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

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(

chemotools/smooth/{savitzky_golay_filter.py → _savitzky_golay_filter.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 SavitzkyGolayFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class SavitzkyGolayFilter(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     A transformer that calculates the Savitzky-Golay filter of the input data.
 
@@ -24,14 +24,6 @@ class SavitzkyGolayFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
         The mode to use for the Savitzky-Golay 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)
@@ -40,8 +32,12 @@ class SavitzkyGolayFilter(OneToOneFeatureMixin, BaseEstimator, TransformerMixin)
     transform(X, y=0, copy=True)
         Transform the input data by calculating the Savitzky-Golay filter.
     """
+
     def __init__(
-        self, window_size: int = 3, polynomial_order: int = 1, mode: str = "nearest"
+        self,
+        window_size: int = 3,
+        polynomial_order: int = 1,
+        mode: Literal["mirror", "constant", "nearest", "wrap", "interp"] = "nearest",
     ) -> None:
         self.window_size = window_size
         self.polynomial_order = polynomial_order
@@ -65,14 +61,9 @@ class SavitzkyGolayFilter(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:
@@ -93,11 +84,18 @@ class SavitzkyGolayFilter(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/{whittaker_smooth.py → _whittaker_smooth.py}

@@ -2,17 +2,17 @@ import numpy as np
 from scipy.sparse import csc_matrix, eye, diags
 from scipy.sparse.linalg import spsolve
 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,
+)  # This code is adapted from the following source:
 
-from chemotools.utils.check_inputs import check_input
-
-# This code is adapted from the following source:
-# Z.-M. Zhang, S. Chen, and Y.-Z. Liang, 
-# Baseline correction using adaptive iteratively reweighted penalized least squares. 
+# Z.-M. Zhang, S. Chen, and Y.-Z. Liang,
+# Baseline correction using adaptive iteratively reweighted penalized least squares.
 # Analyst 135 (5), 1138-1146 (2010).
 
 
-class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class WhittakerSmooth(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     A transformer that calculates the Whittaker smooth of the input data.
 
@@ -24,14 +24,6 @@ class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     differences : int, optional
         The number of differences to use for the Whittaker smooth. Default is 1.
 
-    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)
@@ -40,6 +32,7 @@ class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     transform(X, y=0, copy=True)
         Transform the input data by calculating the Whittaker smooth.
     """
+
     def __init__(
         self,
         lam: float = 1e2,
@@ -66,14 +59,9 @@ class WhittakerSmooth(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:
@@ -94,11 +82,18 @@ class WhittakerSmooth(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_:
@@ -113,14 +108,14 @@ class WhittakerSmooth(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _calculate_whittaker_smooth(self, x):
-        X = np.matrix(x)
+        X = np.array(x)
         m = X.size
         E = eye(m, format="csc")
         w = np.ones(m)
         for i in range(self.differences):
             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-0.0.22.dist-info → chemotools-0.1.6.dist-info}/METADATA

@@ -1,22 +1,24 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: chemotools
-Version: 0.0.22
-Summary: Package to integrate chemometrics in scikit-learn pipelines
-Home-page: https://github.com/paucablop/chemotools
-Author: Pau Cabaneros Lopez
-Author-email: pau.cabaneros@gmail.com
-Project-URL: Bug Tracker, https://github.com/paucablop/chemotools/issues/
-Classifier: Programming Language :: Python :: 3
+Version: 0.1.6
+Summary: chemotools: A Python Package that Integrates Chemometrics and scikit-learn
+License: MIT
+Author: Pau Cabaneros
+Requires-Python: >=3.10,<4.0
 Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.9
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: numpy (>=2.0.0,<3.0.0)
+Requires-Dist: pandas (>=2.0.0,<3.0.0)
+Requires-Dist: polars (>=1.17.0,<2.0.0)
+Requires-Dist: pyarrow (>=18.0.0,<19.0.0)
+Requires-Dist: scikit-learn (>=1.4.0,<2.0.0)
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: numpy
-Requires-Dist: scipy
-Requires-Dist: scikit-learn
 
