Update SpectrumDocument.py

.github/workflows/CI_build.yml

@@ -8,14 +8,14 @@ on:
 jobs:
 
   first_check:
-    name: first code check / python-3.8 / ubuntu-latest
+    name: first code check / python-3.9 / ubuntu-latest
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
       - name: Set up Python
         uses: actions/setup-python@v1
         with:
-          python-version: 3.8
+          python-version: 3.9
       - name: Python info
         run: |
           which python
@@ -53,10 +53,10 @@ jobs:
       fail-fast: false
       matrix:
         os: ['ubuntu-latest', 'macos-latest', 'windows-latest']
-        python-version: ['3.7', '3.8', '3.9']
+        python-version: ['3.9']
         exclude:
           # already tested in first_check job
-          - python-version: 3.8
+          - python-version: 3.9
             os: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
@@ -108,7 +108,7 @@ jobs:
           echo "The code is sufficiently documented with ${UNCOVERED_MEMBERS} uncovered members out of ${UNCOVERED_MEMBERS_ALLOWED} allowed.";
 
   anaconda_build:
-    name: Anaconda build / python-3.7 / ubuntu-latest
+    name: Anaconda build / python-3.9 / ubuntu-latest
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
@@ -123,7 +123,7 @@ jobs:
           activate-environment: spec2vec-build
           auto-update-conda: true
           environment-file: conda/environment-build.yml
-          python-version: 3.8
+          python-version: 3.9
       - name: Show conda config
         shell: bash -l {0}
         run: |

README.rst

@@ -139,7 +139,6 @@ dataset.
         s = msfilters.normalize_intensities(s)
         s = msfilters.reduce_to_number_of_peaks(s, n_required=10, ratio_desired=0.5, n_max=500)
         s = msfilters.select_by_mz(s, mz_from=0, mz_to=1000)
-        s = msfilters.add_losses(s, loss_mz_from=10.0, loss_mz_to=200.0)
         s = msfilters.require_minimum_number_of_peaks(s, n_required=10)
         return s
 
@@ -150,7 +149,7 @@ dataset.
     spectrums = [s for s in spectrums if s is not None]
 
     # Create spectrum documents
-    reference_documents = [SpectrumDocument(s, n_decimals=2) for s in spectrums]
+    reference_documents = [SpectrumDocument(s, n_decimals=2, loss_mz_from=10.0, loss_mz_to=200.0) for s in spectrums]
 
     model_file = "references.model"
     model = train_new_word2vec_model(reference_documents, iterations=[10, 20, 30], filename=model_file,

integration-tests/test_user_workflow_spec2vec.py

@@ -2,7 +2,7 @@
 import gensim
 import numpy as np
 from matchms import calculate_scores
-from matchms.filtering import (add_losses, add_parent_mass, default_filters,
+from matchms.filtering import (add_parent_mass, default_filters,
                                normalize_intensities,
                                reduce_to_number_of_peaks,
                                require_minimum_number_of_peaks, select_by_mz)
@@ -26,7 +26,6 @@ def apply_my_filters(s):
         s = normalize_intensities(s)
         s = reduce_to_number_of_peaks(s, n_required=10, ratio_desired=0.5)
         s = select_by_mz(s, mz_from=0, mz_to=1000)
-        s = add_losses(s, loss_mz_from=10.0, loss_mz_to=200.0)
         s = require_minimum_number_of_peaks(s, n_required=5)
         return s
 
@@ -40,7 +39,7 @@ def apply_my_filters(s):
     spectrums = [s for s in spectrums if s is not None]
 
     # convert spectrums to spectrum 'documents'
-    documents = [SpectrumDocument(s, n_decimals=1) for s in spectrums]
+    documents = [SpectrumDocument(s, n_decimals=1,  loss_mz_from=10.0, loss_mz_to=200.0) for s in spectrums]
 
     model_file = os.path.join(repository_root, "integration-tests", "test_user_workflow_spec2vec.model")
     if os.path.isfile(model_file):

setup.py

@@ -39,15 +39,13 @@
         "License :: OSI Approved :: Apache Software License",
         "Natural Language :: English",
         "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
         "Programming Language :: Python :: 3.9",
     ],
     test_suite="tests",
-    python_requires='>=3.7',
+    python_requires='>=3.9',
     install_requires=[
         "gensim >=4.2.0",
-        "matchms >=0.14.0",
+        "matchms >=0.27.0",
         "numba >=0.51",
         "numpy",
         "scipy",

spec2vec/SpectrumDocument.py

@@ -38,7 +38,7 @@ class SpectrumDocument(Document):
         [100.   150.   200.51]
         substance1
     """
-    def __init__(self, spectrum, n_decimals: int = 2):
+    def __init__(self, spectrum, n_decimals: int = 2, loss_mz_from=10, loss_mz_to=200):
         """
 
