Merge remote-tracking branch 'origin/main' into ag/similaritysearchupdate

Author: baraline

aeon/distances/_dft_sfa_mindist.py

@@ -45,7 +45,7 @@ def dft_sfa_mindist(
     >>> x = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
     >>> y = np.array([[11, 12, 13, 14, 15, 16, 17, 18, 19, 20]])
     >>> transform = SFAFast(
-    ...    word_length=16,
+    ...    word_length=8,
     ...    alphabet_size=8,
     ...    window_size=x.shape[-1],
     ...    norm=True,

aeon/distances/_paa_sax_mindist.py

@@ -45,7 +45,7 @@ def paa_sax_mindist(
     >>> from aeon.transformations.collection.dictionary_based import SAX
     >>> x = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
     >>> y = np.array([[11, 12, 13, 14, 15, 16, 17, 18, 19, 20]])
-    >>> transform = SAX(n_segments=16, alphabet_size=8)
+    >>> transform = SAX(n_segments=8, alphabet_size=8)
     >>> x_sax = transform.fit_transform(x).squeeze()
     >>> x_paa = transform._get_paa(x).squeeze()
     >>> y_sax = transform.transform(y).squeeze()

aeon/distances/_sax_mindist.py

@@ -43,7 +43,7 @@ def sax_mindist(x: np.ndarray, y: np.ndarray, breakpoints: np.ndarray, n: int) -
     >>> from aeon.transformations.collection.dictionary_based import SAX
     >>> x = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
     >>> y = np.array([[11, 12, 13, 14, 15, 16, 17, 18, 19, 20]])
-    >>> transform = SAX(n_segments=16, alphabet_size=8)
+    >>> transform = SAX(n_segments=8, alphabet_size=8)
     >>> x_sax = transform.fit_transform(x).squeeze()
     >>> y_sax = transform.transform(y).squeeze()
     >>> dist = paa_sax_mindist(x_sax, y_sax, transform.breakpoints, x.shape[-1])

aeon/distances/_sfa_mindist.py

@@ -43,7 +43,7 @@ def sfa_mindist(x: np.ndarray, y: np.ndarray, breakpoints: np.ndarray) -> float:
     >>> x = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]])
     >>> y = np.array([[11, 12, 13, 14, 15, 16, 17, 18, 19, 20]])
     >>> transform = SFAFast(
-    ...    word_length=16,
+    ...    word_length=8,
     ...    alphabet_size=8,
     ...    window_size=x.shape[-1],
     ...    norm=True,

aeon/transformations/collection/dictionary_based/_sfa_fast.py

@@ -242,6 +242,13 @@ def _fit_transform(self, X, y=None):
 
         offset = 2 if self.norm else 0
         self.word_length_actual = min(self.window_size - offset, self.word_length)
+
+        if self.word_length > X.shape[-1] and self.word_length_actual > X.shape[-1]:
+            raise ValueError(
+                "Please set the word-length to a value smaller than or equal to "
+                "the time series length and window-length."
+            )
+
         self.dft_length = (
             self.window_size - offset
             if (self.anova or self.variance) is True