chemotools 0.1.6__py3-none-any.whl → 0.1.7__py3-none-any.whl

chemotools/augmentation/index_shift.py

@@ -1,6 +1,7 @@
-from typing import Optional
+from typing import Literal, Optional
 
 import numpy as np
+from numpy.polynomial import polynomial as poly
 from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
 from sklearn.utils.validation import check_is_fitted, validate_data
 
@@ -35,8 +36,14 @@ class IndexShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
         Transform the input data by shifting the spectrum.
     """
 
-    def __init__(self, shift: int = 0, random_state: Optional[int] = None):
+    def __init__(
+        self,
+        shift: int = 0,
+        fill_method: Literal["constant", "linear", "quadratic"] = "constant",
+        random_state: Optional[int] = None,
+    ):
         self.shift = shift
+        self.fill_method = fill_method
         self.random_state = random_state
 
     def fit(self, X: np.ndarray, y=None) -> "IndexShift":
@@ -111,10 +118,82 @@ class IndexShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
 
         # Calculate the standard normal variate
         for i, x in enumerate(X_):
-            X_[i] = self._shift_spectrum(x)
+            X_[i] = self._shift_vector(x)
 
         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, endpoint=True)
         return np.roll(x, shift_amount)
+
+    def _shift_vector(
+        self,
+        x: np.ndarray,
+    ) -> np.ndarray:
+        """
+        Shift vector with option to fill missing values.
+
+        Args:
+            arr: Input numpy array
+            shift: Number of positions to shift
+            fill_method: Method to fill missing values
+                'constant': fill with first/last value
+                'linear': fill using linear regression
+                'quadratic': fill using quadratic regression
+
+        Returns:
+            Shifted numpy array
+        """
+        shift = self._rng.integers(-self.shift, self.shift, endpoint=True)
+
+        result = np.roll(x, shift)
+
+        if self.fill_method == "constant":
+            if shift > 0:
+                result[:shift] = x[0]
+            elif shift < 0:
+                result[shift:] = x[-1]
+
+        elif self.fill_method == "linear":
+            if shift > 0:
+                x_ = np.arange(5)
+                coeffs = poly.polyfit(x_, x[:5], 1)
+
+                extrapolate_x = np.arange(-shift, 0)
+                extrapolated_values = poly.polyval(extrapolate_x, coeffs)
+
+                result[:shift] = extrapolated_values
+
+            elif shift < 0:
+                x_ = np.arange(5)
+                coeffs = poly.polyfit(x_, x[-5:], 1)
+
+                extrapolate_x = np.arange(len(x_), len(x_) - shift)
+                extrapolated_values = poly.polyval(extrapolate_x, coeffs)
+
+                result[shift:] = extrapolated_values
+
+        elif self.fill_method == "quadratic":
+            if shift > 0:
+                # Use first 3 values for quadratic regression
+                x_ = np.arange(5)
+                coeffs = poly.polyfit(x_, x[:5], 2)
+
+                # Extrapolate to fill shifted region
+                extrapolate_x = np.arange(-shift, 0)
+                extrapolated_values = poly.polyval(extrapolate_x, coeffs)
+
+                result[:shift] = extrapolated_values
+
+            elif shift < 0:
+                # Use last 3 values for quadratic regression
+                x_ = np.arange(5)
+                coeffs = poly.polyfit(x_, x[-5:], 2)
+
+                # Extrapolate to fill shifted region
+                extrapolate_x = np.arange(len(x_), len(x_) - shift)
+                extrapolated_values = poly.polyval(extrapolate_x, coeffs)
+
+                result[shift:] = extrapolated_values
+
+        return result

chemotools/scatter/_extended_multiplicative_scatter_correction.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Literal, Optional
 
 import numpy as np
 from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
@@ -46,18 +46,20 @@ class ExtendedMultiplicativeScatterCorrection(
     model-based pre-processing, doi:10.1016/j.chemolab.2021.104350
     """
 
