Fix missing load_specific_dataset(), update testing_daily workflow, release v0.7.1

.github/workflows/publish_to_PyPI.yml

@@ -48,7 +48,7 @@ jobs:
 
     - name: Build package
       run: |
-        python -m build --no-isolation
+        python -m build
 
     - name: Publish the new package to PyPI
       uses: pypa/[email protected]

.github/workflows/testing_daily.yml

@@ -4,6 +4,9 @@ on:
     schedule:
         # https://crontab.guru. Run everyday at 0:00AM UTC, i.e. 08:00AM Beijing, i.e. 08:00PM Montreal (summer time)
         - cron: "0 0 * * *"
+    push:
+        branches:
+            - temp_test_branch  # if in need, create such a temporary branch to test some functions
 
 jobs:
     Daily-testing:
@@ -14,49 +17,44 @@ jobs:
         strategy:
             fail-fast: false
             matrix:
-                os: [ubuntu-latest, windows-latest, macOS-13]
-                python-version: ["3.7", "3.11"]
+                os: [ ubuntu-latest, windows-latest, macOS-latest ]
+                python-version: [ "3.8" ]
+                pytorch-version: ["2.3.0"]
 
         steps:
             - name: Check out the repo code
               uses: actions/checkout@v3
 
-            - name: Determine the PyTorch version
-              uses: haya14busa/action-cond@v1
-              id: determine_pytorch_ver
-              with:
-                cond: ${{ matrix.python-version == 3.7 }}
-                if_true: "1.13.1"
-                if_false: "2.1.0"
 
             - name: Set up Conda
               uses: conda-incubator/setup-miniconda@v2
               with:
-                  activate-environment: pypots-test
+                  miniconda-version: "latest"
+                  activate-environment: pypots
                   python-version: ${{ matrix.python-version }}
-                  environment-file: tests/environment_for_conda_test.yml
+                  environment-file: requirements/conda_env.yml
                   auto-activate-base: false
 
             - name: Fetch the test environment details
               run: |
+                  # many libs not compatible with numpy 2.0. Note 3.12 requests for numpy>=2.0. fix pandas version to avoid installing pandas 2.0, the same reason with numpy
+                  conda install -c conda-forge numpy=1.24 pandas=1.5
                   which python
                   conda info
                   conda list
 
+            - name: Replace with the latest PyPOTS code for testing
+              run: |
+                  python_site_path=`python -c "import site; print(site.getsitepackages()[0])"`
+                  echo "python site-packages path: $python_site_path"
+                  rm -rf $python_site_path/pypots
+                  python -c "import shutil;import site;shutil.copytree('pypots',site.getsitepackages()[0]+'/pypots')"
+
             - name: Test with pytest
               run: |
-                  # run tests separately here due to Segmentation Fault in test_clustering when run all in
-                  # one command with `pytest` on MacOS. Bugs not caught, so this is a trade-off to avoid SF.
-                  python tests/global_test_config.py
                   rm -rf testing_results && rm -rf tests/__pycache__ && rm -rf tests/*/__pycache__
-                  python -m pytest -rA tests/classification/* -s -n auto --cov=pypots --dist=loadgroup --cov-config=.coveragerc
-                  python -m pytest -rA tests/imputation/* -s -n auto --cov=pypots --cov-append --dist=loadgroup --cov-config=.coveragerc
-                  python -m pytest -rA tests/clustering/* -s -n auto --cov=pypots --cov-append --dist=loadgroup --cov-config=.coveragerc
-                  python -m pytest -rA tests/forecasting/* -s -n auto --cov=pypots --cov-append --dist=loadgroup --cov-config=.coveragerc
-                  python -m pytest -rA tests/optim/* -s -n auto --cov=pypots --cov-append --dist=loadgroup --cov-config=.coveragerc
-                  python -m pytest -rA tests/data/* -s -n auto --cov=pypots --cov-append --dist=loadgroup --cov-config=.coveragerc
-                  python -m pytest -rA tests/utils/* -s -n auto --cov=pypots --cov-append --dist=loadgroup --cov-config=.coveragerc
-                  python -m pytest -rA tests/cli/* -s -n auto --cov=pypots --cov-append --dist=loadgroup --cov-config=.coveragerc
+                  python tests/global_test_config.py
+                  python -m pytest -rA tests/*/* -s -n auto --cov=pypots --dist=loadgroup --cov-config=.coveragerc
 
