From 4385dd871a53c3250d97c84a52fad1d5e058e6dc Mon Sep 17 00:00:00 2001 From: "vn.py" Date: Thu, 2 May 2019 22:32:05 +0800 Subject: [PATCH] [Add]genetic optimization of strategy parameters --- requirements.txt | 1 + tests/backtesting/turtle.ipynb | 601 ++++++++++++++++++++++----- vnpy/app/cta_strategy/backtesting.py | 146 +++++++ 3 files changed, 653 insertions(+), 95 deletions(-) diff --git a/requirements.txt b/requirements.txt index 0706dba5..8eaa8cf4 100644 --- a/requirements.txt +++ b/requirements.txt @@ -17,3 +17,4 @@ tigeropen rqdatac ta-lib ibapi +deap \ No newline at end of file diff --git a/tests/backtesting/turtle.ipynb b/tests/backtesting/turtle.ipynb index 9807424b..8a4f75f4 100644 --- a/tests/backtesting/turtle.ipynb +++ b/tests/backtesting/turtle.ipynb @@ -16,7 +16,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -54,115 +54,526 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "2019-04-15 22:19:49.696835\t参数：{'atr_length': 22}, 目标：121.19996051999999\n", - "2019-04-15 22:19:49.709531\t参数：{'atr_length': 23}, 目标：116.54901966000013\n", - "2019-04-15 22:19:49.710507\t参数：{'atr_length': 24}, 目标：113.29820520000014\n" + "2019-05-02 22:29:22.289010\t开始运行遗传算法，每代族群总数：100, 优良品种筛选个数：80，迭代次数：300，交叉概率：0.95，突变概率：0.05\n", + "2019-05-02 22:29:22.289010\t开始加载历史数据\n", + "2019-05-02 22:29:24.103532\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:24.173848\t策略初始化完成\n", + "2019-05-02 22:29:24.173848\t开始回放历史数据\n", + "2019-05-02 22:29:24.788129\t历史数据回放结束\n", + "2019-05-02 22:29:24.789106\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:24.789106\t成交记录为空，无法计算\n", + "2019-05-02 22:29:24.789106\t开始计算策略统计指标\n", + "2019-05-02 22:29:24.789106\t开始加载历史数据\n", + "2019-05-02 22:29:24.789106\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:24.867234\t策略初始化完成\n", + "2019-05-02 22:29:24.868210\t开始回放历史数据\n", + "2019-05-02 22:29:25.834068\t历史数据回放结束\n", + "2019-05-02 22:29:25.835044\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:25.839927\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:25.840904\t开始计算策略统计指标\n", + "2019-05-02 22:29:25.856529\t开始加载历史数据\n", + "2019-05-02 22:29:25.857506\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:25.939540\t策略初始化完成\n", + "2019-05-02 22:29:25.939540\t开始回放历史数据\n", + "2019-05-02 22:29:27.055794\t历史数据回放结束\n", + "2019-05-02 22:29:27.056771\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:27.062630\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:27.062630\t开始计算策略统计指标\n", + "2019-05-02 22:29:27.074350\t开始加载历史数据\n", + "2019-05-02 22:29:27.074350\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:27.156384\t策略初始化完成\n", + "2019-05-02 22:29:27.156384\t开始回放历史数据\n", + "2019-05-02 22:29:28.159352\t历史数据回放结束\n", + "2019-05-02 22:29:28.160329\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:28.165212\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:28.165212\t开始计算策略统计指标\n", + "2019-05-02 22:29:28.176931\t开始加载历史数据\n", + "2019-05-02 22:29:28.176931\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:28.260919\t策略初始化完成\n", + "2019-05-02 22:29:28.260919\t开始回放历史数据\n", + "2019-05-02 22:29:29.418190\t历史数据回放结束\n", + "2019-05-02 22:29:29.418190\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:29.424049\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:29.424049\t开始计算策略统计指标\n", + "2019-05-02 22:29:29.436745\t开始加载历史数据\n", + "2019-05-02 22:29:29.436745\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:29.521709\t策略初始化完成\n", + "2019-05-02 22:29:29.522686\t开始回放历史数据\n", + "2019-05-02 22:29:30.513935\t历史数据回放结束\n", + "2019-05-02 22:29:30.514911\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:30.519794\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:30.519794\t开始计算策略统计指标\n", + "2019-05-02 22:29:30.531514\t开始加载历史数据\n", + "2019-05-02 22:29:30.531514\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:30.611595\t策略初始化完成\n", + "2019-05-02 22:29:30.611595\t开始回放历史数据\n", + "2019-05-02 22:29:31.729802\t历史数据回放结束\n", + "2019-05-02 22:29:31.730778\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:31.735661\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:31.735661\t开始计算策略统计指标\n", + "2019-05-02 22:29:31.747381\t开始加载历史数据\n", + "2019-05-02 22:29:31.747381\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:31.825509\t策略初始化完成\n", + "2019-05-02 22:29:31.826485\t开始回放历史数据\n", + "2019-05-02 22:29:32.840196\t历史数据回放结束\n", + "2019-05-02 22:29:32.840196\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:32.846056\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:32.847032\t开始计算策略统计指标\n", + "2019-05-02 22:29:32.858751\t开始加载历史数据\n", + "2019-05-02 22:29:32.858751\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:32.936879\t策略初始化完成\n", + "2019-05-02 22:29:32.936879\t开始回放历史数据\n", + "2019-05-02 22:29:34.065829\t历史数据回放结束\n", + "2019-05-02 22:29:34.066806\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:34.071689\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:34.072665\t开始计算策略统计指标\n", + "2019-05-02 22:29:34.085361\t开始加载历史数据\n", + "2019-05-02 22:29:34.085361\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:34.161536\t策略初始化完成\n", + "2019-05-02 22:29:34.162512\t开始回放历史数据\n", + "2019-05-02 22:29:35.174270\t历史数据回放结束\n", + "2019-05-02 22:29:35.175247\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:35.180130\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:35.180130\t开始计算策略统计指标\n", + "2019-05-02 22:29:35.192825\t开始加载历史数据\n", + "2019-05-02 22:29:35.192825\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:35.274860\t策略初始化完成\n", + "2019-05-02 22:29:35.274860\t开始回放历史数据\n", + "2019-05-02 22:29:35.918439\t历史数据回放结束\n", + "2019-05-02 22:29:35.918439\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:35.918439\t成交记录为空，无法计算\n", + "2019-05-02 22:29:35.918439\t开始计算策略统计指标\n", + "2019-05-02 22:29:35.918439\t开始加载历史数据\n", + "2019-05-02 22:29:35.918439\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:35.999497\t策略初始化完成\n", + "2019-05-02 22:29:35.999497\t开始回放历史数据\n", + "2019-05-02 22:29:36.671398\t历史数据回放结束\n", + "2019-05-02 22:29:36.671398\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:36.672374\t成交记录为空，无法计算\n", + "2019-05-02 22:29:36.672374\t开始计算策略统计指标\n", + "2019-05-02 22:29:36.673351\t开始加载历史数据\n", + "2019-05-02 22:29:36.673351\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:36.761245\t策略初始化完成\n", + "2019-05-02 22:29:36.762222\t开始回放历史数据\n", + "2019-05-02 22:29:37.830622\t历史数据回放结束\n", + "2019-05-02 22:29:37.831599\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:37.837458\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:37.837458\t开始计算策略统计指标\n", + "2019-05-02 22:29:37.849177\t开始加载历史数据\n", + "2019-05-02 22:29:37.849177\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:37.926329\t策略初始化完成\n", + "2019-05-02 22:29:37.927305\t开始回放历史数据\n", + "2019-05-02 22:29:38.877537\t历史数据回放结束\n", + "2019-05-02 22:29:38.878514\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:38.884373\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:38.884373\t开始计算策略统计指标\n", + "2019-05-02 22:29:38.895116\t开始加载历史数据\n", + "2019-05-02 22:29:38.896093\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:38.974221\t策略初始化完成\n", + "2019-05-02 22:29:38.974221\t开始回放历史数据\n", + "2019-05-02 22:29:40.131492\t历史数据回放结束\n", + "2019-05-02 22:29:40.131492\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:40.137351\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:40.137351\t开始计算策略统计指标\n", + "2019-05-02 22:29:40.149070\t开始加载历史数据\n", + "2019-05-02 22:29:40.149070\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:40.234035\t策略初始化完成\n", + "2019-05-02 22:29:40.235011\t开始回放历史数据\n", + "2019-05-02 22:29:41.257511\t历史数据回放结束\n", + "2019-05-02 22:29:41.258488\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:41.263371\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:41.263371\t开始计算策略统计指标\n", + "2019-05-02 22:29:41.275090\t开始加载历史数据\n", + "2019-05-02 22:29:41.275090\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:41.353218\t策略初始化完成\n", + "2019-05-02 22:29:41.353218\t开始回放历史数据\n", + "2019-05-02 22:29:42.819095\t历史数据回放结束\n", + "2019-05-02 22:29:42.819095\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:42.823978\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:42.823978\t开始计算策略统计指标\n", + "2019-05-02 22:29:42.835697\t开始加载历史数据\n", + "2019-05-02 22:29:42.836674\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:42.917731\t策略初始化完成\n", + "2019-05-02 22:29:42.917731\t开始回放历史数据\n", + "2019-05-02 22:29:43.901168\t历史数据回放结束\n", + "2019-05-02 22:29:43.901168\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:43.907027\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:43.908004\t开始计算策略统计指标\n", + "2019-05-02 22:29:43.920700\t开始加载历史数据\n", + "2019-05-02 22:29:43.921676\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:44.004687\t策略初始化完成\n", + "2019-05-02 22:29:44.005664\t开始回放历史数据\n", + "2019-05-02 22:29:45.120941\t历史数据回放结束\n", + "2019-05-02 22:29:45.121918\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:45.126801\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:45.126801\t开始计算策略统计指标\n", + "2019-05-02 22:29:45.137543\t开始加载历史数据\n", + "2019-05-02 22:29:45.138520\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:45.216648\t策略初始化完成\n", + "2019-05-02 22:29:45.217624\t开始回放历史数据\n", + "2019-05-02 22:29:46.272352\t历史数据回放结束\n", + "2019-05-02 22:29:46.272352\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:46.277235\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:46.278212\t开始计算策略统计指标\n", + "2019-05-02 22:29:46.289931\t开始加载历史数据\n", + "2019-05-02 22:29:46.289931\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:46.372942\t策略初始化完成\n", + "2019-05-02 22:29:46.372942\t开始回放历史数据\n", + "2019-05-02 22:29:47.500915\t历史数据回放结束\n", + "2019-05-02 22:29:47.501892\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:47.507751\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:47.507751\t开始计算策略统计指标\n", + "2019-05-02 22:29:47.519471\t开始加载历史数据\n", + "2019-05-02 