chemotools 0.1.4__py3-none-any.whl → 0.1.5__py3-none-any.whl

chemotools/datasets/_base.py

@@ -1,14 +1,22 @@
-import pandas as pd
 import os
 
+
+import pandas as pd
+import polars as pl
+
 PACKAGE_DIRECTORY = os.path.dirname(os.path.abspath(__file__))
 
 
-def load_fermentation_train():
+def load_fermentation_train(set_output="pandas"):
     """
-    Loads the training data of the fermentation dataset. This data corresponds to a synthetic dataset measured 
+    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.
@@ -20,17 +28,32 @@ def load_fermentation_train():
     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")
+    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
 
-    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():
+
+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. 
+    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
     -------
@@ -43,27 +66,57 @@ def load_fermentation_test():
     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():
+    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 
+    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.
     """
-
-    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 == "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/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
     -------
@@ -75,6 +77,7 @@ 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)

{chemotools-0.1.4.dist-info → chemotools-0.1.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chemotools
-Version: 0.1.4
+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-0.1.4.dist-info → chemotools-0.1.5.dist-info}/RECORD

@@ -16,7 +16,7 @@ chemotools/baseline/_non_negative.py,sha256=SyiS_-cfnypLXY3gC80oo7doqXUlHAAgmwrk
 chemotools/baseline/_polynomial_correction.py,sha256=0w9qA_w5dc9IIv5KMmAOZ06hWDuk-uyealsTaZX2qgw,3749
 chemotools/baseline/_subtract_reference.py,sha256=vfre6Z-bgDCwwl3VnpahmGJTBFJVK9HGBrUsjfl2O9o,3135
 chemotools/datasets/__init__.py,sha256=ojqxb-C_eDmizwUqVCJ8BqJxwULD7_hWCyVIA1uRO0c,116
-chemotools/datasets/_base.py,sha256=Z174CaIlpx17Yu8Pg1qZPuHWkS3BYWn7gtOYsoe8zNk,2895
+chemotools/datasets/_base.py,sha256=ftAmf2jHWUW_YQobXCsIFC617PeXwsmZIwAgab9EvL8,4890
 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
@@ -29,7 +29,7 @@ chemotools/derivative/_norris_william.py,sha256=NKmuo95vNWHQOdcww7APU9Z4s1wWExIR
 chemotools/derivative/_savitzky_golay.py,sha256=5At4sexJH0RvjkrvVfJvhIfaxXD3vE4Ozq1VClb3qlU,3417
 chemotools/feature_selection/__init__.py,sha256=p47SuyI7jMpV7kiaAsv2hA20smKf5Yo6447LfrNdDhY,76
 chemotools/feature_selection/_index_selector.py,sha256=2z2aAyMUOuP7x1n19RV5JGf6ZcM3mtJZby8tEgBOix4,3379
-chemotools/feature_selection/_range_cut.py,sha256=gcKjmCGn0SwKRHck3QIrqWN3q-S9qRgGlSbqzaOxG7Y,3309
+chemotools/feature_selection/_range_cut.py,sha256=ikWW9FhsbyzijSUYTcx048eOyK65mdbfOuFRF_Ee3rk,3424
 chemotools/scale/__init__.py,sha256=CQPUPx-8pUeHHbN9p5smFro3xtl_UEE0YeXHLVd7Lfk,118
 chemotools/scale/_min_max_scaler.py,sha256=-Wnr7zW-zmW6nR5J5yPdBm1KNuQDa9w27Un7rAr-s8E,2806
 chemotools/scale/_norm_scaler.py,sha256=bjMg1-x2I1xZmmbIgl4vXZZweJV-w3Euta0KGff_2Gk,2363
@@ -48,11 +48,11 @@ chemotools/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 chemotools/utils/check_inputs.py,sha256=fRAV4HIaGamdj_PNXSNnl7LurXytACNTGO51rhPpMUY,512
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/fixtures.py,sha256=Xa-Vd62Kd1fyWg3PLUSP6iIkOK8etrbyOkMJTn3dvX8,1933
-tests/test_datasets.py,sha256=_3mMDYC-vUnb5BenMqvuhmkHI2PPIdsyq_nNu2ggH20,1055
-tests/test_functionality.py,sha256=cWFWSVTaEkMoZD1tB6-wfEXX59bEDzE8EVo0NcmEABw,21237
+tests/test_datasets.py,sha256=ZdyjSJVX-iJyz8SoRgFfRLP9-ajNEyqWxs00ZfIv0eo,2712
+tests/test_functionality.py,sha256=v8dH7TPA2D-5byl1nwpPW9ejx1Fzd5QsKuQQ4aouCjo,21707
 tests/test_sklearn_compliance.py,sha256=CRB_0X9HRGj0pOpUCmiSHwJkCsVB-yK_apsyUONmfmw,5856
-chemotools-0.1.4.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
-chemotools-0.1.4.dist-info/METADATA,sha256=TawdLG6hGhatxlxsWZ4ZoQO3FZIBhJdcgBfi6_P4CxA,5018
-chemotools-0.1.4.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-chemotools-0.1.4.dist-info/top_level.txt,sha256=eNcNcKSdo-1H_2gwSDrS__dr7BM3R73Cnn-pBiW5FEw,17
-chemotools-0.1.4.dist-info/RECORD,,
+chemotools-0.1.5.dist-info/LICENSE,sha256=qtyOy2wDQVX9hxp58h3T-6Lmfv-mSCHoSRkcLUdM9bg,1070
+chemotools-0.1.5.dist-info/METADATA,sha256=s3KJEhQ3jgq6DPl7PW5Hl3x9f5kKyCDi-Cedon48DDA,5071
+chemotools-0.1.5.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+chemotools-0.1.5.dist-info/top_level.txt,sha256=eNcNcKSdo-1H_2gwSDrS__dr7BM3R73Cnn-pBiW5FEw,17
+chemotools-0.1.5.dist-info/RECORD,,

tests/test_datasets.py

@@ -1,9 +1,15 @@
 import pandas as pd
+import polars as pl
+import pytest
 
-from chemotools.datasets import load_coffee, load_fermentation_test, load_fermentation_train
+from chemotools.datasets import (
+    load_coffee,
+    load_fermentation_test,
+    load_fermentation_train,
+)
 
 
-def test_load_coffee():
+def test_load_coffee_pandas():
     # Arrange
 
     # Act
@@ -16,7 +22,28 @@ def test_load_coffee():
     assert isinstance(coffee_labels, pd.DataFrame)
 
 
-def test_load_fermentation_test():
+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
@@ -28,7 +55,29 @@ def test_load_fermentation_test():
     assert isinstance(test_spectra, pd.DataFrame)
     assert isinstance(test_hplc, pd.DataFrame)
 
-def test_load_fermentation_train():
+
+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
@@ -40,4 +89,23 @@ def test_load_fermentation_train():
     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")

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 (
@@ -625,7 +626,7 @@ def test_range_cut_by_wavenumber_with_list():
     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]]))
@@ -638,6 +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)