chemotools 0.1.3__tar.gz → 0.1.5__tar.gz

{chemotools-0.1.3 → chemotools-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chemotools
-Version: 0.1.3
+Version: 0.1.5
 Summary: Package to integrate chemometrics in scikit-learn pipelines
 Home-page: https://github.com/paucablop/chemotools
 Author: Pau Cabaneros Lopez
@@ -14,8 +14,10 @@ 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
+Requires-Dist: scikit-learn>=1.4.0
 
 ![chemotools](assets/images/logo_pixel.png)
 

{chemotools-0.1.3 → chemotools-0.1.5}/chemotools/augmentation/uniform_noise.py

@@ -11,10 +11,10 @@ class UniformNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
 
     Parameters
     ----------
-    low : float, default=0.0
+    min : float, default=0.0
         The lower bound of the uniform distribution.
 
-    high : float, default=0.0
+    max : float, default=0.0
         The upper bound of the uniform distribution.
 
     random_state : int, default=None
@@ -38,9 +38,9 @@ class UniformNoise(OneToOneFeatureMixin, BaseEstimator, TransformerMixin):
     """
 
 
-    def __init__(self, low: float = 0.0, high: float = 0.0, random_state: int = None):
-        self.low = low
-        self.high = high
+    def __init__(self, min: float = 0.0, max: float = 0.0, random_state: int = None):
+        self.min = min
+        self.max = max
         self.random_state = random_state
 
     def fit(self, X: np.ndarray, y=None) -> "UniformNoise":
@@ -109,4 +109,4 @@ class UniformNoise(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.uniform(self.low, self.high, size=x.shape)
+        return x + self._rng.uniform(self.min, self.max, size=x.shape)

