mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-03 11:00:57 +08:00
init commit
This commit is contained in:
Young
257
examples/estimator/analyze_from_estimator.ipynb
Normal file
257
examples/estimator/analyze_from_estimator.ipynb
Normal file
@@ -0,0 +1,257 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import sys\n",
|
||||
"import json\n",
|
||||
"import yaml\n",
|
||||
"import pickle\n",
|
||||
"from pathlib import Path\n",
|
||||
"\n",
|
||||
"import qlib\n",
|
||||
"import pandas as pd\n",
|
||||
"from qlib.config import REG_CN\n",
|
||||
"from qlib.utils import exists_qlib_data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"CUR_DIR = Path.cwd()\n",
|
||||
"MARKET = \"csi300\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# use default data\n",
|
||||
"# NOTE: need to download data from remote: python scripts/get_data.py qlib_data --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(CUR_DIR.parent.parent.joinpath(\"scripts\")))\n",
|
||||
" from get_data import GetData\n",
|
||||
" GetData().qlib_data_cn(provider_uri)\n",
|
||||
"qlib.init(provider_uri=provider_uri, region=REG_CN)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with CUR_DIR.joinpath('estimator_config.yaml').open() as fp:\n",
|
||||
" estimator_name = yaml.load(fp, Loader=yaml.FullLoader)['experiment']['name']\n",
|
||||
"with CUR_DIR.joinpath(estimator_name, 'exp_info.json').open() as fp:\n",
|
||||
" latest_id = json.load(fp)['id']\n",
|
||||
" \n",
|
||||
"estimator_dir = CUR_DIR.joinpath(estimator_name, 'sacred', latest_id)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# read estimator result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pred_df = pd.read_pickle(estimator_dir.joinpath('pred.pkl'))\n",
|
||||
"report_normal_df = pd.read_pickle(estimator_dir.joinpath('report_normal.pkl'))\n",
|
||||
"report_normal_df.index.names = ['index']\n",
|
||||
"\n",
|
||||
"analysis_df = pd.read_pickle(estimator_dir.joinpath('analysis.pkl'))\n",
|
||||
"positions = pickle.load(estimator_dir.joinpath('positions.pkl').open('rb'))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# get label data from qlib"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from qlib.data import D\n",
|
||||
"pred_df_dates = pred_df.index.get_level_values(level='datetime')\n",
|
||||
"features_df = D.features(D.instruments(MARKET), ['Ref($close, -1)/$close - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
|
||||
"features_df.columns = ['label']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# analyze graphs"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from qlib.contrib.report import analysis_model, analysis_position"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## analysis position"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### report"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.report_graph(report_normal_df)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### score IC"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pred_label = pd.concat([features_df, pred_df], axis=1, sort=True).reindex(features_df.index)\n",
|
||||
"analysis_position.score_ic_graph(pred_label)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### cumulative return"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.cumulative_return_graph(positions, report_normal_df, features_df)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### risk analysis"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.risk_analysis_graph(analysis_df, report_normal_df)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### rank label"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.rank_label_graph(positions, features_df, pred_df_dates.min(), pred_df_dates.max())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## analysis model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### model performance"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_model.model_performance_graph(pred_label)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