22:29:47.519471\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:47.590762\t策略初始化完成\n", + "2019-05-02 22:29:47.590762\t开始回放历史数据\n", + "2019-05-02 22:29:48.230435\t历史数据回放结束\n", + "2019-05-02 22:29:48.231412\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:48.231412\t成交记录为空，无法计算\n", + "2019-05-02 22:29:48.231412\t开始计算策略统计指标\n", + "2019-05-02 22:29:48.231412\t开始加载历史数据\n", + "2019-05-02 22:29:48.231412\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:48.315400\t策略初始化完成\n", + "2019-05-02 22:29:48.315400\t开始回放历史数据\n", + "2019-05-02 22:29:49.317391\t历史数据回放结束\n", + "2019-05-02 22:29:49.317391\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:49.323251\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:49.323251\t开始计算策略统计指标\n", + "2019-05-02 22:29:49.335947\t开始加载历史数据\n", + "2019-05-02 22:29:49.335947\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:49.416028\t策略初始化完成\n", + "2019-05-02 22:29:49.416028\t开始回放历史数据\n", + "2019-05-02 22:29:50.513726\t历史数据回放结束\n", + "2019-05-02 22:29:50.513726\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:50.519586\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:50.519586\t开始计算策略统计指标\n", + "2019-05-02 22:29:50.531305\t开始加载历史数据\n", + "2019-05-02 22:29:50.531305\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:50.610410\t策略初始化完成\n", + "2019-05-02 22:29:50.611386\t开始回放历史数据\n", + "2019-05-02 22:29:51.688576\t历史数据回放结束\n", + "2019-05-02 22:29:51.689553\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:51.694436\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:51.695412\t开始计算策略统计指标\n", + "2019-05-02 22:29:51.707131\t开始加载历史数据\n", + "2019-05-02 22:29:51.708108\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:51.804791\t策略初始化完成\n", + "2019-05-02 22:29:51.807721\t开始回放历史数据\n", + "2019-05-02 22:29:53.077301\t历史数据回放结束\n", + "2019-05-02 22:29:53.078278\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:53.083161\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:53.083161\t开始计算策略统计指标\n", + "2019-05-02 22:29:53.094880\t开始加载历史数据\n", + "2019-05-02 22:29:53.094880\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:53.182774\t策略初始化完成\n", + "2019-05-02 22:29:53.183751\t开始回放历史数据\n", + "2019-05-02 22:29:54.420126\t历史数据回放结束\n", + "2019-05-02 22:29:54.421103\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:54.425986\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:54.425986\t开始计算策略统计指标\n", + "2019-05-02 22:29:54.437705\t开始加载历史数据\n", + "2019-05-02 22:29:54.437705\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:54.517786\t策略初始化完成\n", + "2019-05-02 22:29:54.517786\t开始回放历史数据\n" ] }, { - "data": { - "text/plain": [ - "[(\"{'atr_length': 22}\",\n", - " 121.19996051999999,\n", - " {'start_date': datetime.date(2013, 1, 18),\n", - " 'end_date': datetime.date(2019, 4, 11),\n", - " 'total_days': 1514,\n", - " 'profit_days': 763,\n", - " 'loss_days': 750,\n", - " 'capital': 1000000,\n", - " 'end_balance': 2211999.6052,\n", - " 'max_drawdown': -248787.6971999996,\n", - " 'max_ddpercent': -12.636908338002794,\n", - " 'total_net_pnl': 1211999.6052000003,\n", - " 'daily_net_pnl': 800.5281408190227,\n", - " 'total_commission': 242400.39479999998,\n", - " 'daily_commission': 160.10594108322323,\n", - " 'total_slippage': 481860.0,\n", - " 'daily_slippage': 318.2694848084544,\n", - " 'total_turnover': 8080013160.0,\n", - " 'daily_turnover': 5336864.702774108,\n", - " 'total_trade_count': 8031,\n", - " 'daily_trade_count': 5.30449141347424,\n", - " 'total_return': 121.19996051999999,\n", - " 'annual_return': 19.212675379656538,\n", - " 'daily_return': 0.052348808029058974,\n", - " 'return_std': 0.9487639654919149,\n", - " 'sharpe_ratio': 0.854779772691872,\n", - " 'return_drawdown_ratio': 9.590950355754112}),\n", - " (\"{'atr_length': 23}\",\n", - " 116.54901966000013,\n", - " {'start_date': datetime.date(2013, 1, 18),\n", - " 'end_date': datetime.date(2019, 4, 11),\n", - " 'total_days': 1514,\n", - " 'profit_days': 759,\n", - " 'loss_days': 754,\n", - " 'capital': 1000000,\n", - " 'end_balance': 2165490.1966000013,\n", - " 'max_drawdown': -232904.1239999996,\n", - " 'max_ddpercent': -13.536251422505968,\n", - " 'total_net_pnl': 1165490.1966000004,\n", - " 'daily_net_pnl': 769.8085842800531,\n", - " 'total_commission': 242769.80339999998,\n", - " 'daily_commission': 160.34993619550858,\n", - " 'total_slippage': 482700.0,\n", - " 'daily_slippage': 318.82430647291943,\n", - " 'total_turnover': 8092326780.0,\n", - " 'daily_turnover': 5344997.873183619,\n", - " 'total_trade_count': 8045,\n", - " 'daily_trade_count': 5.313738441215324,\n", - " 'total_return': 116.54901966000013,\n", - " 'annual_return': 18.475406022721288,\n", - " 'daily_return': 0.0509452313711608,\n", - " 'return_std': 0.961380153488665,\n", - " 'sharpe_ratio': 0.8209448965768181,\n", - " 'return_drawdown_ratio': 8.610139987960078}),\n", - " (\"{'atr_length': 24}\",\n", - " 113.29820520000014,\n", - " {'start_date': datetime.date(2013, 1, 18),\n", - " 'end_date': datetime.date(2019, 4, 11),\n", - " 'total_days': 1514,\n", - " 'profit_days': 760,\n", - " 'loss_days': 753,\n", - " 'capital': 1000000,\n", - " 'end_balance': 2132982.0520000015,\n", - " 'max_drawdown': -236503.9475999996,\n", - " 'max_ddpercent': -13.23872340727957,\n", - " 'total_net_pnl': 1132982.0520000013,\n", - " 'daily_net_pnl': 748.3368903566719,\n", - " 'total_commission': 242817.948,\n", - " 'daily_commission': 160.3817357992074,\n", - " 'total_slippage': 482700.0,\n", - " 'daily_slippage': 318.82430647291943,\n", - " 'total_turnover': 8093931600.0,\n", - " 'daily_turnover': 5346057.85997358,\n", - " 'total_trade_count': 8045,\n", - " 'daily_trade_count': 5.313738441215324,\n", - " 'total_return': 113.29820520000014,\n", - " 'annual_return': 17.96008536856013,\n", - " 'daily_return': 0.049946173936258026,\n", - " 'return_std': 0.959328411709829,\n", - " 'sharpe_ratio': 0.8065671672003681,\n", - " 'return_drawdown_ratio': 8.558091419728651})]" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" + "name": "stdout", + "output_type": "stream", + "text": [ + "2019-05-02 22:29:55.671151\t历史数据回放结束\n", + "2019-05-02 22:29:55.672127\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:55.677010\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:55.677987\t开始计算策略统计指标\n", + "2019-05-02 22:29:55.689706\t开始加载历史数据\n", + "2019-05-02 22:29:55.689706\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:55.767834\t策略初始化完成\n", + "2019-05-02 22:29:55.767834\t开始回放历史数据\n", + "2019-05-02 22:29:56.790334\t历史数据回放结束\n", + "2019-05-02 22:29:56.790334\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:56.796194\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:56.796194\t开始计算策略统计指标\n", + "2019-05-02 22:29:56.806937\t开始加载历史数据\n", + "2019-05-02 22:29:56.807913\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:56.889948\t策略初始化完成\n", + "2019-05-02 22:29:56.890924\t开始回放历史数据\n", + "2019-05-02 22:29:57.607749\t历史数据回放结束\n", + "2019-05-02 22:29:57.608725\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:57.608725\t成交记录为空，无法计算\n", + "2019-05-02 22:29:57.608725\t开始计算策略统计指标\n", + "2019-05-02 22:29:57.608725\t开始加载历史数据\n", + "2019-05-02 22:29:57.609702\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:57.698572\t策略初始化完成\n", + "2019-05-02 22:29:57.699549\t开始回放历史数据\n", + "2019-05-02 22:29:58.882212\t历史数据回放结束\n", + "2019-05-02 22:29:58.882212\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:29:58.888071\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:29:58.888071\t开始计算策略统计指标\n", + "2019-05-02 22:29:58.898814\t开始加载历史数据\n", + "2019-05-02 22:29:58.898814\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:29:58.986708\t策略初始化完成\n", + "2019-05-02 22:29:58.987684\t开始回放历史数据\n", + "2019-05-02 22:30:00.071710\t历史数据回放结束\n", + "2019-05-02 22:30:00.072687\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:00.077570\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:00.081476\t开始计算策略统计指标\n", + "2019-05-02 22:30:00.092219\t开始加载历史数据\n", + "2019-05-02 22:30:00.095149\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:00.173277\t策略初始化完成\n", + "2019-05-02 22:30:00.174253\t开始回放历史数据\n", + "2019-05-02 22:30:00.906703\t历史数据回放结束\n", + "2019-05-02 22:30:00.907680\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:00.907680\t成交记录为空，无法计算\n", + "2019-05-02 22:30:00.908657\t开始计算策略统计指标\n", + "2019-05-02 22:30:00.908657\t开始加载历史数据\n", + "2019-05-02 22:30:00.908657\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:01.018036\t策略初始化完成\n", + "2019-05-02 22:30:01.019012\t开始回放历史数据\n", + "2019-05-02 22:30:02.128430\t历史数据回放结束\n", + "2019-05-02 22:30:02.135266\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:02.141126\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:02.141126\t开始计算策略统计指标\n", + "2019-05-02 22:30:02.151868\t开始加载历史数据\n", + "2019-05-02 22:30:02.152845\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:02.229020\t策略初始化完成\n", + "2019-05-02 22:30:02.229020\t开始回放历史数据\n", + "2019-05-02 22:30:03.410706\t历史数据回放结束\n", + "2019-05-02 22:30:03.411682\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:03.416565\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:03.416565\t开始计算策略统计指标\n", + "2019-05-02 22:30:03.428285\t开始加载历史数据\n", + "2019-05-02 22:30:03.429261\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:03.533757\t策略初始化完成\n", + "2019-05-02 22:30:03.533757\t开始回放历史数据\n", + "2019-05-02 22:30:04.638292\t历史数据回放结束\n", + "2019-05-02 22:30:04.638292\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:04.643175\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:04.644152\t开始计算策略统计指标\n", + "2019-05-02 22:30:04.654894\t开始加载历史数据\n", + "2019-05-02 22:30:04.654894\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:04.738882\t策略初始化完成\n", + "2019-05-02 22:30:04.738882\t开始回放历史数据\n", + "2019-05-02 22:30:05.721341\t历史数据回放结束\n", + "2019-05-02 