chemotools-0.1.5/chemotools/datasets/_base.py

@@ -0,0 +1,122 @@
+import os
+
+
+import pandas as pd
+import polars as pl
+
+PACKAGE_DIRECTORY = os.path.dirname(os.path.abspath(__file__))
+
+
+def load_fermentation_train(set_output="pandas"):
+    """
+    Loads the training data of the fermentation dataset. This data corresponds to a synthetic dataset measured
+    off-line. This dataset is designed to represent the variability of real fermentation data.
+
+    Arguments
+    -------
+    set_output: str, default='pandas'
+        The output format of the data. It can be 'pandas' or 'polars'. If 'polars', the data is returned as a polars DataFrame.
+
+    Returns
+    -------
+    train_spectra: pd.DataFrame A pandas DataFrame containing the synthetic spectra measured to train the model.
+    train_hplc: pd.DataFrame A pandas DataFrame containing the corresponding reference measurements analyzed with HPLC.
+
+    References
+    -------
+    - Cabaneros Lopez Pau, Udugama Isuru A., Thomsen Sune Tjalfe, Roslander Christian, Junicke Helena,
+    Mauricio Iglesias Miguel, Gernaey Krist V. Transforming data into information:
+    A parallel hybrid model for real-time state estimation in lignocellulose ethanol fermentations.
+    """
+    if set_output == "pandas":
+        train_spectra = pd.read_csv(PACKAGE_DIRECTORY + "/data/train_spectra.csv")
+        train_spectra.columns = train_spectra.columns.astype(float)
+        train_hplc = pd.read_csv(PACKAGE_DIRECTORY + "/data/train_hplc.csv")
+        return train_spectra, train_hplc
+
+    if set_output == "polars":
+        train_spectra = pl.read_csv(PACKAGE_DIRECTORY + "/data/train_spectra.csv")
+        train_hplc = pl.read_csv(PACKAGE_DIRECTORY + "/data/train_hplc.csv")
+        return train_spectra, train_hplc
+
+    else:
+        raise ValueError(
+            "Invalid value for set_output. Please use 'pandas' or 'polars'."
+        )
+
+
+def load_fermentation_test(set_output="pandas"):
+    """
+    Loads the testing data of the fermentation dataset. This data corresponds to real fermentation data measured
+    on-line during a fermentation process.
+
+    Arguments
+    -------
+    set_output: str, default='pandas'
+        The output format of the data. It can be 'pandas' or 'polars'. If 'polars', the data is returned as a polars DataFrame.
+
+    Returns
+    -------
+    test_spectra: pd.DataFrame A pandas DataFrame containing the on-line spectra measured to train the model.
+    test_hplc: pd.DataFrame A pandas DataFrame containing the corresponding HPLC measurements.
+
+    References
+    -------
+    - Cabaneros Lopez Pau, Udugama Isuru A., Thomsen Sune Tjalfe, Roslander Christian, Junicke Helena,
+    Mauricio Iglesias Miguel, Gernaey Krist V. Transforming data into information:
+    A parallel hybrid model for real-time state estimation in lignocellulose ethanol fermentations.
+    """
+    if set_output == "pandas":
+        fermentation_spectra = pd.read_csv(
+            PACKAGE_DIRECTORY + "/data/fermentation_spectra.csv"
+        )
+        fermentation_spectra.columns = fermentation_spectra.columns.astype(float)
+        fermentation_hplc = pd.read_csv(
+            PACKAGE_DIRECTORY + "/data/fermentation_hplc.csv"
+        )
+        return fermentation_spectra, fermentation_hplc
+
+    if set_output == "polars":
+        fermentation_spectra = pl.read_csv(
+            PACKAGE_DIRECTORY + "/data/fermentation_spectra.csv"
+        )
+        fermentation_hplc = pl.read_csv(
+            PACKAGE_DIRECTORY + "/data/fermentation_hplc.csv"
+        )
+        return fermentation_spectra, fermentation_hplc
+
+    else:
+        raise ValueError(
+            "Invalid value for set_output. Please use 'pandas' or 'polars'."
+        )
+
+
+def load_coffee(set_output="pandas"):
+    """
+    Loads the coffee dataset. This data corresponds to a coffee spectra from three different origins
+    measured off-line using attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR).
+
+    Arguments
+    -------
+    set_output: str, default='pandas'
+        The output format of the data. It can be 'pandas' or 'polars'. If 'polars', the data is returned as a polars DataFrame.
+
+    Returns
+    -------
+    coffee_spectra: pd.DataFrame A pandas DataFrame containing the coffee spectra.
+    coffee_labels: pd.DataFrame A pandas DataFrame containing the corresponding labels.
+    """
+    if set_output == "pandas":
+        coffee_spectra = pd.read_csv(PACKAGE_DIRECTORY + "/data/coffee_spectra.csv")
+        coffee_labels = pd.read_csv(PACKAGE_DIRECTORY + "/data/coffee_labels.csv")
+        return coffee_spectra, coffee_labels
+    
+    if set_output == "polars":
+        coffee_spectra = pl.read_csv(PACKAGE_DIRECTORY + "/data/coffee_spectra.csv")
+        coffee_labels = pl.read_csv(PACKAGE_DIRECTORY + "/data/coffee_labels.csv")
+        return coffee_spectra, coffee_labels
+    
+    else:
+        raise ValueError(
+            "Invalid value for set_output. Please use 'pandas' or 'polars'."
+        )

{chemotools-0.1.3 → chemotools-0.1.5}/chemotools/feature_selection/_range_cut.py

@@ -34,6 +34,8 @@ class RangeCut(BaseEstimator, SelectorMixin):
     end_index_ : int
         The index of the end of the range. It is -1 if the wavenumbers are not provided.
 
+    wavenuumbers_ : array-like
+        The cut wavenumbers of the input data.
 
