chore(main): release 0.9.8

* dont manually call setuptools_scm - its integrated

setuptools_scm automatically set the version attribute - manually setting it wrong

* fix(docs): set fallback version for setuptools-scm to fix autodoc import errors on Read the Docs

---------

Co-authored-by: SunsetWolf <Lv.Linlang@hotmail.com>

.commitlintrc.js

@@ -0,0 +1,21 @@
+module.exports = {
+    extends: ["@commitlint/config-conventional"],
+    rules: {
+        // Configuration Format: [level, applicability, value]
+        // level: Error level, usually expressed as a number:
+        //     0 - disable rule
+        //     1 - Warning (does not prevent commits)
+        //     2 - Error (will block the commit)
+        // applicability: the conditions under which the rule applies, commonly used values:
+        //     “always” - always apply the rule
+        //     “never” - never apply the rule
+        // value: the specific value of the rule, e.g. a maximum length of 100.
+        // Refs: https://commitlint.js.org/reference/rules-configuration.html
+      "header-max-length": [2, "always", 100],
+      "type-enum": [
+        2,
+        "always",
+        ["build", "chore", "ci", "docs", "feat", "fix", "perf", "refactor", "revert", "style", "test", "Release-As"]
+      ]
+    }
+  };

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,3 +1,16 @@
+<!--- Thank you for submitting a Pull Request! In order to make our work smoother. -->
+<!--- please make sure your Pull Request meets the following requirements: -->
+<!---   1. Provide a general summary of your changes in the Title above; -->
+<!---   2. Add appropriate prefixes to titles, such as `build:`, `chore:`, `ci:`, `docs:`, `feat:`, `fix:`, `perf:`, `refactor:`, `revert:`, `style:`, `test:`(Ref: https://www.conventionalcommits.org/). -->
+<!--- Category: -->
+<!--- Patch Updates: `fix:` -->
+<!---   Example: fix(auth): correct login validation issue -->
+<!--- minor update (introduces new functionality): `feat` -->
+<!---   Example: feature(parser): add ability to parse arrays -->
+<!--- major update(destructive update): Include BREAKING CHANGE in the commit message footer, or add `! ` in the commit footer to indicate that there is a destructive update. -->
+<!---   Example: feat(auth)! : remove support for old authentication method -->
+<!--- Other updates: `build:`, `chore:`, `ci:`, `docs:`, `perf:`, `refactor:`, `revert:`, `style:`, `test:`. -->
+
 <!--- Provide a general summary of your changes in the Title above -->
 
 ## Description

.github/labeler.yml

@@ -1,6 +0,0 @@
-documentation:
-- 'docs/**/*'
-- '**/*.md'
-
-waiting for triage:
-- any: ['**/*', '!docs/**/*', '!**/*.md']

.github/workflows/labeler.yml

@@ -1,14 +0,0 @@
-name: "Add label automatically"
-on:
-- pull_request_target
-
-jobs:
-  triage:
-    permissions:
-      contents: read
-      pull-requests: write
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/labeler@v4
-      with:
-        repo-token: "${{ secrets.GITHUB_TOKEN }}"

.github/workflows/lint_title.yml

@@ -0,0 +1,35 @@
+name: Lint pull request title
+
+on:
+  pull_request:
+    types:
+      - opened
+      - synchronize
+      - reopened
+      - edited
+
+concurrency:
+  cancel-in-progress: true
+  group: ${{ github.workflow }}-${{ github.ref }}
+
+jobs:
+  lint-title:
+    runs-on: ubuntu-latest
+    steps:
+      # This step is necessary because the lint title uses the .commitlintrc.js file in the project root directory.
+      - name: Checkout Repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '16'
+
+      - name: Install commitlint
+        run: npm install --save-dev @commitlint/{config-conventional,cli}
+
+      - name: Validate PR Title with commitlint
+        env:
+          BODY: ${{ github.event.pull_request.title }}
+        run: |
+          echo "$BODY" | npx commitlint --config .commitlintrc.js