         Parameters
@@ -51,15 +51,17 @@ def __init__(self, spectrum, n_decimals: int = 2):
             word "[email protected]".
         """
         self.n_decimals = n_decimals
+        self.loss_mz_from = loss_mz_from
+        self.loss_mz_to = loss_mz_to
         self.weights = None
         super().__init__(obj=spectrum)
         self._add_weights()
 
     def _make_words(self):
         """Create word from peaks (and losses)."""
         peak_words = [f"peak@{mz:.{self.n_decimals}f}" for mz in self._obj.peaks.mz]
-        if self._obj.losses is not None:
-            loss_words = [f"loss@{mz:.{self.n_decimals}f}" for mz in self._obj.losses.mz]
+        if self.losses is not None:
+            loss_words = [f"loss@{mz:.{self.n_decimals}f}" for mz in self.losses.mz]
         else:
             loss_words = []
         self.words = peak_words + loss_words
@@ -70,8 +72,8 @@ def _add_weights(self):
         assert self._obj.peaks.intensities.max() <= 1, "peak intensities not normalized"
 
         peak_intensities = self._obj.peaks.intensities.tolist()
-        if self._obj.losses is not None:
-            loss_intensities = self._obj.losses.intensities.tolist()
+        if self.losses is not None:
+            loss_intensities = self.losses.intensities.tolist()
         else:
             loss_intensities = []
         self.weights = peak_intensities + loss_intensities
@@ -96,7 +98,7 @@ def metadata(self):
     @property
     def losses(self) -> Optional[Spikes]:
         """Return losses of original spectrum."""
-        return self._obj.losses
+        return self._obj.compute_losses(self.loss_mz_from, self.loss_mz_to)
 
     @property
     def peaks(self) -> Spikes:

tests/test_spectrum_document.py

@@ -1,7 +1,6 @@
 import numpy as np
 import pytest
 from matchms import Spectrum
-from matchms.filtering import add_losses
 from spec2vec import SpectrumDocument
 
 
@@ -11,7 +10,7 @@ def test_spectrum_document_init_n_decimals_default_value_no_losses():
     intensities = np.array([0, 0.01, 0.1, 1], dtype="float")
     metadata = dict(precursor_mz=100.0)
     spectrum = Spectrum(mz=mz, intensities=intensities, metadata=metadata)
-    spectrum_document = SpectrumDocument(spectrum)
+    spectrum_document = SpectrumDocument(spectrum, loss_mz_from = 0.0, loss_mz_to = -1.0)
 
     assert spectrum_document.n_decimals == 2, "Expected different default for n_decimals"
     assert len(spectrum_document) == 4
@@ -26,7 +25,7 @@ def test_spectrum_document_init_n_decimals_1_no_losses():
     intensities = np.array([0, 0.01, 0.1, 1], dtype="float")
     metadata = dict(precursor_mz=100.0)
     spectrum = Spectrum(mz=mz, intensities=intensities, metadata=metadata)
-    spectrum_document = SpectrumDocument(spectrum, n_decimals=1)
+    spectrum_document = SpectrumDocument(spectrum, n_decimals=1, loss_mz_from = 0.0, loss_mz_to = -1.0)
 
     assert spectrum_document.n_decimals == 1
     assert len(spectrum_document) == 4
@@ -42,8 +41,7 @@ def test_spectrum_document_init_default_with_losses():
     intensities = np.array([0, 0.01, 0.1, 1], dtype="float")
     metadata = dict(precursor_mz=100.0)
     spectrum_in = Spectrum(mz=mz, intensities=intensities, metadata=metadata)
-    spectrum = add_losses(spectrum_in)
-    spectrum_document = SpectrumDocument(spectrum)
+    spectrum_document = SpectrumDocument(spectrum_in)
 
     assert spectrum_document.n_decimals == 2, "Expected different default for n_decimals"
     assert len(spectrum_document) == 8
@@ -60,8 +58,7 @@ def test_spectrum_document_init_n_decimals_1():
     intensities = np.array([0, 0.01, 0.1, 1], dtype="float")
     metadata = dict(precursor_mz=100.0)
     spectrum_in = Spectrum(mz=mz, intensities=intensities, metadata=metadata)
-    spectrum = add_losses(spectrum_in)
-    spectrum_document = SpectrumDocument(spectrum, n_decimals=1)
+    spectrum_document = SpectrumDocument(spectrum_in, n_decimals=1)
 
     assert spectrum_document.n_decimals == 1
     assert len(spectrum_document) == 8
@@ -79,7 +76,7 @@ def test_spectrum_document_metadata_getter():
     metadata = {"precursor_mz": 100.0,
                 "smiles": "testsmiles"}
     spectrum_in = Spectrum(mz=mz, intensities=intensities, metadata=metadata)
-    spectrum_document = SpectrumDocument(spectrum_in, n_decimals=2)
+    spectrum_document = SpectrumDocument(spectrum_in, n_decimals=2, loss_mz_from=0.0, loss_mz_to=-1.0)
 
     assert spectrum_document.n_decimals == 2
     assert len(spectrum_document) == 4
@@ -112,7 +109,7 @@ def test_spectrum_document_peak_getter():
     intensities = np.array([0, 0.01, 0.1, 1], dtype="float")
     metadata = {"precursor_mz": 100.0}
     spectrum_in = Spectrum(mz=mz, intensities=intensities, metadata=metadata)
-    spectrum_document = SpectrumDocument(spectrum_in, n_decimals=2)
+    spectrum_document = SpectrumDocument(spectrum_in, n_decimals=2, loss_mz_from=0.0, loss_mz_to=-1.0)
 
     assert spectrum_document.words == [
         "[email protected]", "[email protected]", "[email protected]", "[email protected]"
@@ -127,8 +124,7 @@ def test_spectrum_document_losses_getter():
     intensities = np.array([0, 0.01, 0.1, 1], dtype="float")
     metadata = {"precursor_mz": 100.0}
     spectrum_in = Spectrum(mz=mz, intensities=intensities, metadata=metadata)
-    spectrum = add_losses(spectrum_in)
-    spectrum_document = SpectrumDocument(spectrum, n_decimals=2)
+    spectrum_document = SpectrumDocument(spectrum_in, n_decimals=2)
     assert np.all(spectrum_document.losses.mz == np.array([60., 70., 80., 90.])), \
         "Expected different losses"
     assert np.all(spectrum_document.losses.intensities == intensities[::-1]), \