Add save_dict_into_h5() and sliding_window(), add .gitignore, and update the docs

.gitignore

@@ -0,0 +1,20 @@
+# ignore special files or folds
+*~
+.idea
+.DS_Store
+
+# ignore all building results
+dist
+build
+docs/_build
+*.egg-info
+
+# ignore all testing/running results
+.run
+.coverage
+.pytest_cache
+*__pycache__*
+*testing_results*
+
+# ignore specific kinds of files like all PDFs
+*.pdf

MANIFEST.in

@@ -1,2 +1,3 @@
 prune tests
 prune pypots/*/template
+prune pypots/*/README.md

README.md

@@ -9,12 +9,14 @@
  <a href="https://docs.pypots.com/en/latest/install.html#reasons-of-version-limitations-on-dependencies">
  <img alt="Python version" src="https://img.shields.io/badge/Python-v3.7--3.10-E97040?logo=python&logoColor=white">
  </a>
- <img alt="powered by Pytorch" src="https://img.shields.io/badge/PyTorch-❤️-F8C6B5?logo=pytorch&logoColor=white">
- <a href="https://pypi.org/project/PyPOTS">
- <img alt="the latest release version" src="https://img.shields.io/github/v/release/wenjiedu/pypots?color=EE781F&include_prereleases&label=Release">
+ <a href="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/WenjieDu/PyPOTS">
+ <img alt="powered by Pytorch" src="https://img.shields.io/badge/PyTorch-❤️-F8C6B5?logo=pytorch&logoColor=white">
+ </a>
+ <a href="https://github.com/WenjieDu/PyPOTS/releases">
+ <img alt="the latest release version" src="https://img.shields.io/github/v/release/wenjiedu/pypots?color=EE781F&include_prereleases&label=Release&logo=github&logoColor=white">
  </a>
  <a href="https://github.com/WenjieDu/PyPOTS/blob/main/LICENSE">
- <img alt="GPL-v3 license" src="https://img.shields.io/badge/License-GPL--v3-E9BB41">
+ <img alt="GPL-v3 license" src="https://img.shields.io/badge/License-GPL--v3-E9BB41?logo=opensourceinitiative&logoColor=white">
  </a>
  <a href="https://github.com/WenjieDu/PyPOTS/blob/main/README.md#-community">
  <img alt="Community" src="https://img.shields.io/badge/join_us-community!-C8A062">
@@ -44,7 +46,7 @@
  <img alt="Conda downloads" src="https://img.shields.io/conda/dn/conda-forge/pypots?label=Conda%20Downloads&color=AED0ED&logo=anaconda&logoColor=white">
  </a>
  <a href="https://pepy.tech/project/pypots">
- <img alt="PyPI downloads" src="https://static.pepy.tech/personalized-badge/pypots?period=total&units=international_system&left_color=grey&right_color=blue&left_text=PyPI%20Downloads">
+ <img alt="PyPI downloads" src="https://img.shields.io/endpoint?url=https%3A%2F%2Fraw.githubusercontent.com%2FWenjieDu%2FWenjieDu%2Fmain%2Ffigs%2Fprojects%2Fpypots_downloads.json">
  </a>
 
 </p>

docs/index.rst

@@ -10,19 +10,21 @@ Welcome to PyPOTS docs!
  :target: https://github.com/WenjieDu/PyPOTS
  :alt: PyPOTS logo
 
-.. centered:: A Python Toolbox for Data Mining on Partially-Observed Time Series
+**A Python Toolbox for Data Mining on Partially-Observed Time Series**
 
 .. image:: https://img.shields.io/badge/Python-v3.7--3.10-E97040?logo=python&logoColor=white
  :alt: Python version
+ :target: https://docs.pypots.com/en/latest/install.html#reasons-of-version-limitations-on-dependencies
 
 .. image:: https://img.shields.io/badge/PyTorch-❤️-F8C6B5?logo=pytorch&logoColor=white
  :alt: powered by Pytorch
+ :target: https://github.com/WenjieDu/PyPOTS
 
-.. image:: https://img.shields.io/github/v/release/wenjiedu/pypots?color=EE781F&include_prereleases&label=Release
+.. image:: https://img.shields.io/github/v/release/wenjiedu/pypots?color=EE781F&include_prereleases&label=Release&logo=github&logoColor=white
  :alt: the latest release version
- :target: https://pypi.org/project/pypots
+ :target: https://github.com/WenjieDu/PyPOTS/releases
 