.github/workflows/python-publish.yml

@@ -1,65 +0,0 @@
-# This workflows will upload a Python Package using Twine when a release is created
-# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
-
-name: Upload Python Package
-
-on:
-  release:
-    types: [published]
-
-jobs:
-  deploy_with_bdist_wheel:
-    runs-on: ${{ matrix.os }}
-    strategy:
-      matrix:
-        os: [windows-latest, macos-13, macos-latest]
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
-        exclude:
-          - os: macos-13
-            python-version: "3.11"
-          - os: macos-13
-            python-version: "3.12"
-
-    steps:
-    - uses: actions/checkout@v3
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        make dev
-    - name: Build wheel on ${{ matrix.os }}
-      run: |
-        make build
-    - name: Upload to PyPi
-      env:
-        TWINE_USERNAME: __token__
-        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
-      run: |
-        twine check dist/*.whl
-        twine upload dist/*.whl --verbose
-
-  deploy_with_manylinux:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v3
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Build wheel on Linux
-      uses: RalfG/python-wheels-manylinux-build@v0.7.1-manylinux2014_x86_64
-      with:
-        python-versions: 'cp38-cp38 cp39-cp39 cp310-cp310 cp311-cp311 cp312-cp312'
-        build-requirements: 'numpy cython'
-    - name: Install dependencies
-      run: |
-        python -m pip install twine
-    - name: Upload to PyPi
-      env:
-        TWINE_USERNAME: __token__
-        TWINE_PASSWORD: ${{ secrets.PYPI_TOKEN }}
-      run: |
-        twine check dist/pyqlib-*-manylinux*.whl
-        twine upload dist/pyqlib-*-manylinux*.whl --verbose

.github/workflows/release-drafter.yml

@@ -1,22 +0,0 @@
-name: Release Drafter
-
-on:
-  push:
-    # branches to consider in the event; optional, defaults to all
-    branches:
-      - main
-
-permissions:
-  contents: read
-
-jobs:
-  update_release_draft:
-    permissions:
-      contents: write
-      pull-requests: read
-    runs-on: ubuntu-latest
-    steps:
-      # Drafts your next Release notes as Pull Requests are merged into "master"
-      - uses: release-drafter/release-drafter@v5.11.0
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/release.yml

@@ -0,0 +1,107 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: read
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    outputs:
+      release_created: ${{ steps.release_please.outputs.release_created }}
+
+    steps:
+      - name: Release please
+        id: release_please
+        uses: googleapis/release-please-action@v4
+        with:
+          token: ${{ secrets.PAT }}
+          release-type: simple
+
+  deploy_with_manylinux:
+    needs: release
+    permissions:
+      contents: write
+      pull-requests: read
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        if: needs.release.outputs.release_created == 'true'
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ matrix.python-version }}
+        if: needs.release.outputs.release_created == 'true'
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Build wheel on Linux
+        if: needs.release.outputs.release_created == 'true'
+        uses: RalfG/python-wheels-manylinux-build@v0.7.1-manylinux2014_x86_64
+        with:
+          python-versions: 'cp38-cp38 cp39-cp39 cp310-cp310 cp311-cp311 cp312-cp312'
+          build-requirements: 'numpy cython'
+
+      - name: Install dependencies
+        if: needs.release.outputs.release_created == 'true'
+        run: |
+          python -m pip install twine
+
+      - name: Upload to PyPi
+        if: needs.release.outputs.release_created == 'true'
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.TESTPYPI }}
+        run: |
+          twine check dist/pyqlib-*-manylinux*.whl
+          twine upload --repository-url https://test.pypi.org/legacy/ dist/pyqlib-*-manylinux*.whl --verbose
+
+  deploy_with_bdist_wheel:
+    needs: release
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        # After testing, the whl files of pyqlib built by macos-14 and macos-15 in python environments of 3.8, 3.9, 3.10, 3.11, 3.12,
+        # the filenames are exactly duplicated, which will result in the duplicated whl files not being able to be uploaded to pypi,
+        # so we chose to just keep the latest macos-latest. macos-latest currently points to macos-15.
+        # Also, macos-13 will stop being supported on 2025-11-14.
+        # Refs: https://github.blog/changelog/2025-07-11-upcoming-changes-to-macos-hosted-runners-macos-latest-migration-and-xcode-support-policy-updates/
+        os: [windows-latest, macos-latest]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+
+    steps:
+      - uses: actions/checkout@v4
+        if: needs.release.outputs.release_created == 'true'
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ matrix.python-version }}
+        if: needs.release.outputs.release_created == 'true'
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        if: needs.release.outputs.release_created == 'true'
+        run: |
+          make dev
+
+      - name: Build wheel on ${{ matrix.os }}
+        if: needs.release.outputs.release_created == 'true'
+        run: |
+          make build
+
+      - name: Upload to PyPi
+        if: needs.release.outputs.release_created == 'true'
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.TESTPYPI }}
+        run: |
+          twine check dist/*.whl
+          twine upload --repository-url https://test.pypi.org/legacy/ dist/*.whl --verbose

