1)[0]

    return {'score': score}


m4 = M.hyper_parameter_search.v1(
    param_grid_builder=m4_param_grid_builder_bigquant_run,
    scoring=m4_scoring_bigquant_run,
    search_algorithm='网格搜索',
    search_iterations=10,
    workers=1,
    worker_distributed_run=True,
    worker_silent=True,
    run_now=True,
    bq_graph=g
)

[2021-10-27 15:11:18.606744] INFO: cached.v3.14b3d354: 任务状态: Pending

[2021-10-27 15:11:28.664077] INFO: cached.v3.14b3d354: 任务状态: Running

[2021-10-27 15:11:38.720084] INFO: cached.v3.14b3d354: 任务状态: Succeeded

[2021-10-27 15:11:39.190502] INFO: cached.v3.21008d3c: 任务状态: Pending

[2021-10-27 15:11:49.227861] INFO: cached.v3.21008d3c: 任务状态: Running

[2021-10-27 15:11:59.261457] INFO: cached.v3.21008d3c: 任务状态: Succeeded

[2021-10-27 15:11:59.976243] INFO: cached.v3.2d64ff22: 任务状态: Pending

[2021-10-27 15:12:10.008769] INFO: cached.v3.2d64ff22: 任务状态: Running

[2021-10-27 15:12:40.149197] INFO: cached.v3.2d64ff22: 任务状态: Succeeded

[2021-10-27 15:12:40.649574] INFO: cached.v3.45a32316: 任务状态: Pending

[2021-10-27 15:12:50.682571] INFO: cached.v3.45a32316: 任务状态: Running

[2021-10-27 15:14:51.281199] INFO: cached.v3.45a32316: 任务状态: Succeeded

[2021-10-27 15:14:51.967514] INFO: cached.v3.93e73562: 任务状态: Pending

[2021-10-27 15:15:02.003793] INFO: cached.v3.93e73562: 任务状态: Running

[2021-10-27 15:18:12.617070] INFO: cached.v3.93e73562: 任务状态: Succeeded

[2021-10-27 15:18:13.229415] INFO: cached.v3.0bca0ece: 任务状态: Pending

[2021-10-27 15:18:23.262751] INFO: cached.v3.0bca0ece: 任务状态: Running

[2021-10-27 15:25:44.768543] INFO: cached.v3.0bca0ece: 任务状态: Succeeded

[2021-10-27 15:25:45.230095] INFO: cached.v3.1946feb2: 任务状态: Pending

[2021-10-27 15:25:55.265065] INFO: cached.v3.1946feb2: 任务状态: Running

[2021-10-27 15:28:05.771269] INFO: cached.v3.1946feb2: 任务状态: Succeeded

[2021-10-27 15:28:06.540619] INFO: cached.v3.6d7c04d2: 任务状态: Pending

[2021-10-27 15:28:16.582470] INFO: cached.v3.6d7c04d2: 任务状态: Running

[2021-10-27 15:31:47.517981] INFO: cached.v3.6d7c04d2: 任务状态: Succeeded

[2021-10-27 15:31:47.985278] INFO: cached.v3.f17e8c28: 任务状态: Pending

[2021-10-27 15:31:58.023190] INFO: cached.v3.f17e8c28: 任务状态: Running

[2021-10-27 15:40:29.929540] INFO: cached.v3.f17e8c28: 任务状态: Succeeded

[2021-10-27 15:40:30.767126] INFO: cached.v3.290ab27e: 任务状态: Pending

[2021-10-27 15:40:40.797006] INFO: cached.v3.290ab27e: 任务状态: Running

[2021-10-27 15:40:50.833933] INFO: cached.v3.290ab27e: 任务状态: Succeeded

[2021-10-27 15:40:50.841833] INFO: moduleinvoker: hyper_parameter_search.v1 运行完成[1772.759134s].

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 m6.learning_rate=0.1, m6.number_of_trees=5..................

[CV 1/1; 1/9] END m6.learning_rate=0.1, m6.number_of_trees=5; score: (test=0.772) total time=  20.6s
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:   20.6s remaining:    0.0s
[CV 1/1; 2/9] START m6.learning_rate=0.1, m6.number_of_trees=10.................

[CV 1/1; 2/9] END m6.learning_rate=0.1, m6.number_of_trees=10; score: (test=1.512) total time=  20.8s
[Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed:   41.4s remaining:    0.0s
[CV 1/1; 3/9] START m6.learning_rate=0.1, m6.number_of_trees=20.................

[CV 1/1; 3/9] END m6.learning_rate=0.1, m6.number_of_trees=20; score: (test=1.882) total time=  40.7s
[Parallel(n_jobs=1)]: Done   3 out of   3 | elapsed:  1.4min remaining:    0.0s
[CV 1/1; 4/9] START m6.learning_rate=0.01, m6.number_of_trees=5.................

[CV 1/1; 4/9] END m6.learning_rate=0.01, m6.number_of_trees=5; score: (test=0.813) total time= 2.2min
[Parallel(n_jobs=1)]: Done   4 out of   4 | elapsed:  3.6min remaining:    0.0s
[CV 1/1; 5/9] START m6.learning_rate=0.01, m6.number_of_trees=10................

[CV 1/1; 5/9] END m6.learning_rate=0.01, m6.number_of_trees=10; score: (test=1.488) total time= 3.4min
[Parallel(n_jobs=1)]: Done   5 out of   5 | elapsed:  6.9min remaining:    0.0s
[CV 1/1; 6/9] START m6.learning_rate=0.01, m6.number_of_trees=20................

[CV 1/1; 6/9] END m6.learning_rate=0.01, m6.number_of_trees=20; score: (test=1.495) total time= 7.5min
[Parallel(n_jobs=1)]: Done   6 out of   6 | elapsed: 14.4min remaining:    0.0s
[CV 1/1; 7/9] START m6.learning_rate=0.5, m6.number_of_trees=5..................

[CV 1/1; 7/9] END m6.learning_rate=0.5, m6.number_of_trees=5; score: (test=1.244) total time= 2.4min
[Parallel(n_jobs=1)]: Done   7 out of   7 | elapsed: 16.8min remaining:    0.0s
[CV 1/1; 8/9] START m6.learning_rate=0.5, m6.number_of_trees=10.................

[CV 1/1; 8/9] END m6.learning_rate=0.5, m6.number_of_trees=10; score: (test=1.321) total time= 3.7min
[Parallel(n_jobs=1)]: Done   8 out of   8 | elapsed: 20.5min remaining:    0.0s
[CV 1/1; 9/9] START m6.learning_rate=0.5, m6.number_of_trees=20.................

[CV 1/1; 9/9] END m6.learning_rate=0.5, m6.number_of_trees=20; score: (test=1.562) total time= 8.7min
[Parallel(n_jobs=1)]: Done   9 out of   9 | elapsed: 29.2min remaining:    0.0s
[Parallel(n_jobs=1)]: Done   9 out of   9 | elapsed: 29.2min finished

In [12]:

print(m4.result.best_params_, m4.result.best_score_)

{'m6.learning_rate': 0.1, 'm6.number_of_trees': 20} 1.881598429143087

In [ ]: