复制链接

克隆策略

In [ ]:

In [ ]:

# 本代码由可视化策略环境自动生成 2022年12月29日 17:43
# 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 = 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 / stock_count] * stock_count  #T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])#[1 / stock_count] * stock_count 
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.7
    context.options['hold_days'] = 2

# 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')]
    today = 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()}
#     print(today,"cash_avg=",cash_avg,"context.portfolio.cash=",context.portfolio.cash,"cash_for_buy=",cash_for_buy,"cash_for_sell=",cash_for_sell)
    # 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': '2019-01-01',
    'm1.end_date': '2020-12-31',
    '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.HIX',
    'm2.drop_na_label': True,
    'm2.cast_label_int': True,

    'm3': 'M.input_features.v1',
    'm3.features': """std(close_0, 5)
std(low_0, 5)
std(turn_0, 5)
std(return_0, 5)
return_5
avg_turn_5
avg_amount_0/avg_amount_5
rank_avg_amount_0/rank_avg_amount_5
rank_return_0
rank_return_5
rank_return_0/rank_return_5
pe_ttm_0
rank_fs_roe_0
mf_net_amount_5""",

    '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'),

    'm4': 'M.chinaa_stock_filter.v1',
    'm4.input_data': T.Graph.OutputPort('m13.data'),
    'm4.index_constituent_cond': ['全部'],
    'm4.board_cond': ['上证主板', '深证主板', '创业板'],
    'm4.industry_cond': ['全部'],
    'm4.st_cond': ['全部'],
    'm4.delist_cond': ['非退市'],
    'm4.output_left_data': False,

    'm6': 'M.stock_ranker_train.v6',
    'm6.training_ds': T.Graph.OutputPort('m4.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.data_row_fraction': 1,
    'm6.plot_charts': True,
    'm6.ndcg_discount_base': 1,
    'm6.m_lazy_run': False,

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2021-06-01'),
    'm9.end_date': T.live_run_param('trading_date', '2022-06-31'),
    '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'),

    'm5': 'M.chinaa_stock_filter.v1',
    'm5.input_data': T.Graph.OutputPort('m14.data'),
    'm5.index_constituent_cond': ['全部'],
    'm5.board_cond': ['上证主板', '深证主板', '创业板'],
    'm5.industry_cond': ['全部'],
    'm5.st_cond': ['全部'],
    'm5.delist_cond': ['非退市'],
    'm5.output_left_data': False,

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m6.model'),
    'm8.data': T.Graph.OutputPort('m5.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.HIX',
})

# g.run({})


def m11_run_bigquant_run(bq_graph, inputs):
    g = bq_graph
    #原始因子
    features = [
        'std(close_0, 5)',
        'std(low_0, 5)',
        'std(turn_0, 5)',
        'std(return_0, 5)',
        'return_5',
        'avg_turn_5',
        'avg_amount_0/avg_amount_5',
        'rank_avg_amount_0/rank_avg_amount_5',
        'rank_return_0',
        'rank_return_5',
        'rank_return_0/rank_return_5',
        'pe_ttm_0',
        'rank_fs_roe_0',
        'mf_net_amount_5'
 ]
    

    parameters_list = []
    
    i = 0
    #循环减因子
    for feature in features: 
        print(i," ------------ ",feature)
        parameters = {}
        temp = []
        temp = list(set(features) - set([feature]))
        parameters['m3.features'] = '\n'.join(temp)
        parameters_list.append({'parameters': parameters})
        i+=1

  
    print( parameters_list)
    print('==='*20, len(parameters_list))
    
    def run(parameters):
        try:
            print(parameters)
            result = g.run(parameters)
            return result
        except Exception as e:
            print('ERROR --------', e)
            return None

    results = T.parallel_map(run, parameters_list, max_workers=4,remote_run=True, silent=True,backend='threading')
       
    return results


m11 = M.hyper_run.v1(
    run=m11_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2022-12-29 17:35:50.968023] WARNING: AI: 当前可运行1个高级AI任务，购买资源获取更多高级AI任务位[url="https://bigquant.com/account/big_member/?from=navigation" style="display: inline-block;padding: 5px 7px;border-radius: 2px;background: #F0BC41;color: white"]购买高级AI任务位[/url]

[2022-12-29 17:35:50.969592] INFO: AI: 开始并行运算, remote_run=True, workers=1 ..

[2022-12-29 17:35:50.971056] INFO: AI: [ParallelEx(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.