.github/workflows/test_qlib_from_pip.yml

@@ -21,7 +21,9 @@ jobs:
 
     steps:
     - name: Test qlib from pip
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
 
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v4
@@ -32,19 +34,9 @@ jobs:
       run: |
         python -m pip install --upgrade pip
       
-    # Will cancel this step when the next qlib version is released. The current qlib version is: 0.9.6
-    - name: Installing pywinpt for windows
-      if: ${{ matrix.os == 'windows-latest' }}
-      run: |
-        python -m pip install pywinpty --only-binary=:all:
-
-    # # joblib was released on 2025-05-04 with version 1.5.0, in which _backend_args was removed and replaced by _backend_kwargs.
-    # This change caused the application to fail, so the version of joblib is restricted here. 
-    # This restriction will be removed in the next release. The current qlib version is: 0.9.6
     - name: Qlib installation test
       run: |
         python -m pip install pyqlib
-        python -m pip install "joblib<=1.4.2"
 
     - name: Install Lightgbm for MacOS
       if: ${{ matrix.os == 'macos-14' || matrix.os == 'macos-15' }}
@@ -53,12 +45,10 @@ jobs:
         brew install libomp || brew reinstall libomp
         python -m pip install --no-binary=:all: lightgbm
 
-    # When the new version is released it should be changed to:
-    # python -m qlib.cli.data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
     - name: Downloads dependencies data
       run: |
         cd ..
-        python -m qlib.run.get_data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
+        python -m qlib.cli.data qlib_data --target_dir ~/.qlib/qlib_data/cn_data --region cn
         cd qlib
 
     - name: Test workflow by config

.github/workflows/test_qlib_from_source.yml

@@ -22,7 +22,9 @@ jobs:
 
     steps:
     - name: Test qlib from source
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
 
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v4

.github/workflows/test_qlib_from_source_slow.yml

@@ -22,7 +22,9 @@ jobs:
 
     steps:
     - name: Test qlib from source slow
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
 
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v4
@@ -37,8 +39,6 @@ jobs:
       run: |
         python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
 
-    # install.sh file contents from: https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh
-    # brew_install.sh file contents from: https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh
     - name: Install Lightgbm for MacOS
       if: ${{ matrix.os == 'macos-14' || matrix.os == 'macos-15' }}
       run: |

CHANGELOG.md

@@ -0,0 +1,14 @@
+# Changelog
+
+## [0.9.8](https://github.com/microsoft/qlib/compare/v0.9.7...v0.9.8) (2025-11-13)
+
+
+### Bug Fixes
+
+* download orderbook data error ([#1990](https://github.com/microsoft/qlib/issues/1990)) ([136b2dd](https://github.com/microsoft/qlib/commit/136b2ddf9a16e4106d62b8d1336a56273a8abef0))
+* **gbdt:** correct dtrain assignment in finetune() to use Dataset instead of tuple ([#2049](https://github.com/microsoft/qlib/issues/2049)) ([2b41782](https://github.com/microsoft/qlib/commit/2b41782f0cfb81e8cc065f2915b215758a7838ef))
+* **macd:** remove extra division by close in DEA calculation to ensure dimension consistency ([#2046](https://github.com/microsoft/qlib/issues/2046)) ([66c3622](https://github.com/microsoft/qlib/commit/66c36226aafceabe497e5967f67921e5d3c9d497))
+* replace deprecated pandas fillna(method=) with ffill()/bfill() ([#1987](https://github.com/microsoft/qlib/issues/1987)) ([7095e75](https://github.com/microsoft/qlib/commit/7095e755fa57e011f0483d24b45fc5bd5a4deaf8))
+* spelling errors ([#1996](https://github.com/microsoft/qlib/issues/1996)) ([f26b341](https://github.com/microsoft/qlib/commit/f26b3417363410531dbbb39e425bce6cf05528a1))
+* the bug when auto_mount=True ([#2009](https://github.com/microsoft/qlib/issues/2009)) ([213eb6c](https://github.com/microsoft/qlib/commit/213eb6c2cd12342b6ec98f21300217e1659f3d58))
+* typo in integration documentation: 'userd' -> 'used' ([#2034](https://github.com/microsoft/qlib/issues/2034)) ([3dc5a7d](https://github.com/microsoft/qlib/commit/3dc5a7d299074f0fa45a4b7bb50ab446a8824a32))

