Skip to content

Commit

Permalink
Release of version 0.11.0 (#70)
Browse files Browse the repository at this point in the history
  • Loading branch information
johannfaouzi authored Mar 21, 2020
1 parent d871976 commit 5c07334
Show file tree
Hide file tree
Showing 6 changed files with 122 additions and 27 deletions.
8 changes: 7 additions & 1 deletion doc/changelog.rst
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,11 @@ Change Log
Version 0.11.0
--------------

- Add support for Python 3.8 and drop support for Python 3.5.

- Rework the *BagOfWords* algorithm to match the description of the algorithm
in the original paper.
in the original paper. The former version of *BagOfWords* is available
as *WordExtractor* in the :mod:`pyts.bag_of_words` module.

- Update the *SAXVSM* classifier with the new version of *BagOfWords*.

Expand All @@ -19,6 +22,9 @@ Version 0.11.0
- Add the *LearningShapelets* algorithm in the :mod:`pyts.classification`
module.

- Deprecated specific functions for Dynamic Time Warping (all ``dtw_*`` functions),
only the main :func:`pyts.metrics.dtw` is kept.


Version 0.10.0
--------------
Expand Down
2 changes: 1 addition & 1 deletion doc/conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@

# General information about the project.
project = u'pyts'
copyright = u'2017-2019, Johann Faouzi'
copyright = u'2017-2020, Johann Faouzi'

# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
Expand Down
133 changes: 111 additions & 22 deletions doc/reproducibility.rst
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ The metrics used are:
* Dynamic Time Warping (DTW), and
* Dynamic Time Warping with a learned warping window (DTW(w)).

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.10.0/KNN.ipynb>`__
`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/KNN.ipynb>`__

+------------------+---------------+-----------+----------------+------------+-------------------+----------------+
| Name | ED (reported) | ED (pyts) | DTW (reported) | DTW (pyts) | DTW(w) (reported) | DTW(w) (pyts) |
Expand All @@ -100,10 +100,32 @@ The metrics used are:
+------------------+---------------+-----------+----------------+------------+-------------------+----------------+


Bag-of-Patterns transformer followed by a 1NN classifier using Euclidean distance
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/Bag-of-Patterns.ipynb>`__

+------------------+----------------------------+------------------------+
| Name | Bag-of-Patterns (reported) | Bag-of-Patterns (pyts) |
+==================+============================+========================+
| Adiac | 0.5916 | 0.614 |
+------------------+----------------------------+------------------------+
| ECG200 | 0.7857 | 0.786 |
+------------------+----------------------------+------------------------+
| GunPoint | 0.9703 | 0.980 |
+------------------+----------------------------+------------------------+
| MiddlePhalanxTW | 0.4914 | 0.474 |
+------------------+----------------------------+------------------------+
| Plane | 0.9871 | 1.000 |
+------------------+----------------------------+------------------------+
| SyntheticControl | 0.9258 | 0.926 |
+------------------+----------------------------+------------------------+


BOSS transformer followed by a 1NN classifier using the BOSS metric
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.10.0/BOSS.ipynb>`__
`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/BOSS.ipynb>`__

+------------------+-----------------+-------------+
| Name | BOSS (reported) | BOSS (pyts) |
Expand All @@ -125,7 +147,7 @@ BOSS transformer followed by a 1NN classifier using the BOSS metric
BOSSVS classifier
^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.10.0/BOSSVS.ipynb>`__
`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/BOSSVS.ipynb>`__

+------------------+-------------------+---------------+
| Name | BOSSVS (reported) | BOSSVS (pyts) |
Expand All @@ -144,31 +166,76 @@ BOSSVS classifier
+------------------+-------------------+---------------+


WEASEL transformer followed by a logistic regression
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Learning-Shapelet classifier
^^^^^^^^^^^^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.10.0/WEASEL.ipynb>`__
`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/LearningShapelet.ipynb>`__

+------------------+------------------------------+--------------------------+
| Name | LearningShapelet (reported) | LearningShapelet (pyts) |
+==================+==============================+==========================+
| Adiac | 0.5274 | 0.527 |
+------------------+------------------------------+--------------------------+
| ECG200 | 0.8714 | 0.860 |
+------------------+------------------------------+--------------------------+
| GunPoint | 0.9826 | 0.987 |
+------------------+------------------------------+--------------------------+
| MiddlePhalanxTW | 0.5403 | 0.552 |
+------------------+------------------------------+--------------------------+
| Plane | 0.9948 | 0.990 |
+------------------+------------------------------+--------------------------+
| SyntheticControl | 0.9946 | 0.990 |
+------------------+------------------------------+--------------------------+


ROCKET transformer followed by a Ridge Classifier with built-in cross-validation
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/ROCKET.ipynb>`__

