Fixing missing dependencies while building TSDB package for releasing…

… to PyPI (#47) * refactor: use relative imports to replace absolute ones; * fix: install full dependencies while building TSDB package; * fix: run build with --no-isolation; * fix: install wheel before building the package;
WenjieDu · Nov 6, 2023 · 9beff75 · 9beff75
1 parent 3d13d5c
commit 9beff75
Show file tree

Hide file tree

Showing 10 changed files with 77 additions and 25 deletions.
diff --git a/.github/workflows/publish_to_PyPI.yml b/.github/workflows/publish_to_PyPI.yml
@@ -23,6 +23,7 @@ permissions:
 jobs:
   PyPI-deployment:
     runs-on: ubuntu-latest
+
     steps:
     - uses: actions/checkout@v3
 
@@ -31,11 +32,14 @@ jobs:
       with:
         python-version: '3.10'
         check-latest: true
+        cache-dependency-path: |
+          requirements.txt
 
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install build
+        pip install build wheel
+        pip install -r requirements.txt
 
     - name: Fetch the test environment details
       run: |
@@ -44,7 +48,7 @@ jobs:
 
     - name: Build package
       run: |
-        python -m build
+        python -m build --no-isolation
 
     - name: Publish the new package to PyPI
       uses: pypa/gh-action-pypi-publish@v1.8.7

diff --git a/tsdb/__init__.py b/tsdb/__init__.py
@@ -24,7 +24,7 @@
 __version__ = "0.2"
 
 
-from tsdb.data_processing import (
+from .data_processing import (
     list,
     load,
     download_and_extract,

diff --git a/tsdb/data_processing.py b/tsdb/data_processing.py
@@ -10,18 +10,18 @@
 import sys
 import warnings
 
-from tsdb.database import AVAILABLE_DATASETS, CACHED_DATASET_DIR
-from tsdb.loading_funcs import (
+from .database import AVAILABLE_DATASETS, CACHED_DATASET_DIR
+from .loading_funcs import (
     load_physionet2012,
     load_physionet2019,
     load_electricity,
     load_beijing_air_quality,
     load_ucr_uea_dataset,
     load_ais,
 )
-from tsdb.utils.downloading import download_and_extract
-from tsdb.utils.file import purge_path, pickle_load, pickle_dump
-from tsdb.utils.logging import logger
+from .utils.downloading import download_and_extract
+from .utils.file import purge_path, pickle_load, pickle_dump
+from .utils.logging import logger
 
 
 def list() -> list:

diff --git a/tsdb/database.py b/tsdb/database.py
@@ -32,12 +32,62 @@
     #
     # https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/beijing_multisite_air_quality
     "beijing_multisite_air_quality": "https://archive.ics.uci.edu/ml/machine-learning-databases/00501/"
-                                     "PRSA2017_Data_20130301-20170228.zip",
+    "PRSA2017_Data_20130301-20170228.zip",
     #
     # https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/vessel_ais
     "vessel_ais": "https://zenodo.org/record/8064564/files/parquets.zip",
 }
 
+
+# The list of raw data files to be downloaded
+MATR_LINKS = (
+    (
+        "https://data.matr.io/1/api/v1/file/5c86c0b5fa2ede00015ddf66/download",
+        "2017-05-12_batchdata_updated_struct_errorcorrect.mat",
+    ),
+    (
+        "https://data.matr.io/1/api/v1/file/5c86bf13fa2ede00015ddd82/download",
+        "2017-06-30_batchdata_updated_struct_errorcorrect.mat",
+    ),
+    (
+        "https://data.matr.io/1/api/v1/file/5c86bd64fa2ede00015ddbb2/download",
+        "2018-04-12_batchdata_updated_struct_errorcorrect.mat",
+    ),
+    (
+        "https://data.matr.io/1/api/v1/file/5dcef152110002c7215b2c90/download",
+        "2019-01-24_batchdata_updated_struct_errorcorrect.mat",
+    ),
+)
+
+HUST_LINKS = (
+    (
+        "https://data.mendeley.com/public-files/datasets/nsc7hnsg4s/"
+        "files/5ca0ac3e-d598-4d07-8dcb-879aa047e98b/file_downloaded",
+        "hust_data.zip",
+    ),
+)
+
+CALCE_LINKS = (
+    ("https://web.calce.umd.edu/batteries/data/CS2_33.zip", "CS2_33.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CS2_34.zip", "CS2_34.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CS2_35.zip", "CS2_35.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CS2_36.zip", "CS2_36.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CS2_37.zip", "CS2_37.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CS2_38.zip", "CS2_38.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CX2_16.zip", "CX2_16.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CX2_33.zip", "CX2_33.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CX2_35.zip", "CX2_35.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CX2_34.zip", "CX2_34.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CX2_36.zip", "CX2_36.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CX2_37.zip", "CX2_37.zip"),
+    ("https://web.calce.umd.edu/batteries/data/CX2_38.zip", "CX2_38.zip"),
+)
+
+
+RWTH_LINKS = (
+    ("https://publications.rwth-aachen.de/record/818642/files/Rawdata.zip", "raw.zip"),
+)
+
 # https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/ucr_uea_datasets
 # 128 UCR + 33 UEA + 2 old removed (NonInvasiveFatalECGThorax1 and 2) = 163
 _ucr_uea_datasets = [
@@ -210,7 +260,7 @@
 for i in _ucr_uea_datasets:
     UCR_UEA_DATASETS[
         "ucr_uea_" + i
-        ] = f"https://www.timeseriesclassification.com/aeon-toolkit/{i}.zip"
+    ] = f"https://www.timeseriesclassification.com/aeon-toolkit/{i}.zip"
 