     Methods
     -------
@@ -75,9 +77,11 @@ class RangeCut(BaseEstimator, SelectorMixin):
         if self.wavenumbers is None:
             self.start_index_ = self.start
             self.end_index_ = self.end
+            self.wavenumbers_ = None
         else:
             self.start_index_ = self._find_index(self.start)
             self.end_index_ = self._find_index(self.end)
+            self.wavenumbers_ = self.wavenumbers[self.start_index_ : self.end_index_]
 
         return self
     

{chemotools-0.1.3 → chemotools-0.1.5}/chemotools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chemotools
-Version: 0.1.3
+Version: 0.1.5
 Summary: Package to integrate chemometrics in scikit-learn pipelines
 Home-page: https://github.com/paucablop/chemotools
 Author: Pau Cabaneros Lopez
@@ -14,8 +14,10 @@ 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
+Requires-Dist: scikit-learn>=1.4.0
 
 ![chemotools](assets/images/logo_pixel.png)
 

chemotools-0.1.5/chemotools.egg-info/requires.txt

@@ -0,0 +1,6 @@
+numpy
+pandas
+polars
+pyarrow
+scipy
+scikit-learn>=1.4.0

{chemotools-0.1.3 → chemotools-0.1.5}/setup.py

@@ -27,8 +27,10 @@ setuptools.setup(
     install_requires=[
         "numpy",
         "pandas",
+        "polars",
+        "pyarrow",
         "scipy",
-        "scikit-learn",
+        "scikit-learn>=1.4.0",
     ],
     include_package_data=True,
     package_data={'': ['tests/resources/*.csv',

chemotools-0.1.5/tests/test_datasets.py

@@ -0,0 +1,111 @@
+import pandas as pd
+import polars as pl
+import pytest
+
+from chemotools.datasets import (
+    load_coffee,
+    load_fermentation_test,
+    load_fermentation_train,
+)
+
+
+def test_load_coffee_pandas():
+    # Arrange
+
+    # Act
+    coffee_spectra, coffee_labels = load_coffee()
+
+    # Assert
+    assert coffee_spectra.shape == (60, 1841)
+    assert coffee_labels.shape == (60, 1)
+    assert isinstance(coffee_spectra, pd.DataFrame)
+    assert isinstance(coffee_labels, pd.DataFrame)
+
+
+def test_load_coffee_polars():
+    # Arrange
+
+    # Act
+    coffee_spectra, coffee_labels = load_coffee(set_output="polars")
+
+    # Assert
+    assert coffee_spectra.shape == (60, 1841)
+    assert coffee_labels.shape == (60, 1)
+    assert isinstance(coffee_spectra, pl.DataFrame)
+    assert isinstance(coffee_labels, pl.DataFrame)
+
+
+def test_load_coffee_exception():
+    # Arrange
+
+    # Act and Assert
+    with pytest.raises(ValueError):
+        coffee_spectra, coffee_labels = load_coffee(set_output="plars")
+
+
+def test_load_fermentation_test_pandas():
+    # Arrange
+
+    # Act
+    test_spectra, test_hplc = load_fermentation_test()
+
+    # Assert
+    assert test_spectra.shape == (1629, 1047)
+    assert test_hplc.shape == (34, 6)
+    assert isinstance(test_spectra, pd.DataFrame)
+    assert isinstance(test_hplc, pd.DataFrame)
+
+
+def test_load_fermentation_test_polars():
+    # Arrange
+
+    # Act
+    test_spectra, test_hplc = load_fermentation_test(set_output="polars")
+
+    # Assert
+    assert test_spectra.shape == (1629, 1047)
+    assert test_hplc.shape == (34, 6)
+    assert isinstance(test_spectra, pl.DataFrame)
+    assert isinstance(test_hplc, pl.DataFrame)
+
+
+def test_load_fermentation_test_exception():
+    # Arrange
+
+    # Act and Assert
+    with pytest.raises(ValueError):
+        test_spectra, test_hplc = load_fermentation_test(set_output="plars")
+
+
+def test_load_fermentation_train_pandas():
+    # Arrange
+
+    # Act
+    train_spectra, train_hplc = load_fermentation_train()
+
+    # Assert
+    assert train_spectra.shape == (21, 1047)
+    assert train_hplc.shape == (21, 1)
+    assert isinstance(train_spectra, pd.DataFrame)
+    assert isinstance(train_hplc, pd.DataFrame)
+
+
+def test_load_fermentation_train_polars():
+    # Arrange
+
+    # Act
+    train_spectra, train_hplc = load_fermentation_train(set_output="polars")
+
+    # Assert
+    assert train_spectra.shape == (21, 1047)
+    assert train_hplc.shape == (21, 1)
+    assert isinstance(train_spectra, pl.DataFrame)
+    assert isinstance(train_hplc, pl.DataFrame)
+
+
+def test_load_fermentation_train_exception():
+    # Arrange
+
+    # Act and Assert
+    with pytest.raises(ValueError):
+        train_spectra, train_hplc = load_fermentation_train(set_output="plars")