-![chemotools](assets/images/logo_5.png)
+![chemotools](assets/images/logo_pixel.png)
 
 
 [![pypi](https://img.shields.io/pypi/v/chemotools)](https://pypi.org/project/chemotools)
@@ -24,6 +26,8 @@ Requires-Dist: scikit-learn
 [![pypi](https://img.shields.io/pypi/l/chemotools)](https://github.com/paucablop/chemotools/blob/main/LICENSE)
 [![codecov](https://codecov.io/github/paucablop/chemotools/branch/main/graph/badge.svg?token=D7JUJM89LN)](https://codecov.io/github/paucablop/chemotools)
 [![Downloads](https://static.pepy.tech/badge/chemotools)](https://pepy.tech/project/chemotools)
+[![DOI](https://joss.theoj.org/papers/10.21105/joss.06802/status.svg)](https://doi.org/10.21105/joss.06802)
+
 
 # __chemotools__
 

chemotools-0.1.6.dist-info/RECORD

@@ -0,0 +1,51 @@
+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/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
+chemotools/baseline/__init__.py,sha256=VzoblGg8Hx_FkTc_n7a-ZjGvtKP8JE_NwJKWenGFQkM,584
+chemotools/baseline/_air_pls.py,sha256=eotXuIEsus7Z-c17oLx8UbiwOHM7DzQJ6rruHnwCGPQ,5067
+chemotools/baseline/_ar_pls.py,sha256=Cl0tN0DGQA8JpnbIge4cBqT7aGQ7yltppYEDI6tWqiM,4385
+chemotools/baseline/_constant_baseline_correction.py,sha256=2ARXIma3m_He5KJs0t0Bz3m0Hd7CNHDR4Dd4XfjMWgs,3893
+chemotools/baseline/_cubic_spline_correction.py,sha256=Qr8jLwAM4JIcD-8G6BBU2vLSLyi44iHiIpJrHyZ6qJE,3432
+chemotools/baseline/_linear_correction.py,sha256=jYUy1q5hlBIhoQr5yPWbqr65pTK8NCVPdJdjVg1SFtg,3258
+chemotools/baseline/_non_negative.py,sha256=0Huq4fKAzAoX9nr6Fk-Awx5xBqmah4jTcn0TY31FJQc,2741
+chemotools/baseline/_polynomial_correction.py,sha256=jzoTyj5a9dHBtefTKVer8CVpCwWqV25Ruj7mq7Ra_PI,4005
+chemotools/baseline/_subtract_reference.py,sha256=B92DAYJmJR5VtWTM7Q6_orvIl2xaadmvbGr1r_ZJALA,3379
+chemotools/datasets/__init__.py,sha256=WcchczWPH-A22DmYEnz2-u8A6vfVviJ6tOCBB0zaIAU,196
+chemotools/datasets/_base.py,sha256=g_-R6c9WI5lt_j40FgA_mvEFzFHM9eGW6hj9d1e29P4,4883
+chemotools/datasets/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chemotools/datasets/data/coffee_labels.csv,sha256=ZXQWQIf8faLHjdnHfRoXfxMR56kq9Q1BGPZBkQyhGlY,487
+chemotools/datasets/data/coffee_spectra.csv,sha256=VA-sN4u0hC5iALlRxxkj-K87Lz3b3mmUHBJPoDXychI,2206147
+chemotools/datasets/data/fermentation_hplc.csv,sha256=AMmiFQxwaXrH8aN310-3h1YQDiDrT8JNRv1RDvhEvg4,2140
+chemotools/datasets/data/fermentation_spectra.csv,sha256=MaaNMQP0lygJgFbEoUX0OUqdA-id8mF5Llvf_vj9tJk,15237508
+chemotools/datasets/data/train_hplc.csv,sha256=DjtmqiePOWB-F6TsOGFngE1pKyXkb7Xmsi-1CLxsTnE,249
+chemotools/datasets/data/train_spectra.csv,sha256=iVF19W52NHlbqq8BbLomn8n47kSPT0QxJv7wtQX4yjQ,203244
+chemotools/derivative/__init__.py,sha256=FkckdzO30jrRWPGpIU3cfnaTtxPtNT5Tb2G9F9PmVTw,134
+chemotools/derivative/_norris_william.py,sha256=rMY_yntpiB5fbSM1tPph4AaGmF1k-HqJp7o48ijePBs,4958
+chemotools/derivative/_savitzky_golay.py,sha256=CuCrKoLmrB1YmJ4ihIykgkL3tO3frqkStMogtsVhO3A,3632
+chemotools/feature_selection/__init__.py,sha256=1_i28hIxijjwhMypTy1w2fLbzXXVkKD5IYzzY8ZSuHw,117
+chemotools/feature_selection/_index_selector.py,sha256=lNTP2b7P3doWl30KiAr3Xd2HOMxeUmj24MuqoXl4Voc,3556
+chemotools/feature_selection/_range_cut.py,sha256=lVVVC30ZsK2z9jsDGb_z6l8Ty2I89yM05_dIDbMP73Q,3564
+chemotools/scale/__init__.py,sha256=eztqcHg-TKE1Rr0N9ArfytHk8teuqVfi4SZi2DS96vc,175
+chemotools/scale/_min_max_scaler.py,sha256=YvqRkV2pXu-viQrpjzWcp9KmSSCYSoubSnrZHRLqgKQ,3011
+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/_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
+chemotools/smooth/_mean_filter.py,sha256=KVAqOzYWv-SnDX2HD3zLWSSDNePi2Zy3EV9NwIX2H38,2827
+chemotools/smooth/_median_filter.py,sha256=9ndTJCwrZirWlvDNldiigMddy79KIGq9OwwYNSXaw14,3111
+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-0.0.22.dist-info → chemotools-0.1.6.dist-info}/WHEEL

