策略4：增加股票多样性的QP策略.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 本代码由可视化策略环境自动生成 2019年3月1日 14:18\n",
    "# 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。\n",
    "\n",
    "\n",
    "# 回测引擎：每日数据处理函数，每天执行一次\n",
    "def m19_handle_data_bigquant_run(context, data):\n",
    "    # 按日期过滤得到今日的预测数据\n",
    "    ranker_prediction = context.ranker_prediction[\n",
    "        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n",
    "\n",
    "    # 1. 资金分配\n",
    "    # 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\n",
    "    # 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）\n",
    "    is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）\n",
    "    cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n",
    "    cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n",
    "    cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n",
    "    positions = {e.symbol: p.amount * p.last_sale_price\n",
    "                 for e, p in context.portfolio.positions.items()}\n",
    "\n",
    "    # 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\n",
    "    if not is_staging and cash_for_sell > 0:\n",
    "        equities = {e.symbol: e for e, p in context.portfolio.positions.items()}\n",
    "        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n",
    "                lambda x: x in equities)])))\n",
    "\n",
    "        for instrument in instruments:\n",
    "            context.order_target(context.symbol(instrument), 0)\n",
    "            cash_for_sell -= positions[instrument]\n",
    "            if cash_for_sell <= 0:\n",
    "                break\n",
    "\n",
    "    # 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\n",
    "    buy_cash_weights = context.stock_weights\n",
    "    buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n",
    "    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n",
    "    for i, instrument in enumerate(buy_instruments):\n",
    "        cash = cash_for_buy * buy_cash_weights[i]\n",
    "        if cash > max_cash_per_instrument - positions.get(instrument, 0):\n",
    "            # 确保股票持仓量不会超过每次股票最大的占用资金量\n",
    "            cash = max_cash_per_instrument - positions.get(instrument, 0)\n",
    "        if cash > 0:\n",
    "            context.order_value(context.symbol(instrument), cash)\n",
    "\n",
    "# 回测引擎：准备数据，只执行一次\n",
    "def m19_prepare_bigquant_run(context):\n",
    "    pass\n",
    "\n",
    "# 回测引擎：初始化函数，只执行一次\n",
    "def m19_initialize_bigquant_run(context):\n",
    "    # 加载预测数据\n",
    "    context.ranker_prediction = context.options['data'].read_df()\n",
    "\n",
    "    # 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\n",
    "    context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n",
    "    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)\n",
    "    # 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\n",
    "    stock_count = 5\n",
    "    # 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, ..]\n",
    "    context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])\n",
    "    # 设置每只股票占用的最大资金比例\n",
    "    context.max_cash_per_instrument = 0.2\n",
    "    context.options['hold_days'] = 5\n",
    "\n",
    "\n",
    "m1 = M.instruments.v2(\n",
    "    start_date='2010-01-01',\n",
    "    end_date='2015-01-01',\n",
    "    market='CN_STOCK_A',\n",
    "    instrument_list='',\n",
    "    max_count=0\n",
    ")\n",
    "\n",
    "m2 = M.advanced_auto_labeler.v2(\n",
    "    instruments=m1.data,\n",
    "    label_expr=\"\"\"# #号开始的表示注释\n",
    "# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段\n",
    "# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html\n",
    "#   添加benchmark_前缀，可使用对应的benchmark数据\n",
    "# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_\n",
    "\n",
    "# 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)\n",
    "shift(close, -5) / shift(open, -1)\n",
    "\n",
    "# 极值处理：用1%和99%分位的值做clip\n",