Makefile

@@ -113,7 +113,7 @@ dev: prerequisite all
 
 # Check lint with black.
 black:
-	black . -l 120 --check --diff
+	black . -l 120 --check --diff --exclude qlib/_version.py
 
 # Check code folder with pylint.
 # TODO: These problems we will solve in the future. Important among them are: W0221, W0223, W0237, E1102

README.md

@@ -324,7 +324,7 @@ We recommend users to prepare their own data if they have a high-quality dataset
     ```
 2. Start a new Docker container
     ```bash
-    docker run -it --name <container name> -v <Mounted local directory>:/app qlib_image_stable
+    docker run -it --name <container name> -v <Mounted local directory>:/app pyqlib/qlib_image_stable:stable
     ```
 3. At this point you are in the docker environment and can run the qlib scripts. An example:
     ```bash

docs/advanced/alpha.rst

@@ -42,7 +42,7 @@ Example
 
     .. math::
 
-        DEA = \frac{EMA(DIF, 9)}{CLOSE}
+        DEA = EMA(DIF, 9)
 
 Users can use ``Data Handler`` to build formulaic alphas `MACD` in qlib:
 
@@ -51,7 +51,7 @@ Users can use ``Data Handler`` to build formulaic alphas `MACD` in qlib:
 .. code-block:: python
 
     >> from qlib.data.dataset.loader import QlibDataLoader
-    >> MACD_EXP = '(EMA($close, 12) - EMA($close, 26))/$close - EMA((EMA($close, 12) - EMA($close, 26))/$close, 9)/$close'
+    >> MACD_EXP = '2 * ((EMA($close, 12) - EMA($close, 26))/$close - EMA((EMA($close, 12) - EMA($close, 26))/$close, 9))'
     >> fields = [MACD_EXP] # MACD
     >> names = ['MACD']
     >> labels = ['Ref($close, -2)/Ref($close, -1) - 1'] # label
@@ -66,17 +66,17 @@ Users can use ``Data Handler`` to build formulaic alphas `MACD` in qlib:
                             feature     label
                                MACD     LABEL
     datetime   instrument
-    2010-01-04 SH600000   -0.011547 -0.019672
+    2010-01-04 SH600000    0.008781 -0.019672
-               SH600004    0.002745 -0.014721
+               SH600004    0.006699 -0.014721
-               SH600006    0.010133  0.002911
+               SH600006    0.005714  0.002911
-               SH600008   -0.001113  0.009818
+               SH600008    0.000798  0.009818
-               SH600009    0.025878 -0.017758
+               SH600009    0.017015 -0.017758
     ...                         ...       ...
-    2017-12-29 SZ300124    0.007306 -0.005074
+    2017-12-29 SZ300124    0.015071 -0.005074
-               SZ300136   -0.013492  0.056352
+               SZ300136   -0.015466  0.056352
-               SZ300144   -0.000966  0.011853
+               SZ300144    0.013082  0.011853
-               SZ300251    0.004383  0.021739
+               SZ300251   -0.001026  0.021739
-               SZ300315   -0.030557  0.012455
+               SZ300315   -0.007559  0.012455
 
 Reference
 =========

docs/start/getdata.rst

@@ -129,7 +129,7 @@ For example, it looks quite long and complicated:
 
 
 But using string is not the only way to implement the expression. You can also implement expression by code.
-Here is an exmaple which does the same thing as above examples.
+Here is an example which does the same thing as above examples.
 
 
 .. code-block:: python

docs/start/integration.rst

@@ -71,7 +71,7 @@ The Custom models need to inherit `qlib.model.base.Model <../reference/api.html#
                 )
 
 - Override the `predict` method
-    - The parameters must include the parameter `dataset`, which will be userd to get the test dataset.
+    - The parameters must include the parameter `dataset`, which will be used to get the test dataset.
     - Return the `prediction score`.
     - Please refer to `Model API <../reference/api.html#module-qlib.model.base>`_ for the parameter types of the fit method.
     - Code Example: In the following example, users need to use `LightGBM` to predict the label(such as `preds`) of test data `x_test` and return it.

