In [18]:

m4.data.read().sort_values(['instrument','date']).head(20)

Out[18]:

	turn	adjust_factor	instrument	date	open	volume	low	deal_number	close	high	amount
1579	2.907919	71.053696	000001.SZA	2015-01-05	1136.148560	286043643.0	1108.437622	92327.0	1138.280273	1156.754150	4.565388e+09
3112	2.202384	71.053696	000001.SZA	2015-01-06	1126.201050	216642140.0	1104.885010	80109.0	1121.227295	1164.570068	3.453446e+09
6334	1.728342	71.053696	000001.SZA	2015-01-07	1105.595581	170012067.0	1087.121582	72692.0	1099.911255	1124.780029	2.634796e+09
8227	1.431082	71.053696	000001.SZA	2015-01-08	1101.332275	140771421.0	1058.700073	68467.0	1062.963257	1106.306030	2.128003e+09
11618	2.550141	71.053696	000001.SZA	2015-01-09	1058.700073	250850023.0	1045.199829	99257.0	1071.489746	1127.622192	3.835378e+09
13363	1.579075	71.053696	000001.SZA	2015-01-12	1056.568481	155329086.0	1030.278564	64373.0	1049.463135	1069.358154	2.293105e+09
16286	0.830435	71.053696	000001.SZA	2015-01-13	1040.936646	81687477.0	1038.094482	34702.0	1043.068237	1058.700073	1.204987e+09
19540	1.283996	71.053696	000001.SZA	2015-01-14	1050.173584	126302963.0	1044.489380	50675.0	1052.305298	1080.016235	1.889297e+09
22433	1.262790	71.053696	000001.SZA	2015-01-15	1055.147461	124217032.0	1045.199829	54187.0	1090.674194	1090.674194	1.868796e+09
25102	1.581673	71.053696	000001.SZA	2015-01-16	1094.226929	155584633.0	1078.595093	60481.0	1092.095337	1109.858765	2.403346e+09
26442	2.172600	71.053696	000001.SZA	2015-01-19	995.462280	213712366.0	982.672607	103082.0	982.672607	1035.252319	3.016203e+09
29410	1.515769	71.053696	000001.SZA	2015-01-20	982.672607	149101811.0	963.488159	65546.0	982.672607	999.014954	2.064281e+09
32298	1.972743	71.053696	000001.SZA	2015-01-21	986.225342	194053037.0	976.988342	78664.0	1024.594360	1037.384033	2.758193e+09
35418	1.275849	71.053696	000001.SZA	2015-01-22	1018.910034	125501611.0	1006.120361	53463.0	1016.067871	1031.699707	1.801436e+09
36425	1.483404	71.053696	000001.SZA	2015-01-23	1020.331116	145918192.0	1016.067871	53360.0	1023.173218	1039.515625	2.108747e+09
38950	1.075162	71.053696	000001.SZA	2015-01-26	1020.331116	105760580.0	1006.120361	46881.0	1018.910034	1026.015381	1.508447e+09
41543	1.361730	71.053696	000001.SZA	2015-01-27	1019.620544	133949465.0	982.672607	61656.0	994.041199	1021.041626	1.881059e+09
44618	1.261476	71.053696	000001.SZA	2015-01-28	985.514771	124087755.0	980.541016	55197.0	999.014954	1016.067871	1.742176e+09
47745	1.033631	71.053696	000001.SZA	2015-01-29	981.962097	101675329.0	976.988342	42986.0	987.646362	995.462280	1.408825e+09
50868	0.945556	71.053696	000001.SZA	2015-01-30	989.778015	93011669.0	977.698853	41887.0	989.778015	1003.278198	1.298736e+09

In [21]:

m5.data_1.read()

Out[21]:

	instrument	date	open	high	low	close	volume	ma_10
0	000001.SZA	2015-01-11	1136.148560	1164.570068	1045.199829	1071.489746	1.064319e+09	NaN
1	000001.SZA	2015-01-18	1056.568481	1109.858765	1030.278564	1092.095337	6.431212e+08	NaN
2	000001.SZA	2015-01-25	995.462280	1039.515625	963.488159	1023.173218	8.282870e+08	NaN
3	000001.SZA	2015-02-01	1020.331116	1026.015381	976.988342	989.778015	5.584848e+08	NaN
4	000001.SZA	2015-02-08	966.330261	1025.304810	952.119568	959.935425	5.496042e+08	NaN
...	...	...	...	...	...	...	...	...
292168	603999.SHA	2016-12-04	44.539215	44.767990	41.348381	41.793896	2.475159e+07	46.276715
292169	603999.SHA	2016-12-11	41.805935	43.286964	37.976936	38.615101	3.019998e+07	46.180388
292170	603999.SHA	2016-12-18	38.398365	40.312866	35.424271	39.698780	4.218986e+07	46.192429
292171	603999.SHA	2016-12-25	39.132858	40.144295	37.326729	37.350811	3.738261e+07	44.575338
292172	603999.SHA	2017-01-01	36.869175	37.386932	34.918552	35.303860	2.415130e+07	42.630736