+------------------+------------------------------+--------------------------+
| Name | ROCKET (reported) | ROCKET (pyts) |
+==================+==============================+==========================+
| Adiac | 0.7847 | 0.785 |
+------------------+------------------------------+--------------------------+
| ECG200 | 0.9060 | 0.910 |
+------------------+------------------------------+--------------------------+
| GunPoint | 1.0000 | 1.000 |
+------------------+------------------------------+--------------------------+
| MiddlePhalanxTW | 0.5558 | 0.565 |
+------------------+------------------------------+--------------------------+
| Plane | 1.0000 | 1.000 |
+------------------+------------------------------+--------------------------+
| SyntheticControl | 0.8733 | 1.000 |
+------------------+------------------------------+--------------------------+


SAXVSM classifier
^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/SAXVSM.ipynb>`__

+------------------+------------------------------+--------------------------+
| Name | SAXVSM (reported) | SAXVSM (pyts) |
+==================+==============================+==========================+
| Adiac | 0.4574 | 0.458 |
+------------------+------------------------------+--------------------------+
| ECG200 | 0.8354 | 0.840 |
+------------------+------------------------------+--------------------------+
| GunPoint | 0.9930 | 0.993 |
+------------------+------------------------------+--------------------------+
| MiddlePhalanxTW | 0.5393 | 0.545 |
+------------------+------------------------------+--------------------------+
| Plane | 0.9799 | 0.981 |
+------------------+------------------------------+--------------------------+
| SyntheticControl | 0.8691 | 0.869 |
+------------------+------------------------------+--------------------------+

+------------------+-------------------+---------------+
| Name | WEASEL (reported) | WEASEL (pyts) |
+==================+===================+===============+
| Adiac | 0.8312 | 0.788 |
+------------------+-------------------+---------------+
| ECG200 | 0.8500 | 0.850 |
+------------------+-------------------+---------------+
| GunPoint | 1.0000 | 0.960 |
+------------------+-------------------+---------------+
| MiddlePhalanxTW | 0.5390 | 0.539 |
+------------------+-------------------+---------------+
| Plane | 1.0000 | 1.000 |
+------------------+-------------------+---------------+
| SyntheticControl | 0.9933 | 0.973 |
+------------------+-------------------+---------------+

ShapeletTransform transformer followed by a Support Vector Machine with a linear kernel
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.10.0/ShapeletTransform.ipynb>`__
`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/ShapeletTransform.ipynb>`__

+------------------+------------------------------+--------------------------+
| Name | ShapeletTransform (reported) | ShapeletTransform (pyts) |
Expand All @@ -185,3 +252,25 @@ ShapeletTransform transformer followed by a Support Vector Machine with a linear
+------------------+------------------------------+--------------------------+
| SyntheticControl | 0.8733 | 0.873 |
+------------------+------------------------------+--------------------------+


WEASEL transformer followed by a logistic regression
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

`Link to the notebook <https://github.com/johannfaouzi/pyts-repro/blob/master/0.11.0/WEASEL.ipynb>`__

+------------------+-------------------+---------------+
| Name | WEASEL (reported) | WEASEL (pyts) |
+==================+===================+===============+
| Adiac | 0.8312 | 0.788 |
+------------------+-------------------+---------------+
| ECG200 | 0.8500 | 0.850 |
+------------------+-------------------+---------------+
| GunPoint | 1.0000 | 0.960 |
+------------------+-------------------+---------------+
| MiddlePhalanxTW | 0.5390 | 0.539 |
+------------------+-------------------+---------------+
| Plane | 1.0000 | 1.000 |
+------------------+-------------------+---------------+
| SyntheticControl | 0.9933 | 0.973 |
+------------------+-------------------+---------------+
2 changes: 1 addition & 1 deletion pyts/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
several tools to perform these transformations.
"""

__version__ = '0.11.dev0'
__version__ = '0.11.0'

__all__ = ['approximation', 'bag_of_words', 'classification', 'datasets',
'decomposition', 'image', 'metrics', 'multivariate',
Expand Down
2 changes: 1 addition & 1 deletion pyts/bag_of_words/bow.py
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,7 @@ def __init__(self, window_size=0.5, word_size=0.5, n_bins=4,
warnings.warn("BagOfWords has been reworked in 0.11 in order to match "
"its definition in the literature. To get the old "
"BagOfWords, use pyts.bag_of_words.WordExtractor "
"instead.", UserWarning)
"instead.", FutureWarning)

def fit(self, X, y=None):
"""Pass.
Expand Down
2 changes: 1 addition & 1 deletion setup.cfg
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ addopts = --doctest-modules
filterwarnings =
ignore:the matrix subclass:PendingDeprecationWarning
ignore:Using or importing the ABCs from:DeprecationWarning
ignore:BagOfWords has been reworked in 0.11.*:UserWarning
ignore:BagOfWords has been reworked in 0.11.*:FutureWarning

[flake8]
# Default flake8 3.5 ignored flags
Expand Down

0 comments on commit 5c07334

Please sign in to comment.