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

chemotools/{augmenation → augmentation}/baseline_shift.py

@@ -106,6 +106,6 @@ class BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _add_baseline(self, x) -> np.ndarray:
-        adding_factor = self._rng.uniform(low=0, high=0+self.scale)
+        adding_factor = self._rng.uniform(low=0, high=self.scale)
         return np.add(x, adding_factor)
     

chemotools/{augmenation → augmentation}/index_shift.py

@@ -7,7 +7,8 @@ from chemotools.utils.check_inputs import check_input
 
 class IndexShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     """
-    Shift the spectrum a given number of indices.
+    Shift the spectrum a given number of indices between - shift and + shift drawn
+    from a discrete uniform distribution. 
 
     Parameters
     ----------
@@ -35,7 +36,7 @@ class IndexShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     """
 
 
-    def __init__(self, shift: int = 0.0, random_state: int = None):
+    def __init__(self, shift: int = 0, random_state: int = None):
         self.shift = shift
         self.random_state = random_state
 
@@ -105,6 +106,6 @@ class IndexShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _shift_spectrum(self, x) -> np.ndarray:
-        shift_amount = self._rng.integers(-self.shift, self.shift+1)
+        shift_amount = self._rng.integers(-self.shift, self.shift, endpoint=True)
         return np.roll(x, shift_amount)
     

chemotools/baseline/__init__.py

@@ -1,8 +1,8 @@
-from .air_pls import AirPls
-from .ar_pls import ArPls
-from .constant_baseline_correction import ConstantBaselineCorrection
-from .cubic_spline_correction import CubicSplineCorrection
-from .linear_correction import LinearCorrection
-from .non_negative import NonNegative
-from .polynomial_correction import PolynomialCorrection
-from .subtract_reference import SubtractReference
+from ._air_pls import AirPls
+from ._ar_pls import ArPls
+from ._constant_baseline_correction import ConstantBaselineCorrection
+from ._cubic_spline_correction import CubicSplineCorrection
+from ._linear_correction import LinearCorrection
+from ._non_negative import NonNegative
+from ._polynomial_correction import PolynomialCorrection
+from ._subtract_reference import SubtractReference

chemotools/baseline/{air_pls.py → _air_pls.py}

@@ -30,14 +30,6 @@ class AirPls(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         The number of iterations used to calculate the baseline. Increasing the number of iterations can improve the
         accuracy of the baseline correction, but also increases the computation time.
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of features in the input data.
-
-    _is_fitted : bool
-        A flag indicating whether the estimator has been fitted to data.
-
     Methods
     -------
     fit(X, y=None)
@@ -85,13 +77,7 @@ class AirPls(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             Returns the instance itself.
         """
         # 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
 
@@ -113,7 +99,7 @@ class AirPls(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         """
 
         # 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)
@@ -132,14 +118,14 @@ class AirPls(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _calculate_whittaker_smooth(self, x, w):
-        X = np.matrix(x)
+        X = np.array(x)
         m = X.size
         E = eye(m, format="csc")
         for i in range(self.polynomial_order):
             E = E[1:] - E[:-1]
         W = diags(w, 0, shape=(m, m))
-        A = csc_matrix(W + (self.lam * E.T * E))
-        B = csc_matrix(W * X.T)
+        A = csc_matrix(W + (self.lam * E.T @ E))
+        B = csc_matrix(W @ X.T).toarray().ravel()
         background = spsolve(A, B)
         return np.array(background)
 

chemotools/baseline/{ar_pls.py → _ar_pls.py}

@@ -29,13 +29,6 @@ class ArPls(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     nr_iterations : int, optional (default=100)
         The maximum number of iterations for the weight updating scheme.
 
-    Attributes
-    ----------
-    n_features_in_ : int
-        The number of input features.
-
-    _is_fitted : bool
-        Whether the estimator has been fitted.
 