examples/orderbook_data/README.md

@@ -27,7 +27,7 @@ pip install arctic  # NOTE: pip may fail to resolve the right package dependency
 2. Please follow following steps to download example data
 ```bash
 cd examples/orderbook_data/
-gdown https://drive.google.com/uc?id=15nZF7tFT_eKVZAcMFL1qPS4jGyJflH7e  # Proxies may be necessary here.
+gdown https://drive.google.com/uc?id=15FuUqWn2rkCi8uhJYGEQWKakcEqLJNDG  # Proxies may be necessary here.
 python ../../scripts/get_data.py _unzip --file_path highfreq_orderbook_example_data.zip --target_dir .
 ```
 

pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["setuptools", "cython", "numpy>=1.24.0"]
+requires = ["setuptools", "setuptools-scm", "cython", "numpy>=1.24.0"]
 build-backend = "setuptools.build_meta"
 
 [project]
@@ -22,11 +22,15 @@ dynamic = ["version"]
 description = "A Quantitative-research Platform"
 requires-python = ">=3.8.0"
 readme = {file = "README.md", content-type = "text/markdown"}
+license = { text = "MIT" }
 
 dependencies = [
   "pyyaml",
   "numpy",
-  "pandas>=0.24",
+  # Since version 1.1.0, pandas supports the ffill and bfill methods.
+  # Since version 2.1.0, pandas has deprecated the method parameter of the fillna method. 
+  # qlib has updated the fillna method in PR 1987 and limited the minimum version of pandas.
+  "pandas>=1.1",
   # I encoutered an Error that the set_uri does not work when downloading artifacts in mlflow 3.1.1;
   # But earlier versions of mlflow does not have this problem.
   # But when I switch to 2.*.* version, another error occurs, which is even more strange...
@@ -49,6 +53,7 @@ dependencies = [
   "nbconvert",
   "pyarrow",
   "pydantic-settings",
+  "setuptools-scm",
 ]
 
 [project.optional-dependencies]
@@ -108,3 +113,8 @@ license-files = []
 
 [project.scripts]
 qrun = "qlib.cli.run:run"
+
+[tool.setuptools_scm]
+local_scheme = "no-local-version"
+version_scheme = "guess-next-dev"
+write_to = "qlib/_version.py"

qlib/__init__.py

@@ -2,15 +2,22 @@
 # Licensed under the MIT License.
 from pathlib import Path
 
-__version__ = "0.9.7"
+from setuptools_scm import get_version
+
+try:
+    from ._version import version as __version__
+except ImportError:
+    __version__ = get_version(root="..", relative_to=__file__)
 __version__bak = __version__  # This version is backup for QlibConfig.reset_qlib_version
-import os
-import re
-from typing import Union
-from ruamel.yaml import YAML
 import logging
+import os
 import platform
+import re
 import subprocess
+from typing import Union
+
+from ruamel.yaml import YAML
+
 from .log import get_module_logger
 
 
@@ -136,6 +143,9 @@ def _mount_nfs_uri(provider_uri, mount_path, auto_mount: bool = False):
                     _command_log = [line for line in _command_log if _remote_uri in line]
                 if len(_command_log) > 0:
                     for _c in _command_log:
+                        if isinstance(_c, str):
+                            _temp_mount = _c.split(" ")[2]
+                        else:
                             _temp_mount = _c.decode("utf-8").split(" ")[2]
                         _temp_mount = _temp_mount[:-1] if _temp_mount.endswith("/") else _temp_mount
                         if _temp_mount == _mount_path:

qlib/backtest/profit_attribution.py

@@ -281,13 +281,13 @@ def brinson_pa(
 
     stock_group_field = stock_df[group_field].unstack().T
     # FIXME: some attributes of some suspend stock is NAN.
-    stock_group_field = stock_group_field.fillna(method="ffill")
+    stock_group_field = stock_group_field.ffill()
     stock_group_field = stock_group_field.loc[start_date:end_date]
 
     stock_group = get_stock_group(stock_group_field, bench_stock_weight, group_method, group_n)
 
     deal_price_df = stock_df["deal_price"].unstack().T
-    deal_price_df = deal_price_df.fillna(method="ffill")
+    deal_price_df = deal_price_df.ffill()
 