{chemotools-0.1.3 → chemotools-0.1.5}/tests/test_functionality.py

@@ -1,5 +1,6 @@
 import numpy as np
 import pandas as pd
+import polars as pl
 import pytest
 
 from chemotools.augmentation import (
@@ -622,9 +623,10 @@ def test_range_cut_by_wavenumber_with_list():
 
     # Assert
     assert np.allclose(spectrum_corrected[0], spectrum[0][1:7], atol=1e-8)
+    assert range_cut.wavenumbers_ == [2, 3, 4, 5, 6, 7]
 
 
-def test_range_cut_by_wavenumber_with_dataframe():
+def test_range_cut_by_wavenumber_with_pandas_dataframe():
     # Arrange
     wavenumbers = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
     spectrum = pd.DataFrame(np.array([[10, 12, 14, 16, 14, 12, 10, 12, 14, 16]]))
@@ -637,6 +639,19 @@ def test_range_cut_by_wavenumber_with_dataframe():
     assert type(spectrum_corrected) == pd.DataFrame
 
 
+def test_range_cut_by_wavenumber_with_polars_dataframe():
+    # Arrange
+    wavenumbers = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+    spectrum = pl.DataFrame(np.array([[10, 12, 14, 16, 14, 12, 10, 12, 14, 16]]))
+    range_cut = RangeCut(start=2.5, end=7.9, wavenumbers=wavenumbers).set_output(transform='polars')
+
+    # Act
+    spectrum_corrected = range_cut.fit_transform(spectrum)
+
+    # Assert
+    assert type(spectrum_corrected) == pl.DataFrame
+
+
 def test_robust_normal_variate():
     # Arrange
     spectrum = np.array([2, 3.5, 5, 27, 8, 9]).reshape(1, -1)
@@ -740,7 +755,7 @@ def test_subtract_reference_without_reference(spectrum):
 def test_uniform_noise():
     # Arrange
     spectrum = np.ones(10000).reshape(1, -1)
-    uniform_noise = UniformNoise(low=-1, high=1, random_state=42)
+    uniform_noise = UniformNoise(min=-1, max=1, random_state=42)
 