-.. image:: https://img.shields.io/badge/License-GPL--v3-E9BB41
+.. image:: https://img.shields.io/badge/License-GPL--v3-E9BB41?logo=opensourceinitiative&logoColor=white
  :alt: GPL-v3 license
  :target: https://github.com/WenjieDu/PyPOTS/blob/main/LICENSE
 
@@ -62,7 +64,7 @@ Welcome to PyPOTS docs!
  :alt: Conda downloads
  :target: https://anaconda.org/conda-forge/pypots
 
-.. image:: https://static.pepy.tech/personalized-badge/pypots?period=total&units=international_system&left_color=grey&right_color=blue&left_text=PyPI%20Downloads
+.. image:: https://img.shields.io/endpoint?url=https%3A%2F%2Fraw.githubusercontent.com%2FWenjieDu%2FWenjieDu%2Fmain%2Ffigs%2Fprojects%2Fpypots_downloads.json
  :alt: PyPI downloads
  :target: https://pepy.tech/project/pypots
 

docs/pypots.utils.rst

@@ -1,10 +1,10 @@
 pypots.utils package
 ====================
 
-pypots.utils.files module
+pypots.utils.file module
 -------------------------
 
-.. automodule:: pypots.utils.files
+.. automodule:: pypots.utils.file
  :members:
  :undoc-members:
  :show-inheritance:

pypots/data/__init__.py

@@ -22,6 +22,7 @@
  pickle_load,
  pickle_dump,
 )
+from .saving import save_dict_into_h5
 
 __all__ = [
  # datasets
@@ -39,4 +40,6 @@
  "mcar",
  "pickle_load",
  "pickle_dump",
+ # saving
+ "save_dict_into_h5",
 ]

pypots/data/saving.py

@@ -0,0 +1,43 @@
+"""
+Data saving utilities.
+"""
+
+# Created by Wenjie Du <[email protected]>
+# License: GLP-v3
+
+
+import os
+
+import h5py
+
+from pypots.utils.file import create_dir_if_not_exist
+from pypots.utils.logging import logger
+
+
+def save_dict_into_h5(data_dict: dict, saving_dir: str) -> None:
+ """Save the given data (in a dictionary) into the given h5 file.
+
+ Parameters
+ ----------
+ data_dict : dict,
+ The data to be saved, should be a Python dictionary.
+
+ saving_dir : str,
+ The h5 file to save the data.
+
+ """
+
+ def save_set(handle, name, data):
+ if isinstance(data, dict):
+ single_set_handle = handle.create_group(name)
+ for key, value in data.items():
+ save_set(single_set_handle, key, value)
+ else:
+ handle.create_dataset(name, data=data)
+
+ create_dir_if_not_exist(saving_dir)
+ saving_path = os.path.join(saving_dir, "datasets.h5")
+ with h5py.File(saving_path, "w") as hf:
+ for k, v in data_dict.items():
+ save_set(hf, k, v)
+ logger.info(f"Successfully saved the given data into {saving_path}.")

pypots/data/utils.py

@@ -192,3 +192,46 @@ def cal_delta_for_single_sample(mask: np.ndarray) -> np.ndarray:
  delta_collector.append(delta)
  delta = np.asarray(delta_collector)
  return delta
+
+
+def sliding_window(time_series, n_steps, sliding_len=None):
+ """Generate time series samples with sliding window method, truncating windows from time-series data
+ with a given sequence length.
+
+ Given a time series of shape [seq_len, n_features] (seq_len is the total sequence length of the time series), this
+ sliding_window function will generate time-series samples from this given time series with sliding window method.
+ The number of generated samples is seq_len//sliding_len. And the final returned numpy ndarray has a shape
+ [seq_len//sliding_len, n_steps, n_features].
+
+ Parameters
+ ----------
+ time_series : np.ndarray,
+ time series data, len(shape)=2, [total_length, feature_num]
+
+ n_steps : int,
+ The number of time steps in the generated data samples.
+
+ sliding_len : int, default = None,
+ The size of the sliding window. It will be set as the same with n_steps if None.
+
+ Returns
+ -------
+ samples : np.ndarray,
+ The generated time-series data samples of shape [seq_len//sliding_len, n_steps, n_features].
+
+ """
+ sliding_len = n_steps if sliding_len is None else sliding_len
+ total_len = time_series.shape[0]
+ start_indices = np.asarray(range(total_len // sliding_len)) * sliding_len
+
+ # remove the last one if left length is not enough
+ if total_len - start_indices[-1] * sliding_len < n_steps:
+ start_indices = start_indices[:-1]
+
+ sample_collector = []
+ for idx in start_indices:
+ sample_collector.append(time_series[idx : idx + n_steps])
+
+ samples = np.asarray(sample_collector).astype("float32")
+
+ return samples