chemotools 0.0.22__py3-none-any.whl → 0.1.6__py3-none-any.whl

chemotools/derivative/{savitzky_golay.py → _savitzky_golay.py}

@@ -1,12 +1,12 @@
+from typing import Literal
+
 import numpy as np
 from scipy.signal import savgol_filter
 from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
-from sklearn.utils.validation import check_is_fitted
-
-from chemotools.utils.check_inputs import check_input
+from sklearn.utils.validation import check_is_fitted, validate_data
 
 
-class SavitzkyGolay(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class SavitzkyGolay(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     A transformer that calculates the Savitzky-Golay derivative of the input data.
 
@@ -27,14 +27,6 @@ class SavitzkyGolay(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         The mode to use for the derivative calculation. 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)
@@ -49,7 +41,7 @@ class SavitzkyGolay(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         window_size: int = 3,
         polynomial_order: int = 1,
         derivate_order: int = 1,
-        mode: str = "nearest",
+        mode: Literal["mirror", "constant", "nearest", "wrap", "interp"] = "nearest",
     ) -> None:
         self.window_size = window_size
         self.polynomial_order = polynomial_order
@@ -74,14 +66,9 @@ class SavitzkyGolay(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 = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
         return self
 
     def transform(self, X: np.ndarray, y=None) -> np.ndarray:
@@ -102,29 +89,32 @@ class SavitzkyGolay(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)
-        X_ = X.copy()
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
 
         if X_.shape[1] != self.n_features_in_:
             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_):
-            X_[i] = self._calculate_derivative(x)
+            X_[i] = savgol_filter(
+                x,
+                self.window_size,
+                self.polynomial_order,
+                deriv=self.derivate_order,
+                axis=0,
+                mode=self.mode,
+            )
 
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
-
-    def _calculate_derivative(self, x) -> np.ndarray:
-        return savgol_filter(
-            x,
-            self.window_size,
-            self.polynomial_order,
-            deriv=self.derivate_order,
-            axis=0,
-            mode=self.mode,
-        )

chemotools/feature_selection/__init__.py

@@ -0,0 +1,4 @@
+from ._index_selector import IndexSelector
+from ._range_cut import RangeCut
+
+__all__ = ["IndexSelector", "RangeCut"]

chemotools/feature_selection/_index_selector.py

@@ -0,0 +1,113 @@
+from typing import Optional, Union
+
+import numpy as np
+from sklearn.base import BaseEstimator
+from sklearn.feature_selection._base import SelectorMixin
+
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class IndexSelector(SelectorMixin, BaseEstimator):
+    """
+    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:
+    - by the indices of the wavenumbers to select,
+    - by the wavenumbers to select, the wavenumbers must be provided to the transformer
+        when it is initialised. If the wavenumbers are not provided, the indices will be
+        used instead. The wavenumbers must be provided in ascending order.
+
+    Parameters
+    ----------
+    features : narray-like, optional
+        The index of the features to select. Default is None.
+
+    wavenumbers : array-like, optional
+        The wavenumbers of the input data. If not provided, the indices will be used
+        instead. Default is None. If provided, the wavenumbers must be provided in
+        ascending order.
+
+    Attributes
+    ----------
+    features_index_ : int
+        The index of the features to select.
+
+    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__(
+        self,
+        features: Optional[np.ndarray] = None,
+        wavenumbers: Optional[np.ndarray] = None,
+    ):
+        self.features = features
+        self.wavenumbers = wavenumbers
+
+    def fit(self, X: np.ndarray, y=None) -> "IndexSelector":
+        """
+        Fit the transformer to the input data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : IndexSelector
+            The fitted transformer.
+        """
+        # validate that X is a 2D array and has only finite values
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
+        # Set the fitted attribute to True
+        self._is_fitted = True
+
+        # Set the start and end indices
+        if self.features is None:
+            self.features_index_ = self.features
+            return self
+
+        elif self.wavenumbers is None:
+            self.features_index_ = self.features
+            return self
+
+        else:
+            self.features_index_ = self._find_indices(self.features)
+            return self
+
+    def _get_support_mask(self):
+        """
+        Get the boolean mask indicating which features are selected.
+
+        Returns
+        -------
+        mask : ndarray of shape (n_features_in_,)
+            The mask indicating the selected features.
+        """
+        # Check that the estimator is fitted
+        check_is_fitted(self)
+
+        # Create the mask
+        mask = np.zeros(self.n_features_in_, dtype=bool)
+        mask[self.features_index_] = True
+
+        return mask
+
+    def _find_index(self, target: Union[float, int]) -> int:
+        if self.wavenumbers is None:
+            return int(target)
+        wavenumbers = np.array(self.wavenumbers)
+        return int(np.argmin(np.abs(wavenumbers - target)))
+
+    def _find_indices(self, features: np.ndarray) -> np.ndarray:
+        return np.array([self._find_index(feature) for feature in features])