55
examples/estimator/estimator_config.yaml
Normal file
55
examples/estimator/estimator_config.yaml
Normal file
@@ -0,0 +1,55 @@
|
||||
experiment:
|
||||
name: estimator_example
|
||||
observer_type: file_storage
|
||||
mode: train
|
||||
|
||||
model:
|
||||
class: LGBModel
|
||||
module_path: qlib.contrib.model.gbdt
|
||||
args:
|
||||
loss: mse
|
||||
colsample_bytree: 0.8879
|
||||
learning_rate: 0.0421
|
||||
subsample: 0.8789
|
||||
lambda_l1: 205.6999
|
||||
lambda_l2: 580.9768
|
||||
max_depth: 8
|
||||
num_leaves: 64
|
||||
num_threads: 20
|
||||
min_data_in_leaf: 10
|
||||
data:
|
||||
class: QLibDataHandlerClose
|
||||
args:
|
||||
dropna_label: True
|
||||
filter:
|
||||
market: csi300
|
||||
trainer:
|
||||
class: StaticTrainer
|
||||
args:
|
||||
train_start_date: 2008-01-01
|
||||
train_end_date: 2014-12-31
|
||||
validate_start_date: 2015-01-01
|
||||
validate_end_date: 2016-12-31
|
||||
test_start_date: 2017-01-01
|
||||
test_end_date: 2020-08-01
|
||||
strategy:
|
||||
class: TopkDropoutStrategy
|
||||
args:
|
||||
topk: 50
|
||||
n_drop: 5
|
||||
backtest:
|
||||
normal_backtest_args:
|
||||
verbose: False
|
||||
limit_threshold: 0.095
|
||||
account: 100000000
|
||||
benchmark: SH000300
|
||||
deal_price: close
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5
|
||||
|
||||
qlib_data:
|
||||
# when testing, please modify the following parameters according to the specific environment
|
||||
provider_uri: "~/.qlib/qlib_data/cn_data"
|
||||
region: "cn"
|
||||
redis_port: 4312
|
||||
57
examples/estimator/estimator_config_dnn.yaml
Normal file
57
examples/estimator/estimator_config_dnn.yaml
Normal file
@@ -0,0 +1,57 @@
|
||||
experiment:
|
||||
name: estimator_example
|
||||
observer_type: file_storage
|
||||
mode: train
|
||||
|
||||
model:
|
||||
module_path: qlib.contrib.model.pytorch_nn
|
||||
class: DNNModelPytorch
|
||||
args:
|
||||
loss: mse
|
||||
input_dim: 158
|
||||
output_dim: 1
|
||||
lr: 0.002
|
||||
lr_decay: 0.96
|
||||
lr_decay_steps: 100
|
||||
optimizer: 'adam'
|
||||
max_steps: 8000
|
||||
batch_size: 4096
|
||||
GPU: '0'
|
||||
data:
|
||||
class: QLibDataHandlerClose
|
||||
args:
|
||||
dropna_label: True
|
||||
dropna_feature: True
|
||||
filter:
|
||||
market: csi300
|
||||
trainer:
|
||||
class: StaticTrainer
|
||||
args:
|
||||
train_start_date: 2007-01-01
|
||||
train_end_date: 2014-12-31
|
||||
validate_start_date: 2015-01-01
|
||||
validate_end_date: 2016-12-31
|
||||
test_start_date: 2017-01-01
|
||||
test_end_date: 2020-08-01
|
||||
strategy:
|
||||
class: TopkDropoutStrategy
|
||||
args:
|
||||
topk: 50
|
||||
n_drop: 5
|
||||
backtest:
|
||||
normal_backtest_args:
|
||||
verbose: False
|
||||
limit_threshold: 0.095
|
||||
account: 100000000
|
||||
benchmark: SH000300
|
||||
deal_price: close
|
||||
open_cost: 0.0005
|
||||
close_cost: 0.0015
|
||||
min_cost: 5
|
||||
long_short_backtest_args:
|
||||
topk: 50
|
||||
|
||||
qlib_data:
|
||||
# when testing, please modify the following parameters according to the specific environment
|
||||
provider_uri: "~/.qlib/qlib_data/cn_data"
|
||||
region: "cn"
|
||||
119
examples/train_and_backtest.py
Normal file
119
examples/train_and_backtest.py
Normal file
@@ -0,0 +1,119 @@
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# Licensed under the MIT License.
