senset/vnpy
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[Mod]add return value of run_ga_optimization

Browse Source
This commit is contained in:
vn.py 2019-05-03 16:10:11 +08:00
parent 6e3b7faae3
commit 4cd84b45a5
4 changed files with 153 additions and 202 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
tests/backtesting/GA_Pre_Final.ipynb
View File

@ -20,17 +20,9 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
"数据总体： 13824\n"
]
}
],
"source": [ "source": [
"setting = OptimizationSetting()\n", "setting = OptimizationSetting()\n",
"#setting.add_parameter('atr_length', 10, 50, 2)\n", "#setting.add_parameter('atr_length', 10, 50, 2)\n",
@ -50,20 +42,9 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"data": {
"text/plain": [
"dict_keys(['boll_window', 'cci_window', 'atr_window'])"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"setting_names = random.choice(local_setting).keys()\n", "setting_names = random.choice(local_setting).keys()\n",
"setting_names" "setting_names"
@ -71,7 +52,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -82,40 +63,18 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"data": {
"text/plain": [
"[48, 6, 26]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"parameter_generate()" "parameter_generate()"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"data": {
"text/plain": [
"{'boll_window': 16, 'cci_window': 48, 'atr_window': 6}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"setting=dict(zip(setting_names,parameter_generate()))\n", "setting=dict(zip(setting_names,parameter_generate()))\n",
"setting" "setting"
@ -123,7 +82,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -167,41 +126,16 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
"2019-05-03 15:02:07.528909\t开始加载历史数据\n",
"2019-05-03 15:02:34.854177\t历史数据加载完成，数据量：175440\n",
"2019-05-03 15:02:34.877616\t策略初始化完成\n",
"2019-05-03 15:02:34.877616\t开始回放历史数据\n",
"2019-05-03 15:02:37.000744\t历史数据回放结束\n",
"2019-05-03 15:02:37.000744\t开始计算逐日盯市盈亏\n",
"2019-05-03 15:02:37.012463\t逐日盯市盈亏计算完成\n",
"2019-05-03 15:02:37.012463\t开始计算策略统计指标\n"
]
},
{
"data": {
"text/plain": [
"(0.96, 0.38)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"object_func(parameter_generate())" "object_func(parameter_generate())"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -216,7 +150,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -283,15 +217,7 @@
"metadata": { "metadata": {
"scrolled": false "scrolled": false
}, },
"outputs": [ "outputs": [],
{
"name": "stdout",
"output_type": "stream",
"text": [
"开始运行遗传算法，每代族群总数：34, 优良品种筛选个数：27，迭代次数：30，交叉概率：0.95，突变概率：0.05\n"
]
}
],
"source": [ "source": [
"optimize()" "optimize()"
] ]

27
tests/backtesting/run_ga.py Normal file
View File

@ -0,0 +1,27 @@
from vnpy.app.cta_strategy.backtesting import BacktestingEngine, OptimizationSetting
from vnpy.app.cta_strategy.strategies.atr_rsi_strategy import (
AtrRsiStrategy,
)
from datetime import datetime
if __name__ == "__main__":
engine = BacktestingEngine()
engine.set_parameters(
vt_symbol="IF88.CFFEX",
interval="1m",
start=datetime(2019, 1, 1),
end=datetime(2019, 4, 30),
rate=0.3 / 10000,
slippage=0.2,
size=300,
pricetick=0.2,
capital=1_000_000,
)
engine.add_strategy(AtrRsiStrategy, {})
setting = OptimizationSetting()
setting.set_target("sharpe_ratio")
setting.add_parameter("atr_length", 3, 39, 1)
setting.add_parameter("atr_ma_length", 10, 30, 1)
engine.run_ga_optimization(setting)

