chemotools 0.0.27__py3-none-any.whl → 0.1.6__py3-none-any.whl

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

@@ -1,18 +1,18 @@
+from typing import Optional
+
 import numpy as np
 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 PointScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class PointScaler(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
-    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):
+
+    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.
@@ -62,21 +56,15 @@ 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 = 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:
@@ -97,24 +85,31 @@ 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)
-        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]}"
+            )
 
         # 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:
-        if self.wavenumbers is None:
-            return target
         wavenumbers = np.array(self.wavenumbers)
-        return np.argmin(np.abs(wavenumbers - target))
+        return int(np.argmin(np.abs(wavenumbers - target)))

chemotools/scatter/__init__.py

@@ -1,4 +1,13 @@
-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
+
+__all__ = [
+    "ExtendedMultiplicativeScatterCorrection",
+    "MultiplicativeScatterCorrection",
+    "RobustNormalVariate",
+    "StandardNormalVariate",
+]

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

@@ -1,13 +1,12 @@
+from typing import Optional
+
 import numpy as np
 from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
-from sklearn.preprocessing import StandardScaler
-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 ExtendedMultiplicativeScatterCorrection(
-    OneToOneFeatureMixin, BaseEstimator, TransformerMixin
+    TransformerMixin, OneToOneFeatureMixin, BaseEstimator
 ):
     """Extended multiplicative scatter correction (EMSC) is a preprocessing technique for
     removing non linear scatter effects from spectra. It is based on fitting a polynomial
@@ -37,8 +36,6 @@ 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
     ----------
@@ -51,11 +48,11 @@ class ExtendedMultiplicativeScatterCorrection(
 
     def __init__(
         self,
-        reference: np.ndarray = None,
+        reference: Optional[np.ndarray] = None,
         use_mean: bool = True,
         use_median: bool = False,
         order: int = 2,
-        weights: np.ndarray = None,
+        weights: Optional[np.ndarray] = None,
     ):
         self.reference = reference
         self.use_mean = use_mean
@@ -82,13 +79,9 @@ 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 = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
 
         # Check that the length of the reference is the same as the number of features
         if self.reference is not None:
@@ -146,20 +139,18 @@ 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)
-        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]}"
-            )
-
-        # Calculate the extended multiplicative scatter correction
-        X_ = X.copy()
+        X_ = validate_data(
+            self,
+            X,
+            y="no_validation",
+            ensure_2d=True,
+            copy=True,
+            reset=False,
+            dtype=np.float64,
+        )
 
         if self.weights is None:
             for i, x in enumerate(X_):

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

@@ -1,12 +1,12 @@
+from typing import Optional
+
 import numpy as np
 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 MultiplicativeScatterCorrection(
-    OneToOneFeatureMixin, BaseEstimator, TransformerMixin
+    TransformerMixin, OneToOneFeatureMixin, BaseEstimator
 ):
     """Multiplicative scatter correction (MSC) is a preprocessing technique for
     removing scatter effects from spectra. It is based on fitting a linear
@@ -39,10 +39,10 @@ class MultiplicativeScatterCorrection(
 
     def __init__(
         self,
-        reference: np.ndarray = None,
+        reference: Optional[np.ndarray] = None,
         use_mean: bool = True,
         use_median: bool = False,
-        weights: np.ndarray = None,
+        weights: Optional[np.ndarray] = None,
     ):
         self.reference = reference
         self.use_mean = use_mean
@@ -68,14 +68,9 @@ 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 = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
         # Check that the length of the reference is the same as the number of features
         if self.reference is not None:
             if len(self.reference) != self.n_features_in_:
@@ -129,11 +124,18 @@ 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)
-        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/scatter/{robust_normal_variate.py → _robust_normal_variate.py}

@@ -1,11 +1,9 @@
 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 RobustNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class RobustNormalVariate(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     A transformer that calculates the robust normal variate of the input data.
 
@@ -15,14 +13,6 @@ 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)
@@ -58,14 +48,9 @@ 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 = 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:
@@ -86,11 +71,18 @@ 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)
-        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/scatter/{standard_normal_variate.py → _standard_normal_variate.py}

@@ -1,22 +1,12 @@
 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 StandardNormalVariate(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class StandardNormalVariate(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     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 +15,11 @@ 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)
@@ -43,14 +34,9 @@ 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 = 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:
@@ -71,15 +57,24 @@ 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)
-        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]}"
+            )
 
         # Calculate the standard normal variate
         for i, x in enumerate(X_):
@@ -88,4 +83,4 @@ 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 +1,6 @@
-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
+
+__all__ = ["MeanFilter", "MedianFilter", "SavitzkyGolayFilter", "WhittakerSmooth"]

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

@@ -1,12 +1,10 @@
 import numpy as np
 from scipy.ndimage import uniform_filter1d
 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 MeanFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class MeanFilter(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     A transformer that calculates the mean filter of the input data.
 
@@ -14,19 +12,11 @@ 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 +25,8 @@ 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
 
@@ -57,14 +48,9 @@ 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 = 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:
@@ -85,11 +71,18 @@ 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)
-        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(

chemotools/smooth/{median_filter.py → _median_filter.py}

@@ -1,12 +1,12 @@
+from typing import Literal
+
 import numpy as np
 from scipy.ndimage import median_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 MedianFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class MedianFilter(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     A transformer that calculates the median filter of the input data.
 
@@ -19,14 +19,6 @@ class MedianFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         The mode to use for the median 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 +27,21 @@ class MedianFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     transform(X, y=0, copy=True)
         Transform the input data by calculating the median filter.
     """
-    def __init__(self, window_size: int = 3, mode: str = 'nearest') -> None:
+
+    def __init__(
+        self,
+        window_size: int = 3,
+        mode: Literal[
+            "reflect",
+            "constant",
+            "nearest",
+            "mirror",
+            "wrap",
+            "grid-constant",
+            "grid-mirror",
+            "grid-wrap",
+        ] = "nearest",
+    ) -> None:
         self.window_size = window_size
         self.mode = mode
 
@@ -57,14 +63,9 @@ class MedianFilter(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:
@@ -85,11 +86,18 @@ class MedianFilter(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(