 DATABASE = {**_DATABASE, **UCR_UEA_DATASETS}
 AVAILABLE_DATASETS = list(DATABASE.keys())
diff --git a/tsdb/loading_funcs/__init__.py b/tsdb/loading_funcs/__init__.py
@@ -5,14 +5,12 @@
 # Created by Wenjie Du <wenjay.du@gmail.com>
 # License: BSD-3-Clause
 
-from tsdb.loading_funcs.beijing_multisite_air_quality import (
-    load_beijing_air_quality,
-)
-from tsdb.loading_funcs.electricity_load_diagrams import load_electricity
-from tsdb.loading_funcs.physionet_2012 import load_physionet2012
-from tsdb.loading_funcs.physionet_2019 import load_physionet2019
-from tsdb.loading_funcs.ucr_uea_datasets import load_ucr_uea_dataset
-from tsdb.loading_funcs.vessel_ais import load_ais
+from .beijing_multisite_air_quality import load_beijing_air_quality
+from .electricity_load_diagrams import load_electricity
+from .physionet_2012 import load_physionet2012
+from .physionet_2019 import load_physionet2019
+from .ucr_uea_datasets import load_ucr_uea_dataset
+from .vessel_ais import load_ais
 
 __all__ = [
     "load_beijing_air_quality",

diff --git a/tsdb/loading_funcs/beijing_multisite_air_quality.py b/tsdb/loading_funcs/beijing_multisite_air_quality.py
@@ -12,7 +12,7 @@
 
 import pandas as pd
 
-from tsdb.utils.logging import logger
+from ..utils.logging import logger
 
 
 def load_beijing_air_quality(local_path):

diff --git a/tsdb/loading_funcs/physionet_2012.py b/tsdb/loading_funcs/physionet_2012.py
@@ -13,7 +13,7 @@
 
 import pandas as pd
 
-from tsdb.utils.logging import logger
+from ..utils.logging import logger
 
 
 def load_physionet2012(local_path):

diff --git a/tsdb/loading_funcs/vessel_ais.py b/tsdb/loading_funcs/vessel_ais.py
@@ -16,7 +16,7 @@
 import pandas as pd
 from pandas.errors import UnsupportedFunctionCall
 
-from tsdb.utils.logging import logger
+from ..utils.logging import logger
 
 
 def load_ais(local_path):

diff --git a/tsdb/utils/downloading.py b/tsdb/utils/downloading.py
@@ -12,8 +12,8 @@
 import warnings
 from typing import Optional
 
-from tsdb.database import DATABASE
-from tsdb.utils.logging import logger
+from ..database import DATABASE
+from .logging import logger
 
 
 def _download_and_extract(url: str, saving_path: str) -> Optional[str]:

diff --git a/tsdb/utils/file.py b/tsdb/utils/file.py
@@ -11,8 +11,8 @@
 import shutil
 from typing import Optional
 
-from tsdb.database import CACHED_DATASET_DIR
-from tsdb.utils.logging import logger
+from ..database import CACHED_DATASET_DIR
+from .logging import logger
 
 
 def pickle_dump(data: object, path: str) -> Optional[str]: