mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-05 20:11:08 +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"
|
||||
Reference in New Issue
Block a user