chemotools 0.1.5__tar.gz → 0.1.7__tar.gz

{chemotools-0.1.5 → chemotools-0.1.7}/PKG-INFO

@@ -1,23 +1,22 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: chemotools
-Version: 0.1.5
-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: 0.1.7
+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: pandas
-Requires-Dist: polars
-Requires-Dist: pyarrow
-Requires-Dist: scipy
-Requires-Dist: scikit-learn>=1.4.0
 
 ![chemotools](assets/images/logo_pixel.png)
 
@@ -27,6 +26,8 @@ Requires-Dist: scikit-learn>=1.4.0
 [![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-0.1.5 → chemotools-0.1.7}/README.md

@@ -6,6 +6,8 @@
 [![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-0.1.5 → chemotools-0.1.7}/chemotools/augmentation/__init__.py

@@ -4,3 +4,13 @@ from .normal_noise import NormalNoise
 from .index_shift import IndexShift
 from .spectrum_scale import SpectrumScale
 from .uniform_noise import UniformNoise
+
+
+__all__ = [
+    "BaselineShift",
+    "ExponentialNoise",
+    "NormalNoise",
+    "IndexShift",
+    "SpectrumScale",
+    "UniformNoise",
+]

{chemotools-0.1.5 → chemotools-0.1.7}/chemotools/augmentation/baseline_shift.py

@@ -1,11 +1,11 @@
+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 BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class BaselineShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     Adds a constant baseline to the data. The baseline is drawn from a one-sided
     uniform distribution between 0 and 0 + scale.
@@ -17,7 +17,7 @@ class BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     random_state : int, default=None
         The random state to use for the random number generator.
-    
+
     Attributes
     ----------
     n_features_in_ : int
@@ -25,7 +25,7 @@ class BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     _is_fitted : bool
         Whether the transformer has been fitted to data.
-    
+
     Methods
     -------
     fit(X, y=None)
@@ -35,15 +35,14 @@ class BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         Transform the input data by adding a baseline the spectrum.
     """
 
-
-    def __init__(self, scale: int = 0.0, random_state: int = None):
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
         self.scale = scale
         self.random_state = random_state
 
     def fit(self, X: np.ndarray, y=None) -> "BaselineShift":
         """
         Fit the transformer to the input data.
-        
+
         Parameters
         ----------
         X : np.ndarray of shape (n_samples, n_features)
@@ -58,8 +57,9 @@ class BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
         # Set the number of features
         self.n_features_in_ = X.shape[1]
 
@@ -92,12 +92,21 @@ class BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         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()
+        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 scaled spectrum
         for i, x in enumerate(X_):
@@ -108,4 +117,3 @@ class BaselineShift(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     def _add_baseline(self, x) -> np.ndarray:
         adding_factor = self._rng.uniform(low=0, high=self.scale)
         return np.add(x, adding_factor)
-    

{chemotools-0.1.5 → chemotools-0.1.7}/chemotools/augmentation/exponential_noise.py

@@ -1,11 +1,11 @@
+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 ExponentialNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class ExponentialNoise(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     Add exponential noise to the input data.
 
@@ -16,7 +16,7 @@ class ExponentialNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     random_state : int, default=None
         The random state to use for the random number generator.
-    
+
     Attributes
     ----------
     n_features_in_ : int
@@ -24,7 +24,7 @@ class ExponentialNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     _is_fitted : bool
         Whether the transformer has been fitted to data.
-    
+
     Methods
     -------
     fit(X, y=None)
@@ -34,15 +34,14 @@ class ExponentialNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         Transform the input data by adding random noise.
     """
 
-
-    def __init__(self, scale: float = 0.0, random_state: int = None):
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
         self.scale = scale
         self.random_state = random_state
 
     def fit(self, X: np.ndarray, y=None) -> "ExponentialNoise":
         """
         Fit the transformer to the input data.
-        
+
         Parameters
         ----------
         X : np.ndarray of shape (n_samples, n_features)
@@ -57,8 +56,9 @@ class ExponentialNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
-
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
         # Set the number of features
         self.n_features_in_ = X.shape[1]
 