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import qlib
|
||||
import pandas as pd
|
||||
from qlib.config import REG_CN
|
||||
from qlib.contrib.model.gbdt import LGBModel
|
||||
from qlib.contrib.estimator.handler import QLibDataHandlerClose
|
||||
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
|
||||
from qlib.contrib.evaluate import (
|
||||
backtest as normal_backtest,
|
||||
risk_analysis,
|
||||
)
|
||||
from qlib.utils import exists_qlib_data
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
# use default data
|
||||
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
|
||||
if not exists_qlib_data(provider_uri):
|
||||
print(f"Qlib data is not found in {provider_uri}")
|
||||
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
|
||||
from get_data import GetData
|
||||
|
||||
GetData().qlib_data_cn(provider_uri)
|
||||
|
||||
qlib.init(provider_uri=provider_uri, region=REG_CN)
|
||||
|
||||
MARKET = "CSI300"
|
||||
BENCHMARK = "SH000300"
|
||||
|
||||
###################################
|
||||
# train model
|
||||
###################################
|
||||
DATA_HANDLER_CONFIG = {
|
||||
"dropna_label": True,
|
||||
"start_date": "2008-01-01",
|
||||
"end_date": "2020-08-01",
|
||||
"market": MARKET,
|
||||
}
|
||||
|
||||
TRAINER_CONFIG = {
|
||||
"train_start_date": "2008-01-01",
|
||||
"train_end_date": "2014-12-31",
|
||||
"validate_start_date": "2015-01-01",
|
||||
"validate_end_date": "2016-12-31",
|
||||
"test_start_date": "2017-01-01",
|
||||
"test_end_date": "2020-08-01",
|
||||
}
|
||||
|
||||
# use default DataHandler
|
||||
# custom DataHandler, refer to: TODO: DataHandler API url
|
||||
x_train, y_train, x_validate, y_validate, x_test, y_test = QLibDataHandlerClose(
|
||||
**DATA_HANDLER_CONFIG
|
||||
).get_split_data(**TRAINER_CONFIG)
|
||||
|
||||
MODEL_CONFIG = {
|
||||
"loss": "mse",
|
||||
"colsample_bytree": 0.8879,
|
||||
"learning_rate": 0.0421,
|
||||
"subsample": 0.8789,
|
||||
"lambda_l1": 205.6999,
|
||||
"lambda_l2": 580.9768,
|
||||
"max_depth": 8,
|
||||
"num_leaves": 210,
|
||||
"num_threads": 20,
|
||||
}
|
||||
# use default model
|
||||
# custom Model, refer to: TODO: Model API url
|
||||
model = LGBModel(**MODEL_CONFIG)
|
||||
model.fit(x_train, y_train, x_validate, y_validate)
|
||||
_pred = model.predict(x_test)
|
||||
_pred = pd.DataFrame(_pred, index=x_test.index, columns=y_test.columns)
|
||||
|
||||
# backtest requires pred_score
|
||||
pred_score = pd.DataFrame(index=_pred.index)
|
||||
pred_score["score"] = _pred.iloc(axis=1)[0]
|
||||
|
||||
# save pred_score to file
|
||||
pred_score_path = Path("~/tmp/qlib/pred_score.pkl").expanduser()
|
||||
pred_score_path.parent.mkdir(exist_ok=True, parents=True)
|
||||
pred_score.to_pickle(pred_score_path)
|
||||
|
||||
###################################
|
||||
# backtest
|
||||
###################################
|
||||
STRATEGY_CONFIG = {
|
||||
"topk": 50,
|
||||
"n_drop": 5,
|
||||
}
|
||||
BACKTEST_CONFIG = {
|
||||
"verbose": False,
|
||||
"limit_threshold": 0.095,
|
||||
"account": 100000000,
|
||||
"benchmark": BENCHMARK,
|
||||
"deal_price": "close",
|
||||
"open_cost": 0.0005,
|
||||
"close_cost": 0.0015,
|
||||
"min_cost": 5,
|
||||
}
|
||||
|
||||
# use default strategy
|
||||
# custom Strategy, refer to: TODO: Strategy API url
|
||||
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
|
||||
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
|
||||
|
||||
###################################
|
||||
# analyze
|
||||
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
|
||||
###################################
|
||||
analysis = dict()
|
||||
analysis["sub_bench"] = risk_analysis(report_normal["return"] - report_normal["bench"])
|
||||
analysis["sub_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"] - report_normal["cost"])
|
||||
analysis_df = pd.concat(analysis) # type: pd.DataFrame
|
||||
print(analysis_df)
|
||||
355
examples/train_backtest_analyze.ipynb
Normal file
355
examples/train_backtest_analyze.ipynb
Normal file
@@ -0,0 +1,355 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import sys\n",
|
||||
"from pathlib import Path\n",
|
||||
"\n",
|
||||
"import qlib\n",
|
||||
"import pandas as pd\n",
|
||||
"from qlib.config import REG_CN\n",
|
||||
"from qlib.contrib.model.gbdt import LGBModel\n",
|
||||
"from qlib.contrib.estimator.handler import QLibDataHandlerClose\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"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# use default data\n",
|
||||
"# NOTE: need to download data from remote: python scripts/get_data.py qlib_data --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_cn(provider_uri)\n",
|
||||
"qlib.init(provider_uri=provider_uri, region=REG_CN)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"MARKET = \"csi300\"\n",
|
||||
"BENCHMARK = \"SH000300\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# train model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": true,
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"###################################\n",
|
||||
"# train model\n",
|
||||
"###################################\n",
