{ "metadata": { "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.9-final" }, "orig_nbformat": 2, "kernelspec": { "name": "python3", "display_name": "Python 3" } }, "nbformat": 4, "nbformat_minor": 2, "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import sys\n", "import copy\n", "from pathlib import Path\n", "\n", "import qlib\n", "import numpy as np\n", "import pandas as pd\n", "from qlib.config import REG_CN\n", "from qlib.contrib.model.gbdt import LGBModel\n", "from qlib.contrib.data.handler import Alpha158\n", "from qlib.contrib.strategy.strategy import TopkDropoutStrategy\n", "from qlib.contrib.evaluate import (\n", " backtest as normal_backtest,\n", " risk_analysis,\n", ")\n", "from qlib.utils import exists_qlib_data, init_instance_by_config\n", "from qlib.workflow import R\n", "from qlib.workflow.record_temp import SignalRecord, PortAnaRecord\n", "from qlib.utils import flatten_dict" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[36502:MainThread](2020-11-27 16:26:57,240) INFO - qlib.Initialization - [__init__.py:41] - default_conf: client.\n", "[36502:MainThread](2020-11-27 16:26:57,242) WARNING - qlib.Initialization - [__init__.py:57] - redis connection failed(host=127.0.0.1 port=6379), cache will not be used!\n", "[36502:MainThread](2020-11-27 16:26:57,243) INFO - qlib.Initialization - [__init__.py:76] - qlib successfully initialized based on client settings.\n", "[36502:MainThread](2020-11-27 16:26:57,244) INFO - qlib.Initialization - [__init__.py:79] - data_path=/home/dongzho/.qlib/qlib_data/cn_data\n" ] } ], "source": [ "# use default data\n", "# NOTE: need to download data from remote: python scripts/get_data.py qlib_data_cn --target_dir ~/.qlib/qlib_data/cn_data\n", "provider_uri = \"~/.qlib/qlib_data/cn_data\" # target_dir\n", "if not exists_qlib_data(provider_uri):\n", " print(f\"Qlib data is not found in {provider_uri}\")\n", " sys.path.append(str(Path.cwd().parent.joinpath(\"scripts\")))\n", " from get_data import GetData\n", " GetData().qlib_data(target_dir=provider_uri, region=REG_CN)\n", "qlib.init(provider_uri=provider_uri, region=REG_CN)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "market = \"csi300\"\n", "benchmark = \"SH000300\"" ] }, { "source": [ "## Model Training" ], "cell_type": "markdown", "metadata": {} }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[36502:MainThread](2020-11-27 16:27:17,338) INFO - qlib.timer - [log.py:81] - Time cost: 19.994s | Loading data Done\n", "[36502:MainThread](2020-11-27 16:27:18,164) INFO - qlib.timer - [log.py:81] - Time cost: 0.245s | DropnaLabel Done\n", "[36502:MainThread](2020-11-27 16:27:26,086) INFO - qlib.timer - [log.py:81] - Time cost: 7.921s | CSZScoreNorm Done\n", "[36502:MainThread](2020-11-27 16:27:26,087) INFO - qlib.timer - [log.py:81] - Time cost: 8.747s | fit & process data Done\n", "[36502:MainThread](2020-11-27 16:27:26,088) INFO - qlib.timer - [log.py:81] - Time cost: 28.744s | Init data Done\n", "[36502:MainThread](2020-11-27 16:27:26,097) INFO - qlib.workflow - [exp.py:180] - Experiment 2 starts running ...\n", "[36502:MainThread](2020-11-27 16:27:26,221) INFO - qlib.workflow - [recorder.py:234] - Recorder 3fa4def1f6694119a3d336a7a06c88cb starts running under Experiment 2 ...\n", "[36502:MainThread](2020-11-27 16:27:26,223) INFO - qlib.workflow - [expm.py:251] - No tracking URI is provided. The default tracking URI is set as `mlruns` under the working directory.