sklearn tests and tags rework (#7)

* actually change python version

* dummy classifiers and sklearn lower bound change

* test fix

* test fix

* dev

* early sklearn version fixes

* all interval classifiers

* dummy and conversion bugfix

* version

* test

* testing update

* version

* pandas

* stop all workflows failing

* copy check

Author: MatthewMiddlehurst

.github/workflows/tests.yml

@@ -30,6 +30,7 @@ jobs:
     runs-on: ${{ matrix.os }}
 
     strategy:
+      fail-fast: false
       matrix:
         os: [ ubuntu-latest, macOS-latest, windows-latest ]
         python-version: [ '3.8', '3.9', '3.10' ]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tsml"
-version = "0.0.6"
+version = "0.0.7"
 description = "A toolkit for time series machine learning algorithms."
 authors = [
     {name = "Matthew Middlehurst", email = "m.middlehurst@uea.ac.uk"},
@@ -38,6 +38,7 @@ dependencies = [
     "numba>=0.55",
     "numpy>=1.21.0",
     "scikit-learn>=1.0.2",
+    "pandas",
 ]
 
 [project.optional-dependencies]

tsml/__init__.py

@@ -1,4 +1,4 @@
 # -*- coding: utf-8 -*-
 """tsml."""
 
-__version__ = "0.0.6"
+__version__ = "0.0.7"

tsml/dummy/_dummy.py

@@ -10,7 +10,7 @@
 from sklearn.dummy import DummyRegressor as SklearnDummyRegressor
 from sklearn.utils import check_random_state
 from sklearn.utils.multiclass import check_classification_targets
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import _num_samples, check_is_fitted
 
 from tsml.base import BaseTimeSeriesEstimator
 
@@ -85,65 +85,77 @@ class prior probabilities.
     0.5
     """
 
-    def __init__(self, strategy="prior", random_state=None, constant=None):
+    def __init__(
+        self, strategy="prior", validate=False, random_state=None, constant=None
+    ):
         self.strategy = strategy
+        self.validate = validate
         self.random_state = random_state
         self.constant = constant
 
         super(DummyClassifier, self).__init__()
 
     def fit(self, X, y):
         """"""
-        X, y = self._validate_data(X=X, y=y, ensure_min_series_length=1)
+        if self.validate:
+            X, y = self._validate_data(X=X, y=y, ensure_min_series_length=1)
 
-        check_classification_targets(y)
+            check_classification_targets(y)
 
-        self.classes_ = np.unique(y)
-        self.n_classes_ = self.classes_.shape[0]
-        self.class_dictionary_ = {}
-        for index, classVal in enumerate(self.classes_):
-            self.class_dictionary_[classVal] = index
+        self.classes_ = np.unique(np.asarray(y))
 
-        if self.n_classes_ == 1:
-            return self
+        if self.validate:
+            self.n_classes_ = self.classes_.shape[0]
+            self.class_dictionary_ = {}
+            for index, classVal in enumerate(self.classes_):
+                self.class_dictionary_[classVal] = index
 
-        self._clf = SklearnDummyClassifier(
+            if self.n_classes_ == 1:
+                return self
+
+        self.clf_ = SklearnDummyClassifier(
             strategy=self.strategy,
             random_state=self.random_state,
             constant=self.constant,
         )
-        self._clf.fit(None, y)
+        self.clf_.fit(None, y)
 
         return self
 
     def predict(self, X) -> np.ndarray:
         """"""
         check_is_fitted(self)
 
-        X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
+        if self.validate:
+            # treat case of single class seen in fit
+            if self.n_classes_ == 1:
+                return np.repeat(
+                    list(self.class_dictionary_.keys()), X.shape[0], axis=0
+                )
 
-        # treat case of single class seen in fit
-        if self.n_classes_ == 1:
-            return np.repeat(list(self.class_dictionary_.keys()), X.shape[0], axis=0)
+            X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
 
-        return self._clf.predict(np.zeros(X.shape))
+        return self.clf_.predict(np.zeros((_num_samples(X), 2)))
 
     def predict_proba(self, X) -> np.ndarray:
         """"""
         check_is_fitted(self)
 
-        # treat case of single class seen in fit
-        if self.n_classes_ == 1:
-            return np.repeat([[1]], X.shape[0], axis=0)
+        if self.validate:
+            # treat case of single class seen in fit
+            if self.n_classes_ == 1:
+                return np.repeat([[1]], X.shape[0], axis=0)
 
-        X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
+            X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
 
