mirror of
https://github.com/microsoft/qlib.git
synced 2026-06-06 05:51:17 +08:00
Merge nested main (#597)
* MVP for Indian Stocks in qlib using yahooquery * cleaned with black * cleaned with black * add YahooNormalizeIN and YahooNormalizeIN1d * cleaned the code * added 1min for IN and also updated readme * update comments * fix comments * recorder support upload both raw file and directory * fix comments * Update README.md * Fix docs of QlibRecorder * sort index after loader (#538) make sure the fetch method is based on a index-sorted pd.DataFrame * refactor online serving rolling api * refactor TRA * format by black * fix horizon * fix TRA when use single head * clean up * improve pretrain * update README * fix tra when logdir is None * fix tra when logdir is None * Update strategy.py * Update README.md * Update README.md * Conda Suggestion * code standard docs * Update ensemble.py (#560) * Fix CI Bug (#575) Co-authored-by: yuxwang <anduinnn@foxmail.com> * Update gen.py (#576) * Fix multi-process loop calls (#574) * check lexsort in the 'lazy_sort_index' function (#566) * check lexsort * check lexsort * lexsort comment * lexsort comment * Delete .DS_Store * Update README.md * bug fix & use oracle transport pretrain * mend * Add `backend_freq_config` parameter, support multi-freq uri * Add sample_config to QlibDataLoader, support multi-freq * add multi-freq example * get_cls_kwargs renamed get_callable_kwargs * support multi-freq uri * Add inst_processors to D.features * Fix typo * Fix the index type of the multi-freq example * Fix duplicate mlflow directories in tests * Add DataPathManager to QlibConfig && modify inst_processors to supports list only * Modify the default value in the multi_freq example * Modify client-server mode and dataset-cache to disable inst_processor * Add wheel package to github CI * fix comment * Update FAQ.rst * Update README.md Fix wrong link * Update the docs of TaskManager (#586) * Update manage.py * update yaml * update run_all_model * Modify the Feature to be case sensitive (#589) * update README * remove verbose * fix spell bug * fix typos (#592) * Update Release Note * fix portfolio bug * Add calendar support for resample * add freq kwargs * test.yml: Remove redundant code (#595) * Supporting shared processor (#596) * Supporting shared processor * fix readonly reverse bug * remove pytests dependency * with fit bug * fix parameter error * fix comments * Fix undefined names in Python code (#599) * Update pytorch_tabnet.py $ `flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics` ``` ./qlib/qlib/contrib/model/pytorch_tabnet.py:567:38: F821 undefined name 'inp' self.independ.append(GLU(inp, out_dim, vbs=vbs)) ^ ./qlib/examples/model_rolling/task_manager_rolling.py:75:18: F821 undefined name 'task_train' run_task(task_train, self.task_pool, experiment_name=self.experiment_name) ^ 2 F821 undefined name 'task_train' 2 ``` * Fix undefined names in Python code * from qlib.model.trainer import task_train * update seed * fix some docstring * add comments * Fix SimpleDatasetCache * Update setup.py updated classifiers * Update setup.py change to matplotlib==3.3 * Update python-publish.yml added python 3.9 * updategrade version number * Update model list * fix the type of filter_pipe * fix comment * fix record_temp * update cvxpy version * Update code_standard.rst (#587) * Update code_standard.rst * Update docs/developer/code_standard.rst Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> * Add file lock for MLflowExpManager (#619) * fix torch version * Share version number (#620) * Update initialization.rst (#622) * Update initialization.rst * Update docs/start/initialization.rst Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> * Update docs/start/initialization.rst Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> * fix bugs for running previous exmaple * fix deal amount bug * update change doc (#623) * Add files via upload * Update README.md * Update README.md * Update README.md * Delete change doc.gif * Add files via upload * Update README.md * Delete change doc.gif * Add files via upload * Delete change doc.gif * Add files via upload * Update README.md Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> * update doc * simplify run all model * fix run all model bug * Fix Models (#483) * fix gat dataset * fix tft model * Update tft.py * Fix tft.py Co-authored-by: Pengrong Zhu <zhu.pengrong@foxmail.com> * type and skip empty exp * fix model yaml config * fix tft import bug * skip empty result * fix model and yaml bug * fix wrong generate parameter * Modify multi-freq example (#626) * modify the example of multi-freq * add Copyright * add a comment to average_ops.py * modify the example of multi-freq * add comment to multi_freq_handler.py * add the Ref expression description to multi_freq_handler.py * add expression description to multi_freq_handler.py * update images * fix workflow and update framework Co-authored-by: Gaurav <2796gaurav@gmail.com> Co-authored-by: 2796gaurav <17353992+2796gaurav@users.noreply.github.com> Co-authored-by: bxdd <bxd98@126.com> Co-authored-by: Young <afe.young@gmail.com> Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> Co-authored-by: Dong Zhou <Zhou.Dong@microsoft.com> Co-authored-by: ZhangTP1996 <ztp18@mails.tsinghua.edu.cn> Co-authored-by: demon143 <59681577+demon143@users.noreply.github.com> Co-authored-by: Wangwuyi123 <51237097+Wangwuyi123@users.noreply.github.com> Co-authored-by: yuxwang <anduinnn@foxmail.com> Co-authored-by: Pengrong Zhu <zhu.pengrong@foxmail.com> Co-authored-by: Mark Zhao <50850474+markzhao98@users.noreply.github.com> Co-authored-by: cslwqxx <cslwqxx@users.noreply.github.com> Co-authored-by: Dong Zhou <evanzd@users.noreply.github.com> Co-authored-by: SaintMalik <37118134+saintmalik@users.noreply.github.com> Co-authored-by: Christian Clauss <cclauss@me.com> Co-authored-by: Anurag Kumar <mailanu98@gmail.com> Co-authored-by: demon143 <785696300@qq.com>
This commit is contained in:
wangwenxi-handsome
committed by
GitHub
GitHub
parent
163e3c6266
commit
3760a18a8d
@@ -6,6 +6,7 @@ import sys
|
||||
import fire
|
||||
import time
|
||||
import glob
|
||||
import yaml
|
||||
import shutil
|
||||
import signal
|
||||
import inspect
|
||||
@@ -23,22 +24,6 @@ from qlib.config import REG_CN
|
||||
from qlib.workflow import R
|
||||
from qlib.tests.data import GetData
|
||||
|
||||
# init qlib
|
||||
provider_uri = "~/.qlib/qlib_data/cn_data"
|
||||
exp_folder_name = "run_all_model_records"
|
||||
exp_path = str(Path(os.getcwd()).resolve() / exp_folder_name)
|
||||
exp_manager = {
|
||||
"class": "MLflowExpManager",
|
||||
"module_path": "qlib.workflow.expm",
|
||||
"kwargs": {
|
||||
"uri": "file:" + exp_path,
|
||||
"default_exp_name": "Experiment",
|
||||
},
|
||||
}
|
||||
|
||||
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
|
||||
qlib.init(provider_uri=provider_uri, region=REG_CN, exp_manager=exp_manager)
|
||||
|
||||
|
||||
# decorator to check the arguments
|
||||
def only_allow_defined_args(function_to_decorate):
|
||||
@@ -88,11 +73,11 @@ def create_env():
|
||||
sys.stderr.write("\n")
|
||||
# get anaconda activate path
|
||||
conda_activate = Path(os.environ["CONDA_PREFIX"]) / "bin" / "activate" # TODO: FIX ME!
|
||||
return env_path, python_path, conda_activate
|
||||
return temp_dir, env_path, python_path, conda_activate
|
||||
|
||||
|
||||
# function to execute the cmd
|
||||
def execute(cmd, wait_when_err=False):
|
||||
def execute(cmd, wait_when_err=False, raise_err=True):
|
||||
print("Running CMD:", cmd)
|
||||
with subprocess.Popen(cmd, stdout=subprocess.PIPE, bufsize=1, universal_newlines=True, shell=True) as p:
|
||||
for line in p.stdout:
|
||||
@@ -105,6 +90,8 @@ def execute(cmd, wait_when_err=False):
|
||||
if p.returncode != 0:
|
||||
if wait_when_err:
|
||||
input("Press Enter to Continue")
|
||||
if raise_err:
|
||||
raise RuntimeError(f"Error when executing command: {cmd}")
|
||||
return p.stderr
|
||||
else:
|
||||
return None
|
||||