             - name: Generate the LCOV report
               run: |

pypots/data/__init__.py

@@ -23,6 +23,7 @@
     sliding_window,
     inverse_sliding_window,
 )
+from .load_specific_datasets import load_specific_dataset
 
 __all__ = [
     # base dataset classes
@@ -33,6 +34,7 @@
     "gene_complete_random_walk_for_anomaly_detection",
     "gene_complete_random_walk_for_classification",
     "gene_random_walk",
+    "load_specific_dataset",
     # utils
     "parse_delta",
     "sliding_window",

pypots/data/load_specific_datasets.py

@@ -0,0 +1,73 @@
+"""
+Functions to load supported open-source time-series datasets.
+"""
+
+# Created by Wenjie Du <[email protected]>
+# License: BSD-3-Clause
+
+
+from benchpots.datasets import preprocess_physionet2012
+
+from ..utils.logging import logger
+
+# currently supported datasets
+SUPPORTED_DATASETS = [
+    "physionet_2012",
+]
+
+# preprocessing functions of the supported datasets
+PREPROCESSING_FUNC = {
+    "physionet_2012": preprocess_physionet2012,
+}
+
+
+def list_supported_datasets() -> list:
+    """Return the datasets natively supported by PyPOTS so far.
+
+    Returns
+    -------
+    SUPPORTED_DATASETS :
+        A list including all supported datasets.
+
+    """
+    return SUPPORTED_DATASETS
+
+
+def load_specific_dataset(dataset_name: str, use_cache: bool = True) -> dict:
+    """Load specific datasets supported by PyPOTS.
+    Different from tsdb.load_dataset(), which only produces merely raw data,
+    load_specific_dataset here does some preprocessing operations,
+    like truncating time series to generate samples with the same length.
+
+    Parameters
+    ----------
+    dataset_name :
+        The name of the dataset to be loaded, which should be supported, i.e. in SUPPORTED_DATASETS.
+
+    use_cache :
+        Whether to use cache. This is an argument of tsdb.load_dataset().
+
+    Returns
+    -------
+    data :
+        A dict contains the preprocessed dataset.
+        Users only need to continue the preprocessing steps to generate the data they want,
+        e.g. standardizing and splitting.
+
+    """
+    logger.info(
+        f"Loading the dataset {dataset_name} with TSDB (https://github.com/WenjieDu/Time_Series_Data_Beans)..."
+    )
+    assert dataset_name in SUPPORTED_DATASETS, (
+        f"Dataset {dataset_name} is not supported. "
+        f"If you believe this dataset is valuable to be supported by PyPOTS,"
+        f"please create an issue on GitHub "
+        f"https://github.com/WenjieDu/PyPOTS/issues"
+    )
+    logger.info(f"Starting preprocessing {dataset_name}...")
+    data = PREPROCESSING_FUNC[dataset_name]("all", 0.1)
+    logger.warning(
+        "⚠️ load_specific_dataset() will be deprecated in the near future. Data preprocessing functions "
+        "are moved to BenchPOTS, which now supports processing 170+ public time-series datasets."
+    )
+    return data

pypots/version.py

@@ -22,4 +22,4 @@
 #
 # Dev branch marker is: 'X.Y.dev' or 'X.Y.devN' where N is an integer.
 # 'X.Y.dev0' is the canonical version of 'X.Y.dev'
-__version__ = "0.7"
+__version__ = "0.7.1"

requirements/conda_env.yml

@@ -8,12 +8,12 @@ channels:
 
 dependencies:
     # basic
+    - conda-forge::python >=3.8
     - conda-forge::pip
     - conda-forge::h5py
     - conda-forge::numpy
     - conda-forge::scipy
     - conda-forge::sympy
-    - conda-forge::python
     - conda-forge::einops
     - conda-forge::pandas
     - conda-forge::seaborn
@@ -46,6 +46,7 @@ dependencies:
     # dev
     - conda-forge::black
     - conda-forge::flake8
+    - conda-forge::flake8-pyproject
     - conda-forge::pre-commit
     - conda-forge::jupyterlab