+    ALLOWED_METHODS = ["mean", "median"]
+
+    # TODO: Check method is valid in instantiation. Right now it is check on fit because it breaks the scikitlearn check_estimator()
+
     def __init__(
         self,
-        reference: Optional[np.ndarray] = None,
-        use_mean: bool = True,
-        use_median: bool = False,
+        method: Literal["mean", "median"] = "mean",
         order: int = 2,
+        reference: Optional[np.ndarray] = None,
         weights: Optional[np.ndarray] = None,
     ):
-        self.reference = reference
-        self.use_mean = use_mean
-        self.use_median = use_median
+        self.method = method
         self.order = order
+        self.reference = reference
         self.weights = weights
 
     def fit(self, X: np.ndarray, y=None) -> "ExtendedMultiplicativeScatterCorrection":
@@ -104,21 +106,24 @@ class ExtendedMultiplicativeScatterCorrection(
             self.weights_ = np.array(self.weights)
             return self
 
-        if self.use_median:
-            self.reference_ = np.median(X, axis=0)
+        if self.method == "mean":
+            self.reference_ = X.mean(axis=0)
             self.indices_ = self._calculate_indices(X[0])
             self.A_ = self._calculate_A(self.indices_, self.reference_)
             self.weights_ = np.array(self.weights)
             return self
 
-        if self.use_mean:
-            self.reference_ = X.mean(axis=0)
+        elif self.method == "median":
+            self.reference_ = np.median(X, axis=0)
             self.indices_ = self._calculate_indices(X[0])
             self.A_ = self._calculate_A(self.indices_, self.reference_)
             self.weights_ = np.array(self.weights)
             return self
 
-        raise ValueError("No reference was provided")
+        else:
+            raise ValueError(
+                f"Invalid method: {self.method}. Must be one of {self.ALLOWED_METHODS}"
+            )
 
     def transform(self, X: np.ndarray, y=None) -> np.ndarray:
         """

chemotools/scatter/_multiplicative_scatter_correction.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Literal, Optional
 
 import numpy as np
 from sklearn.base import BaseEstimator, TransformerMixin, OneToOneFeatureMixin
@@ -37,16 +37,18 @@ class MultiplicativeScatterCorrection(
 
     """
 
+    ALLOWED_METHODS = ["mean", "median"]
+
+    # TODO: Check method is valid in instantiation. Right now it is check on fit because it breaks the scikitlearn check_estimator()
+
     def __init__(
         self,
+        method: Literal["mean", "median"] = "mean",
         reference: Optional[np.ndarray] = None,
-        use_mean: bool = True,
-        use_median: bool = False,
         weights: Optional[np.ndarray] = None,
     ):
+        self.method = method
         self.reference = reference
-        self.use_mean = use_mean
-        self.use_median = use_median
         self.weights = weights
 
     def fit(self, X: np.ndarray, y=None) -> "MultiplicativeScatterCorrection":
@@ -91,18 +93,23 @@ class MultiplicativeScatterCorrection(
             self.weights_ = np.array(self.weights)
             return self
 
-        if self.use_median:
-            self.reference_ = np.median(X, axis=0)
+        if self.method == "mean":
+            self.reference_ = X.mean(axis=0)
             self.A_ = self._calculate_A(self.reference_)
             self.weights_ = np.array(self.weights)
             return self
 
-        if self.use_mean:
-            self.reference_ = X.mean(axis=0)
+        elif self.method == "median":
+            self.reference_ = np.median(X, axis=0)
             self.A_ = self._calculate_A(self.reference_)
             self.weights_ = np.array(self.weights)
             return self
 
+        else:
+            raise ValueError(
+                f"Invalid method: {self.method}. Must be one of {self.ALLOWED_METHODS}"
+            )
+
         raise ValueError("No reference was provided")
 
     def transform(self, X: np.ndarray, y=None) -> np.ndarray:

{chemotools-0.1.6.dist-info → chemotools-0.1.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: chemotools
-Version: 0.1.6
+Version: 0.1.7
 Summary: chemotools: A Python Package that Integrates Chemometrics and scikit-learn
 License: MIT
 Author: Pau Cabaneros