@@ -134,14 +121,23 @@ def get_all_folders(models, exclude) -> dict:
|
||||
def get_all_files(folder_path, dataset) -> (str, str):
|
||||
yaml_path = str(Path(f"{folder_path}") / f"*{dataset}*.yaml")
|
||||
req_path = str(Path(f"{folder_path}") / f"*.txt")
|
||||
return glob.glob(yaml_path)[0], glob.glob(req_path)[0]
|
||||
yaml_file = glob.glob(yaml_path)
|
||||
req_file = glob.glob(req_path)
|
||||
if len(yaml_file) == 0:
|
||||
return None, None
|
||||
else:
|
||||
return yaml_file[0], req_file[0]
|
||||
|
||||
|
||||
# function to retrieve all the results
|
||||
def get_all_results(folders) -> dict:
|
||||
results = dict()
|
||||
for fn in folders:
|
||||
exp = R.get_exp(experiment_name=fn, create=False)
|
||||
try:
|
||||
exp = R.get_exp(experiment_name=fn, create=False)
|
||||
except ValueError:
|
||||
# No experiment results
|
||||
continue
|
||||
recorders = exp.list_recorders()
|
||||
result = dict()
|
||||
result["annualized_return_with_cost"] = list()
|
||||
@@ -155,9 +151,9 @@ def get_all_results(folders) -> dict:
|
||||
if recorders[recorder_id].status == "FINISHED":
|
||||
recorder = R.get_recorder(recorder_id=recorder_id, experiment_name=fn)
|
||||
metrics = recorder.list_metrics()
|
||||
result["annualized_return_with_cost"].append(metrics["excess_return_with_cost.annualized_return"])
|
||||
result["information_ratio_with_cost"].append(metrics["excess_return_with_cost.information_ratio"])
|
||||
result["max_drawdown_with_cost"].append(metrics["excess_return_with_cost.max_drawdown"])
|
||||
result["annualized_return_with_cost"].append(metrics["1day.excess_return_with_cost.annualized_return"])
|
||||
result["information_ratio_with_cost"].append(metrics["1day.excess_return_with_cost.information_ratio"])
|
||||
result["max_drawdown_with_cost"].append(metrics["1day.excess_return_with_cost.max_drawdown"])
|
||||
result["ic"].append(metrics["IC"])
|
||||
result["icir"].append(metrics["ICIR"])
|
||||
result["rank_ic"].append(metrics["Rank IC"])
|
||||
@@ -185,6 +181,25 @@ def gen_and_save_md_table(metrics, dataset):
|
||||
return table
|
||||
|
||||
|
||||
# read yaml, remove seed kwargs of model, and then save file in the temp_dir
|
||||
def gen_yaml_file_without_seed_kwargs(yaml_path, temp_dir):
|
||||
with open(yaml_path, "r") as fp:
|
||||
config = yaml.load(fp)
|
||||
try:
|
||||
del config["task"]["model"]["kwargs"]["seed"]
|
||||
except KeyError:
|
||||
# If the key does not exists, use original yaml
|
||||
# NOTE: it is very important if the model most run in original path(when sys.rel_path is used)
|
||||
return yaml_path
|
||||
else:
|
||||
# otherwise, generating a new yaml without random seed
|
||||
file_name = yaml_path.split("/")[-1]
|
||||
temp_path = os.path.join(temp_dir, file_name)
|
||||
with open(temp_path, "w") as fp:
|
||||
yaml.dump(config, fp)
|
||||
return temp_path
|
||||
|
||||
|
||||
# function to run the all the models
|
||||
@only_allow_defined_args
|
||||
def run(
|
||||
@@ -193,12 +208,13 @@ def run(
|
||||
dataset="Alpha360",
|
||||
exclude=False,
|
||||
qlib_uri: str = "git+https://github.com/microsoft/qlib#egg=pyqlib",
|
||||
exp_folder_name: str = "run_all_model_records",
|
||||
wait_before_rm_env: bool = False,
|
||||
wait_when_err: bool = False,
|
||||
):
|
||||
"""
|
||||
Please be aware that this function can only work under Linux. MacOS and Windows will be supported in the future.
|
||||
Any PR to enhance this method is highly welcomed. Besides, this script doesn't support parrallel running the same model
|
||||
Any PR to enhance this method is highly welcomed. Besides, this script doesn't support parallel running the same model
|
||||
for multiple times, and this will be fixed in the future development.
|
||||
|
||||
Parameters:
|
||||
@@ -214,6 +230,8 @@ def run(
|
||||
qlib_uri : str
|
||||
the uri to install qlib with pip
|
||||
it could be url on the we or local path
|
||||
exp_folder_name: str
|
||||
the name of the experiment folder
|
||||
wait_before_rm_env : bool
|
||||
wait before remove environment.