\n", "Training until validation scores don't improve for 50 rounds\n", "[20]\ttrain's l2: 0.990559\tvalid's l2: 0.994332\n", "[40]\ttrain's l2: 0.98687\tvalid's l2: 0.993702\n", "[60]\ttrain's l2: 0.984308\tvalid's l2: 0.993503\n", "[80]\ttrain's l2: 0.982202\tvalid's l2: 0.993446\n", "[100]\ttrain's l2: 0.980318\tvalid's l2: 0.993423\n", "[120]\ttrain's l2: 0.97854\tvalid's l2: 0.993409\n", "[140]\ttrain's l2: 0.97679\tvalid's l2: 0.993413\n", "[160]\ttrain's l2: 0.975116\tvalid's l2: 0.993473\n", "Early stopping, best iteration is:\n", "[127]\ttrain's l2: 0.977957\tvalid's l2: 0.993381\n" ] } ], "source": [ "###################################\n", "# train model\n", "###################################\n", "data_handler_config = {\n", " \"start_time\": \"2008-01-01\",\n", " \"end_time\": \"2020-08-01\",\n", " \"fit_start_time\": \"2008-01-01\",\n", " \"fit_end_time\": \"2014-12-31\",\n", " \"instruments\": market,\n", "}\n", "\n", "task = {\n", " \"model\": {\n", " \"class\": \"LGBModel\",\n", " \"module_path\": \"qlib.contrib.model.gbdt\",\n", " \"kwargs\": {\n", " \"loss\": \"mse\",\n", " \"colsample_bytree\": 0.8879,\n", " \"learning_rate\": 0.0421,\n", " \"subsample\": 0.8789,\n", " \"lambda_l1\": 205.6999,\n", " \"lambda_l2\": 580.9768,\n", " \"max_depth\": 8,\n", " \"num_leaves\": 210,\n", " \"num_threads\": 20,\n", " },\n", " },\n", " \"dataset\": {\n", " \"class\": \"DatasetH\",\n", " \"module_path\": \"qlib.data.dataset\",\n", " \"kwargs\": {\n", " \"handler\": {\n", " \"class\": \"Alpha158\",\n", " \"module_path\": \"qlib.contrib.data.handler\",\n", " \"kwargs\": data_handler_config,\n", " },\n", " \"segments\": {\n", " \"train\": (\"2008-01-01\", \"2014-12-31\"),\n", " \"valid\": (\"2015-01-01\", \"2016-12-31\"),\n", " \"test\": (\"2017-01-01\", \"2017-12-31\"), # NOTE: use a shorter time range\n", " },\n", " },\n", " },\n", "}\n", "\n", "# model initiaiton\n", "model = init_instance_by_config(task[\"model\"])\n", "dataset = init_instance_by_config(task[\"dataset\"])\n", "\n", "# start exp to train model\n", "with R.start(experiment_name=\"train_model\"):\n", " R.log_params(**flatten_dict(task))\n", " model.fit(dataset)\n", " R.save_objects(trained_model=model)\n", " rid = R.get_recorder().id\n" ] }, { "source": [ "## Optimization Based Strategy" ], "cell_type": "markdown", "metadata": {} }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "from qlib.contrib.strategy.strategy import BaseStrategy\n", "\n", "\n", "class OptBasedStrategy(BaseStrategy):\n", " \"\"\"Optimization Based Strategy\"\"\"\n", "\n", " def __init__(self, data_handler, cov_estimator, optimizer):\n", " self.data_handler = data_handler\n", " self.cov_estimator = cov_estimator\n", " self.optimizer = optimizer\n", "\n", " def generate_order_list(self, score_series, current, trade_exchange, pred_date, trade_date):\n", " \"\"\"\n", " Parameters\n", " -----------\n", " score_series : pd.Seires\n", " stock_id , score.\n", " current : Position()\n", " current of account.\n", " trade_exchange : Exchange()\n", " exchange.\n", " trade_date : pd.Timestamp\n", " date.\n", " \"\"\"\n", " score_series = score_series.dropna()\n", "\n", " # check stock holdings, if\n", " # 1. doesn't have score: target amount = 0 (force sell)\n", " # 2. stock not tradable: target amount = current amount\n", " current_position = current.get_stock_amount_dict()\n", " target_position = {}\n", " for stock_id in current_position:\n", " if not trade_exchange.is_stock_tradable(stock_id=stock_id, trade_date=trade_date):\n", " target_position[stock_id] = current_position[stock_id]\n", " elif stock_id not in score_series.index:\n", " target_position[stock_id] = 0\n", " else:\n", " # need to be solved by optimizer\n", " pass\n", "\n", " # filter scores, if\n", " # 1. kept in `amount_dict` by previous rules\n", " # 2. not tradable\n", " skipped = []\n", " for stock_id in score_series.index:\n", " if stock_id in target_position:\n", " skipped.append(stock_id)\n", " elif not trade_exchange.is_stock_tradable(stock_id=stock_id, trade_date=trade_date):\n", " skipped.append(stock_id)\n", " score_series = score_series[~score_series.index.isin(skipped)]\n", "\n", " # calc remaining value\n", " current_value = pd.Series({\n", " stock_id: current.get_stock_price(stock_id) * amount\n", " for stock_id, amount in current_position.items()\n", " })\n", " risk_total_value = self.get_risk_degree(trade_date) * current.calculate_value()\n", " traded_value = risk_total_value - current_value.loc[list(target_position)].sum()\n", "\n", " # portfolio init weight\n", " init_weight = current_value.reindex(score_series.index, fill_value=0)\n", " init_weight_sum = init_weight.sum()\n", " if init_weight_sum > 0:\n", " init_weight /= init_weight_sum\n", "\n", " # covariance estimation\n", " selector = (self.data_handler.get_range_selector(pred_date, 252), score_series.index)\n", " price = self.data_handler.fetch(selector, level=None, squeeze=True)\n", " cov = self.cov_estimator(price)\n", " cov = cov.reindex(\n", " index=score_series.index, \n", " columns=score_series.index, \n", " #fill_value=cov.max().max()\n", " )\n", "\n", " # optimize target portfolio\n", " try:\n", " if init_weight.sum() > 0:\n", " target_weight = self.optimizer(cov, score_series, init_weight)\n", " else:\n", " target_weight = self.optimizer(cov, score_series)\n", " target_weight = target_weight[target_weight > 1e-6]\n", " for stock_id, weight in target_weight.items():\n", " target_position[stock_id] = int(traded_value * weight / trade_exchange.get_close(stock_id, pred_date))\n", " except Exception as e:\n", " print('Unknown exception:', trade_date, e)\n", " for stock_id in score_series.index:\n", " if stock_id in current_position:\n", " target_position[stock_id] = current_position[stock_id]\n", "\n", " # generate order list\n", " order_list = trade_exchange.generate_order_for_target_amount_position(\n", " target_position=target_position,\n", " current_position=current_position,\n", " trade_date=trade_date,\n", " )\n", "\n", " return order_list" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "from qlib.data.dataset.loader import QlibDataLoader\n", "from qlib.data.dataset.handler import DataHandler\n", "from qlib.model.riskmodel import ShrinkCovEstimator\n", "from qlib.portfolio.optimizer import PortfolioOptimizer" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[36502:MainThread](2020-11-27 16:27:43,722) INFO - qlib.timer - [log.py:81] - Time cost: 6.369s | Loading data Done\n", "[36502:MainThread](2020-11-27 16:27:43,724) INFO - qlib.timer - [log.py:81] - Time cost: 6.371s | Init data Done\n" ] } ], "source": [ "data_loader = QlibDataLoader([\"$close\"])\n", "data_handler = DataHandler(\"all\", \"2015-01-01\", \"2020-08-01\", data_loader)\n", "cov_estimator = ShrinkCovEstimator(nan_option=\"mask\")\n", "optimizer = PortfolioOptimizer(\"mvo\", lamb=2, delta=0.2, tol=1e-5)\n", "strategy = OptBasedStrategy(data_handler, cov_estimator, optimizer)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "tags": [] }, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[36502:MainThread](2020-11-27 16:27:43,761) INFO - qlib.workflow - [exp.py:180] - Experiment 3 starts running ...\n", "[36502:MainThread](2020-11-27 16:27:43,779) INFO - qlib.workflow - [recorder.py:234] - Recorder 67d105113f424259889fc0b6b0b94973 starts running under Experiment 3 ...\n", "[36502:MainThread](2020-11-27 16:27:43,780) INFO - qlib.workflow - [expm.py:251] - No tracking URI is provided. The default tracking URI is set as `mlruns` under the working directory.\n", "[36502:MainThread](2020-11-27 16:27:43,991) INFO - qlib.workflow - [record_temp.py:127] - Signal record 'pred.pkl' has been saved as the artifact of the Experiment 3\n", "[36502:MainThread](2020-11-27 16:27:44,050) INFO - qlib.Evaluate - [evaluate.py:161] - Create new exchange\n", "'The following are prediction results of the LGBModel model.'