More content and compatability for earlier sklearn versions (#4)

* actually change python version

* dummy classifiers and sklearn lower bound change

* test fix

* test fix

* dev

* early sklearn version fixes

Author: MatthewMiddlehurst

.github/workflows/release.yml

@@ -36,7 +36,7 @@ jobs:
           python -m pip install build
           python -m build
 
-      - name: Store built files
+      - name: Store build files
         uses: actions/upload-artifact@v3
         with:
           name: dist
@@ -73,10 +73,10 @@ jobs:
 
       - if: matrix.os == 'windows-latest'
         name: Windows install
-        run: python -m pip install "${env:WHEELNAME}[optional_dependencies,dev]"
+        run: python -m pip install "${env:WHEELNAME}[extras,dev]"
       - if: matrix.os != 'windows-latest'
         name: Unix install
-        run: python -m pip install "${{ env.WHEELNAME }}[optional_dependencies,dev]"
+        run: python -m pip install "${{ env.WHEELNAME }}[extras,dev]"
 
       - name: Tests
         run: python -m pytest

.github/workflows/tests.yml

@@ -18,8 +18,7 @@ jobs:
         with:
           python-version: "3.10"
 
-      - id: file_changes
-        uses: trilom/file-changes-action@v1.2.4
+      - uses: trilom/file-changes-action@v1.2.4
         with:
           output: " "
 
@@ -43,7 +42,7 @@ jobs:
           python-version: ${{ matrix.python-version }}
 
       - name: Install
-        run: python -m pip install .[dev,optional_dependencies]
+        run: python -m pip install .[dev,extras]
 
       - name: Tests
         run: python -m pytest
@@ -63,7 +62,7 @@ jobs:
         run: echo "NUMBA_DISABLE_JIT=1" >> $GITHUB_ENV
 
       - name: Install
-        run: python -m pip install .[dev,optional_dependencies]
+        run: python -m pip install .[dev,extras]
 
       - name: Tests
         run: python -m pytest --cov=tsml --cov-report=xml

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tsml"
-version = "0.0.3"
+version = "0.0.4"
 description = "A toolkit for time series machine learning algorithms."
 authors = [
     {name = "Matthew Middlehurst", email = "m.middlehurst@uea.ac.uk"},
@@ -41,8 +41,9 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-optional_dependencies = [
+extras = [
     "pycatch22",
+    "pyfftw"
 ]
 dev = [
     "pre-commit",

tsml/__init__.py

@@ -1,4 +1,4 @@
 # -*- coding: utf-8 -*-
 """tsml."""
 
-__version__ = "0.0.3"
+__version__ = "0.0.4"

tsml/base.py

@@ -7,6 +7,7 @@
     "_clone_estimator",
 ]
 
+from abc import ABCMeta
 from typing import List, Tuple, Union
 
 import numpy as np
@@ -19,7 +20,7 @@
 from tsml.utils.validation import _num_features, check_X, check_X_y
 
 
-class BaseTimeSeriesEstimator(BaseEstimator):
+class BaseTimeSeriesEstimator(BaseEstimator, metaclass=ABCMeta):
     """Base class for time series estimators in tsml."""
 
     def _validate_data(
@@ -40,7 +41,7 @@ def _validate_data(
 
         Parameters
         ----------
-        X : ndarray or list of ndarrays of shape (n_samples, n_dimensions, \
+        X : ndarray or list of ndarrays of shape (n_samples, n_channels, \
                 series_length), array-like, or 'no validation', default='no validation'
             The input samples. ideally a 3D numpy array or a list of 2D numpy
             arrays.
@@ -109,6 +110,67 @@ def _validate_data(
 