|
||||
wait_when_err : bool
|
||||
@@ -240,26 +258,58 @@ def run(
|
||||
# Case 5 - run specific models for one time
|
||||
python run_all_model.py --models=[mlp,lightgbm]
|
||||
|
||||
# Case 6 - run other models except those are given as aruments for one time
|
||||
# Case 6 - run other models except those are given as arguments for one time
|
||||
python run_all_model.py --models=[mlp,tft,sfm] --exclude=True
|
||||
|
||||
"""
|
||||
# init qlib
|
||||
GetData().qlib_data(exists_skip=True)
|
||||
qlib.init(
|
||||
exp_manager={
|
||||
"class": "MLflowExpManager",
|
||||
"module_path": "qlib.workflow.expm",
|
||||
"kwargs": {
|
||||
"uri": "file:" + str(Path(os.getcwd()).resolve() / exp_folder_name),
|
||||
"default_exp_name": "Experiment",
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
# get all folders
|
||||
folders = get_all_folders(models, exclude)
|
||||
# init error messages:
|
||||
errors = dict()
|
||||
# run all the model for iterations
|
||||
for fn in folders:
|
||||
# create env by anaconda
|
||||
env_path, python_path, conda_activate = create_env()
|
||||
# get all files
|
||||
sys.stderr.write("Retrieving files...\n")
|
||||
yaml_path, req_path = get_all_files(folders[fn], dataset)
|
||||
if yaml_path is None:
|
||||
sys.stderr.write(f"There is no {dataset}.yaml file in {folders[fn]}")
|
||||
continue
|
||||
sys.stderr.write("\n")
|
||||
# create env by anaconda
|
||||
temp_dir, env_path, python_path, conda_activate = create_env()
|
||||
|
||||
# install requirements.txt
|
||||
sys.stderr.write("Installing requirements.txt...\n")
|
||||
execute(f"{python_path} -m pip install -r {req_path}", wait_when_err=wait_when_err)
|
||||
with open(req_path) as f:
|
||||
content = f.read()
|
||||
if "torch" in content:
|
||||
# automatically install pytorch according to nvidia's version
|
||||
execute(
|
||||
f"{python_path} -m pip install light-the-torch", wait_when_err=wait_when_err
|
||||
) # for automatically installing torch according to the nvidia driver
|
||||
execute(
|
||||
f"{env_path / 'bin' / 'ltt'} install --install-cmd '{python_path} -m pip install {{packages}}' -- -r {req_path}",
|
||||
wait_when_err=wait_when_err,
|
||||
)
|
||||
else:
|
||||
execute(f"{python_path} -m pip install -r {req_path}", wait_when_err=wait_when_err)
|
||||
sys.stderr.write("\n")
|
||||
|
||||
# read yaml, remove seed kwargs of model, and then save file in the temp_dir
|
||||
yaml_path = gen_yaml_file_without_seed_kwargs(yaml_path, temp_dir)
|
||||
# setup gpu for tft
|
||||
if fn == "TFT":
|
||||
execute(
|
||||
@@ -302,19 +352,20 @@ def run(
|
||||
# getting all results
|
||||
sys.stderr.write(f"Retrieving results...\n")
|
||||
results = get_all_results(folders)
|
||||
# calculating the mean and std
|
||||
sys.stderr.write(f"Calculating the mean and std of results...\n")
|
||||
results = cal_mean_std(results)
|
||||
# generating md table
|
||||
sys.stderr.write(f"Generating markdown table...\n")
|
||||
gen_and_save_md_table(results, dataset)
|
||||
sys.stderr.write("\n")
|
||||
# print erros
|
||||
if len(results) > 0:
|
||||
# calculating the mean and std
|
||||
sys.stderr.write(f"Calculating the mean and std of results...\n")
|
||||
results = cal_mean_std(results)
|
||||
# generating md table
|
||||
sys.stderr.write(f"Generating markdown table...\n")
|
||||
gen_and_save_md_table(results, dataset)
|
||||
sys.stderr.write("\n")
|
||||
# print errors
|
||||
sys.stderr.write(f"Here are some of the errors of the models...\n")
|
||||
pprint(errors)
|
||||
sys.stderr.write("\n")
|
||||
# move results folder
|
||||
shutil.move(exp_path, exp_path + f"_{dataset}_{datetime.now().strftime('%Y-%m-%d_%H:%M:%S')}")
|
||||
shutil.move(exp_folder_name, exp_folder_name + f"_{dataset}_{datetime.now().strftime('%Y-%m-%d_%H:%M:%S')}")
|
||||
shutil.move("table.md", f"table_{dataset}_{datetime.now().strftime('%Y-%m-%d_%H:%M:%S')}.md")
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user