chemotools/feature_selection/_range_cut.py

@@ -0,0 +1,111 @@
+from typing import Optional
+
+import numpy as np
+from sklearn.base import BaseEstimator
+from sklearn.feature_selection._base import SelectorMixin
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class RangeCut(SelectorMixin, BaseEstimator):
+    """
+    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
+        are not provided, the indices will be used instead. The wavenumbers must be
+        provided in ascending order.
+
+    Parameters
+    ----------
+    start : int, optional
+        The index or wavenumber of the start of the range. Default is 0.
+
+    end : int, optional
+        The index or wavenumber of the end of the range. Default is -1.
+
+    wavenumbers : array-like, optional
+        The wavenumbers of the input data. If not provided, the indices will be used
+        instead. Default is None. If provided, the wavenumbers must be provided in
+        ascending order.
+
+    Attributes
+    ----------
+    start_index_ : int
+        The index of the start of the range. It is 0 if the wavenumbers are not provided.
+
+    end_index_ : int
+        The index of the end of the range. It is -1 if the wavenumbers are not provided.
+
+    wavenuumbers_ : array-like
+        The cut wavenumbers of the input data.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data.
+    """
+
+    def __init__(
+        self,
+        start: int = 0,
+        end: int = -1,
+        wavenumbers: Optional[np.ndarray] = None,
+    ):
+        self.start = start
+        self.end = end
+        self.wavenumbers = wavenumbers
+
+    def fit(self, X: np.ndarray, y=None) -> "RangeCut":
+        """
+        Fit the transformer to the input data.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : RangeCut
+            The fitted transformer.
+        """
+        # Check that X is a 2D array and has only finite values
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
+        # Set the start and end indices
+        if self.wavenumbers is None:
+            self.start_index_ = self.start
+            self.end_index_ = self.end
+            self.wavenumbers_ = None
+        else:
+            self.start_index_ = self._find_index(self.start)
+            self.end_index_ = self._find_index(self.end)
+            self.wavenumbers_ = self.wavenumbers[self.start_index_ : self.end_index_]
+
+        return self
+
+    def _get_support_mask(self):
+        """
+        Get the boolean mask indicating which features are selected.
+
+        Returns
+        -------
+        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, ["start_index_", "end_index_"])
+
+        # Create the mask
+        mask = np.zeros(self.n_features_in_, dtype=bool)
+        mask[self.start_index_ : self.end_index_] = True
+
+        return mask
+
+    def _find_index(self, target: float) -> int:
+        wavenumbers = np.array(self.wavenumbers)
+        return int(np.argmin(np.abs(wavenumbers - target)))

chemotools/scale/__init__.py

@@ -1,3 +1,5 @@
-from .index_scaler import IndexScaler
-from .min_max_scaler import MinMaxScaler
-from .norm_scaler import NormScaler
+from ._min_max_scaler import MinMaxScaler
+from ._norm_scaler import NormScaler
+from ._point_scaler import PointScaler
+
+__all__ = ["MinMaxScaler", "NormScaler", "PointScaler"]

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

@@ -1,27 +1,19 @@
 import numpy as np
 from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import check_is_fitted, validate_data
 
-from chemotools.utils.check_inputs import check_input
 
-
-class MinMaxScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class MinMaxScaler(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
-    A transformer that scales the input data by the maximum value or minimum 
-    value in the spectrum.
+    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 data is scaled by the maximum.
 
     Parameters
     ----------
-    norm : str, optional
-        The normalization to use. Can be "max" or "min". Default is "max".
-
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        Whether the transformer has been fitted to data.
+    use_min : bool, default=True
+        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.
 