         return out
 
+    def _convert_X(
+        self, X: Union[np.ndarray, List[np.ndarray]], concatenate_channels: bool = False
+    ) -> Union[np.ndarray, List[np.ndarray]]:
+        dtypes = self._get_tags()["X_types"]
+
+        if isinstance(X, np.ndarray) and X.ndim == 3:
+            if "3darray" in dtypes:
+                return X
+            elif dtypes[0] == "2darray":
+                if X.shape[1] == 1 or concatenate_channels:
+                    return X.reshape((X.shape[0], -1))
+                else:
+                    raise ValueError(
+                        "Can only convert 3D numpy array with 1 channel to 2D numpy "
+                        f"array if concatenate_channels is True, found {X.shape[1]} "
+                        "channels."
+                    )
+            elif dtypes[0] == "np_list":
+                return [x for x in X]
+        elif isinstance(X, np.ndarray) and X.ndim == 2:
+            if "2darray" in dtypes:
+                return X
+            elif dtypes[0] == "3darray":
+                return X.reshape((X.shape[0], 1, -1))
+            elif dtypes[0] == "np_list":
+                return [x.reshape(1, X.shape[1]) for x in X]
+        elif isinstance(X, list) and all(
+            isinstance(x, np.ndarray) and x.ndim == 2 for x in X
+        ):
+            if "np_list" in dtypes:
+                return X
+            elif dtypes[0] == "3darray":
+                max_len = max(x.shape[1] for x in X)
+                arr = np.zeros((len(X), X[0].shape[0], max_len))
+
+                for i, x in enumerate(X):
+                    arr[i, :, : x.shape[1]] = x
+
+                return arr
+            elif dtypes[0] == "2darray":
+                if X[0].shape[0] == 1 or concatenate_channels:
+                    max_len = max(x.shape[1] for x in X)
+                    arr = np.zeros((len(X), X[0].shape[0], max_len))
+
+                    for i, x in enumerate(X):
+                        arr[i, :, : x.shape[1]] = x
+
+                    return arr.reshape((arr.shape[0], -1))
+                else:
+                    raise ValueError(
+                        "Can only convert list of 2D numpy arrays with 1 channel to 2D "
+                        "numpy array if concatenate_channels is True, found "
+                        f"{X[0].shape[0]} channels."
+                    )
+        else:
+            raise ValueError(
+                "X must be a 2D/3D numpy array or a list of 2D numpy arrays, got "
+                f"{f'list of {type(X[0])}' if isinstance(X, list) else type(X)} "
+                "instead."
+            )
+
     def _check_n_features(self, X: Union[np.ndarray, List[np.ndarray]], reset: bool):
         """Set the `n_features_in_` attribute, or check against it.
 
@@ -117,14 +179,14 @@ def _check_n_features(self, X: Union[np.ndarray, List[np.ndarray]], reset: bool)
         Parameters
         ----------
         X : ndarray or list of ndarrays of shape \
-                (n_samples, n_dimensions, series_length)
+                (n_samples, n_channels, series_length)
             The input samples. Should be a 3D numpy array or a list of 2D numpy
             arrays.
         reset : bool
             If True, the `n_features_in_` attribute is set to
-            `(n_dimensions, min_series_length, max_series_length)`.
+            `(n_channels, min_series_length, max_series_length)`.
             If False and the attribute exists, then check that it is equal to
-            `(n_dimensions, min_series_length, max_series_length)`.
+            `(n_channels, min_series_length, max_series_length)`.
             If False and the attribute does *not* exist, then the check is skipped.
             .. note::
                It is recommended to call reset=True in `fit`. All other methods that
@@ -137,7 +199,7 @@ def _check_n_features(self, X: Union[np.ndarray, List[np.ndarray]], reset: bool)
                 raise ValueError(
                     "X does not contain any features to extract, but "
                     f"{self.__class__.__name__} is expecting "
-                    f"{self.n_features_in_[0]} dimensions as input."
+                    f"{self.n_features_in_[0]} channels as input."
                 ) from e
             # If the number of features is not defined and reset=True,
             # then we skip this check
@@ -155,8 +217,8 @@ def _check_n_features(self, X: Union[np.ndarray, List[np.ndarray]], reset: bool)
 
