[ENH] SFA testing

aeon/distances/_dft_sfa_mindist.py

@@ -49,7 +49,7 @@ def dft_sfa_mindist(
     ...    alphabet_size=8,
     ...    window_size=x.shape[-1],
     ...    norm=True,
-    ...    lower_bounding_distances=True   # This must be set!
+    ...    lower_bounding=True   # This must be set!
     ... )
     >>> transform.fit(x)
     SFAFast(...)

aeon/distances/_sfa_mindist.py

@@ -47,7 +47,7 @@ def sfa_mindist(x: np.ndarray, y: np.ndarray, breakpoints: np.ndarray) -> float:
     ...    alphabet_size=8,
     ...    window_size=x.shape[-1],
     ...    norm=True,
-    ...    lower_bounding_distances=True   # This must be set!
+    ...    lower_bounding=True   # This must be set!
     ... )
     >>> transform.fit(x)
     SFAFast(...)

aeon/distances/tests/test_symbolic_mindist.py

@@ -70,7 +70,7 @@ def test_sfa_mindist():
         binning_method=histogram_type,
         norm=True,
         variance=True,
-        lower_bounding_distances=True,  # This must be set!
+        lower_bounding=True,  # This must be set!
     )
 
     sfa_old = SFA(
@@ -79,7 +79,7 @@ def test_sfa_mindist():
         window_size=X_train.shape[-1],
         binning_method=histogram_type,
         norm=True,
-        lower_bounding_distances=True,  # This must be set!
+        lower_bounding=True,  # This must be set!
     )
     transforms = [sfa_old, sfa_fast]
 

aeon/transformations/collection/dictionary_based/_sfa.py

@@ -3,7 +3,7 @@
 Configurable SFA transform for discretising time series into words.
 """
 
-__maintainer__ = []
+__maintainer__ = ["patrickzib", "MatthewMiddlehurst"]
 __all__ = ["SFA"]
 
 import math
@@ -21,13 +21,14 @@
 
 from aeon.transformations.collection import BaseCollectionTransformer
 
-# The binning methods to use: equi-depth, equi-width, information gain or kmeans
+# The binning methods to use
 binning_methods = {
     "equi-depth",
     "equi-width",
     "information-gain",
     "information-gain-mae",
     "kmeans",
+    "quantile",
 }
 
 
@@ -40,47 +41,42 @@ class SFA(BaseCollectionTransformer):
             shorten the series with DFT
             discretise the shortened series into bins set by MFC
             form a word from these discrete values
-    by default SFA produces a single word per series (window_size=0)
-    if a window is used, it forms a histogram of counts of words.
+    SFA returns a dictionary of word counts for each series
+
+    This is a slower but more flexible version of the SFA transform, which can store
+    greater than 64 bit words. This is at the cost of efficiency, however.
 
     Parameters
     ----------
-    word_length:         int, default = 8
-        length of word to shorten window to (using DFT)
-
-    alphabet_size:       int, default = 4
-        number of values to discretise each value to
-
-    window_size:         int, default = 12
-        size of window for sliding. Input series
-        length for whole series transform
-
-    norm:                boolean, default = False
-        mean normalise words by dropping first fourier coefficient
-
-    binning_method:      {"equi-depth", "equi-width", "information-gain",
-        "information-gain-mae", "kmeans"}, default="equi-depth"
-        the binning method used to derive the breakpoints.
-
-    anova:               boolean, default = False
-        If True, the Fourier coefficient selection is done via a one-way
-        ANOVA test. If False, the first Fourier coefficients are selected.
-        Only applicable if labels are given
-
-    bigrams:             boolean, default = False
-        whether to create bigrams of SFA words
-
-    skip_grams:          boolean, default = False
-        whether to create skip-grams of SFA words
-
-    remove_repeat_words: boolean, default = False
-        whether to use numerosity reduction (default False)
+    word_length : int, default=8
+        Length of word to shorten window to (using PAA).
+    alphabet_size : int, default=4
+        Number of values to discretise each value to.
+    window_size : int, default=12
+        Size of window for sliding. Input series length for whole series transform.
+    norm : boolean, default=False
+        Mean normalise words by dropping first fourier coefficient.
+    binning_method : str, default="equi-depth"
+        The binning method used to derive the breakpoints. One of {"equi-depth",
+        "equi-width", "information-gain", "information-gain-mae", "kmeans",
+        "quantile"}.
+    anova : boolean, default=False
+        If True, the Fourier coefficient selection is done via a one-way ANOVA test.
+        If False, the first Fourier coefficients are selected. Only applicable if
+        labels are given.
+    bigrams : boolean, default=False
+        Whether to create bigrams of SFA words.
+    skip_grams : boolean, default=False
+        Whether to create skip-grams of SFA words.
+    levels: int, default=1
+        Number of spatial pyramid levels
+    remove_repeat_words : boolean, default=False
+       Whether to use numerosity reduction.
 
     lower_bounding_distances : boolean, default = None
         If set to True, the FFT is normed to allow for ED lower bounding.
 
-    levels:              int, default = 1
-        Number of spatial pyramid levels
+
 
     save_words:          boolean, default = False
         whether to save the words generated for each series (default False)
@@ -123,10 +119,9 @@ def __init__(
         anova=False,
         bigrams=False,
         skip_grams=False,
-        remove_repeat_words=False,
         levels=1,
+        remove_repeat_words=False,
         lower_bounding=True,
-        lower_bounding_distances=None,
         save_words=False,
         keep_binning_dft=False,
         use_fallback_dft=False,
@@ -151,13 +146,8 @@ def __init__(
 
         self.norm = norm
         self.lower_bounding = lower_bounding
-        self.lower_bounding_distances = lower_bounding_distances
 
-        self.inverse_sqrt_win_size = (
-            1.0 / math.sqrt(window_size)
-            if (not lower_bounding or lower_bounding_distances)
-            else 1.0
-        )
+        self.inverse_sqrt_win_size = 1.0 / math.sqrt(window_size)
 
         self.remove_repeat_words = remove_repeat_words
 
@@ -626,7 +616,7 @@ def _binning_dft(self, series, num_windows_per_inst):
                     self.dft_length,
                     self.norm,
                     self.inverse_sqrt_win_size,
-                    self.lower_bounding or self.lower_bounding_distances,
+                    self.lower_bounding,
                 )
                 if self._use_fallback_dft
                 else self._fast_fourier_transform(row)
@@ -664,7 +654,7 @@ def _fast_fourier_transform(self, series):
         dft = np.empty((length,), dtype=reals.dtype)
         dft[0::2] = reals[: np.uint32(length / 2)]
         dft[1::2] = imags[: np.uint32(length / 2)]
-        if self.lower_bounding or self.lower_bounding_distances:
+        if self.lower_bounding:
             dft[1::2] = dft[1::2] * -1  # lower bounding
         dft *= self.inverse_sqrt_win_size / std
         return dft[start:]
@@ -741,7 +731,7 @@ def _mft(self, series):
                 self.dft_length,
                 self.norm,
                 self.inverse_sqrt_win_size,
-                self.lower_bounding or self.lower_bounding_distances,
+                self.lower_bounding,
                 apply_normalising_factor=False,
                 cut_start_if_norm=False,
             )