    "clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n",
    "\n",
    "# 将分数映射到分类，这里使用20个分类\n",
    "all_wbins(label, 20)\n",
    "\n",
    "# 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)\n",
    "where(shift(high, -1) == shift(low, -1), NaN, label)\n",
    "\"\"\",\n",
    "    start_date='',\n",
    "    end_date='',\n",
    "    benchmark='000300.SHA',\n",
    "    drop_na_label=True,\n",
    "    cast_label_int=True\n",
    ")\n",
    "\n",
    "m3 = M.input_features.v1(\n",
    "    features=\"\"\"# #号开始的表示注释\n",
    "# 多个特征，每行一个，可以包含基础特征和衍生特征\n",
    "return_5\n",
    "return_10\n",
    "return_20\n",
    "avg_amount_0/avg_amount_5\n",
    "avg_amount_5/avg_amount_20\n",
    "rank_avg_amount_0/rank_avg_amount_5\n",
    "rank_avg_amount_5/rank_avg_amount_10\n",
    "rank_return_0\n",
    "rank_return_5\n",
    "rank_return_10\n",
    "rank_return_0/rank_return_5\n",
    "rank_return_5/rank_return_10\n",
    "pe_ttm_0\n",
    "\"\"\"\n",
    ")\n",
    "\n",
    "m15 = M.general_feature_extractor.v7(\n",
    "    instruments=m1.data,\n",
    "    features=m3.data,\n",
    "    start_date='',\n",
    "    end_date='',\n",
    "    before_start_days=90\n",
    ")\n",
    "\n",
    "m16 = M.derived_feature_extractor.v3(\n",
    "    input_data=m15.data,\n",
    "    features=m3.data,\n",
    "    date_col='date',\n",
    "    instrument_col='instrument',\n",
    "    drop_na=False,\n",
    "    remove_extra_columns=False\n",
    ")\n",
    "\n",
    "m7 = M.join.v3(\n",
    "    data1=m2.data,\n",
    "    data2=m16.data,\n",
    "    on='date,instrument',\n",
    "    how='inner',\n",
    "    sort=False\n",
    ")\n",
    "\n",
    "m13 = M.dropnan.v1(\n",
    "    input_data=m7.data\n",
    ")\n",
    "\n",
    "m6 = M.stock_ranker_train.v5(\n",
    "    training_ds=m13.data,\n",
    "    features=m3.data,\n",
    "    learning_algorithm='排序',\n",
    "    number_of_leaves=30,\n",
    "    minimum_docs_per_leaf=1000,\n",
    "    number_of_trees=20,\n",
    "    learning_rate=0.1,\n",
    "    max_bins=1023,\n",
    "    feature_fraction=1,\n",
    "    m_lazy_run=False\n",
    ")\n",
    "\n",
    "m9 = M.instruments.v2(\n",
    "    start_date=T.live_run_param('trading_date', '2015-01-01'),\n",
    "    end_date=T.live_run_param('trading_date', '2017-01-01'),\n",
    "    market='CN_STOCK_A',\n",
    "    instrument_list='',\n",
    "    max_count=0\n",
    ")\n",
    "\n",
    "m17 = M.general_feature_extractor.v7(\n",
    "    instruments=m9.data,\n",
    "    features=m3.data,\n",
    "    start_date='',\n",
    "    end_date='',\n",
    "    before_start_days=90\n",
    ")\n",
    "\n",
    "m18 = M.derived_feature_extractor.v3(\n",
    "    input_data=m17.data,\n",
    "    features=m3.data,\n",
    "    date_col='date',\n",
    "    instrument_col='instrument',\n",
    "    drop_na=False,\n",
    "    remove_extra_columns=False\n",
    ")\n",
    "\n",
    "m14 = M.dropnan.v1(\n",
    "    input_data=m18.data\n",
    ")\n",
    "\n",
    "m8 = M.stock_ranker_predict.v5(\n",
    "    model=m6.model,\n",
    "    data=m14.data,\n",
    "    m_lazy_run=False\n",
    ")\n",
    "\n",
    "m19 = M.trade.v4(\n",
    "    instruments=m9.data,\n",
    "    options_data=m8.predictions,\n",
    "    start_date='',\n",
    "    end_date='',\n",
    "    handle_data=m19_handle_data_bigquant_run,\n",
    "    prepare=m19_prepare_bigquant_run,\n",
    "    initialize=m19_initialize_bigquant_run,\n",
    "    volume_limit=0.025,\n",
    "    order_price_field_buy='open',\n",
    "    order_price_field_sell='close',\n",
    "    capital_base=1000000,\n",
    "    auto_cancel_non_tradable_orders=True,\n",
    "    data_frequency='daily',\n",
    "    price_type='真实价格',\n",
    "    product_type='股票',\n",
    "    plot_charts=True,\n",
    "    backtest_only=False,\n",
    "    benchmark='000300.SHA'\n",
    ")\n"
   ]
  }
 ],
 "metadata": {
  "is_mlstudio": "false",
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}