[2022-12-29 17:35:51.172431] INFO: cached.v2.2ec9bbb0: 任务状态: Pending

[2022-12-29 17:36:01.209895] INFO: cached.v2.2ec9bbb0: 任务状态: Running

[2022-12-29 17:36:31.349706] INFO: cached.v2.2ec9bbb0: 任务状态: Succeeded

[2022-12-29 17:36:31.357653] INFO: AI: [ParallelEx(n_jobs=1)]: Done   1 out of   1 | elapsed:   40.4s remaining:    0.0s

[2022-12-29 17:36:31.611805] INFO: cached.v2.46dd0dce: 任务状态: Pending

[2022-12-29 17:36:41.644994] INFO: cached.v2.46dd0dce: 任务状态: Running

[2022-12-29 17:37:01.719062] INFO: cached.v2.46dd0dce: 任务状态: Succeeded

[2022-12-29 17:37:01.725073] INFO: AI: [ParallelEx(n_jobs=1)]: Done   2 out of   2 | elapsed:  1.2min remaining:    0.0s

[2022-12-29 17:37:02.117392] INFO: cached.v2.58f8ab3a: 任务状态: Pending

[2022-12-29 17:37:12.175330] INFO: cached.v2.58f8ab3a: 任务状态: Running

[2022-12-29 17:37:32.269838] INFO: cached.v2.58f8ab3a: 任务状态: Succeeded

[2022-12-29 17:37:32.273922] INFO: AI: [ParallelEx(n_jobs=1)]: Done   3 out of   3 | elapsed:  1.7min remaining:    0.0s

[2022-12-29 17:37:32.547339] INFO: cached.v2.6b2fe160: 任务状态: Pending

[2022-12-29 17:37:42.595401] INFO: cached.v2.6b2fe160: 任务状态: Running

[2022-12-29 17:38:22.854464] INFO: cached.v2.6b2fe160: 任务状态: Succeeded

[2022-12-29 17:38:22.860327] INFO: AI: [ParallelEx(n_jobs=1)]: Done   4 out of   4 | elapsed:  2.5min remaining:    0.0s

[2022-12-29 17:38:23.200516] INFO: cached.v2.89529fe8: 任务状态: Pending

[2022-12-29 17:38:33.241907] INFO: cached.v2.89529fe8: 任务状态: Running

[2022-12-29 17:39:03.357773] INFO: cached.v2.89529fe8: 任务状态: Succeeded

[2022-12-29 17:39:03.363366] INFO: AI: [ParallelEx(n_jobs=1)]: Done   5 out of   5 | elapsed:  3.2min remaining:    0.0s

[2022-12-29 17:39:03.648160] INFO: cached.v2.a1769c8c: 任务状态: Pending

[2022-12-29 17:39:13.684149] INFO: cached.v2.a1769c8c: 任务状态: Running

[2022-12-29 17:39:33.762316] INFO: cached.v2.a1769c8c: 任务状态: Succeeded

[2022-12-29 17:39:33.766623] INFO: AI: [ParallelEx(n_jobs=1)]: Done   6 out of   6 | elapsed:  3.7min remaining:    0.0s

[2022-12-29 17:39:34.041438] INFO: cached.v2.b39857c0: 任务状态: Pending

[2022-12-29 17:39:44.102889] INFO: cached.v2.b39857c0: 任务状态: Running

[2022-12-29 17:39:54.151957] INFO: cached.v2.b39857c0: 任务状态: Succeeded

[2022-12-29 17:39:54.158646] INFO: AI: [ParallelEx(n_jobs=1)]: Done   7 out of   7 | elapsed:  4.1min remaining:    0.0s

[2022-12-29 17:39:54.525050] INFO: cached.v2.bfbde1d2: 任务状态: Pending

[2022-12-29 17:40:04.568271] INFO: cached.v2.bfbde1d2: 任务状态: Running

[2022-12-29 17:40:24.670429] INFO: cached.v2.bfbde1d2: 任务状态: Succeeded

[2022-12-29 17:40:24.677042] INFO: AI: [ParallelEx(n_jobs=1)]: Done   8 out of   8 | elapsed:  4.6min remaining:    0.0s

[2022-12-29 17:40:25.019850] INFO: cached.v2.d1ef5f8e: 任务状态: Pending

[2022-12-29 17:40:35.060421] INFO: cached.v2.d1ef5f8e: 任务状态: Running

[2022-12-29 17:41:05.301101] INFO: cached.v2.d1ef5f8e: 任务状态: Succeeded

[2022-12-29 17:41:05.312018] INFO: AI: [ParallelEx(n_jobs=1)]: Done   9 out of   9 | elapsed:  5.2min remaining:    0.0s

[2022-12-29 17:41:05.778681] INFO: cached.v2.ea2ab756: 任务状态: Pending

[2022-12-29 17:41:15.831995] INFO: cached.v2.ea2ab756: 任务状态: Running

[2022-12-29 17:41:35.906366] INFO: cached.v2.ea2ab756: 任务状态: Succeeded

[2022-12-29 17:41:35.910878] INFO: AI: [ParallelEx(n_jobs=1)]: Done  10 out of  10 | elapsed:  5.7min remaining:    0.0s

