chemotools 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

chemotools/{variable_selection/select_features.py → feature_selection/_index_selector.py}

@@ -1,11 +1,13 @@
 import numpy as np
-from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.base import BaseEstimator
+from sklearn.feature_selection._base import SelectorMixin
+
 from sklearn.utils.validation import check_is_fitted
 
 from chemotools.utils.check_inputs import check_input
 
 
-class SelectFeatures(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class IndexSelector(BaseEstimator, SelectorMixin):
     """
     A transformer that Selects the spectral data to a specified array of features. This
     array can be continuous or discontinuous. The array of features is specified by:
@@ -29,12 +31,6 @@ class SelectFeatures(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     features_index_ : int
         The index of the features to select.
 
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -52,7 +48,7 @@ class SelectFeatures(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         self.features = features
         self.wavenumbers = wavenumbers
 
-    def fit(self, X: np.ndarray, y=None) -> "SelectFeatures":
+    def fit(self, X: np.ndarray, y=None) -> "IndexSelector":
         """
         Fit the transformer to the input data.
 
@@ -66,14 +62,11 @@ class SelectFeatures(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
         Returns
         -------
-        self : SelectFeatures
+        self : IndexSelector
             The fitted transformer.
         """
-        # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
+        # validate that X is a 2D array and has only finite values
+        X = self._validate_data(X)
 
         # Set the fitted attribute to True
         self._is_fitted = True
@@ -91,41 +84,23 @@ class SelectFeatures(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
         return self
 
-    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+    def _get_support_mask(self):
         """
-        Transform the input data by cutting it to the specified range.
-
-        Parameters
-        ----------
-        X : array-like of shape (n_samples, n_features)
-            The input data to transform.
-
-        y : None
-            Ignored.
+        Get the boolean mask indicating which features are selected.
 
         Returns
         -------
-        X_ : np.ndarray of shape (n_samples, n_features)
-            The transformed data.
+        mask : ndarray of shape (n_features_in_,)
+            The mask indicating the selected features.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self)
 
-        # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-        X_ = X.copy()
-
-        # Check that the number of features is the same as the fitted data
-        if X_.shape[1] != self.n_features_in_:
-            raise ValueError(
-                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
-            )
-
-        # Select the features
-        if self.features is None:
-            return X_
+        # Create the mask
+        mask = np.zeros(self.n_features_in_, dtype=bool)
+        mask[self.features_index_] = True
 
-        return X_[:, self.features_index_]
+        return mask
 
     def _find_index(self, target: float) -> int:
         if self.wavenumbers is None:

chemotools/{variable_selection/range_cut.py → feature_selection/_range_cut.py}

@@ -1,13 +1,12 @@
 import numpy as np
-from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.base import BaseEstimator
+from sklearn.feature_selection._base import SelectorMixin
 from sklearn.utils.validation import check_is_fitted
 
-from chemotools.utils.check_inputs import check_input
 
-
-class RangeCut(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class RangeCut(BaseEstimator, SelectorMixin):
     """
-    A transformer that cuts the input data to a specified range. The range is specified:
+    A selector that cuts the input data to a specified range. The range is specified:
     - by the indices of the start and end of the range,
     - by the wavenumbers of the start and end of the range. In this case, the wavenumbers
         must be provided to the transformer when it is initialised. If the wavenumbers
@@ -35,19 +34,11 @@ class RangeCut(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     end_index_ : int
         The index of the end of the range. It is -1 if the wavenumbers are not provided.
 
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
 
     Methods
     -------
     fit(X, y=None)
         Fit the transformer to the input data.
-
-    transform(X, y=0, copy=True)
-        Transform the input data by cutting it to the specified range.
     """
 
     def __init__(
@@ -78,13 +69,7 @@ class RangeCut(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         # Set the start and end indices
         if self.wavenumbers is None:
@@ -95,39 +80,25 @@ class RangeCut(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             self.end_index_ = self._find_index(self.end)
 
         return self
+    
 
-    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+    def _get_support_mask(self):
         """
-        Transform the input data by cutting it to the specified range.
-
-        Parameters
-        ----------
-        X : array-like of shape (n_samples, n_features)
-            The input data to transform.
-
-        y : None
-            Ignored.
+        Get the boolean mask indicating which features are selected.
 
         Returns
         -------
-        X_ : np.ndarray of shape (n_samples, n_features)
-            The transformed data.
+        mask : np.ndarray of shape (n_features,)
+            The boolean mask indicating which features are selected.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
-
-        # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-        X_ = X.copy()
+        check_is_fitted(self, ["start_index_", "end_index_"])
 
-        # Check that the number of features is the same as the fitted data
-        if X_.shape[1] != self.n_features_in_:
-            raise ValueError(
-                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
-            )
+        # Create the mask
+        mask = np.zeros(self.n_features_in_, dtype=bool)
+        mask[self.start_index_ : self.end_index_] = True
 
-        # Range cut the spectra
-        return X_[:, self.start_index_ : self.end_index_]
+        return mask
 
     def _find_index(self, target: float) -> int:
         wavenumbers = np.array(self.wavenumbers)

chemotools/scale/__init__.py

@@ -1,3 +1,3 @@
-from .min_max_scaler import MinMaxScaler
-from .norm_scaler import NormScaler
-from .point_scaler import PointScaler
+from ._min_max_scaler import MinMaxScaler
+from ._norm_scaler import NormScaler
+from ._point_scaler import PointScaler

chemotools/scale/{min_max_scaler.py → _min_max_scaler.py}

@@ -8,23 +8,15 @@ from chemotools.utils.check_inputs import check_input
 class MinMaxScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     """
     A transformer that scales the input data by subtracting the minimum and dividing by
-    the difference between the maximum and the minimum. When the use_min parameter is False, 
+    the difference between the maximum and the minimum. When the use_min parameter is False,
     the data is scaled by the maximum.
 
     Parameters
     ----------
     use_min : bool, default=True
-        The normalization to use. If True, the data is subtracted by the minimum and 
+        The normalization to use. If True, the data is subtracted by the minimum and
         scaled by the maximum. If False, the data is scaled by the maximum.
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -55,13 +47,7 @@ class MinMaxScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         return self
 
@@ -83,7 +69,7 @@ class MinMaxScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)
@@ -97,8 +83,9 @@ class MinMaxScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
         # Normalize the data by the maximum value
         if self.use_min:
-            X_ = (X_ - np.min(X_, axis=1, keepdims=True)) / (np.max(
-                X_, axis=1, keepdims=True) - np.min(X_, axis=1, keepdims=True))
+            X_ = (X_ - np.min(X_, axis=1, keepdims=True)) / (
+                np.max(X_, axis=1, keepdims=True) - np.min(X_, axis=1, keepdims=True)
+            )
 
         else:
             X_ = X_ / np.max(X_, axis=1, keepdims=True)

chemotools/scale/{norm_scaler.py → _norm_scaler.py}

@@ -12,15 +12,7 @@ class NormScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     Parameters
     ----------
     l_norm : int, optional
-        The L-norm to use. Default is 2. 
-
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
+        The L-norm to use. Default is 2.
 
     Methods
     -------
@@ -30,13 +22,14 @@ class NormScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     transform(X, y=0, copy=True)
         Transform the input data by scaling by the L-norm.
     """
+
     def __init__(self, l_norm: int = 2):
         self.l_norm = l_norm
 
     def fit(self, X: np.ndarray, y=None) -> "NormScaler":
         """
         Fit the transformer to the input data.
-        
+
         Parameters
         ----------
         X : np.ndarray of shape (n_samples, n_features)
@@ -51,13 +44,7 @@ class NormScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         return self
 
@@ -79,7 +66,7 @@ class NormScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)

chemotools/scale/{point_scaler.py → _point_scaler.py}

@@ -7,12 +7,12 @@ from chemotools.utils.check_inputs import check_input
 
 class PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     """
-    A transformer that scales the input data by the intensity value at a given point. 
+    A transformer that scales the input data by the intensity value at a given point.
     The point can be specified by an index or by a wavenumber.
 
     Parameters
     ----------
-    point : int, 
+    point : int,
         The point to scale the data by. It can be an index or a wavenumber.
 
     wavenumber : array-like, optional
@@ -25,12 +25,6 @@ class PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     point_index_ : int
         The index of the point to scale the data by. It is 0 if the wavenumbers are not provided.
 
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -39,11 +33,11 @@ class PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     transform(X, y=0, copy=True)
         Transform the input data by scaling by the value at a given Point.
     """
+
     def __init__(self, point: int = 0, wavenumbers: np.ndarray = None):
         self.point = point
         self.wavenumbers = wavenumbers
 
-
     def fit(self, X: np.ndarray, y=None) -> "PointScaler":
         """
         Fit the transformer to the input data.
@@ -62,13 +56,7 @@ class PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         # Set the point index
         if self.wavenumbers is None:
@@ -76,7 +64,6 @@ class PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         else:
             self.point_index_ = self._find_index(self.point)
 
-
         return self
 
     def transform(self, X: np.ndarray, y=None) -> np.ndarray:
@@ -97,7 +84,7 @@ class PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "point_index_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)
@@ -105,14 +92,16 @@ class PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
         # Check that the number of features is the same as the fitted data
         if X_.shape[1] != self.n_features_in_:
-            raise ValueError(f"Expected {self.n_features_in_} features but got {X_.shape[1]}")
+            raise ValueError(
+                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
+            )
 