|
||||
"DATA_HANDLER_CONFIG = {\n",
|
||||
" \"dropna_label\": True,\n",
|
||||
" \"start_date\": \"2008-01-01\",\n",
|
||||
" \"end_date\": \"2020-08-01\",\n",
|
||||
" \"market\": MARKET,\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"TRAINER_CONFIG = {\n",
|
||||
" \"train_start_date\": \"2008-01-01\",\n",
|
||||
" \"train_end_date\": \"2014-12-31\",\n",
|
||||
" \"validate_start_date\": \"2015-01-01\",\n",
|
||||
" \"validate_end_date\": \"2016-12-31\",\n",
|
||||
" \"test_start_date\": \"2017-01-01\",\n",
|
||||
" \"test_end_date\": \"2020-08-01\",\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"# use default DataHandler\n",
|
||||
"# custom DataHandler, refer to: TODO: DataHandler api url\n",
|
||||
"x_train, y_train, x_validate, y_validate, x_test, y_test = QLibDataHandlerClose(**DATA_HANDLER_CONFIG).get_split_data(**TRAINER_CONFIG)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"MODEL_CONFIG = {\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",
|
||||
"# use default model\n",
|
||||
"# custom Model, refer to: TODO: Model api url\n",
|
||||
"model = LGBModel(**MODEL_CONFIG)\n",
|
||||
"model.fit(x_train, y_train, x_validate, y_validate)\n",
|
||||
"_pred = model.predict(x_test)\n",
|
||||
"_pred = pd.DataFrame(_pred, index=x_test.index, columns=y_test.columns)\n",
|
||||
"\n",
|
||||
"# backtest requires pred_score\n",
|
||||
"pred_score = pd.DataFrame(index=_pred.index)\n",
|
||||
"pred_score[\"score\"] = _pred.iloc(axis=1)[0]\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# backtest"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"###################################\n",
|
||||
"# backtest\n",
|
||||
"###################################\n",
|
||||
"STRATEGY_CONFIG = {\n",
|
||||
" \"topk\": 50,\n",
|
||||
" \"n_drop\": 5",
|
||||
"}\n",
|
||||
"BACKTEST_CONFIG = {\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",
|
||||
"# use default strategy\n",
|
||||
"# custom Strategy, refer to: TODO: Strategy api url\n",
|
||||
"strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)\n",
|
||||
"report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# analyze"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"###################################\n",
|
||||
"# analyze\n",
|
||||
"# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb\n",
|
||||
"###################################\n",
|
||||
"analysis = dict()\n",
|
||||
"analysis[\"sub_bench\"] = risk_analysis(report_normal[\"return\"] - report_normal[\"bench\"])\n",
|
||||
"analysis[\"sub_cost\"] = risk_analysis(\n",
|
||||
" report_normal[\"return\"] - report_normal[\"bench\"] - report_normal[\"cost\"]\n",
|
||||
")\n",
|
||||
"analysis_df = pd.concat(analysis) # type: pd.DataFrame\n",
|
||||
"print(analysis_df)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# analyze graphs"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from qlib.contrib.report import analysis_model, analysis_position"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# get label data\n",
|
||||
"from qlib.data import D\n",
|
||||
"pred_df_dates = pred_score.index.get_level_values(level='datetime')\n",
|
||||
"features_df = D.features(D.instruments(MARKET), ['Ref($close, -1)/$close - 1'], pred_df_dates.min(), pred_df_dates.max())\n",
|
||||
"features_df.columns = ['label']"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## analysis position"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### report"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.report_graph(report_normal)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### score IC"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"pred_label = pd.concat([features_df, pred_score], axis=1, sort=True).reindex(features_df.index)\n",
|
||||
"analysis_position.score_ic_graph(pred_label)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### cumulative return"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.cumulative_return_graph(positions_normal, report_normal, features_df)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### risk analysis"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.risk_analysis_graph(analysis_df, report_normal)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### rank label"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_position.rank_label_graph(positions_normal, features_df, pred_df_dates.min(), pred_df_dates.max())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## analysis model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### model performance"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"analysis_model.model_performance_graph(pred_label)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"toc": {
|
||||
"base_numbering": 1,
|
||||
"nav_menu": {},
|
||||
"number_sections": true,
|
||||
"sideBar": true,
|
||||
"skip_h1_title": false,
|
||||
"title_cell": "Table of Contents",
|
||||
"title_sidebar": "Contents",
|
||||
"toc_cell": false,
|
||||
"toc_position": {},
|
||||
"toc_section_display": true,
|
||||
"toc_window_display": false
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
Reference in New Issue
Block a user