         if n_features[0] != self.n_features_in_[0]:
             raise ValueError(
-                f"X has {n_features[0]} dimensions, but {self.__class__.__name__} "
-                f"is expecting {self.n_features_in_[0]} dimensions as input."
+                f"X has {n_features[0]} channels, but {self.__class__.__name__} "
+                f"is expecting {self.n_features_in_[0]} channels as input."
             )
 
         tags = _safe_tags(self)

tsml/datasets/_data_io.py

@@ -161,15 +161,15 @@ def load_from_ts_file(
                 if len(tokens) != 2:
                     raise IOError(
                         "Invalid .ts file. @dimension tag requires a int value "
-                        "(the number of dimensions for the problem)."
+                        "(the number of channels for the problem)."
                     )
 
                 try:
                     dimensions = int(tokens[1])
                 except ValueError:
                     raise IOError(
                         "Invalid .ts file. @dimension tag requires a int value "
-                        "(the number of dimensions for the problem)."
+                        "(the number of channels for the problem)."
                     )
 
                 dimensions_tag = True
@@ -194,15 +194,15 @@ def load_from_ts_file(
                 if len(tokens) != 2:
                     raise IOError(
                         "Invalid .ts file. @serieslength tag requires a int value "
-                        "(the number of dimensions for the problem)."
+                        "(the series length for the problem)."
                     )
 
                 try:
                     serieslength = int(tokens[1])
                 except ValueError:
                     raise IOError(
                         "Invalid .ts file. @serieslength tag requires a int value "
-                        "(the number of dimensions for the problem)."
+                        "(the series length for the problem)."
                     )
 
                 serieslength_tag = True
@@ -341,13 +341,13 @@ def load_from_ts_file(
             ) and data_dims > 1:
                 raise IOError(
                     "Value mismatch in .ts file. @univariate tag is missing or True "
-                    "but data has more than one dimension."
+                    "but data has more than one channel."
                 )
 
             if dimensions_tag and dimensions != data_dims:
                 raise IOError(
                     f"Value mismatch in .ts file. @dimensions tag value {dimensions} "
-                    f"and read number of dimensions {data_dims} do not match."
+                    f"and read number of channels {data_dims} do not match."
                 )
 
             if serieslength_tag and serieslength != data_length:
@@ -375,19 +375,19 @@ def load_from_ts_file(
 
             line = line.split(":")
 
-            # Does not support different number of dimensions
+            # Does not support different number of channels
             read_dims = len(line) - 1 if has_labels else len(line)
             if read_dims != data_dims:
                 raise IOError(
-                    "Unable to read .ts file. Inconsistent number of dimensions."
+                    "Unable to read .ts file. Inconsistent number of channels."
                     f"Expected {data_dims} but read {read_dims} on line {data_idx}."
                 )
 
             dimensions = line[:data_dims]
             if not equallength:
                 data_length = len(dimensions[0].strip().split(","))
 
-            # Process the data for each dimension
+            # Process the data for each channel
             series = np.zeros((data_dims, data_length), dtype=X_dtype)
             for i in range(data_dims):
                 series[i, :] = dimensions[i].strip().split(",")
@@ -500,7 +500,7 @@ def load_equal_minimal_japanese_vowels(
     stripped down version of the JapaneseVowels problem that is used in correctness
     tests for classification. It has been altered so all series are equal length. It
     loads a nine class classification problem with 20 cases for both the train and test
-    split, 12 dimensions and a series length of 25.
+    split, 12 channels and a series length of 25.
 
     For the full dataset see
     http://www.timeseriesclassification.com/description.php?Dataset=JapaneseVowels
@@ -534,7 +534,7 @@ def load_minimal_japanese_vowels(
     This is an unequal length multivariate time series classification problem. It is a
     stripped down version of the JapaneseVowels problem that is used in correctness
     tests for classification. It loads a nine class classification problem with 20 cases
-    for both the train and test split and 12 dimensions.
+    for both the train and test split and 12 channels.
 
     For the full dataset see
     http://www.timeseriesclassification.com/description.php?Dataset=JapaneseVowels