22:30:05.722318\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:05.728178\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:05.728178\t开始计算策略统计指标\n", + "2019-05-02 22:30:05.739897\t开始加载历史数据\n", + "2019-05-02 22:30:05.739897\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:05.824861\t策略初始化完成\n", + "2019-05-02 22:30:05.825838\t开始回放历史数据\n", + "2019-05-02 22:30:06.928419\t历史数据回放结束\n", + "2019-05-02 22:30:06.928419\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:06.933302\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:06.934279\t开始计算策略统计指标\n", + "2019-05-02 22:30:06.945998\t开始加载历史数据\n", + "2019-05-02 22:30:06.945998\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:07.024126\t策略初始化完成\n", + "2019-05-02 22:30:07.025102\t开始回放历史数据\n", + "2019-05-02 22:30:08.041743\t历史数据回放结束\n", + "2019-05-02 22:30:08.042720\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:08.048579\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:08.048579\t开始计算策略统计指标\n", + "2019-05-02 22:30:08.062252\t开始加载历史数据\n", + "2019-05-02 22:30:08.062252\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:08.145263\t策略初始化完成\n", + "2019-05-02 22:30:08.145263\t开始回放历史数据\n", + "2019-05-02 22:30:09.292768\t历史数据回放结束\n", + "2019-05-02 22:30:09.293744\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:09.298627\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:09.298627\t开始计算策略统计指标\n", + "2019-05-02 22:30:09.311323\t开始加载历史数据\n", + "2019-05-02 22:30:09.311323\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:09.393357\t策略初始化完成\n", + "2019-05-02 22:30:09.393357\t开始回放历史数据\n", + "2019-05-02 22:30:10.363121\t历史数据回放结束\n", + "2019-05-02 22:30:10.363121\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:10.368981\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:10.369957\t开始计算策略统计指标\n", + "2019-05-02 22:30:10.380700\t开始加载历史数据\n", + "2019-05-02 22:30:10.381677\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:10.459805\t策略初始化完成\n", + "2019-05-02 22:30:10.459805\t开始回放历史数据\n", + "2019-05-02 22:30:11.536994\t历史数据回放结束\n", + "2019-05-02 22:30:11.536994\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:11.542854\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:11.542854\t开始计算策略统计指标\n", + "2019-05-02 22:30:11.554573\t开始加载历史数据\n", + "2019-05-02 22:30:11.554573\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:11.638561\t策略初始化完成\n", + "2019-05-02 22:30:11.639537\t开始回放历史数据\n", + "2019-05-02 22:30:12.632740\t历史数据回放结束\n", + "2019-05-02 22:30:12.633716\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:12.638599\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:12.639576\t开始计算策略统计指标\n", + "2019-05-02 22:30:12.650318\t开始加载历史数据\n", + "2019-05-02 22:30:12.651295\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:12.733329\t策略初始化完成\n", + "2019-05-02 22:30:12.734306\t开始回放历史数据\n", + "2019-05-02 22:30:13.352494\t历史数据回放结束\n", + "2019-05-02 22:30:13.353470\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:13.353470\t成交记录为空，无法计算\n", + "2019-05-02 22:30:13.353470\t开始计算策略统计指标\n", + "2019-05-02 22:30:13.354447\t开始加载历史数据\n", + "2019-05-02 22:30:13.354447\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:13.436481\t策略初始化完成\n", + "2019-05-02 22:30:13.436481\t开始回放历史数据\n", + "2019-05-02 22:30:14.540039\t历史数据回放结束\n", + "2019-05-02 22:30:14.541016\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:14.546876\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:14.546876\t开始计算策略统计指标\n", + "2019-05-02 22:30:14.558595\t开始加载历史数据\n", + "2019-05-02 22:30:14.558595\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:14.650395\t策略初始化完成\n", + "2019-05-02 22:30:14.650395\t开始回放历史数据\n", + "2019-05-02 22:30:15.294951\t历史数据回放结束\n", + "2019-05-02 22:30:15.294951\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:15.294951\t成交记录为空，无法计算\n", + "2019-05-02 22:30:15.294951\t开始计算策略统计指标\n", + "2019-05-02 22:30:15.294951\t开始加载历史数据\n", + "2019-05-02 22:30:15.294951\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:15.377962\t策略初始化完成\n", + "2019-05-02 22:30:15.377962\t开始回放历史数据\n", + "2019-05-02 22:30:16.346749\t历史数据回放结束\n", + "2019-05-02 22:30:16.346749\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:16.352609\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:16.352609\t开始计算策略统计指标\n", + "2019-05-02 22:30:16.365305\t开始加载历史数据\n", + "2019-05-02 22:30:16.365305\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:16.445386\t策略初始化完成\n", + "2019-05-02 22:30:16.446363\t开始回放历史数据\n", + "2019-05-02 22:30:17.544061\t历史数据回放结束\n", + "2019-05-02 22:30:17.545038\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:17.550897\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:17.550897\t开始计算策略统计指标\n", + "2019-05-02 22:30:17.563593\t开始加载历史数据\n", + "2019-05-02 22:30:17.563593\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:17.640744\t策略初始化完成\n", + "2019-05-02 22:30:17.640744\t开始回放历史数据\n", + "2019-05-02 22:30:18.641759\t历史数据回放结束\n", + "2019-05-02 22:30:18.642736\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:18.647619\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:18.647619\t开始计算策略统计指标\n", + "2019-05-02 