@@ -1,5 +1,4 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.40.0)
+Generator: poetry-core 2.0.1
 Root-Is-Purelib: true
 Tag: py3-none-any
-

chemotools/scale/index_scaler.py

@@ -1,97 +0,0 @@
-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
-
-
-class IndexScaler(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
-    """
-    A transformer that scales the input data by the value at a given index.
-
-    Parameters
-    ----------
-    index : int, optional
-        The index to scale the data by.
-
-    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)
-        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 index.
-    """
-    def __init__(self, index: int = 0):
-        self.index = index
-
-
-    def fit(self, X: np.ndarray, y=None) -> "IndexScaler":
-        """
-        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 : IndexScaler
-            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
-
-        return self
-
-    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
-        """
-        Transform the input data by scaling by the value at a given index.
-
-        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, "_is_fitted")
-
-        # 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]}")
-
-        # Scale the data by index
-        for i, x in enumerate(X_):
-            X_[i] = x / x[self.index]
-        
-        return X_.reshape(-1, 1) if X_.ndim == 1 else X_

chemotools/scatter/extended_multiplicative_scatter_correction.py

@@ -1,33 +0,0 @@
-import numpy as np
-from sklearn.base import BaseEstimator, TransformerMixin
-from sklearn.utils.validation import check_is_fitted
-
-from chemotools.utils.check_inputs import check_input
-
-class ExtendedMultiplicativeScatterCorrection(BaseEstimator, TransformerMixin):
-    def __init__(self):
-        self.ref_spec = None
-        self.coeffs = None
-
-    def fit(self, X, ref_spec=None):
-        if ref_spec is None:
-            # Use mean spectrum as reference if none provided
-            ref_spec = np.mean(X, axis=0)
-        self.ref_spec = ref_spec
-
-        # Calculate the mean spectrum
-        mean_spec = np.mean(X, axis=0)
-
-        # Fit a linear model to the reference spectrum
-        coeffs = np.polyfit(mean_spec, ref_spec, deg=1)
-        self.coeffs = coeffs
-
-    def transform(self, X):
-        # Divide the spectra by the linear model
-        X_emsc = X / np.polyval(self.coeffs, X.mean(axis=1))
-        return X_emsc
-
-    def fit_transform(self, X, ref_spec=None):
-        self.fit(X, ref_spec=ref_spec)
-        X_emsc = self.transform(X)
-        return X_emsc