     # NOTE:
     # The return will be slightly different from the of the return in the report.

qlib/contrib/model/gbdt.py

@@ -51,7 +51,7 @@ class LGBModel(ModelFT, LightGBMFInt):
                     w = reweighter.reweight(df)
                 else:
                     raise ValueError("Unsupported reweighter type.")
-                ds_l.append((lgb.Dataset(x.values, label=y, weight=w), key))
+                ds_l.append((lgb.Dataset(x.values, label=y, weight=w, free_raw_data=False), key))
         return ds_l
 
     def fit(
@@ -109,8 +109,10 @@ class LGBModel(ModelFT, LightGBMFInt):
             verbose level
         """
         # Based on existing model and finetune by train more rounds
-        dtrain, _ = self._prepare_data(dataset, reweighter)  # pylint: disable=W0632
+        ds_l = self._prepare_data(dataset, reweighter)
-        if dtrain.empty:
+        dtrain, _ = ds_l[0]
+
+        if dtrain.construct().num_data() == 0:
             raise ValueError("Empty data from dataset, please check your dataset config.")
         verbose_eval_callback = lgb.log_evaluation(period=verbose_eval)
         self.model = lgb.train(

qlib/contrib/ops/high_freq.py

@@ -135,7 +135,7 @@ class FFillNan(ElemOperator):
 
     def _load_internal(self, instrument, start_index, end_index, freq):
         series = self.feature.load(instrument, start_index, end_index, freq)
-        return series.fillna(method="ffill")
+        return series.ffill()
 
 
 class BFillNan(ElemOperator):
@@ -154,7 +154,7 @@ class BFillNan(ElemOperator):
 
     def _load_internal(self, instrument, start_index, end_index, freq):
         series = self.feature.load(instrument, start_index, end_index, freq)
-        return series.fillna(method="bfill")
+        return series.bfill()
 
 
 class Date(ElemOperator):

qlib/contrib/report/analysis_position/parse_position.py

@@ -33,7 +33,7 @@ def parse_position(position: dict = None) -> pd.DataFrame:
 
     position_weight_df = get_stock_weight_df(position)
     # If the day does not exist, use the last weight
-    position_weight_df.fillna(method="ffill", inplace=True)
+    position_weight_df.ffill(inplace=True)
 
     previous_data = {"date": None, "code_list": []}
 

qlib/data/dataset/storage.py

@@ -67,7 +67,6 @@ class NaiveDFStorage(BaseHandlerStorage):
         col_set: Union[str, List[str]] = DataHandler.CS_ALL,
         fetch_orig: bool = True,
     ) -> pd.DataFrame:
-
         # Following conflicts may occur
         # - Does [20200101", "20210101"] mean selecting this slice or these two days?
         # To solve this issue

qlib/utils/mod.py

@@ -161,7 +161,6 @@ def init_instance_by_config(
             # path like 'file:///<path to pickle file>/obj.pkl'
             pr = urlparse(config)
             if pr.scheme == "file":
-
                 # To enable relative path like file://data/a/b/c.pkl.  pr.netloc will be data
                 path = pr.path
                 if pr.netloc != "":

qlib/utils/resam.py

@@ -109,7 +109,7 @@ def resam_ts_data(
     """
     Resample value from time-series data
 
-        - If `feature` has MultiIndex[instrument, datetime], apply the `method` to each instruemnt data with datetime in [start_time, end_time]
+        - If `feature` has MultiIndex[instrument, datetime], apply the `method` to each instrument data with datetime in [start_time, end_time]
             Example:
 
             .. code-block::
@@ -222,7 +222,7 @@ def get_valid_value(series, last=True):
     Nan | float
         the first/last valid value
     """
-    return series.fillna(method="ffill").iloc[-1] if last else series.fillna(method="bfill").iloc[0]
+    return series.ffill().iloc[-1] if last else series.bfill().iloc[0]
 
 
 def _ts_data_valid(ts_feature, last=False):

scripts/collect_info.py

@@ -28,32 +28,32 @@ class InfoCollector:
         """collect qlib related info"""
         print("Qlib version: {}".format(qlib.__version__))
         REQUIRED = [
+            "setuptools",
+            "wheel",
+            "cython",
+            "pyyaml",
             "numpy",
             "pandas",
-            "scipy",
-            "requests",
-            "sacred",
-            "python-socketio",
-            "redis",
-            "python-redis-lock",
-            "schedule",
-            "cvxpy",
-            "hyperopt",
-            "fire",
-            "statsmodels",
-            "xlrd",
-            "plotly",
-            "matplotlib",
-            "tables",
-            "pyyaml",
             "mlflow",
-            "tqdm",
+            "filelock",
-            "loguru",
+            "redis",
-            "lightgbm",
+            "dill",
-            "tornado",
-            "joblib",
             "fire",
             "ruamel.yaml",
+            "python-redis-lock",
+            "tqdm",
+            "pymongo",
+            "loguru",
+            "lightgbm",
+            "gym",
+            "cvxpy",
+            "joblib",
+            "matplotlib",
+            "jupyter",
+            "nbconvert",
+            "pyarrow",
+            "pydantic-settings",
+            "setuptools-scm",
         ]
 