22:30:18.659338\t开始加载历史数据\n", + "2019-05-02 22:30:18.660315\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:18.736490\t策略初始化完成\n", + "2019-05-02 22:30:18.736490\t开始回放历史数据\n", + "2019-05-02 22:30:19.827352\t历史数据回放结束\n", + "2019-05-02 22:30:19.828328\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:19.833211\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:19.833211\t开始计算策略统计指标\n", + "2019-05-02 22:30:19.844931\t开始加载历史数据\n", + "2019-05-02 22:30:19.845907\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:19.927942\t策略初始化完成\n", + "2019-05-02 22:30:19.928918\t开始回放历史数据\n", + "2019-05-02 22:30:20.916261\t历史数据回放结束\n", + "2019-05-02 22:30:20.916261\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:20.922120\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:20.922120\t开始计算策略统计指标\n", + "2019-05-02 22:30:20.934816\t开始加载历史数据\n", + "2019-05-02 22:30:20.935793\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:21.010991\t策略初始化完成\n", + "2019-05-02 22:30:21.011968\t开始回放历史数据\n", + "2019-05-02 22:30:22.131151\t历史数据回放结束\n", + "2019-05-02 22:30:22.131151\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:22.137011\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:22.137011\t开始计算策略统计指标\n", + "2019-05-02 22:30:22.149707\t开始加载历史数据\n", + "2019-05-02 22:30:22.149707\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:22.227835\t策略初始化完成\n", + "2019-05-02 22:30:22.228811\t开始回放历史数据\n", + "2019-05-02 22:30:23.201505\t历史数据回放结束\n", + "2019-05-02 22:30:23.202481\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:23.207364\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:23.207364\t开始计算策略统计指标\n", + "2019-05-02 22:30:23.219084\t开始加载历史数据\n", + "2019-05-02 22:30:23.219084\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:23.295258\t策略初始化完成\n", + "2019-05-02 22:30:23.295258\t开始回放历史数据\n", + "2019-05-02 22:30:24.418348\t历史数据回放结束\n", + "2019-05-02 22:30:24.418348\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:24.423231\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:24.424208\t开始计算策略统计指标\n", + "2019-05-02 22:30:24.437880\t开始加载历史数据\n", + "2019-05-02 22:30:24.437880\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:24.517962\t策略初始化完成\n", + "2019-05-02 22:30:24.517962\t开始回放历史数据\n", + "2019-05-02 22:30:25.200605\t历史数据回放结束\n", + "2019-05-02 22:30:25.201582\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:25.201582\t成交记录为空，无法计算\n", + "2019-05-02 22:30:25.202558\t开始计算策略统计指标\n", + "2019-05-02 22:30:25.202558\t开始加载历史数据\n", + "2019-05-02 22:30:25.203535\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:25.275803\t策略初始化完成\n", + "2019-05-02 22:30:25.276780\t开始回放历史数据\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "2019-05-02 22:30:25.947704\t历史数据回放结束\n", + "2019-05-02 22:30:25.948681\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:25.948681\t成交记录为空，无法计算\n", + "2019-05-02 22:30:25.949657\t开始计算策略统计指标\n", + "2019-05-02 22:30:25.949657\t开始加载历史数据\n", + "2019-05-02 22:30:25.949657\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:26.027785\t策略初始化完成\n", + "2019-05-02 22:30:26.027785\t开始回放历史数据\n", + "2019-05-02 22:30:27.024894\t历史数据回放结束\n", + "2019-05-02 22:30:27.025870\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:27.030753\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:27.030753\t开始计算策略统计指标\n", + "2019-05-02 22:30:27.042473\t开始加载历史数据\n", + "2019-05-02 22:30:27.042473\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:27.127437\t策略初始化完成\n", + "2019-05-02 22:30:27.128413\t开始回放历史数据\n", + "2019-05-02 22:30:28.317912\t历史数据回放结束\n", + "2019-05-02 22:30:28.317912\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:28.323772\t逐日盯市盈亏计算完成\n", + "2019-05-02 22:30:28.324748\t开始计算策略统计指标\n", + "2019-05-02 22:30:28.335491\t开始加载历史数据\n", + "2019-05-02 22:30:28.336468\t历史数据加载完成，数据量：18240\n", + "2019-05-02 22:30:28.412642\t策略初始化完成\n", + "2019-05-02 22:30:28.413619\t开始回放历史数据\n", + "2019-05-02 22:30:29.072824\t历史数据回放结束\n", + "2019-05-02 22:30:29.072824\t开始计算逐日盯市盈亏\n", + "2019-05-02 22:30:29.072824\t成交记录为空，无法计算\n", + "2019-05-02 22:30:29.072824\t开始计算策略统计指标\n", + "gen\tnevals\tmean \tstd \tmin \tmax \n", + "0 \t100 \t[1.24452619]\t[2.90495733]\t[-3.24204978]\t[8.88922512]\n" + ] + }, + { + "ename": "ValueError", + "evalue": "empty range for randrange() (1,1, 0)", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0msetting\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0madd_parameter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"atr_length\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m3\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m105\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m \u001b[0mengine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrun_ga_optimization\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msetting\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;32mC:\\Github\\vnpy\\vnpy\\app\\cta_strategy\\backtesting.py\u001b[0m