[2022-12-29 17:41:36.198351] INFO: cached.v2.fc62f2da: 任务状态: Pending

[2022-12-29 17:41:46.244406] INFO: cached.v2.fc62f2da: 任务状态: Running

[2022-12-29 17:42:16.351207] INFO: cached.v2.fc62f2da: 任务状态: Succeeded

[2022-12-29 17:42:16.356170] INFO: AI: [ParallelEx(n_jobs=1)]: Done  11 out of  11 | elapsed:  6.4min remaining:    0.0s

[2022-12-29 17:42:16.680842] INFO: cached.v2.14801686: 任务状态: Pending

[2022-12-29 17:42:26.715711] INFO: cached.v2.14801686: 任务状态: Running

[2022-12-29 17:42:56.829510] INFO: cached.v2.14801686: 任务状态: Succeeded

[2022-12-29 17:42:56.835180] INFO: AI: [ParallelEx(n_jobs=1)]: Done  12 out of  12 | elapsed:  7.1min remaining:    0.0s

[2022-12-29 17:42:57.140659] INFO: cached.v2.2ca4abd2: 任务状态: Pending

[2022-12-29 17:43:07.180670] INFO: cached.v2.2ca4abd2: 任务状态: Running

0  ------------  std(close_0, 5)
1  ------------  std(low_0, 5)
2  ------------  std(turn_0, 5)
3  ------------  std(return_0, 5)
4  ------------  return_5
5  ------------  avg_turn_5
6  ------------  avg_amount_0/avg_amount_5
7  ------------  rank_avg_amount_0/rank_avg_amount_5
8  ------------  rank_return_0
9  ------------  rank_return_5
10  ------------  rank_return_0/rank_return_5
11  ------------  pe_ttm_0
12  ------------  rank_fs_roe_0
13  ------------  mf_net_amount_5
[{'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'rank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\nstd(close_0, 5)\nrank_fs_roe_0\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nmf_net_amount_5\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}, {'parameters': {'m3.features': 'avg_amount_0/avg_amount_5\nrank_return_5\nrank_avg_amount_0/rank_avg_amount_5\nstd(return_0, 5)\nrank_return_0\nrank_return_0/rank_return_5\npe_ttm_0\nstd(close_0, 5)\nrank_fs_roe_0\nstd(turn_0, 5)\nreturn_5\navg_turn_5\nstd(low_0, 5)'}}]
============================================================ 14

In [ ]:

#回测结果统计
import pandas as pd
pd.set_option("display.max_columns", None)
pd.set_option("display.max_rows", 500)
pd.set_option('display.width', 5000)
pd.set_option('max_colwidth',1000) #某列最大宽度
pd.set_option('expand_frame_repr', False)
#pd.set_option('display.float_format',lambda x: '%.1f'%x)
pd.set_option('display.unicode.ambiguous_as_wide',True) 
pd.set_option('display.unicode.east_asian_width',True) 



import empyrical
# 统计策略指标
def get_stats(results):
    return_ratio  = empyrical.cum_returns_final(results.returns)
    annual_return_ratio  = empyrical.annual_return(results.returns)
    sharp_ratio = results.iloc[-1].sharpe
    return_volatility = empyrical.annual_volatility(results.returns)
    max_drawdown  = empyrical.max_drawdown(results.returns)
    benchmark_returns = (results.benchmark_period_return+1)/(results.benchmark_period_return+1).shift(1)-1
    alpha, beta =empyrical.alpha_beta_aligned(results.returns, benchmark_returns)

    return {
      'return_ratio': round(return_ratio,2),
      'annual_return_ratio': round(annual_return_ratio,2),
      'beta': beta,
      'alpha': alpha,
      'sharp_ratio': sharp_ratio,
      'return_volatility': round(return_volatility,2),
      'max_drawdown': round(max_drawdown,2),
    }
result_df = pd.DataFrame()
for i in range(len(m11.result)):
    try:
        perf = m11.result[i]['m19'].raw_perf.read()
    except :
        print("no data",i)
        continue
    result = get_stats(perf) # 这里m是Trade模块的模块号，自行替换即可
    para = i
    result_df = result_df.append({"参数":para,'收益率':result['return_ratio'],'年化收益率':result['annual_return_ratio'],'最大回撤':abs(result['max_drawdown']),'夏普率':round(result['sharp_ratio'],2)},ignore_index=True)
    
result_df
result_df['收益回撤比'] = (result_df['年化收益率'] / result_df['最大回撤']).round(2)
result_df = result_df.sort_values('夏普率',ascending=False)
result_df

In [ ]: