Deprecate functions for specific versions of Dynamic Time Warping

doc/_static/custom.css

@@ -10,6 +10,34 @@ div.topic ul{
   margin-top: -10px;
 }
 
+
+/* Properties for API changes */
+
+.deprecated {
+  color: rgba(190, 0, 0, 1);
+  background-color: rgba(255, 0, 0, 0.2);
+  border: 1px solid;
+  border-color: rgba(255, 0, 0, 1);
+  padding: 8px 8px 0px 8px;
+  border-radius: 5px;
+  margin-bottom: 8px;
+}
+
+.deprecated p span.versionmodified {
+    font-weight: bold;
+}
+
+.deprecated p a code {
+  background-color: transparent;
+  border-bottom: none;
+}
+
+.deprecated span.pre {
+  background-color: transparent;
+  border-bottom: none;
+}
+
+
 /* Properties for hyperlinks */
 
 a.reference {
@@ -153,6 +181,31 @@ div.body dl.function dt[id^="pyts"] {
   margin-bottom: 15px;
 }
 
+div[id^="dtw-method"] table.docutils dl dt {
+  border-radius: 0px !important;
+  padding: 0px !important;
+  background-color: transparent !important;
+  margin-top: 0px !important;
+  margin-bottom: 0px !important;
+}
+
+
+div[id^="dtw-method"] dl.function dt {
+  border-radius: 5px;
+  padding: 10px;
+  background-color: rgba(47, 47, 47, 0.08);
+  margin-top: 0px;
+  margin-bottom: 15px;
+}
+
+
+/* Properties for rubric in autodoc */
+
+p.rubric {
+  font-size: 18px;
+  margin-bottom: 4px;
+}
+
 
 /* Properties for code blocks in Examples section of an object */
 
@@ -170,6 +223,10 @@ div.highlight pre {
 
 /* Properties for tables */
 
+table.docutils.citation {
+  margin: 0px !important;
+}
+
 table.docutils col.field-name {
   background-color: rgba(47, 79, 79, 0.1);
 }
@@ -265,3 +322,20 @@ div.sphx-glr-download-link-note.admonition.note p.admonition-title {
   font-weight: 900;
   color: rgba(47, 79, 79, 1);
 }
+
+/* Properties for See also blocks */
+
+div.admonition.seealso {
+  background-color: rgba(226, 237, 33, 0.4);
+  border-radius: 4px;
+  padding: 10px;
+}
+
+div.admonition.seealso p.first.admonition-title{
+  font-size: 14px;
+  font-weight: bold;
+}
+
+div.admonition.seealso code {
+  background-color: transparent;
+}

doc/conf.py

@@ -30,13 +30,16 @@
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
+sys.path.insert(0, os.path.abspath(os.path.dirname(__file__)))
+
 extensions = [
     'sphinx.ext.autodoc',
     'sphinx.ext.autosummary',
     'sphinx.ext.doctest',
     'sphinx.ext.intersphinx',
     'sphinx.ext.viewcode',
     'numpydoc',
+    'pytsdtwdoc',
     'sphinx_gallery.gen_gallery',
 ]
 

doc/metrics.dtw-classic.rst

@@ -0,0 +1,10 @@
+:orphan:
+
+.. _metrics.dtw-classic:
+
+dtw(method='classic')
+---------------------
+
+.. pyts-metrics:function:: pyts.metrics.dtw
+   :impl: pyts.metrics.dtw._dtw_classic
+   :method: classic

doc/metrics.dtw-fast.rst

@@ -0,0 +1,10 @@
+:orphan:
+
+.. _metrics.dtw-fast:
+
+dtw(method='fast')
+------------------
+
+.. pyts-metrics:function:: pyts.metrics.dtw
+   :impl: pyts.metrics.dtw._dtw_fast
+   :method: fast

doc/metrics.dtw-itakura.rst

@@ -0,0 +1,10 @@
+:orphan:
+
+.. _metrics.dtw-itakura:
+
+dtw(method='itakura')
+---------------------
+
+.. pyts-metrics:function:: pyts.metrics.dtw
+   :impl: pyts.metrics.dtw._dtw_itakura
+   :method: itakura

doc/metrics.dtw-multiscale.rst

@@ -0,0 +1,10 @@
+:orphan:
+
+.. _metrics.dtw-multiscale:
+
+dtw(method='multiscale')
+------------------------
+
+.. pyts-metrics:function:: pyts.metrics.dtw
+   :impl: pyts.metrics.dtw._dtw_multiscale
+   :method: multiscale

doc/metrics.dtw-region.rst

@@ -0,0 +1,10 @@
+:orphan:
+
+.. _metrics.dtw-region:
+
+dtw(method='region')
+--------------------
+
+.. pyts-metrics:function:: pyts.metrics.dtw
+   :impl: pyts.metrics.dtw._dtw_region
+   :method: region

doc/metrics.dtw-sakoechiba.rst

@@ -0,0 +1,10 @@
+:orphan:
+
+.. _metrics.dtw-sakoechiba:
+
+dtw(method='sakoechiba')
+------------------------
+
+.. pyts-metrics:function:: pyts.metrics.dtw
+   :impl: pyts.metrics.dtw._dtw_sakoechiba
+   :method: sakoechiba

doc/modules/classification.rst

@@ -27,7 +27,7 @@ a good baseline for time series classification::
     >>> from pyts.datasets import load_gunpoint
     >>> X_train, X_test, y_train, y_test = load_gunpoint(return_X_y=True)
     >>> clf = KNeighborsClassifier(metric='dtw')
-    >>> clf.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> clf.fit(X_train, y_train)
     KNeighborsClassifier(...)
     >>> clf.score(X_test, y_test)
     0.91...
@@ -63,7 +63,7 @@ is the class yielding the highest cosine similarity.
     >>> from pyts.datasets import load_gunpoint
     >>> X_train, X_test, y_train, y_test = load_gunpoint(return_X_y=True)
     >>> clf = SAXVSM(window_size=34, sublinear_tf=False, use_idf=False)
-    >>> clf.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> clf.fit(X_train, y_train)
     SAXVSM(...)
     >>> clf.score(X_test, y_test)
     0.76
@@ -96,7 +96,7 @@ the words are generated with the :ref:`approximation_sfa` algorithm.
     >>> from pyts.datasets import load_gunpoint
     >>> X_train, X_test, y_train, y_test = load_gunpoint(return_X_y=True)
     >>> clf = BOSSVS(window_size=28)
-    >>> clf.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> clf.fit(X_train, y_train)
     BOSSVS(...)
     >>> clf.score(X_test, y_test)
     0.98

doc/modules/multivariate.rst

@@ -28,7 +28,7 @@ performed at prediction time.
     >>> from pyts.multivariate.classification import MultivariateClassifier
     >>> X_train, X_test, y_train, y_test = load_basic_motions(return_X_y=True)
     >>> clf = MultivariateClassifier(BOSSVS())
-    >>> clf.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> clf.fit(X_train, y_train)
     MultivariateClassifier(...)
     >>> clf.score(X_test, y_test)
     1.0

doc/modules/transformation.rst

@@ -134,11 +134,11 @@ corresponding words::
     >>> from pyts.transformation import BOSS
     >>> X_train, X_test, _, _ = load_gunpoint(return_X_y=True)
     >>> boss = BOSS(word_size=2, n_bins=2, sparse=False)
-    >>> boss.fit(X_train) # doctest: +ELLIPSIS
+    >>> boss.fit(X_train)
     BOSS(...)
     >>> sorted(boss.vocabulary_.values())
     ['aa', 'ab', 'ba', 'bb']
-    >>> boss.transform(X_test) # doctest: +ELLIPSIS
+    >>> boss.transform(X_test)
     array(...)
 
 Classification can be performed with any standard classifier. In the example
@@ -153,7 +153,7 @@ below, we use a k-nearest neighbors classifier with the
     >>> boss = BOSS(word_size=8, window_size=40, norm_mean=True, drop_sum=True, sparse=False)
     >>> knn = KNeighborsClassifier(metric='boss')
     >>> clf = make_pipeline(boss, knn)
-    >>> clf.fit(X_train, y_train) # doctest: +ELLIPSIS
+    >>> clf.fit(X_train, y_train)
     Pipeline(...)
     >>> clf.score(X_test, y_test)
     1.0