60
tests/backtesting/turtle.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -16,7 +16,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -54,44 +54,38 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": null,
"metadata": {}, "metadata": {
"outputs": [ "scrolled": true
{ },
"name": "stdout", "outputs": [],
"output_type": "stream",
"text": [
"2019-05-03 14:58:44.510371\t开始运行遗传算法，每代族群总数：20, 优良品种筛选个数：16，迭代次数：300，交叉概率：0.95，突变概率：0.05\n"
]
},
{
"ename": "AttributeError",
"evalue": "Can't pickle local object 'create_ga_optimize.<locals>.ga_optimize'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-3-d83ea019c683>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 4\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_ma_length\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m10\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m80\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 5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 6\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 601\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 602\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--> 603\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 604\u001b[0m ) \n\u001b[0;32m 605\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 301\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[0;32m 302\u001b[0m \u001b[0minvalid_ind\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mind\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mind\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mpopulation\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mind\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfitness\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalid\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 303\u001b[1;33m \u001b[0mfitnesses\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtoolbox\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[0mevaluate\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minvalid_ind\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 304\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mind\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfit\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minvalid_ind\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfitnesses\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 305\u001b[0m \u001b[0mind\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[0mfit\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mc:\\miniconda3\\lib\\multiprocessing\\pool.py\u001b[0m in \u001b[0;36mmap\u001b[1;34m(self, func, iterable, chunksize)\u001b[0m\n\u001b[0;32m 288\u001b[0m \u001b[1;32min\u001b[0m \u001b[0ma\u001b[0m \u001b[0mlist\u001b[0m \u001b[0mthat\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mreturned\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 289\u001b[0m '''\n\u001b[1;32m--> 290\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_map_async\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0miterable\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmapstar\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mchunksize\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\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 291\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 292\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mstarmap\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0miterable\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mchunksize\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\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;32mc:\\miniconda3\\lib\\multiprocessing\\pool.py\u001b[0m in \u001b[0;36mget\u001b[1;34m(self, timeout)\u001b[0m\n\u001b[0;32m 681\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_value\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 682\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 683\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_value\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 684\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 685\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_set\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mi\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mobj\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;32mc:\\miniconda3\\lib\\multiprocessing\\pool.py\u001b[0m in \u001b[0;36m_handle_tasks\u001b[1;34m(taskqueue, put, outqueue, pool, cache)\u001b[0m\n\u001b[0;32m 455\u001b[0m \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 456\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 457\u001b[1;33m \u001b[0mput\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtask\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 458\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 459\u001b[0m \u001b[0mjob\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0midx\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtask\u001b[0m\u001b[1;33m[\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[0m\n",
"\u001b[1;32mc:\\miniconda3\\lib\\multiprocessing\\connection.py\u001b[0m in \u001b[0;36msend\u001b[1;34m(self, obj)\u001b[0m\n\u001b[0;32m 204\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_check_closed\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 205\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_check_writable\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--> 206\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_send_bytes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_ForkingPickler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdumps\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\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 207\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 208\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mrecv_bytes\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmaxlength\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\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;32mc:\\miniconda3\\lib\\multiprocessing\\reduction.py\u001b[0m in \u001b[0;36mdumps\u001b[1;34m(cls, obj, protocol)\u001b[0m\n\u001b[0;32m 49\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mdumps\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcls\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mprotocol\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\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 50\u001b[0m \u001b[0mbuf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mio\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mBytesIO\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---> 51\u001b[1;33m \u001b[0mcls\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbuf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mprotocol\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdump\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\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 52\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mbuf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetbuffer\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 53\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mAttributeError\u001b[0m: Can't pickle local object 'create_ga_optimize.<locals>.ga_optimize'"
]
}
],
"source": [ "source": [
"setting = OptimizationSetting()\n", "setting = OptimizationSetting()\n",
"setting.set_target(\"sharpe_ratio\")\n", "setting.set_target(\"sharpe_ratio\")\n",
"setting.add_parameter(\"atr_length\", 3, 105, 1)\n", "setting.add_parameter(\"atr_length\", 3, 39, 1)\n",
"setting.add_parameter(\"atr_ma_length\", 10, 80, 1)\n", "setting.add_parameter(\"atr_ma_length\", 10, 30, 1)\n",
"\n", "\n",
"engine.run_ga_optimization(setting)" "engine.run_ga_optimization(setting)"
] ]
}, },
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"result = _"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(result)"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,