     # Act
     spectrum_corrected = uniform_noise.fit_transform(spectrum)

chemotools-0.1.3/chemotools/datasets/_base.py

@@ -1,69 +0,0 @@
-import pandas as pd
-import os
-
-PACKAGE_DIRECTORY = os.path.dirname(os.path.abspath(__file__))
-
-
-def load_fermentation_train():
-    """
-    Loads the training data of the fermentation dataset. This data corresponds to a synthetic dataset measured 
-    off-line. This dataset is designed to represent the variability of real fermentation data.
-
-    Returns
-    -------
-    train_spectra: pd.DataFrame A pandas DataFrame containing the synthetic spectra measured to train the model.
-    train_hplc: pd.DataFrame A pandas DataFrame containing the corresponding reference measurements analyzed with HPLC.
-
-    References
-    -------
-    - Cabaneros Lopez Pau, Udugama Isuru A., Thomsen Sune Tjalfe, Roslander Christian, Junicke Helena,
-    Mauricio Iglesias Miguel, Gernaey Krist V. Transforming data into information:
-    A parallel hybrid model for real-time state estimation in lignocellulose ethanol fermentations.
-    """
-    train_spectra = pd.read_csv(PACKAGE_DIRECTORY + "/data/train_spectra.csv")
-    train_spectra.columns = train_spectra.columns.astype(float)
-    train_hplc = pd.read_csv(PACKAGE_DIRECTORY + "/data/train_hplc.csv")
-
-    return train_spectra, train_hplc
-
-
-def load_fermentation_test():
-    """
-    Loads the testing data of the fermentation dataset. This data corresponds to real fermentation data measured
-    on-line during a fermentation process. 
-
-    Returns
-    -------
-    test_spectra: pd.DataFrame A pandas DataFrame containing the on-line spectra measured to train the model.
-    test_hplc: pd.DataFrame A pandas DataFrame containing the corresponding HPLC measurements.
-
-    References
-    -------
-    - Cabaneros Lopez Pau, Udugama Isuru A., Thomsen Sune Tjalfe, Roslander Christian, Junicke Helena,
-    Mauricio Iglesias Miguel, Gernaey Krist V. Transforming data into information:
-    A parallel hybrid model for real-time state estimation in lignocellulose ethanol fermentations.
-    """
-    fermentation_spectra = pd.read_csv(
-        PACKAGE_DIRECTORY + "/data/fermentation_spectra.csv"
-    )
-    fermentation_spectra.columns = fermentation_spectra.columns.astype(float)
-    fermentation_hplc = pd.read_csv(PACKAGE_DIRECTORY + "/data/fermentation_hplc.csv")
-
-    return fermentation_spectra, fermentation_hplc
-
-
-def load_coffee():
-    """
-    Loads the coffee dataset. This data corresponds to a coffee spectra from three different origins 
-    measured off-line using attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR).
-
-    Returns
-    -------
-    coffee_spectra: pd.DataFrame A pandas DataFrame containing the coffee spectra.
-    coffee_labels: pd.DataFrame A pandas DataFrame containing the corresponding labels.
-    """
-
-    coffee_spectra = pd.read_csv(PACKAGE_DIRECTORY + "/data/coffee_spectra.csv")
-    coffee_labels = pd.read_csv(PACKAGE_DIRECTORY + "/data/coffee_labels.csv")
-
-    return coffee_spectra, coffee_labels

chemotools-0.1.3/chemotools.egg-info/requires.txt

@@ -1,4 +0,0 @@
-numpy
-pandas
-scipy
-scikit-learn

chemotools-0.1.3/tests/test_datasets.py

@@ -1,43 +0,0 @@
-import pandas as pd
-
-from chemotools.datasets import load_coffee, load_fermentation_test, load_fermentation_train
-
-
-def test_load_coffee():
-    # Arrange
-
-    # Act
-    coffee_spectra, coffee_labels = load_coffee()
-
-    # Assert
-    assert coffee_spectra.shape == (60, 1841)
-    assert coffee_labels.shape == (60, 1)
-    assert isinstance(coffee_spectra, pd.DataFrame)
-    assert isinstance(coffee_labels, pd.DataFrame)
-
-
-def test_load_fermentation_test():
-    # Arrange
-
-    # Act
-    test_spectra, test_hplc = load_fermentation_test()
-
-    # Assert
-    assert test_spectra.shape == (1629, 1047)
-    assert test_hplc.shape == (34, 6)
-    assert isinstance(test_spectra, pd.DataFrame)
-    assert isinstance(test_hplc, pd.DataFrame)
-
-def test_load_fermentation_train():
-    # Arrange
-
-    # Act
-    train_spectra, train_hplc = load_fermentation_train()
-
-    # Assert
-    assert train_spectra.shape == (21, 1047)
-    assert train_hplc.shape == (21, 1)
-    assert isinstance(train_spectra, pd.DataFrame)
-    assert isinstance(train_hplc, pd.DataFrame)
-
-