     Methods
     -------
@@ -86,13 +79,7 @@ class ArPls(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         """
 
         # 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
 
@@ -114,7 +101,7 @@ class ArPls(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         """
 
         # 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/baseline/{constant_baseline_correction.py → _constant_baseline_correction.py}

@@ -30,12 +30,6 @@ class ConstantBaselineCorrection(OneToOneFeatureMixin, BaseEstimator, Transforme
     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)
@@ -46,7 +40,10 @@ class ConstantBaselineCorrection(OneToOneFeatureMixin, BaseEstimator, Transforme
     """
 
     def __init__(
-        self, start: int = 0, end: int = 1, wavenumbers: np.ndarray = None,
+        self,
+        start: int = 0,
+        end: int = 1,
+        wavenumbers: np.ndarray = None,
     ) -> None:
         self.start = start
         self.end = end
@@ -70,13 +67,7 @@ class ConstantBaselineCorrection(OneToOneFeatureMixin, BaseEstimator, Transforme
             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:
@@ -109,7 +100,7 @@ class ConstantBaselineCorrection(OneToOneFeatureMixin, BaseEstimator, Transforme
             The transformed input data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, ["start_index_", "end_index_"])
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)

chemotools/baseline/{cubic_spline_correction.py → _cubic_spline_correction.py}

@@ -5,9 +5,10 @@ from sklearn.utils.validation import check_is_fitted
 
 from chemotools.utils.check_inputs import check_input
 
+
 class CubicSplineCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     """
-    A transformer that corrects a baseline by subtracting a cubic spline through the 
+    A transformer that corrects a baseline by subtracting a cubic spline through the
     points defined by the indices.
 
     Parameters
@@ -32,6 +33,7 @@ class CubicSplineCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
         Transform the input data by subtracting the constant baseline value.
 
     """
+
     def __init__(self, indices: list = None) -> None:
         self.indices = indices
 
@@ -53,13 +55,7 @@ class CubicSplineCorrection(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)
 
         if self.indices is None:
             self.indices_ = [0, len(X[0]) - 1]
@@ -89,7 +85,7 @@ class CubicSplineCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "indices_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)
@@ -97,7 +93,9 @@ class CubicSplineCorrection(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 spline baseline correction
         for i, x in enumerate(X_):
@@ -106,7 +104,7 @@ class CubicSplineCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixi
 
     def _spline_baseline_correct(self, x: np.ndarray) -> np.ndarray:
         indices = self.indices_
-        intensity = x[indices]  
+        intensity = x[indices]
         spl = CubicSpline(indices, intensity)
-        baseline = spl(range(len(x)))      
-        return x - baseline
+        baseline = spl(range(len(x)))
+        return x - baseline

chemotools/baseline/{linear_correction.py → _linear_correction.py}

@@ -10,17 +10,6 @@ class LinearCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     A transformer that corrects a baseline by subtracting a linear baseline through the
     initial and final points of the spectrum.
 
-    Parameters
-    ----------
-
-    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)
@@ -68,13 +57,7 @@ class LinearCorrection(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
 
@@ -99,7 +82,7 @@ class LinearCorrection(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/baseline/{non_negative.py → _non_negative.py}

@@ -14,14 +14,6 @@ class NonNegative(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     mode : str, optional
         The mode to use for the non-negative values. Can be "zero" or "abs".
 
-    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)
@@ -52,13 +44,7 @@ class NonNegative(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
 
@@ -80,7 +66,7 @@ class NonNegative(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/baseline/{polynomial_correction.py → _polynomial_correction.py}

@@ -4,9 +4,10 @@ from sklearn.utils.validation import check_is_fitted
 
 from chemotools.utils.check_inputs import check_input
 
+
 class PolynomialCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     """
-    A transformer that subtracts a polynomial baseline from the input data. The polynomial is 
+    A transformer that subtracts a polynomial baseline from the input data. The polynomial is
     fitted to the points in the spectrum specified by the indices parameter.
 
     Parameters
@@ -18,14 +19,6 @@ class PolynomialCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin
         The indices of the points in the spectrum to fit the polynomial to. Defaults to None,
         which fits the polynomial to all points in the spectrum (equivalent to detrend).
 