in \u001b[0;36mrun_ga_optimization\u001b[1;34m(self, optimization_setting, output)\u001b[0m\n\u001b[0;32m 602\u001b[0m \u001b[0mNGEN\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 603\u001b[0m \u001b[0mstats\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 604\u001b[1;33m \u001b[0mhalloffame\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mhof\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 605\u001b[0m ) \n\u001b[0;32m 606\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mc:\\miniconda3\\lib\\site-packages\\deap\\algorithms.py\u001b[0m in \u001b[0;36meaMuPlusLambda\u001b[1;34m(population, toolbox, mu, lambda_, cxpb, mutpb, ngen, stats, halloffame, verbose)\u001b[0m\n\u001b[0;32m 316\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mgen\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mngen\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 317\u001b[0m \u001b[1;31m# Vary the population\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 318\u001b[1;33m \u001b[0moffspring\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvarOr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpopulation\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtoolbox\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlambda_\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcxpb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmutpb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 319\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 320\u001b[0m \u001b[1;31m# Evaluate the individuals with an invalid fitness\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mc:\\miniconda3\\lib\\site-packages\\deap\\algorithms.py\u001b[0m in \u001b[0;36mvarOr\u001b[1;34m(population, toolbox, lambda_, cxpb, mutpb)\u001b[0m\n\u001b[0;32m 234\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mop_choice\u001b[0m \u001b[1;33m<\u001b[0m \u001b[0mcxpb\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;31m# Apply crossover\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 235\u001b[0m \u001b[0mind1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mind2\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmap\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtoolbox\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrandom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msample\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpopulation\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 236\u001b[1;33m \u001b[0mind1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mind2\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtoolbox\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mind1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mind2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 237\u001b[0m \u001b[1;32mdel\u001b[0m \u001b[0mind1\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfitness\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 238\u001b[0m \u001b[0moffspring\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mind1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mc:\\miniconda3\\lib\\site-packages\\deap\\tools\\crossover.py\u001b[0m in \u001b[0;36mcxTwoPoint\u001b[1;34m(ind1, ind2)\u001b[0m\n\u001b[0;32m 42\u001b[0m \u001b[0msize\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mmin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mind1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mind2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 43\u001b[0m \u001b[0mcxpoint1\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mrandom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msize\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 44\u001b[1;33m \u001b[0mcxpoint2\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mrandom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msize\u001b[0m \u001b[1;33m-\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 45\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mcxpoint2\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[0mcxpoint1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 46\u001b[0m \u001b[0mcxpoint2\u001b[0m \u001b[1;33m+=\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32mc:\\miniconda3\\lib\\random.py\u001b[0m in \u001b[0;36mrandint\u001b[1;34m(self, a, b)\u001b[0m\n\u001b[0;32m 220\u001b[0m \"\"\"\n\u001b[0;32m 221\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 222\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrandrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0ma\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mb\u001b[0m\u001b[1;33m+\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 223\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 224\u001b[0m def _randbelow(self, n, int=int, maxsize=1< 200\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"empty range for randrange() (%d,%d, %d)\"\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mistart\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mistop\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mwidth\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 201\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 202\u001b[0m \u001b[1;31m# Non-unit step argument supplied.