         # Scale the data by Point
         for i, x in enumerate(X_):
             X_[i] = x / x[self.point_index_]
-        
+
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
-    
+
     def _find_index(self, target: float) -> int:
         wavenumbers = np.array(self.wavenumbers)
-        return np.argmin(np.abs(wavenumbers - target))
+        return np.argmin(np.abs(wavenumbers - target))

chemotools/scatter/__init__.py

@@ -1,4 +1,4 @@
-from .extended_multiplicative_scatter_correction import ExtendedMultiplicativeScatterCorrection
-from .multiplicative_scatter_correction import MultiplicativeScatterCorrection
-from .robust_normal_variate import RobustNormalVariate
-from .standard_normal_variate import StandardNormalVariate
+from ._extended_multiplicative_scatter_correction import ExtendedMultiplicativeScatterCorrection
+from ._multiplicative_scatter_correction import MultiplicativeScatterCorrection
+from ._robust_normal_variate import RobustNormalVariate
+from ._standard_normal_variate import StandardNormalVariate

chemotools/scatter/{extended_multiplicative_scatter_correction.py → _extended_multiplicative_scatter_correction.py}

@@ -37,8 +37,6 @@ class ExtendedMultiplicativeScatterCorrection(
     ----------
     reference_ : np.ndarray
         The reference spectrum used for the correction.
-    n_features_in_ : int
-        The number of features in the training data.
 
     References
     ----------
@@ -82,13 +80,7 @@ class ExtendedMultiplicativeScatterCorrection(
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         # Check that the length of the reference is the same as the number of features
         if self.reference is not None:
@@ -146,7 +138,7 @@ class ExtendedMultiplicativeScatterCorrection(
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)

chemotools/scatter/{multiplicative_scatter_correction.py → _multiplicative_scatter_correction.py}

@@ -68,13 +68,7 @@ class MultiplicativeScatterCorrection(
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         # Check that the length of the reference is the same as the number of features
         if self.reference is not None:
@@ -129,7 +123,7 @@ class MultiplicativeScatterCorrection(
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)

chemotools/scatter/{robust_normal_variate.py → _robust_normal_variate.py}

@@ -15,14 +15,6 @@ class RobustNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
         The percentile to use for the robust normal variate. The value should be
         between 0 and 100. The default is 25.
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -58,13 +50,7 @@ class RobustNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         return self
 
@@ -86,7 +72,7 @@ class RobustNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)

chemotools/scatter/{standard_normal_variate.py → _standard_normal_variate.py}

@@ -9,14 +9,6 @@ class StandardNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
     """
     A transformer that calculates the standard normal variate of the input data.
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -25,10 +17,11 @@ class StandardNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
     transform(X, y=0, copy=True)
         Transform the input data by calculating the standard normal variate.
     """
+
     def fit(self, X: np.ndarray, y=None) -> "StandardNormalVariate":
         """
         Fit the transformer to the input data.
-        
+
         Parameters
         ----------
         X : np.ndarray of shape (n_samples, n_features)
@@ -43,13 +36,7 @@ class StandardNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         return self
 
@@ -71,7 +58,7 @@ class StandardNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)
@@ -79,7 +66,9 @@ class StandardNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
 
         # Check that the number of features is the same as the fitted data
         if X_.shape[1] != self.n_features_in_:
-            raise ValueError(f"Expected {self.n_features_in_} features but got {X_.shape[1]}")
+            raise ValueError(
+                f"Expected {self.n_features_in_} features but got {X_.shape[1]}"
+            )
 
         # Calculate the standard normal variate
         for i, x in enumerate(X_):
@@ -88,4 +77,4 @@ class StandardNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _calculate_standard_normal_variate(self, x) -> np.ndarray:
-        return (x - x.mean()) / x.std()
+        return (x - x.mean()) / x.std()

chemotools/smooth/__init__.py

@@ -1,4 +1,4 @@
-from .mean_filter import MeanFilter
-from .median_filter import MedianFilter
-from .savitzky_golay_filter import SavitzkyGolayFilter
-from .whittaker_smooth import WhittakerSmooth
+from ._mean_filter import MeanFilter
+from ._median_filter import MedianFilter
+from ._savitzky_golay_filter import SavitzkyGolayFilter
+from ._whittaker_smooth import WhittakerSmooth

chemotools/smooth/{mean_filter.py → _mean_filter.py}

@@ -14,19 +14,11 @@ class MeanFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     ----------
     window_size : int, optional
         The size of the window to use for the mean filter. Must be odd. Default is 3.
-    
+
     mode : str, optional
         The mode to use for the mean filter. Can be "nearest", "constant", "reflect",
         "wrap", "mirror" or "interp". Default is "nearest".
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -35,7 +27,8 @@ class MeanFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     transform(X, y=0, copy=True)
         Transform the input data by calculating the mean filter.
     """
-    def __init__(self, window_size: int = 3, mode='nearest') -> None:
+
+    def __init__(self, window_size: int = 3, mode="nearest") -> None:
         self.window_size = window_size
         self.mode = mode
 
@@ -57,13 +50,7 @@ class MeanFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
-        # Set the number of features
-        self.n_features_in_ = X.shape[1]
-
-        # Set the fitted attribute to True
-        self._is_fitted = True
+        X = self._validate_data(X)
 
         return self
 
@@ -85,7 +72,7 @@ class MeanFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "n_features_in_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)