feat: change default value of parameter normalized

xeofs/models/_base_model_cross_set.py

@@ -317,7 +317,7 @@ def transform(
         X, Y: DataObject | None
             Data to be transformed. At least one of them must be provided.
         normalized: bool, default=False
-            Whether to return normalized scores.
+            Whether to return L2 normalized scores.
 
         Returns
         -------

xeofs/models/_base_model_single_set.py

@@ -178,14 +178,14 @@ def _fit_algorithm(self, data: DataArray) -> Self:
         """
         raise NotImplementedError
 
-    def transform(self, data: DataObject, normalized=True) -> DataArray:
+    def transform(self, data: DataObject, normalized=False) -> DataArray:
         """Project data onto the components.
 
         Parameters
         ----------
         data: DataObject
             Data to be transformed.
-        normalized: bool, default=True
+        normalized: bool, default=False
             Whether to normalize the scores by the L2 norm.
 
         Returns
@@ -250,7 +250,7 @@ def fit_transform(
         return self.fit(data, dim, weights).transform(data, **kwargs)
 
     def inverse_transform(
-        self, scores: DataArray, normalized: bool = True
+        self, scores: DataArray, normalized: bool = False
     ) -> DataObject:
         """Reconstruct the original data from transformed data.
 
@@ -260,7 +260,7 @@ def inverse_transform(
             Transformed data to be reconstructed. This could be a subset
             of the `scores` data of a fitted model, or unseen data. Must
             have a 'mode' dimension.
-        normalized: bool, default=True
+        normalized: bool, default=False
             Whether the scores data have been normalized by the L2 norm.
 
         Returns
@@ -305,12 +305,23 @@ def _inverse_transform_algorithm(self, scores: DataArray) -> DataArray:
         """
         raise NotImplementedError
 
-    def components(self) -> DataObject:
-        """Get the components."""
+    def components(self, normalized: bool = True) -> DataObject:
+        """Get the components.
+
+        Parameters
+        ----------
+        normalized: bool, default=True
+            Whether to normalize the components by the L2 norm.
+
+        """
         components = self.data["components"]
+        if not normalized:
+            name = components.name
+            components = components * self.data["norms"]
+            components.name = name
         return self.preprocessor.inverse_transform_components(components)
 
-    def scores(self, normalized=True) -> DataArray:
+    def scores(self, normalized: bool = False) -> DataArray:
         """Get the scores.
 
         Parameters
@@ -320,8 +331,7 @@ def scores(self, normalized=True) -> DataArray:
         """
         scores = self.data["scores"].copy()
         if normalized:
-            attrs = scores.attrs.copy()
+            name = scores.name
             scores = scores / self.data["norms"]
-            scores.attrs.update(attrs)
-            scores.name = "scores"
+            scores.name = name
         return self.preprocessor.inverse_transform_scores(scores)

xeofs/models/cpcca_rotator.py

@@ -310,19 +310,19 @@ def transform(
         Y: DataObject | None = None,
         normalized: bool = False,
     ) -> DataArray | List[DataArray]:
-        """Project new "unseen" data onto the rotated singular vectors.
+        """Transform the data.
 
         Parameters
         ----------
-        X : DataObject
-            Data to be projected onto the rotated singular vectors of the first dataset.
-        Y : DataObject
-            Data to be projected onto the rotated singular vectors of the second dataset.
+        X, Y: DataObject | None
+            Data to be transformed. At least one of them must be provided.
+        normalized: bool, default=False
+            Whether to return L2 normalized scores.
 
         Returns
         -------
-        DataArray | List[DataArray]
-            Projected data.
+        Sequence[DataArray] | DataArray
+            Transformed data.
 
         """
         # raise error if no data is provided

xeofs/models/eof.py

@@ -156,21 +156,20 @@ def _inverse_transform_algorithm(self, scores: DataArray) -> DataArray:
 
         return reconstructed_data
 
-    def components(self) -> DataObject:
-        """Return the (EOF) components.
+    def components(self, normalized: bool = True) -> DataObject:
+        """Return the components.
 
-        The components in EOF anaylsis are the eigenvectors of the covariance/correlation matrix.
-        Other names include the principal components or EOFs.
+        The components are also refered to as eigenvectors, EOFs or loadings depending on the context.
 
         Returns
         -------
         components: DataArray | Dataset | List[DataArray]
             Components of the fitted model.
 
         """
-        return super().components()
+        return super().components(normalized=normalized)
 
-    def scores(self, normalized: bool = True) -> DataArray:
+    def scores(self, normalized: bool = False) -> DataArray:
         """Return the (PC) scores.
 
         The scores in EOF anaylsis are the projection of the data matrix onto the
@@ -341,7 +340,7 @@ def _fit_algorithm(self, X: DataArray) -> Self:
 
         return super()._fit_algorithm(X)
 
-    def components_amplitude(self) -> DataObject:
+    def components_amplitude(self, normalized=True) -> DataObject:
         """Return the amplitude of the (EOF) components.
 
         The amplitude of the components are defined as
@@ -352,13 +351,22 @@ def components_amplitude(self) -> DataObject:
         where :math:`C_{ij}` is the :math:`i`-th entry of the :math:`j`-th component and
         :math:`|\\cdot|` denotes the absolute value.
 
+        Parameters
+        ----------
+        normalized : bool, default=True
+            Whether to normalize the components by the singular values
+
         Returns
         -------
         components_amplitude: DataArray | Dataset | List[DataArray]
             Amplitude of the components of the fitted model.
 
         """
         amplitudes = abs(self.data["components"])
+
+        if not normalized:
+            amplitudes = amplitudes * self.data["norms"]
+
         amplitudes.name = "components_amplitude"
         return self.preprocessor.inverse_transform_components(amplitudes)
 

xeofs/models/sparse_pca.py

@@ -297,7 +297,7 @@ def components(self) -> DataObject:
         """
         return super().components()
 
-    def scores(self, normalized: bool = True) -> DataArray:
+    def scores(self, normalized: bool = False) -> DataArray:
         """Return the component scores.
 
         The component scores :math:`U` are defined as the projection of the fitted
@@ -309,7 +309,7 @@ def scores(self, normalized: bool = True) -> DataArray:
 
         Parameters
         ----------
-        normalized : bool, default=True
+        normalized : bool, default=False
             Whether to normalize the scores by the L2 norm.
 
         Returns