chemotools/scatter/multiplicative_scatter_correction.py

@@ -1,123 +0,0 @@
-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
-
-
-class MultiplicativeScatterCorrection(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
-    """Multiplicative scatter correction (MSC) is a preprocessing technique for
-    removing scatter effects from spectra. It is based on fitting a linear
-    regression model to the spectrum using a reference spectrum. The reference
-    spectrum is usually a mean or median spectrum of a set of spectra.
-
-    Parameters
-    ----------
-    reference : np.ndarray, optional
-        The reference spectrum to use for the correction. If None, the mean
-        spectrum will be used. The default is None.
-    use_mean : bool, optional
-        Whether to use the mean spectrum as the reference. The default is True.
-    use_median : bool, optional
-        Whether to use the median spectrum as the reference. The default is False.
-
-    Attributes
-    ----------
-    reference_ : np.ndarray
-        The reference spectrum used for the correction.
-    n_features_in_ : int
-        The number of features in the training data.
-
-    Raises
-    ------
-    ValueError
-        If no reference is provided.
-    
-    """
-    def __init__(
-        self,
-        reference: np.ndarray = None,
-        use_mean: bool = True,
-        use_median: bool = False,
-    ):
-        self.reference = reference
-        self.use_mean = use_mean
-        self.use_median = use_median
-
-    def fit(self, X: np.ndarray, y=None) -> "MultiplicativeScatterCorrection":
-        """
-        Fit the transformer to the input data. If no reference is provided, the
-        mean or median spectrum will be calculated from 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 : 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
-
-        # Set the reference
-        if self.reference is None and self.use_mean:
-            self.reference_ = X.mean(axis=0)
-            return self
-
-        if self.reference is None and self.use_median:
-            self.reference_ = np.median(X, axis=0)
-            return self
-
-        if self.reference is not None:
-            self.reference_ = self.reference.copy()
-            return self
-
-        raise ValueError("No reference was provided")
-
-    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
-        """
-        Transform the input data by applying the multiplicative scatter
-        correction.
-
-        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, "_is_fitted")
-
-        # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-        X_ = X.copy()
-
-        # Calculate the multiplicative signal correction
-        ones = np.ones(X.shape[1])
-        for i, x in enumerate(X_):
-            X_[i] = self._calculate_multiplicative_correction(x, ones)
-        return X_.reshape(-1, 1) if X_.ndim == 1 else X_
-
-    def _calculate_multiplicative_correction(self, x, ones) -> np.ndarray:
-        A = np.vstack([self.reference_, ones]).T
-        m, c = np.linalg.lstsq(A, x, rcond=None)[0]
-        return (x - c) / m

chemotools/utils/check_inputs.py

@@ -1,14 +0,0 @@
-from sklearn.utils.validation import check_array
-
-
-def check_input(X, y=None):
-    # Check that X is a 2D array and has only finite values
-    X = check_array(X, ensure_2d=True, force_all_finite=True)
-
-    # Check that y is None or a 1D array of the same length as X
-    if y is not None:
-        y = y.reshape(-1, 1) if y.ndim == 1 else y
-        y = check_array(y, force_all_finite=True)
-        if len(y) != X.shape[0]:
-            raise ValueError("y must have the same number of samples as X")
-    return X

chemotools/variable_selection/__init__.py

@@ -1 +0,0 @@
-from .range_cut import RangeCut