292173 rows × 8 columns

In [15]:

m5.data_1.read()

Out[15]:

	instrument	date	open	high	low	close	volume	ma_10
0	000001.SZA	2015-01-05	1136.148560	1164.570068	1045.199829	1071.489746	1.064319e+09	NaN
1	000001.SZA	2015-01-10	1056.568481	1080.016235	1030.278564	1052.305298	3.633195e+08	NaN
2	000001.SZA	2015-01-15	1055.147461	1109.858765	982.672607	982.672607	4.935140e+08	NaN
3	000001.SZA	2015-01-20	982.672607	1039.515625	963.488159	1023.173218	6.145747e+08	NaN
4	000001.SZA	2015-01-25	1020.331116	1026.015381	976.988342	987.646362	4.654731e+08	NaN
...	...	...	...	...	...	...	...	...
409865	603999.SHA	2016-12-09	40.577766	40.577766	35.424271	36.640396	2.683112e+07	44.698155
409866	603999.SHA	2016-12-14	36.604275	40.312866	35.905903	39.698780	2.700377e+07	44.085274
409867	603999.SHA	2016-12-19	39.132858	40.144295	37.326729	37.350811	3.738261e+07	42.996778
409868	603999.SHA	2016-12-24	36.869175	37.386932	34.918552	36.568153	1.401517e+07	41.860120
409869	603999.SHA	2016-12-29	36.604275	36.604275	35.231613	35.303860	1.013612e+07	40.619909

409870 rows × 8 columns

In [20]:

# 本代码由可视化策略环境自动生成 2021年9月16日 15:47
# 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 m5_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    
    df = input_1.read()      
    df.set_index('date', inplace=True)

    def resample(df):
        ohlc_dict = {
            'open':'first',
            'high':'max',
            'low':'min',
            'close':'last',
            'volume':'sum'
            }
        resample_df = df.resample('W').agg(ohlc_dict)
        resample_df = resample_df.ffill()
        resample_df['ma_10'] = resample_df['close'].rolling(10).mean()
        return resample_df


    week_df = df.groupby('instrument').apply(resample).reset_index()

    data_1 = DataSource.write_pickle(week_df)
    return Outputs(data_1=data_1)
# 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 m5_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 m10_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    
    pred_df = input_1.read() 
    week_df = input_2.read() 
    
    data_1 = DataSource.write_pickle({
        
        'pred_df':pred_df,
        'week_df':week_df,
        
    })
    return Outputs(data_1=data_1)
# 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 m10_post_run_bigquant_run(outputs):
    return outputs

# 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()['pred_df']
    context.week_df = context.options['data'].read()['week_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')]
    
    week_df = context.week_df[context.week_df.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):
        
        try:
            #print('=====', instrument,  data.current_dt.strftime('%Y-%m-%d'), week_df[(week_df['instrument'] == instrument)])
            price  = week_df[(week_df['instrument'] == instrument)]['close'].values[-1]
            ma_10  = week_df[(week_df['instrument'] == instrument)]['ma_10'].values[-1]
            if price < ma_10:
                continue
        except IndexError as e:
            pass
        
        
        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


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/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)
""",
    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_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(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m13 = M.dropnan.v1(
    input_data=m7.data
)

m6 = M.stock_ranker_train.v5(
    training_ds=m13.data,
    features=m3.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
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2015-01-01'),
    end_date=T.live_run_param('trading_date', '2017-01-01'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m14 = M.dropnan.v1(
    input_data=m18.data
)

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

m4 = M.use_datasource.v1(
    instruments=m9.data,
    datasource_id='bar1d_CN_STOCK_A',
    start_date='',
    end_date=''
)

m5 = M.cached.v3(
    input_1=m4.data,
    run=m5_run_bigquant_run,
    post_run=m5_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m10 = M.cached.v3(
    input_1=m8.predictions,
    input_2=m5.data_1,
    run=m10_run_bigquant_run,
    post_run=m10_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m10.data_1,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_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='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.SHA'
)

[2021-09-16 15:34:33.016537] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-09-16 15:34:33.025330] INFO: moduleinvoker: 命中缓存

[2021-09-16 15:34:33.027198] INFO: moduleinvoker: instruments.v2 运行完成[0.010671s].

[2021-09-16 15:34:33.032622] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2021-09-16 15:34:33.041880] INFO: moduleinvoker: 命中缓存

[2021-09-16 15:34:33.043762] INFO: moduleinvoker: use_datasource.v1 运行完成[0.011115s].

[2021-09-16 15:34:33.056136] INFO: moduleinvoker: cached.v3 开始运行..

[2021-09-16 15:35:13.470436] INFO: moduleinvoker: cached.v3 运行完成[40.414277s].

In [ ]: