机器学习+择时+跟踪止损+技术分析

策略分享
用户成长系列
标签: #<Tag:0x00007faff0c8e748> #<Tag:0x00007faff0c8e108>

(a790523632) #1
克隆策略
In [5]:
benchmark_df = D.history_data(['000300.SHA'], '2010-01-01', '2019-5-31', ['close','volume','high','open'])
benchmark_df['ma_close_5'] = benchmark_df['close'].rolling(5).mean()
benchmark_df['ma_close_30'] = benchmark_df['close'].rolling(30).mean()
benchmark_df['ma_volume_5'] = benchmark_df['volume'].rolling(5).mean()
benchmark_df['ma_volume_30'] = benchmark_df['volume'].rolling(30).mean()
benchmark_df['close_1'] = benchmark_df['close'].shift(1)
benchmark_df['close_2'] = benchmark_df['close'].shift(2)
benchmark_df['open_1'] = benchmark_df['open'].shift(1)
benchmark_df['open_2'] = benchmark_df['open'].shift(2)
benchmark_df['highest'] = benchmark_df['high'].rolling(30).max()


def judge_direction(df):
    cond1 = df['ma_close_5'] >= df['ma_close_30']
    cond2 = df['ma_volume_5'] >= df['ma_volume_30']
    cond3 = df['close'] >= df['open'] and df['close_1'] >= df['open_1'] and df['close_2'] >= df['open_2'] 
    
    cond4 =  df['ma_close_5'] < df['ma_close_30']
    cond5 = df['close'] < df['open'] and df['close_1']  < df['open_1']  and df['close_2']  < df['open_2'] 
    cond6 = df['close'] / df['highest'] - 1 <= -0.1
    
    if  cond1 and cond2 and cond3:
        return 'Long'
    elif cond4 and cond5 and cond6 :
        return 'Short'  
    
benchmark_df['direction'] = benchmark_df.apply(judge_direction, axis=1)
time_select = benchmark_df[['date','direction']].set_index('date')
In [6]:
# 基础参数配置
class conf:
    start_date = '2010-01-01'
    end_date='2019-5-31'
    # split_date 之前的数据用于训练,之后的数据用作效果评估
    split_date = '2014-01-01'
    # D.instruments: https://bigquant.com/docs/data_instruments.html
    instruments = D.instruments(start_date, split_date)

    # 机器学习目标标注函数
    # 如下标注函数等价于 min(max((持有期间的收益 * 100), -20), 20) + 20 (后面的M.fast_auto_labeler会做取整操作)
    # 说明:max/min这里将标注分数限定在区间[-20, 20],+20将分数变为非负数 (StockRanker要求标注分数非负整数)
    label_expr = ['return * 100', 'where(label > {0}, {0}, where(label < -{0}, -{0}, label)) + {0}'.format(20)]
    # 持有天数,用于计算label_expr中的return值(收益)
    hold_days = 5

    # 特征 https://bigquant.com/docs/data_features.html,你可以通过表达式构造任何特征
    features = [
       'rank_pb_lf_0',
    ]

# 给数据做标注:给每一行数据(样本)打分,一般分数越高表示越好
m1 = M.fast_auto_labeler.v8(
    instruments=conf.instruments, start_date=conf.start_date, end_date=conf.split_date,
    label_expr=conf.label_expr, hold_days=conf.hold_days,
    benchmark='000300.SHA', sell_at='open', buy_at='open')
# 计算特征数据
m2 = M.general_feature_extractor.v5(
    instruments=conf.instruments, start_date=conf.start_date, end_date=conf.split_date,
    features=conf.features)
# 数据预处理:缺失数据处理,数据规范化,T.get_stock_ranker_default_transforms为StockRanker模型做数据预处理
m3 = M.transform.v2(
    data=m2.data, transforms=T.get_stock_ranker_default_transforms(),
    drop_null=True, astype='int32', except_columns=['date', 'instrument'],
    clip_lower=0, clip_upper=200000000)
# 合并标注和特征数据
m4 = M.join.v2(data1=m1.data, data2=m3.data, on=['date', 'instrument'], sort=True)
# StockRanker机器学习训练
m5 = M.stock_ranker_train.v3(training_ds=m4.data, features=conf.features)


## 量化回测 https://bigquant.com/docs/module_trade.html
# 回测引擎:准备数据,只执行一次
def prepare(context):
    # context.start_date / end_date,回测的时候,为trader传入参数;在实盘运行的时候,由系统替换为实盘日期
    n1 = M.general_feature_extractor.v5(
        instruments=D.instruments(),
        start_date=context.start_date, end_date=context.end_date,
        model_id=context.options['model_id'])
    n2 = M.transform.v2(
        data=n1.data, transforms=T.get_stock_ranker_default_transforms(),
        drop_null=True, astype='int32', except_columns=['date', 'instrument'],
        clip_lower=0, clip_upper=200000000)
    n3 = M.stock_ranker_predict.v2(model_id=context.options['model_id'], data=n2.data)
    context.instruments = n3.instruments
    context.options['predictions'] = n3.predictions

# 回测引擎:初始化函数,只执行一次
def initialize(context):
    # 加载预测数据
    context.ranker_prediction = context.options['predictions'].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

# 回测引擎:每日数据处理函数,每天执行一次
def handle_data(context, data):
    time_select = context.options['time_select']
    today_direction = time_select.ix[data.current_dt.strftime('%Y-%m-%d')].ix[0]
   
    positions = {e.symbol: p.cost_basis  for e, p in context.portfolio.positions.items()}
      
    if today_direction == 'Short':
        print('大盘择时应该空仓!')
        positions = {e.symbol: p.cost_basis  for e, p in context.portfolio.positions.items()}
        stock_hold = positions.keys()
        for sid in stock_hold:
            context.order_target(context.symbol(sid), 0)
            
        
    
    # 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.perf_tracker.position_tracker.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StockRanker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.perf_tracker.position_tracker.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        # print('rank order for sell %s' % instruments)
        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StockRanker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):
        if today_direction != 'Long':
            break
        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)
            
     #------------------------------------------止损模块START--------------------------------------------
    date = data.current_dt.strftime('%Y-%m-%d')  
    equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
    # 新建当日止损股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
    current_stoploss_stock = [] 
    if len(equities) > 0:
        for i in equities.keys():
            stock_market_price = data.current(context.symbol(i), 'price')  # 最新市场价格
            last_sale_date = equities[i].last_sale_date   # 上次交易日期
            delta_days = data.current_dt - last_sale_date  
            hold_days = delta_days.days # 持仓天数
            # 建仓以来的最高价
            highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()
            # 确定止损位置
            stoploss_line = highest_price_since_buy - highest_price_since_buy * 0.1
            record('止损位置', stoploss_line)
            # 如果价格下穿止损位置
            if stock_market_price < stoploss_line:
                context.order_target_percent(context.symbol(i), 0)     
                current_stoploss_stock.append(i)
                print('日期:', date , '股票:', i, '出现止损状况')
    #-------------------------------------------止损模块END-----------------------
            

# 调用交易引擎
m6 = M.trade.v2(
    instruments=None,
    start_date=conf.split_date,
    end_date=conf.end_date,
    prepare=prepare,
    initialize=initialize,
    handle_data=handle_data,
    order_price_field_buy='open',       # 表示 开盘 时买入
    order_price_field_sell='close',     # 表示 收盘 前卖出
    capital_base=1000000,               # 初始资金
    benchmark='000300.SHA',             # 比较基准,不影响回测结果
    # 通过 options 参数传递预测数据和参数给回测引擎
    options={'hold_days': conf.hold_days, 'model_id': m5.model_id,'time_select':time_select}
)
  • 收益率122.81%
  • 年化收益率16.54%
  • 基准收益率55.78%
  • 阿尔法0.12
  • 贝塔0.12
  • 夏普比率1.46
  • 胜率0.63
  • 盈亏比1.52
  • 收益波动率8.74%
  • 信息比率0.01
  • 最大回撤10.67%
bigcharts-data-start/{"__id":"bigchart-b1ecbe53c5734ecc91c1aa4ea4bc754d","__type":"tabs"}/bigcharts-data-end

请问这个策略该如何加入技术分析指标,如MACD、KDJ等? @iQuant


(iQuant) #2

您好,可以参考此片帖子:【宽客学院】借助Talib库构建技术分析指标因子