164
vnpy/app/cta_strategy/backtesting.py
View File

@ -6,6 +6,7 @@ from functools import lru_cache
from time import time from time import time
import multiprocessing import multiprocessing
import random import random
import math
import numpy as np import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
@ -29,6 +30,8 @@ from .base import (
from .template import CtaTemplate from .template import CtaTemplate
sns.set_style("whitegrid") sns.set_style("whitegrid")
creator.create("FitnessMax", base.Fitness, weights=(1.0,))
creator.create("Individual", list, fitness=creator.FitnessMax)
class OptimizationSetting: class OptimizationSetting:
@ -537,44 +540,52 @@ class BacktestingEngine:
return list(random.choice(settings).values()) return list(random.choice(settings).values())
# Create ga object function # Create ga object function
object_func = create_ga_optimize( global ga_target_name
target_name, global ga_strategy_class
self.strategy_class, global ga_setting
settings[0], global ga_vt_symbol
self.vt_symbol, global ga_interval
self.interval, global ga_start
self.start, global ga_rate
self.rate, global ga_slippage
self.slippage, global ga_size
self.size, global ga_pricetick
self.pricetick, global ga_capital
self.capital, global ga_end
self.end, global ga_mode
self.mode
) ga_target_name = target_name
ga_strategy_class = self.strategy_class
ga_setting = settings[0]
ga_vt_symbol = self.vt_symbol
ga_interval = self.interval
ga_start = self.start
ga_rate = self.rate
ga_slippage = self.slippage
ga_size = self.size
ga_pricetick = self.pricetick
ga_capital = self.capital
ga_end = self.end
ga_mode = self.mode
# Set up genetic algorithem # Set up genetic algorithem
creator.create("FitnessMax", base.Fitness, weights=(1.0,))
creator.create("Individual", list, fitness=creator.FitnessMax)
toolbox = base.Toolbox() toolbox = base.Toolbox()
toolbox.register("individual", tools.initIterate, creator.Individual, generate_parameter) toolbox.register("individual", tools.initIterate, creator.Individual, generate_parameter)
toolbox.register("population", tools.initRepeat, list, toolbox.individual) toolbox.register("population", tools.initRepeat, list, toolbox.individual)
toolbox.register("mate", tools.cxTwoPoint) toolbox.register("mate", tools.cxTwoPoint)
toolbox.register("mutate", tools.mutUniformInt, low=4, up=40, indpb=1) toolbox.register("mutate", tools.mutUniformInt, low=4, up=40, indpb=1)
toolbox.register("evaluate", object_func) toolbox.register("evaluate", ga_optimize)
toolbox.register("select", tools.selNSGA2) toolbox.register("select", tools.selNSGA2)
pool = multiprocessing.Pool(multiprocessing.cpu_count()) total_size = len(settings)
toolbox.register("map", pool.map) pop_size = int(pow(total_size, 1 / math.e)) # number of individuals in each generation
lambda_ = pop_size # number of children to produce at each generation
mu = 16 # number of individuals to select for the next generation mu = int(pop_size * 0.8) # number of individuals to select for the next generation
lambda_ = 20 # number of children to produce at each generation
cxpb = 0.95 # probability that an offspring is produced by crossover cxpb = 0.95 # probability that an offspring is produced by crossover
mutpb = 0.05 # probability that an offspring is produced by mutation mutpb = 1 - cxpb # probability that an offspring is produced by mutation
ngen = 300 # number of generation ngen = 30 # number of generation
pop_size = 20 # number of individuals in each generation
pop = toolbox.population(pop_size) pop = toolbox.population(pop_size)
hof = tools.ParetoFront() # end result of pareto front hof = tools.ParetoFront() # end result of pareto front
@ -584,11 +595,15 @@ class BacktestingEngine:
stats.register("std", np.std, axis=0) stats.register("std", np.std, axis=0)
stats.register("min", np.min, axis=0) stats.register("min", np.min, axis=0)
stats.register("max", np.max, axis=0) stats.register("max", np.max, axis=0)
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_size, mu, ngen, cxpb, mutpb) # Multiprocessing is not supported yet.
self.output(msg) # pool = multiprocessing.Pool(multiprocessing.cpu_count())
# toolbox.register("map", pool.map)
# Run ga optimization # Run ga optimization
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_size, mu, ngen, cxpb, mutpb)
self.output(msg)
start = time() start = time()
algorithms.eaMuPlusLambda( algorithms.eaMuPlusLambda(
@ -607,9 +622,17 @@ class BacktestingEngine:
cost = int((end - start)) cost = int((end - start))
self.output(f"遗传算法优化完成，耗时{cost}秒") 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 # Return result list
results = []
parameter_keys = list(ga_setting.keys())
for parameter_values in hof:
setting = dict(zip(parameter_keys, parameter_values))
target_value = ga_optimize(parameter_values)[0]
results.append((setting, target_value))
return results
def update_daily_close(self, price: float): def update_daily_close(self, price: float):
"""""" """"""
@ -1065,52 +1088,33 @@ def optimize(
return (str(setting), target_value, statistics) return (str(setting), target_value, statistics)
def create_ga_optimize( @lru_cache(maxsize=1000000)
target_name: str, def _ga_optimizae(parameter_values: tuple):
strategy_class: CtaTemplate, """"""
setting: dict, parameter_keys = list(ga_setting.keys())
vt_symbol: str, setting = dict(zip(parameter_keys, parameter_values))
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) result = optimize(
def _optimizae(parameter_values: tuple): ga_target_name,
"""""" ga_strategy_class,
setting = dict(zip(parameter_keys, parameter_values)) setting,
result = optimize( ga_vt_symbol,
target_name, ga_interval,
strategy_class, ga_start,
setting, ga_rate,
vt_symbol, ga_slippage,
interval, ga_size,
start, ga_pricetick,
rate, ga_capital,
slippage, ga_end,
size, ga_mode
pricetick, )
capital, return (result[1],)
end,
mode
)
return (result[1],)
def ga_optimize(parameter_values: list):
""""""
return _optimizae(tuple(parameter_values))
return ga_optimize def ga_optimize(parameter_values: list):
""""""
return _ga_optimizae(tuple(parameter_values))
@lru_cache(maxsize=10) @lru_cache(maxsize=10)
@ -1141,6 +1145,8 @@ def load_tick_data(
# GA related global value # GA related global value
ga_end = None
ga_mode = None
ga_target_name = None ga_target_name = None
ga_strategy_class = None ga_strategy_class = None
ga_setting = None ga_setting = None
@ -1151,6 +1157,4 @@ ga_rate = None
ga_slippage = None ga_slippage = None
ga_size = None ga_size = None
ga_pricetick = None ga_pricetick = None
ga_capital = None ga_capital = None
ga_end = None
ga_mode = None