\n", " score\n", "datetime instrument \n", "2017-01-03 SH600000 -0.053414\n", " SH600008 0.001820\n", " SH600009 0.023472\n", " SH600010 -0.005625\n", " SH600015 -0.137476\n", "/home/dongzho/miniconda3/lib/python3.7/site-packages/ipykernel_launcher.py:55: DeprecationWarning: The default dtype for empty Series will be 'object' instead of 'float64' in a future version. Specify a dtype explicitly to silence this warning.\n", "/home/dongzho/qlib/qlib/portfolio/optimizer.py:256: UserWarning: optimization not success (9)\n", " warnings.warn(f\"optimization not success ({sol.status})\")\n", "Unknown exception: 2017-01-16 00:00:00 ('SZ300104', Timestamp('2017-01-13 00:00:00'))\n", "Unknown exception: 2017-01-23 00:00:00 ('SZ000671', Timestamp('2017-01-20 00:00:00'))\n", "Unknown exception: 2017-03-03 00:00:00 ('SZ002465', Timestamp('2017-03-02 00:00:00'))\n", "Unknown exception: 2017-03-07 00:00:00 ('SH601127', Timestamp('2017-03-06 00:00:00'))\n", "/home/dongzho/qlib/qlib/portfolio/optimizer.py:256: UserWarning: optimization not success (4)\n", " warnings.warn(f\"optimization not success ({sol.status})\")\n", "Unknown exception: 2017-05-08 00:00:00 ('SH601727', Timestamp('2017-05-05 00:00:00'))\n", "Unknown exception: 2017-06-20 00:00:00 ('SH600036', Timestamp('2017-06-19 00:00:00'))\n", "Unknown exception: 2017-06-21 00:00:00 ('SH600739', Timestamp('2017-06-20 00:00:00'))\n", "Unknown exception: 2017-06-29 00:00:00 ('SZ300168', Timestamp('2017-06-28 00:00:00'))\n", "Unknown exception: 2017-09-01 00:00:00 ('SH601088', Timestamp('2017-08-31 00:00:00'))\n", "Unknown exception: 2017-09-12 00:00:00 ('SH601872', Timestamp('2017-09-11 00:00:00'))\n", "Unknown exception: 2017-09-21 00:00:00 ('SH600100', Timestamp('2017-09-20 00:00:00'))\n", "Unknown exception: 2017-09-22 00:00:00 ('SH600021', Timestamp('2017-09-21 00:00:00'))\n", "Unknown exception: 2017-10-11 00:00:00 ('SH600959', Timestamp('2017-10-10 00:00:00'))\n", "Unknown exception: 2017-10-25 00:00:00 ('SZ000792', Timestamp('2017-10-24 00:00:00'))\n", "Unknown exception: 2017-12-26 00:00:00 ('SH600682', Timestamp('2017-12-25 00:00:00'))\n", "[36502:MainThread](2020-11-27 17:28:14,269) INFO - qlib.workflow - [record_temp.py:249] - Portfolio analysis record 'port_analysis.pkl' has been saved as the artifact of the Experiment 3\n", "'The following are analysis results of the excess return without cost.'\n", " risk\n", "mean 0.001247\n", "std 0.005437\n", "annualized_return 0.314237\n", "information_ratio 3.640637\n", "max_drawdown -0.033416\n", "'The following are analysis results of the excess return with cost.'\n", " risk\n", "mean 0.001028\n", "std 0.005432\n", "annualized_return 0.259041\n", "information_ratio 3.003970\n", "max_drawdown -0.041455\n" ] } ], "source": [ "###################################\n", "# prediction, backtest & analysis\n", "###################################\n", "port_analysis_config = {\n", " \"strategy\": strategy,\n", " \"backtest\": {\n", " \"verbose\": False,\n", " \"limit_threshold\": 0.095,\n", " \"account\": 100000000,\n", " \"benchmark\": benchmark,\n", " \"deal_price\": \"close\",\n", " \"open_cost\": 0.0005,\n", " \"close_cost\": 0.0015,\n", " \"min_cost\": 5,\n", " },\n", "}\n", "\n", "\n", "# backtest and analysis\n", "with R.start(experiment_name=\"backtest_analysis\"):\n", " recorder = R.get_recorder(rid, experiment_name=\"train_model\")\n", " model = recorder.load_object(\"trained_model\")\n", "\n", " # prediction\n", " recorder = R.get_recorder()\n", " ba_rid = recorder.id\n", " sr = SignalRecord(model, dataset, recorder)\n", " sr.generate()\n", "\n", " # backtest & analysis\n", " par = PortAnaRecord(recorder, port_analysis_config)\n", " par.generate()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ] }