-        return self._clf.predict_proba(np.zeros(X.shape))
+        return self.clf_.predict_proba(np.zeros((_num_samples(X), 2)))
 
     def _more_tags(self):
         return {
             "X_types": ["3darray", "2darray", "np_list"],
             "equal_length_only": False,
+            "no_validation": not self.validate,
+            "allow_nan": True,
         }
 
 
@@ -199,36 +211,41 @@ class DummyRegressor(RegressorMixin, BaseTimeSeriesEstimator):
     -0.07184048625633688
     """
 
-    def __init__(self, strategy="mean", constant=None, quantile=None):
+    def __init__(self, strategy="mean", validate=False, constant=None, quantile=None):
         self.strategy = strategy
+        self.validate = validate
         self.constant = constant
         self.quantile = quantile
 
         super(DummyRegressor, self).__init__()
 
     def fit(self, X, y):
         """"""
-        _, y = self._validate_data(X=X, y=y, ensure_min_series_length=1)
+        if self.validate:
+            _, y = self._validate_data(X=X, y=y, ensure_min_series_length=1)
 
-        self._reg = SklearnDummyRegressor(
+        self.reg_ = SklearnDummyRegressor(
             strategy=self.strategy, constant=self.constant, quantile=self.quantile
         )
-        self._reg.fit(None, y)
+        self.reg_.fit(None, y)
 
         return self
 
     def predict(self, X):
         """"""
         check_is_fitted(self)
 
-        X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
+        if self.validate:
+            X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
 
-        return self._reg.predict(np.zeros(X.shape))
+        return self.reg_.predict(np.zeros((_num_samples(X), 2)))
 
     def _more_tags(self):
         return {
             "X_types": ["3darray", "2darray", "np_list"],
             "equal_length_only": False,
+            "no_validation": not self.validate,
+            "allow_nan": True,
         }
 
 
@@ -257,16 +274,20 @@ class DummyClusterer(ClusterMixin, BaseTimeSeriesEstimator):
     0.2087729039422543
     """
 
-    def __init__(self, strategy="single", n_clusters=2, random_state=None):
+    def __init__(
+        self, strategy="single", validate=False, n_clusters=2, random_state=None
+    ):
         self.strategy = strategy
+        self.validate = validate
         self.n_clusters = n_clusters
         self.random_state = random_state
 
         super(DummyClusterer, self).__init__()
 
     def fit(self, X, y=None):
         """"""
-        X = self._validate_data(X=X, ensure_min_series_length=1)
+        if self.validate:
+            X = self._validate_data(X=X, ensure_min_series_length=1)
 
         if self.strategy == "single":
             self.labels_ = np.zeros(len(X), dtype=np.int32)
@@ -284,20 +305,23 @@ def predict(self, X):
         """"""
         check_is_fitted(self)
 
-        X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
+        if self.validate:
+            X = self._validate_data(X=X, reset=False, ensure_min_series_length=1)
 
         if self.strategy == "single":
-            return np.zeros(len(X), dtype=np.int32)
+            return np.zeros(_num_samples(X), dtype=np.int32)
         elif self.strategy == "unique":
-            return np.arange(len(X), dtype=np.int32)
+            return np.arange(_num_samples(X), dtype=np.int32)
         elif self.strategy == "random":
             rng = check_random_state(self.random_state)
-            return rng.randint(self.n_clusters, size=len(X), dtype=np.int32)
+            return rng.randint(self.n_clusters, size=_num_samples(X), dtype=np.int32)
         else:
             raise ValueError(f"Unknown strategy {self.strategy}")
 
     def _more_tags(self):
         return {
             "X_types": ["3darray", "2darray", "np_list"],
             "equal_length_only": False,
+            "no_validation": not self.validate,
+            "allow_nan": True,
         }

tsml/interval_based/_base.py

@@ -214,6 +214,8 @@ def fit(self, X, y):
         X, y = self._validate_data(X=X, y=y, ensure_min_samples=2)
         X = self._convert_X(X)
 
+        rng = check_random_state(self.random_state)
+
         self.n_instances_, self.n_dims_, self.series_length_ = X.shape
         if is_classifier(self):
             check_classification_targets(y)
@@ -260,9 +262,7 @@ def fit(self, X, y):
             self._series_transformers = [None]
         # clone series_transformers if it is a transformer and transform the input data
         elif is_transformer(self.series_transformers):
-            t = _clone_estimator(
-                self.series_transformers, random_state=self.random_state
-            )
+            t = _clone_estimator(self.series_transformers, random_state=rng)
             Xt = [t.fit_transform(X, y)]
             self._series_transformers = [t]
         # clone each series_transformers transformer and include the base series if None
@@ -276,7 +276,7 @@ def fit(self, X, y):
                     Xt.append(X)
                     self._series_transformers.append(None)
                 elif is_transformer(transformer):
-                    t = _clone_estimator(transformer, random_state=self.random_state)
+                    t = _clone_estimator(transformer, random_state=rng)
                     Xt.append(t.fit_transform(X, y))
                     self._series_transformers.append(t)
                 else:
@@ -458,7 +458,8 @@ def fit(self, X, y):
         # single transformer or function for all series_transformers
         if is_transformer(self.interval_features):
             self._interval_transformer = [True] * len(Xt)
-            self._interval_features = [[self.interval_features]] * len(Xt)
+            transformer = _clone_estimator(self.interval_features, random_state=rng)
+            self._interval_features = [[transformer]] * len(Xt)
         elif callable(self.interval_features):
             self._interval_function = [True] * len(Xt)
             self._interval_features = [[self.interval_features]] * len(Xt)
@@ -491,6 +492,7 @@ def fit(self, X, y):
                         for method in feature:
                             if is_transformer(method):
                                 self._interval_transformer[i] = True
+                                feature = _clone_estimator(feature, random_state=rng)
                             elif callable(method):
                                 self._interval_function[i] = True
                             else:
@@ -503,6 +505,7 @@ def fit(self, X, y):
                         self._interval_features.append(feature)
                     elif is_transformer(feature):
                         self._interval_transformer[i] = True
+                        feature = _clone_estimator(feature, random_state=rng)
                         self._interval_features.append([feature])
                     elif callable(feature):
                         self._interval_function[i] = True
@@ -1030,4 +1033,3 @@ def _predict_for_estimator(self, Xt, estimator, intervals, predict_proba=False):
             return estimator.predict_proba(interval_features)
         else:
             return estimator.predict(interval_features)
-

tsml/interval_based/_interval_pipelines.py

@@ -99,6 +99,7 @@ def fit(self, X, y):
         X, y = self._validate_data(
             X=X, y=y, ensure_min_samples=2, ensure_min_series_length=3
         )
+        X = self._convert_X(X)
 
         self.n_instances_, self.n_dims_, self.series_length_ = X.shape
         self.classes_ = np.unique(y)
@@ -152,6 +153,7 @@ def predict(self, X) -> np.ndarray:
         check_is_fitted(self)
 
         X = self._validate_data(X=X, reset=False, ensure_min_series_length=3)
+        X = self._convert_X(X)
 
         return self._estimator.predict(self._transformer.transform(X))
 
@@ -171,6 +173,7 @@ def predict_proba(self, X) -> np.ndarray:
         check_is_fitted(self)
 
         X = self._validate_data(X=X, reset=False, ensure_min_series_length=3)
+        X = self._convert_X(X)
 
         m = getattr(self._estimator, "predict_proba", None)
         if callable(m):
@@ -311,6 +314,7 @@ def fit(self, X, y):
         X, y = self._validate_data(
             X=X, y=y, ensure_min_samples=2, ensure_min_series_length=3
         )
+        X = self._convert_X(X)
 
         self.n_instances_, self.n_dims_, self.series_length_ = X.shape
 
@@ -359,6 +363,7 @@ def predict(self, X) -> np.ndarray:
         check_is_fitted(self)
 
         X = self._validate_data(X=X, reset=False, ensure_min_series_length=3)
+        X = self._convert_X(X)
 
         return self._estimator.predict(self._transformer.transform(X))
 
@@ -489,6 +494,7 @@ def fit(self, X, y):
         X, y = self._validate_data(
             X=X, y=y, ensure_min_samples=2, ensure_min_series_length=7
         )
+        X = self._convert_X(X)
 
         self.n_instances_, self.n_dims_, self.series_length_ = X.shape
         self.classes_ = np.unique(y)
@@ -542,6 +548,7 @@ def predict(self, X) -> np.ndarray:
         check_is_fitted(self)
 
         X = self._validate_data(X=X, reset=False, ensure_min_series_length=7)
+        X = self._convert_X(X)
 
         return self._estimator.predict(self._transformer.transform(X))
 
@@ -561,6 +568,7 @@ def predict_proba(self, X) -> np.ndarray:
         check_is_fitted(self)
 
         X = self._validate_data(X=X, reset=False, ensure_min_series_length=7)
+        X = self._convert_X(X)
 
         m = getattr(self._estimator, "predict_proba", None)
         if callable(m):