-    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)
@@ -37,6 +30,7 @@ class PolynomialCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin
     _baseline_correct_spectrum(x)
         Subtract the polynomial baseline from a single spectrum.
     """
+
     def __init__(self, order: int = 1, indices: list = None) -> None:
         self.order = order
         self.indices = indices
@@ -59,13 +53,7 @@ class PolynomialCorrection(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)
 
         if self.indices is None:
             self.indices_ = range(0, len(X[0]))
@@ -73,8 +61,8 @@ class PolynomialCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin
             self.indices_ = self.indices
 
         return self
-    
-    def transform(self, X: np.ndarray, y:int=0, copy:bool=True) -> np.ndarray:
+
+    def transform(self, X: np.ndarray, y: int = 0, copy: bool = True) -> np.ndarray:
         """
         Transform the input data by subtracting the polynomial baseline.
 
@@ -95,7 +83,7 @@ class PolynomialCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin
             The transformed data.
         """
         # Check that the estimator is fitted
-        check_is_fitted(self, "_is_fitted")
+        check_is_fitted(self, "indices_")
 
         # Check that X is a 2D array and has only finite values
         X = check_input(X)
@@ -103,13 +91,15 @@ class PolynomialCorrection(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]}"
+            )
 
         # Calculate polynomial baseline correction
         for i, x in enumerate(X_):
             X_[i] = self._baseline_correct_spectrum(x)
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
-    
+
     def _baseline_correct_spectrum(self, x: np.ndarray) -> np.ndarray:
         """
         Subtract the polynomial baseline from a single spectrum.
@@ -126,5 +116,5 @@ class PolynomialCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin
         """
         intensity = x[self.indices_]
         poly = np.polyfit(self.indices_, intensity, self.order)
-        baseline = [np.polyval(poly, i) for i in range(0, len(x))]      
-        return x - baseline
+        baseline = [np.polyval(poly, i) for i in range(0, len(x))]
+        return x - baseline

chemotools/baseline/{subtract_reference.py → _subtract_reference.py}

@@ -15,14 +15,6 @@ class SubtractReference(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         The reference spectrum to subtract from the input data. If None, the original spectrum
         is returned.
 
-    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)
@@ -34,6 +26,7 @@ class SubtractReference(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     _subtract_reference(x)
         Subtract the reference spectrum from a single spectrum.
     """
+
     def __init__(
         self,
         reference: np.ndarray = None,
@@ -58,20 +51,13 @@ class SubtractReference(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 reference
-
         if self.reference is not None:
             self.reference_ = self.reference.copy()
             return self
-        
+
         return self
 
     def transform(self, X: np.ndarray, y=None) -> np.ndarray:
@@ -92,7 +78,7 @@ class SubtractReference(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)
@@ -100,7 +86,9 @@ class SubtractReference(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]}"
+            )
 
         if self.reference is None:
             return X_.reshape(-1, 1) if X_.ndim == 1 else X_

chemotools/derivative/__init__.py

@@ -1,2 +1,2 @@
-from .norris_william import NorrisWilliams
-from .savitzky_golay import SavitzkyGolay
+from ._norris_william import NorrisWilliams
+from ._savitzky_golay import SavitzkyGolay

chemotools/derivative/{norris_william.py → _norris_william.py}

@@ -22,17 +22,9 @@ class NorrisWilliams(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         The order of the derivative to calculate. Can be 1 or 2. Default is 1.
 
     mode : str, optional
-        The mode to use for the derivative calculation. Can be "nearest", "constant", 
+        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)
@@ -41,6 +33,7 @@ class NorrisWilliams(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     transform(X, y=0, copy=True)
         Transform the input data by calculating the Norris-Williams derivative.
     """
+
     def __init__(
         self,
         window_size: int = 5,
@@ -71,13 +64,7 @@ class NorrisWilliams(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
 
@@ -99,7 +86,7 @@ class NorrisWilliams(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/derivative/{savitzky_golay.py → _savitzky_golay.py}

@@ -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)
@@ -74,13 +66,7 @@ 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 = self._validate_data(X)
 
         return self
 
@@ -102,7 +88,7 @@ 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)

chemotools/feature_selection/__init__.py

@@ -0,0 +1,2 @@
+from ._index_selector import IndexSelector
+from ._range_cut import RangeCut