         for package in REQUIRED:

scripts/data_collector/baostock_5min/collector.py

@@ -172,7 +172,7 @@ class BaostockNormalizeHS3005min(BaseNormalize):
     @staticmethod
     def calc_change(df: pd.DataFrame, last_close: float) -> pd.Series:
         df = df.copy()
-        _tmp_series = df["close"].fillna(method="ffill")
+        _tmp_series = df["close"].ffill()
         _tmp_shift_series = _tmp_series.shift(1)
         if last_close is not None:
             _tmp_shift_series.iloc[0] = float(last_close)

scripts/data_collector/utils.py

@@ -82,7 +82,7 @@ def get_calendar_list(bench_code="CSI300") -> List[pd.Timestamp]:
             if bench_code.upper() == "ALL":
 
                 @deco_retry
-                def _get_calendar(month):
+                def _get_calendar_from_month(month):
                     _cal = []
                     try:
                         resp = requests.get(
@@ -98,7 +98,7 @@ def get_calendar_list(bench_code="CSI300") -> List[pd.Timestamp]:
                 month_range = pd.date_range(start="2000-01", end=pd.Timestamp.now() + pd.Timedelta(days=31), freq="M")
                 calendar = []
                 for _m in month_range:
-                    cal = _get_calendar(_m.strftime("%Y-%m"))
+                    cal = _get_calendar_from_month(_m.strftime("%Y-%m"))
                     if cal:
                         calendar += cal
                 calendar = list(filter(lambda x: x <= pd.Timestamp.now(), calendar))

scripts/data_collector/yahoo/collector.py

@@ -371,7 +371,7 @@ class YahooNormalize(BaseNormalize):
     @staticmethod
     def calc_change(df: pd.DataFrame, last_close: float) -> pd.Series:
         df = df.copy()
-        _tmp_series = df["close"].fillna(method="ffill")
+        _tmp_series = df["close"].ffill()
         _tmp_shift_series = _tmp_series.shift(1)
         if last_close is not None:
             _tmp_shift_series.iloc[0] = float(last_close)
@@ -459,7 +459,7 @@ class YahooNormalize1d(YahooNormalize, ABC):
         df.set_index(self._date_field_name, inplace=True)
         if "adjclose" in df:
             df["factor"] = df["adjclose"] / df["close"]
-            df["factor"] = df["factor"].fillna(method="ffill")
+            df["factor"] = df["factor"].ffill()
         else:
             df["factor"] = 1
         for _col in self.COLUMNS:
@@ -613,10 +613,6 @@ class YahooNormalize1min(YahooNormalize, ABC):
     def symbol_to_yahoo(self, symbol):
         raise NotImplementedError("rewrite symbol_to_yahoo")
 
-    @abc.abstractmethod
-    def _get_1d_calendar_list(self) -> Iterable[pd.Timestamp]:
-        raise NotImplementedError("rewrite _get_1d_calendar_list")
-
 
 class YahooNormalizeUS:
     def _get_calendar_list(self) -> Iterable[pd.Timestamp]:

setup.py

@@ -1,29 +1,13 @@
-from setuptools import setup, Extension
-import numpy
 import os
 
-
+import numpy
-def read(rel_path: str) -> str:
+from setuptools import Extension, setup
-    here = os.path.abspath(os.path.dirname(__file__))
-    with open(os.path.join(here, rel_path), encoding="utf-8") as fp:
-        return fp.read()
-
-
-def get_version(rel_path: str) -> str:
-    for line in read(rel_path).splitlines():
-        if line.startswith("__version__"):
-            delim = '"' if '"' in line else "'"
-            return line.split(delim)[1]
-    raise RuntimeError("Unable to find version string.")
 
 
 NUMPY_INCLUDE = numpy.get_include()
 
-VERSION = get_version("qlib/__init__.py")
-
 
 setup(
-    version=VERSION,
     ext_modules=[
         Extension(
             "qlib.data._libs.rolling",