update python version

.github/workflows/test_qlib_from_source.yml

@@ -21,7 +21,7 @@ jobs:
         # so we limit the macos version to macos-13.
         os: [windows-latest, ubuntu-20.04, ubuntu-22.04, macos-13]
         # not supporting 3.6 due to annotations is not supported https://stackoverflow.com/a/52890129
-        python-version: [3.7, 3.8]
+        python-version: ["3.8", "3.10"]
 
     steps:
     - name: Test qlib from source
@@ -63,8 +63,8 @@ jobs:
 
     - name: Set up Python tools
       run: |
-        python -m pip install --upgrade cython
-        python -m pip install -e .[dev]
+        python -m pip install pytest-timeout
+        make dev
 
     - name: Lint with Black
       # Python 3.7 will use a black with low level. So we use python with higher version for black check
@@ -108,8 +108,8 @@ jobs:
     # We use sys.setrecursionlimit(2000) to make the recursion depth larger to ensure that pylint works properly (the default recursion depth is 1000).
     - name: Check Qlib with pylint
       run: |
-        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' qlib --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
-        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0246,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' scripts --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R0917,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' qlib --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
+        pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R0917,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,E1123,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0246,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}$' scripts --init-hook "import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
 
     # The following flake8 error codes were ignored:
       # E501 line too long
@@ -179,4 +179,4 @@ jobs:
         max_attempts: 3
         command: |
           cd tests
-          python -m pytest . -m "not slow" --durations=0
+          python -m pytest . -m "not slow" --durations=0 --timeout=600

.github/workflows/test_qlib_from_source_slow.yml

@@ -45,8 +45,7 @@ jobs:
     - name: Set up Python tools
       run: |
         python -m pip install --upgrade pip
-        pip install --upgrade cython numpy
-        pip install -e .[dev]
+        make dev
 
     - name: Downloads dependencies data
       run: |

.gitignore

@@ -48,4 +48,5 @@ tags
 *.swp
 
 ./pretrain
-.idea/
+.idea/
+.aider*

MANIFEST.in

@@ -1 +1,5 @@
-include qlib/VERSION.txt
+exclude tests/*
+include qlib/*
+include qlib/*/*
+include qlib/*/*/*
+include qlib/*/*/*/*