{chemotools-0.1.6.dist-info → chemotools-0.1.7.dist-info}/RECORD

@@ -2,7 +2,7 @@ chemotools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chemotools/augmentation/__init__.py,sha256=xIUoWov_aluoW5L3zpVAahyPdkWA5erApW-duzdE_9A,385
 chemotools/augmentation/baseline_shift.py,sha256=kIlYvmKS9pu9vh_-eZ7PSHPuH_58V9mgYbSJt6Gq3BA,3476
 chemotools/augmentation/exponential_noise.py,sha256=fhZ4zQGGqmW-OiSu388th6IhgXrFj1xOguqKYAgj8Y4,3348
-chemotools/augmentation/index_shift.py,sha256=DWVfnxCUgm2NNQfASTpqNoMkfhlW1WZT8EoWVsSSF4c,3459
+chemotools/augmentation/index_shift.py,sha256=w1maDHGLAKSiGAQ8c9yYHofs_PJnxeN0nB1RU-pINcE,6042
 chemotools/augmentation/normal_noise.py,sha256=-se2Xv1pAWt9HY7H5yC4XlxRArPKZWGeTy2MdyN4lBE,3318
 chemotools/augmentation/spectrum_scale.py,sha256=hMsmzXpssbI7tGm_YnQn9wjbByso3CgVxd3Hs8kfLS8,3442
 chemotools/augmentation/uniform_noise.py,sha256=8a-AYzEDIkLckL6FK2i8mr_jXnQGcFaKXh_roGCICaQ,3456
@@ -35,8 +35,8 @@ chemotools/scale/_min_max_scaler.py,sha256=YvqRkV2pXu-viQrpjzWcp9KmSSCYSoubSnrZH
 chemotools/scale/_norm_scaler.py,sha256=CHWSir2q-pL1hxzw_ZB45yi4mw-SkJ4YOa1CUL4nm2I,2568
 chemotools/scale/_point_scaler.py,sha256=je-vomAk7g3Q7yxmisQK4-3ndKEKI2wDwLrUiNuwzzA,3505
 chemotools/scatter/__init__.py,sha256=ftyC_MGurzxpWMie8WlFDGh5ylalK2K3aCSN4qUzQAw,459
-chemotools/scatter/_extended_multiplicative_scatter_correction.py,sha256=7OpOcvWX1hlMUR18tC29pkSiADLZViDrTh-wro738E4,6560
-chemotools/scatter/_multiplicative_scatter_correction.py,sha256=nPMPYKHl6-U--GAuQdZL8KVNPlr3V52teUAoJ0iRs3g,5801
+chemotools/scatter/_extended_multiplicative_scatter_correction.py,sha256=2OitT0QBYepvigmfmfpGWOLjq9y3iycOdTt-WhqLNhs,6801
+chemotools/scatter/_multiplicative_scatter_correction.py,sha256=XKa19Vk7F6-JxWPMIt7qmxdySdbliAVJwsKwPhY02O0,6097
 chemotools/scatter/_robust_normal_variate.py,sha256=nPfcvjHEpwkcSCjdvD86WN9q2wVMCeZ2Z8wMzcBpM3Y,3110
 chemotools/scatter/_standard_normal_variate.py,sha256=22mJzbbZoXQY-_hHAhGO0vzfYwr3oMqaR6xPjJryHtk,2582
 chemotools/smooth/__init__.py,sha256=G8JvAoBK9d18-k6XgukqN6dbJP-dsEgeDdbKbZdCIkA,265
@@ -45,7 +45,7 @@ chemotools/smooth/_median_filter.py,sha256=9ndTJCwrZirWlvDNldiigMddy79KIGq9OwwYN
 chemotools/smooth/_savitzky_golay_filter.py,sha256=27iFUWxdL9_7oZabR0R5L0ZTpBmYfVUjx2XCTukihBE,3509
 chemotools/smooth/_whittaker_smooth.py,sha256=lpLAyf4GdyDW4ulT1nyEoK6xQEl2cVUKquawQdGWbHU,3571
 chemotools/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chemotools-0.1.6.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
-chemotools-0.1.6.dist-info/METADATA,sha256=79TZ--QC_SOHj3ou6bDaRYsJsQoFS0sx2Rfe2BUOrG4,5239
-chemotools-0.1.6.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
-chemotools-0.1.6.dist-info/RECORD,,
+chemotools-0.1.7.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
+chemotools-0.1.7.dist-info/METADATA,sha256=cLjx8z4fGKdTHdIyDZ1VGd6WgXX-WlXtw9OwqaYm0Fo,5239
+chemotools-0.1.7.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+chemotools-0.1.7.dist-info/RECORD,,