Merge pull request #69 from WenjieDu/dev

Change the default data_home_path and update the docs

README.md

@@ -95,7 +95,8 @@ tsdb.delete_cache(dataset_name='physionet_2012')
 # or you can delete all cache with delete_cached_data() to free disk space
 tsdb.delete_cache()
 
-# to avoid taking up too much space if downloading many datasets,
+# The default cache directory is ~/.pypots/tsdb under the user's home directory.
+# To avoid taking up too much space if downloading many datasets ,
 # TSDB cache directory can be migrated to an external disk
 tsdb.migrate_cache("/mnt/external_disk/TSDB_cache")
 ```
@@ -145,9 +146,9 @@ year={2023},
 }
 ```
 or
-> Wenjie Du. (2023).
+> Wenjie Du.
 > PyPOTS: a Python toolbox for data mining on Partially-Observed Time Series.
-> arXiv, abs/2305.18811. https://arxiv.org/abs/2305.18811
+> arXiv, abs/2305.18811, 2023.
 
 
 

docs/index.rst

@@ -49,7 +49,7 @@ Welcome to TSDB documentation!
 .. image:: https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FWenjieDu%2FTime_Series_Database&count_bg=%2379C83D&title_bg=%23555555&icon=&icon_color=%23E7E7E7&title=Visits+since+April+2022&edge_flat=false
    :alt: Visit num
 
-📣 TSDB now supports a total of 1️⃣6️⃣9️⃣ time-series datasets ‼️
+📣 TSDB now supports a total of 1️⃣7️⃣2️⃣ time-series datasets ‼️
 
 .. image:: https://pypots.com/figs/pypots_logos/PyPOTS/logo_FFBG.svg
    :width: 120
@@ -100,12 +100,15 @@ or install from source code:
    tsdb.download_and_extract('physionet_2012', './save_it_here')
    # datasets you once loaded are cached, and you can check them with list_cached_data()
    tsdb.list_cache()
-   # you can delete only one specific dataset and preserve others
+   # you can delete only one specific dataset's pickled cache
+   tsdb.delete_cache(dataset_name='physionet_2012', only_pickle=True)
+   # you can delete only one specific dataset raw files and preserve others
    tsdb.delete_cache(dataset_name='physionet_2012')
    # or you can delete all cache with delete_cached_data() to free disk space
    tsdb.delete_cache()
 
-   # to avoid taking up too much space if downloading many datasets,
+   # The default cache directory is ~/.pypots/tsdb under the user's home directory.
+   # To avoid taking up too much space if downloading many datasets ,
    # TSDB cache directory can be migrated to an external disk
    tsdb.migrate_cache("/mnt/external_disk/TSDB_cache")
 
@@ -124,6 +127,8 @@ That's all. Simple and efficient. Enjoy it! 😃
  `Electricity Load Diagrams <https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/electricity_load_diagrams>`_  :cite:`trindade2015electricity`                     Forecasting, Imputation
  `Electricity Transformer Temperature (ETT) <https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/electricity_transformer_temperature>`_  :cite:`zhou2021informer`  Forecasting, Imputation
  `Vessel AIS data <https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/vessel_ais>`_  :cite:`grgicevic2023ais`                                                     Forecasting, Imputation, Classification
+ `PeMS Traffic <https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/pems_traffic>`_                                                                                Forecasting, Imputation
+ `Solar Alabama <https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/solar_alabama>`_                                                                              Forecasting, Imputation
  `UCR & UEA Datasets <https://github.com/WenjieDu/TSDB/tree/main/dataset_profiles/ucr_uea_datasets>`_ (all 163 datasets)  :cite:`bagnall2018uea` :cite:`dau2018ucr`        Classification
 ========================================================================================================================================================================== ==========================================
 
@@ -145,22 +150,18 @@ please cite it as below and 🌟star `PyPOTS repository <https://github.com/Wenj
 .. code-block:: bibtex
    :linenos:
 
-   @article{du2023PyPOTS,
-   title={{PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series}},
+   @article{du2023pypots,
+   title={{PyPOTS: a Python toolbox for data mining on Partially-Observed Time Series}},
    author={Wenjie Du},
+   journal={arXiv preprint arXiv:2305.18811},
    year={2023},
-   eprint={2305.18811},
-   archivePrefix={arXiv},
-   primaryClass={cs.LG},
-   url={https://arxiv.org/abs/2305.18811},
-   doi={10.48550/arXiv.2305.18811},
    }
 
 or
 
-   Wenjie Du. (2023).
+   Wenjie Du.
    PyPOTS: A Python Toolbox for Data Mining on Partially-Observed Time Series.
-   arXiv, abs/2305.18811. https://doi.org/10.48550/arXiv.2305.18811
+   arXiv, abs/2305.18811, 2023.
 
 
 .. toctree::

tsdb/__init__.py

@@ -21,7 +21,7 @@
 #
 # 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__ = "0.4"
+__version__ = "0.5"
 
 from .data_processing import (
     CACHED_DATASET_DIR,

tsdb/config.ini

@@ -1,2 +1,2 @@
 [path]
-data_home = ~/.tsdb
+data_home = ~/.pypots/tsdb

tsdb/utils/file.py

@@ -103,25 +103,33 @@ def determine_data_home():
     data_home_path = config.get("path", "data_home")
     # replace '~' with the absolute path if existing in the path
     data_home_path = data_home_path.replace("~", os.path.expanduser("~"))
-    old_cached_dataset_dir = os.path.join(
+
+    # old cached dataset dir path used in TSDB v0.2
+    old_cached_dataset_dir_02 = os.path.join(
         os.path.expanduser("~"), ".tsdb_cached_datasets"
     )
+    # old cached dataset dir path used in TSDB v0.4
+    old_cached_dataset_dir_04 = os.path.join(os.path.expanduser("~"), ".tsdb")
 
-    if os.path.exists(old_cached_dataset_dir):
-        # use the old path and warn the user
+    if os.path.exists(old_cached_dataset_dir_02) or os.path.exists(
+        old_cached_dataset_dir_04
+    ):
         logger.warning(
-            "‼️ Detected the home dir of the old version TSDB. "
-            "Since v0.3, TSDB has changed the default cache dir to '~/.tsdb'. "
-            "Auto migrating downloaded datasets to the new path. "
+            "‼️ Detected the home dir of the old version TSDB. Auto migrating... Please wait."
         )
         cached_dataset_dir = data_home_path
-        migrate(old_cached_dataset_dir, cached_dataset_dir)
+        if os.path.exists(old_cached_dataset_dir_02):
+            migrate(old_cached_dataset_dir_02, cached_dataset_dir)
+        else:
+            migrate(old_cached_dataset_dir_04, cached_dataset_dir)
+        logger.info("🌟 Migrating finished.")
     elif os.path.exists(data_home_path):
         # use the path directly, may be in a portable disk
         cached_dataset_dir = data_home_path
     else:
-        # use the default path
-        default_path = os.path.join(os.path.expanduser("~"), ".tsdb")
+        # use the default path for initialization,
+        # e.g. `data_home_path` in a portable disk but the disk is not connected
+        default_path = os.path.join(os.path.expanduser("~"), ".pypots", "tsdb")
         cached_dataset_dir = default_path
         if os.path.abspath(data_home_path) != os.path.abspath(default_path):
             logger.warning(