Makefile

@@ -0,0 +1,134 @@
+.PHONY: prerequisite clean deepclean install init-qlib-env dev constraints black isort mypy ruff toml-sort lint pre-commit test-run test build upload docs-autobuild changelog docs-gen docs-mypy docs-coverage docs
+#You can modify it according to your terminal
+SHELL := /bin/bash
+
+########################################################################################
+# Variables
+########################################################################################
+
+# Documentation target directory, will be adapted to specific folder for readthedocs.
+PUBLIC_DIR := $(shell [ "$$READTHEDOCS" = "True" ] && echo "$$READTHEDOCS_OUTPUT/html" || echo "public")
+
+SO_DIR := qlib/data/_libs
+SO_FILES := $(wildcard $(SO_DIR)/*.so)
+
+########################################################################################
+# Development Environment Management
+########################################################################################
+# Remove common intermediate files.
+clean:
+	-rm -rf \
+		$(PUBLIC_DIR) \
+		qlib/data/_libs \
+		mlruns \
+		build \
+		.coverage \
+		.mypy_cache \
+		.pytest_cache \
+		.ruff_cache \
+		Pipfile* \
+		coverage.xml \
+		dist \
+		release-notes.md
+
+	find . -name '*.egg-info' -print0 | xargs -0 rm -rf
+	find . -name '*.pyc' -print0 | xargs -0 rm -f
+	find . -name '*.swp' -print0 | xargs -0 rm -f
+	find . -name '.DS_Store' -print0 | xargs -0 rm -f
+	find . -name '__pycache__' -print0 | xargs -0 rm -rf
+
+# Remove pre-commit hook, virtual environment alongside itermediate files.
+deepclean: clean
+	if command -v pre-commit > /dev/null 2>&1; then pre-commit uninstall --hook-type pre-push; fi
+	if command -v pipenv >/dev/null 2>&1 && pipenv --venv >/dev/null 2>&1; then pipenv --rm; fi
+
+# Prerequisite section
+prerequisite:
+	@if [ -n "$(SO_FILES)" ]; then \
+		echo "Shared library files exist, skipping build."; \
+	else \
+		echo "No shared library files found, building..."; \
+		python -m pip install cython numpy; \
+		python -c "from setuptools import setup, Extension; from Cython.Build import cythonize; import numpy; extensions = [Extension('qlib.data._libs.rolling', ['qlib/data/_libs/rolling.pyx'], language='c++', include_dirs=[numpy.get_include()]), Extension('qlib.data._libs.expanding', ['qlib/data/_libs/expanding.pyx'], language='c++', include_dirs=[numpy.get_include()])]; setup(ext_modules=cythonize(extensions, language_level='3'), script_args=['build_ext', '--inplace'])"; \
+	fi
+
+# Install the package in editable mode.
+dependencies:
+	python -m pip install -e .
+
+lightgbm:
+	python -m pip install lightgbm --prefer-binary
+
+rl:
+	python -m pip install -e .[rl]
+
+develop:
+	python -m pip install -e .[dev]
+
+lint:
+	python -m pip install -e .[lint]
+
+docs:
+	python -m pip install -e .[docs]
+
+package:
+	python -m pip install -e .[package]
+
+all:
+	python -m pip install -e .[rl,dev,lint,docs,package]
+
+install: prerequisite dependencies
+
+dev: prerequisite all
+
+########################################################################################
+# Lint and pre-commit
+########################################################################################
+
+# Check lint with black.
+black:
+	black . -l 120 --check --diff
+
+# Check code folder with pylint.
+pylint:
+	pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R0917,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1730,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}' qlib --init-hook="import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
+	pylint --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R0917,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,E1123,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0246,W0612,W0621,W0622,W0703,W1309,E1102,E1136 --const-rgx='[a-z_][a-z0-9_]{2,30}' scripts --init-hook="import astroid; astroid.context.InferenceContext.max_inferred = 500; import sys; sys.setrecursionlimit(2000)"
+
+# Check code with flake8.
+flake8:
+	flake8 --ignore=E501,F541,E266,E402,W503,E731,E203 --per-file-ignores="__init__.py:F401,F403" qlib
+
+# Check code with mypy.
+mypy:
+	mypy qlib --install-types --non-interactive
+	mypy qlib --verbose
+
+# Check ipynb with nbqa.
+nbqa:
+	nbqa black . -l 120 --check --diff
+	nbqa pylint . --disable=C0104,C0114,C0115,C0116,C0301,C0302,C0411,C0413,C1802,R0401,R0801,R0902,R0903,R0911,R0912,R0913,R0914,R0915,R1720,W0105,W0123,W0201,W0511,W0613,W1113,W1514,E0401,E1121,C0103,C0209,R0402,R1705,R1710,R1725,R1735,W0102,W0212,W0221,W0223,W0231,W0237,W0612,W0621,W0622,W0703,W1309,E1102,E1136,W0719,W0104,W0404,C0412,W0611,C0410 --const-rgx='[a-z_][a-z0-9_]{2,30}'
+
+# Check ipynb with nbconvert.
+nbconvert:
+	jupyter nbconvert --to notebook --execute examples/workflow_by_code.ipynb
+
+lint: black pylint flake8 mypy nbqa
+
+########################################################################################
+# Package
+########################################################################################
+
+# Build the package.
+build:
+	python -m build
+
+# Upload the package.
+upload:
+	python -m twine upload dist/*
+
+########################################################################################
+# Documentation
+########################################################################################
+
+docs-gen:
+	python -m sphinx.cmd.build -W docs $(PUBLIC_DIR)

examples/benchmarks/TRA/example.py

@@ -1,14 +1,15 @@
 import argparse
 
 import qlib
-import ruamel.yaml as yaml
+from ruamel.yaml import YAML
 from qlib.utils import init_instance_by_config
 
 
 def main(seed, config_file="configs/config_alstm.yaml"):
     # set random seed
     with open(config_file) as f:
-        config = yaml.safe_load(f)
+        yaml = YAML(typ="safe", pure=True)
+        config = yaml.load(f)
 
     # seed_suffix = "/seed1000" if "init" in config_file else f"/seed{seed}"
     seed_suffix = ""

examples/data_demo/data_cache_demo.py

@@ -9,8 +9,8 @@
 from pathlib import Path
 import pickle
 from pprint import pprint
+from ruamel.yaml import YAML
 import subprocess
-import yaml
 from qlib.log import TimeInspector
 
 from qlib import init
@@ -30,7 +30,8 @@
         subprocess.run(f"qrun {config_path}", shell=True)
 
     # 2) dump handler
-    task_config = yaml.safe_load(config_path.open())
+    yaml = YAML(typ="safe", pure=True)
+    task_config = yaml.load(config_path.open())
     hd_conf = task_config["task"]["dataset"]["kwargs"]["handler"]
     pprint(hd_conf)
     hd: DataHandlerLP = init_instance_by_config(hd_conf)

examples/data_demo/data_mem_resuse_demo.py

@@ -9,10 +9,9 @@
 from pathlib import Path
 import pickle
 from pprint import pprint
+from ruamel.yaml import YAML
 import subprocess
 
-import yaml
-
 from qlib import init
 from qlib.data.dataset.handler import DataHandlerLP
 from qlib.log import TimeInspector
@@ -29,7 +28,8 @@
     exp_name = "data_mem_reuse_demo"
 
     config_path = DIRNAME.parent / "benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml"
-    task_config = yaml.safe_load(config_path.open())
+    yaml = YAML(typ="safe", pure=True)
+    task_config = yaml.load(config_path.open())
 
     # 1) without using processed data in memory
     with TimeInspector.logt("The original time without reusing processed data in memory:"):

examples/run_all_model.py

@@ -6,7 +6,6 @@
 import fire
 import time
 import glob
-import yaml
 import shutil
 import signal
 import inspect
@@ -15,6 +14,7 @@
 import statistics
 import subprocess
 from datetime import datetime
+from ruamel.yaml import YAML
 from pathlib import Path
 from operator import xor
 from pprint import pprint
@@ -188,7 +188,8 @@ def gen_and_save_md_table(metrics, dataset):
 # 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.safe_load(fp)
+        yaml = YAML(typ="safe", pure=True)
+        config = yaml.load(fp)
     try:
         del config["task"]["model"]["kwargs"]["seed"]
     except KeyError:

pyproject.toml

@@ -1,2 +1,84 @@
 [build-system]
-requires = ["setuptools", "numpy", "Cython"]
+requires = ["setuptools", "cython", "numpy"]
+build-backend = "setuptools.build_meta"
+
+[project]
+classifiers = [
+  "Operating System :: POSIX :: Linux",
+  "Operating System :: Microsoft :: Windows",
+  "Operating System :: MacOS",
+  "License :: OSI Approved :: MIT License",
+  "Development Status :: 3 - Alpha",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.7",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+]
+name = "pyqlib"
+dynamic = ["version"]
+description = "A Quantitative-research Platform"
+requires-python = ">=3.7.0"
+
+dependencies = [
+  "pyyaml",
+  "numpy",
+  "pandas",
+  "mlflow",
+  "filelock",
+  "redis",
+  "dill",
+  "fire",
+  "ruamel.yaml",
+  "python-redis-lock",
+  "tqdm",
+  "pymongo",
+  "loguru",
+  "lightgbm",
+  "gym",
+  "cvxpy",
+  "joblib",
+  "matplotlib",
+]
+
+[project.optional-dependencies]
+dev = [
+  "pytest",
+  "baostock",
+  "tianshou",
+  "yahooquery",
+  "plotly",
+  "statsmodels",
+]
+rl = [
+  "tianshou<=0.4.10",
+  "torch",
+]
+lint = [
+  "black",
+  "pylint",
+  "mypy<1.5.0",
+  "flake8",
+  "nbqa",
+  "jupyter",
+  "nbconvert",
+]
+docs = [
+  "sphinx",
+  "sphinx_rtd_theme",
+  "readthedocs_sphinx_ext",
+]
+package = [
+  "twine",
+  "build",
+]
+
+[tool.setuptools]
+packages = [
+  "qlib",
+]
+
+[project.scripts]
+qrun = "qlib.workflow.cli:run"

qlib/__init__.py

@@ -6,7 +6,7 @@
 __version__bak = __version__  # This version is backup for QlibConfig.reset_qlib_version
 import os
 from typing import Union
-import yaml
+from ruamel.yaml import YAML
 import logging
 import platform
 import subprocess
@@ -176,7 +176,8 @@ def init_from_yaml_conf(conf_path, **kwargs):
         config = {}
     else:
         with open(conf_path) as f:
-            config = yaml.safe_load(f)
+            yaml = YAML(typ="safe", pure=True)
+            config = yaml.load(f)
     config.update(kwargs)
     default_conf = config.pop("default_conf", "client")
     init(default_conf, **config)
@@ -272,7 +273,8 @@ def auto_init(**kwargs):
         logger = get_module_logger("Initialization")
         conf_pp = pp / "config.yaml"
         with conf_pp.open() as f:
-            conf = yaml.safe_load(f)
+            yaml = YAML(typ="safe", pure=True)
+            conf = yaml.load(f)
 
         conf_type = conf.get("conf_type", "origin")
         if conf_type == "origin":