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mValueError\u001b[0m: empty range for randrange() (1,1, 0)" + ] } ], "source": [ "setting = OptimizationSetting()\n", "setting.set_target(\"total_return\")\n", - "setting.add_parameter(\"atr_length\", 22, 24, 1)\n", + "setting.add_parameter(\"atr_length\", 3, 105, 1)\n", "\n", - "engine.run_optimization(setting)" + "engine.run_ga_optimization(setting)" ] }, { diff --git a/vnpy/app/cta_strategy/backtesting.py b/vnpy/app/cta_strategy/backtesting.py index e4aa25c7..083cb2d0 100644 --- a/vnpy/app/cta_strategy/backtesting.py +++ b/vnpy/app/cta_strategy/backtesting.py @@ -3,12 +3,15 @@ from datetime import date, datetime from typing import Callable from itertools import product from functools import lru_cache +from time import time import multiprocessing +import random import numpy as np import matplotlib.pyplot as plt import seaborn as sns from pandas import DataFrame +from deap import creator, base, tools, algorithms from vnpy.trader.constant import (Direction, Offset, Exchange, Interval, Status) @@ -514,6 +517,101 @@ class BacktestingEngine: return result_values + def run_ga_optimization(self, optimization_setting: OptimizationSetting, output=True): + """""" + # Get optimization setting and target + settings = optimization_setting.generate_setting() + target_name = optimization_setting.target_name + + if not settings: + self.output("优化参数组合为空，请检查") + return + + if not target_name: + self.output("优化目标未设置，请检查") + return + + # Define parameter generation function + def generate_parameter(): + """""" + return list(random.choice(settings).values()) + + # Create ga object function + object_func = create_ga_optimize( + target_name, + self.strategy_class, + settings[0], + self.vt_symbol, + self.interval, + self.start, + self.rate, + self.slippage, + self.size, + self.pricetick, + self.capital, + self.end, + self.mode + ) + + # Set up genetic algorithem + creator.create("FitnessMax", base.Fitness, weights=(1.0,)) + creator.create("Individual", list, fitness=creator.FitnessMax) + + toolbox = base.Toolbox() + toolbox.register("individual", tools.initIterate, creator.Individual, generate_parameter) + toolbox.register("population", tools.initRepeat, list, toolbox.individual) + toolbox.register("mate", tools.cxTwoPoint) + toolbox.register("mutate", tools.mutUniformInt, low=4, up=40, indpb=1) + toolbox.register("evaluate", object_func) + toolbox.register("select", tools.selNSGA2) + + # pool = multiprocessing.Pool(multiprocessing.cpu_count()) + # toolbox.register("map", pool.map) + + MU = 80 # 设置每一代选择的个体数 + LAMBDA = 100 # 设置每一代产生的子女数 + POP = 100 + CXPB = 0.95 # 交叉概率 + MUTPB = 0.05 # 变异概率 + NGEN = 300 # 种群代数 + + pop = toolbox.population(POP) # 设置族群里面的个体数量 + hof = tools.ParetoFront() # 解的集合：帕累托前沿(非占优最优集) + + stats = tools.Statistics(lambda ind: ind.fitness.values) + np.set_printoptions(suppress=True) # 对numpy默认输出的科学计数法转换 + stats.register("mean", np.mean, axis=0) # 统计目标优化函数结果的平均值 + stats.register("std", np.std, axis=0) # 统计目标优化函数结果的标准差 + stats.register("min", np.min, axis=0) # 统计目标优化函数结果的最小值 + stats.register("max", np.max, axis=0) # 统计目标优化函数结果的最大值 + + msg = "开始运行遗传算法，每代族群总数：%s, 优良品种筛选个数：%s，迭代次数：%s，交叉概率：%s，突变概率：%s" %(POP,MU,NGEN,CXPB,MUTPB) + self.output(msg) + + # Run ga optimization + # esMuPlusLambda是一种基于(μ+λ)选择策略的多目标优化分段遗传算法 + start = time() + + algorithms.eaMuPlusLambda( + pop, + toolbox, + MU, + LAMBDA, + CXPB, + MUTPB, + NGEN, + stats, + halloffame=hof + ) + + end = time() + cost = int((end - start)) + + self.output(f"遗传算法优化完成，耗时{cost}秒") + self.output("输出帕累托前沿解集：") + + return hof + def update_daily_close(self, price: float): """""" d = self.datetime.date() @@ -968,6 +1066,54 @@ def optimize( return (str(setting), target_value, statistics) +def create_ga_optimize( + target_name: str, + strategy_class: CtaTemplate, + setting: dict, + vt_symbol: str, + interval: Interval, + start: datetime, + rate: float, + slippage: float, + size: float, + pricetick: float, + capital: int, + end: datetime, + mode: BacktestingMode, +): + """ + Function for running in multiprocessing.pool + """ + parameter_keys = list(setting.keys()) + + @lru_cache(maxsize=1000000) + def _optimizae(parameter_values: tuple): + """""" + setting = dict(zip(parameter_keys, parameter_values)) + result = optimize( + target_name, + strategy_class, + setting, + vt_symbol, + interval, + start, + rate, + slippage, + size, + pricetick, + capital, + end, + mode + ) + return (result[1],) + + def ga_optimize(parameter_values: list): + """""" + return _optimizae(tuple(parameter_values)) + + return ga_optimize + + @lru_cache(maxsize=10) def load_bar_data( symbol: str,