     Methods
     -------
@@ -31,9 +23,9 @@ class MinMaxScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     transform(X, y=0, copy=True)
         Transform the input data by scaling by the maximum value.
     """
-    def __init__(self, norm: str = 'max'):
-        self.norm = norm
 
+    def __init__(self, use_min: bool = True):
+        self.use_min = use_min
 
     def fit(self, X: np.ndarray, y=None) -> "MinMaxScaler":
         """
@@ -53,19 +45,14 @@ 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 = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
         return self
 
     def transform(self, X: np.ndarray, y=None) -> np.ndarray:
         """
-        Transform the input data by scaling by the maximum or minimum value.
+        Transform the input data by scaling it.
 
         Parameters
         ----------
@@ -81,22 +68,32 @@ 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)
-        X_ = X.copy()
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
 
         # 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]}"
+            )
 
         # Normalize the data by the maximum value
-        for i, x in enumerate(X_):
-            if self.norm == 'max':
-                X_[i] = x / np.max(x)
-            
-            if self.norm == 'min':
-                X_[i] = x / np.min(x)
-
-        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
+        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)
+            )
+
+        else:
+            X_ = X_ / np.max(X_, axis=1, keepdims=True)
+
+        return X_.reshape(-1, 1) if X_.ndim == 1 else X_

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

@@ -1,26 +1,16 @@
 import numpy as np
 from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
-from sklearn.utils.validation import check_is_fitted
+from sklearn.utils.validation import check_is_fitted, validate_data
 
-from chemotools.utils.check_inputs import check_input
 
-
-class NormScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class NormScaler(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     A transformer that scales the input data by the L-norm of the spectrum.
 
     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 +20,14 @@ 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)
@@ -51,14 +42,9 @@ 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 = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
         return self
 
     def transform(self, X: np.ndarray, y=None) -> np.ndarray:
@@ -79,11 +65,18 @@ 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)
-        X_ = X.copy()
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
 
         # Check that the number of features is the same as the fitted data
         if X_.shape[1] != self.n_features_in_:

chemotools/scale/_point_scaler.py

@@ -0,0 +1,115 @@
+from typing import Optional
+
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
+from sklearn.utils.validation import check_is_fitted, validate_data
+
+
+class PointScaler(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
+    """
+    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,
+        The point to scale the data by. It can be an index or a wavenumber.
+
+    wavenumber : array-like, optional
+        The wavenumbers of the input data. If not provided, the indices will be used
+        instead. Default is None. If provided, the wavenumbers must be provided in
+        ascending order.
+
+    Attributes
+    ----------
+    point_index_ : int
+        The index of the point to scale the data by. It is 0 if the wavenumbers are not provided.
+
+    Methods
+    -------
+    fit(X, y=None)
+        Fit the transformer to the input data.
+
+    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: Optional[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.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to fit the transformer to.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        self : PointScaler
+            The fitted transformer.
+        """
+        # Check that X is a 2D array and has only finite values
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
+        # Set the point index
+        if self.wavenumbers is None:
+            self.point_index_ = self.point
+        else:
+            self.point_index_ = self._find_index(self.point)
+
+        return self
+
+    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+        """
+        Transform the input data by scaling by the value at a given Point.
+
+        Parameters
+        ----------
+        X : np.ndarray of shape (n_samples, n_features)
+            The input data to transform.
+
+        y : None
+            Ignored.
+
+        Returns
+        -------
+        X_ : np.ndarray of shape (n_samples, n_features)
+            The transformed data.
+        """
+        # Check that the estimator is fitted
+        check_is_fitted(self, "point_index_")
+
+        # Check that X is a 2D array and has only finite values
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
+
+        # 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]}"
+            )
+
+        # 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 int(np.argmin(np.abs(wavenumbers - target)))

chemotools/scatter/__init__.py

@@ -1,2 +1,13 @@
-from .multiplicative_scatter_correction import MultiplicativeScatterCorrection
-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
+
+__all__ = [
+    "ExtendedMultiplicativeScatterCorrection",
+    "MultiplicativeScatterCorrection",
+    "RobustNormalVariate",
+    "StandardNormalVariate",
+]