@@ -91,12 +91,21 @@ class ExponentialNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         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()
+        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 exponential variate
         for i, x in enumerate(X_):
@@ -105,4 +114,4 @@ class ExponentialNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _add_random_noise(self, x) -> np.ndarray:
-        return x + self._rng.exponential(self.scale, size=x.shape)
+        return x + self._rng.exponential(self.scale, size=x.shape)

chemotools-0.1.7/chemotools/augmentation/index_shift.py

@@ -0,0 +1,199 @@
+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
+
+
+class IndexShift(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
+    """
+    Shift the spectrum a given number of indices between - shift and + shift drawn
+    from a discrete uniform distribution.
+
+    Parameters
+    ----------
+    shift : float, default=0.0
+        Shifts the data by a random integer between -shift and shift.
+
+    random_state : int, default=None
+        The random state to use for the random number generator.
+
+    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 shifting the spectrum.
+    """
+
+    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":
+        """
+        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 : IndexShift
+            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 number of features
+        self.n_features_in_ = X.shape[1]
+
+        # Set the fitted attribute to True
+        self._is_fitted = True
+
+        # Instantiate the random number generator
+        self._rng = np.random.default_rng(self.random_state)
+
+        return self
+
+    def transform(self, X: np.ndarray, y=None) -> np.ndarray:
+        """
+        Transform the input data by shifting the spectrum.
+
+        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_ = 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]}"
+            )
+
+        # Calculate the standard normal variate
+        for i, x in enumerate(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-0.1.5 → chemotools-0.1.7}/chemotools/augmentation/normal_noise.py

@@ -1,11 +1,11 @@
+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 NormalNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class NormalNoise(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     Add normal noise to the input data.
 
@@ -16,7 +16,7 @@ class NormalNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     random_state : int, default=None
         The random state to use for the random number generator.
-    
+
     Attributes
     ----------
     n_features_in_ : int
@@ -24,7 +24,7 @@ class NormalNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     _is_fitted : bool
         Whether the transformer has been fitted to data.
-    
+
     Methods
     -------
     fit(X, y=None)
@@ -34,15 +34,14 @@ class NormalNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         Transform the input data by adding random noise.
     """
 
-
-    def __init__(self, scale: float = 0.0, random_state: int = None):
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
         self.scale = scale
         self.random_state = random_state
 
     def fit(self, X: np.ndarray, y=None) -> "NormalNoise":
         """
         Fit the transformer to the input data.
-        
+
         Parameters
         ----------
         X : np.ndarray of shape (n_samples, n_features)
@@ -57,7 +56,9 @@ class NormalNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
 
         # Set the number of features
         self.n_features_in_ = X.shape[1]
@@ -91,12 +92,21 @@ class NormalNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         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()
+        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_):
@@ -105,4 +115,4 @@ class NormalNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _add_random_noise(self, x) -> np.ndarray:
-        return x + self._rng.normal(0, self.scale, size=x.shape)
+        return x + self._rng.normal(0, self.scale, size=x.shape)

{chemotools-0.1.5 → chemotools-0.1.7}/chemotools/augmentation/spectrum_scale.py

@@ -1,11 +1,11 @@
+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 SpectrumScale(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
+class SpectrumScale(TransformerMixin, OneToOneFeatureMixin, BaseEstimator):
     """
     Scales the data by a value drawn from the uniform distribution centered
     around 1.0.
@@ -17,7 +17,7 @@ class SpectrumScale(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     random_state : int, default=None
         The random state to use for the random number generator.
-    
+
     Attributes
     ----------
     n_features_in_ : int
@@ -25,7 +25,7 @@ class SpectrumScale(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     _is_fitted : bool
         Whether the transformer has been fitted to data.
-    
+
     Methods
     -------
     fit(X, y=None)
@@ -35,15 +35,14 @@ class SpectrumScale(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         Transform the input data by scaling the spectrum.
     """
 
-
-    def __init__(self, scale: int = 0.0, random_state: int = None):
+    def __init__(self, scale: float = 0.0, random_state: Optional[int] = None):
         self.scale = scale
         self.random_state = random_state
 
     def fit(self, X: np.ndarray, y=None) -> "SpectrumScale":
         """
         Fit the transformer to the input data.
-        
+
         Parameters
         ----------
         X : np.ndarray of shape (n_samples, n_features)
@@ -58,7 +57,9 @@ class SpectrumScale(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
             The fitted transformer.
         """
         # Check that X is a 2D array and has only finite values
-        X = check_input(X)
+        X = validate_data(
+            self, X, y="no_validation", ensure_2d=True, reset=True, dtype=np.float64
+        )
 
         # Set the number of features
         self.n_features_in_ = X.shape[1]
@@ -92,12 +93,21 @@ class SpectrumScale(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         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()
+        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 scaled spectrum
         for i, x in enumerate(X_):
@@ -106,6 +116,5 @@ class SpectrumScale(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
         return X_.reshape(-1, 1) if X_.ndim == 1 else X_
 
     def _scale_spectrum(self, x) -> np.ndarray:
-        scaling_factor = self._rng.uniform(low=1-self.scale, high=1+self.scale)
+        scaling_factor = self._rng.uniform(low=1 - self.scale, high=1 + self.scale)
         return np.multiply(x, scaling_factor)
-