Update to latest matchms, gensim and poetry buildsystem

.github/workflows/CI_build.yml

@@ -8,36 +8,36 @@ 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
+      - uses: actions/checkout@v4
       - name: Set up Python
-        uses: actions/setup-python@v1
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: 3.9
       - name: Python info
         run: |
           which python
           python --version
       - name: Build package and create dev environment
         run: |
-          python -m pip install --upgrade pip
-          pip install -e .[dev]
+          python -m pip install --upgrade pip poetry
+          poetry install
       - name: Show pip list
         run: |
           pip list
       - name: Test with coverage
         run: |
-          pytest --cov --cov-report term --cov-report xml --junitxml=xunit-result.xml
+          poetry run pytest --cov --cov-report term --cov-report xml --junitxml=xunit-result.xml
       - name: Correct coverage paths
         run: sed -i "s+$PWD/++g" coverage.xml
       - name: Check style against standards using prospector
         shell: bash -l {0}
-        run: prospector -o grouped -o pylint:pylint-report.txt
+        run: poetry run prospector -o grouped -o pylint:pylint-report.txt
       - name: Check whether import statements are used consistently
         shell: bash -l {0}
-        run: isort --check-only --diff --conda-env spec2vec-dev .
+        run: poetry run isort --check-only --diff --conda-env spec2vec-dev .
       - name: SonarCloud Scan
         if: github.repository == 'iomega/spec2vec'
         uses: sonarsource/sonarcloud-github-action@master
@@ -53,15 +53,15 @@ 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
+      - uses: actions/checkout@v4
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Python info
@@ -70,30 +70,31 @@ jobs:
           python --version
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip
+          python -m pip install --upgrade pip poetry
       - name: Build package
         run: |
-          pip install wheel twine
-          python setup.py sdist bdist_wheel
+          poetry build
       - name: Test package
         run: |
+          poetry install --only dev
           python -m twine check dist/*
       - name: Show pip list
         run: |
           pip list
       - name: Install development dependencies
         run: |
-          pip install -e .[dev]
+          poetry install
       - name: Test
         run: |
-          pytest
+          poetry run pytest
       - name: Show environment variables
         shell: bash -l {0}
         run: |
           env | sort
       - name: Build documentation
         shell: bash -l {0}
         run: |
+          cd readthedocs
           make coverage doctest html
         working-directory: readthedocs/
         env:
@@ -108,7 +109,7 @@ 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 +124,7 @@ 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: |

.github/workflows/cffconvert.yml

@@ -0,0 +1,19 @@
+name: cffconvert
+
+on:
+  push:
+    paths:
+      - CITATION.cff
+
+jobs:
+  validate:
+    name: "validate"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out a copy of the repository
+        uses: actions/checkout@v2
+
+      - name: Check whether the citation metadata from CITATION.cff is valid
+        uses: citation-file-format/[email protected]
+        with:
+          args: "--validate"

.github/workflows/pypi_publish.yml

@@ -5,21 +5,11 @@ on:
     types: [published]
 
 jobs:
-  publish:
+  build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python
-      uses: actions/setup-python@v1
-      with:
-        python-version: 3.7
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install setuptools wheel twine
-        python setup.py sdist bdist_wheel
-    - name: Publish package
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        user: __token__
-        password: ${{ secrets.PYPI_TOKEN }}
+      - uses: actions/checkout@v4
+      - name: Build and publish to pypi
+        uses: JRubics/[email protected]
+        with:
+          pypi_token: ${{ secrets.PYPI_TOKEN }}

.gitignore

@@ -16,8 +16,8 @@ pylint-report.txt
 xunit-result.xml
 .scannerwork/
 
-docs/_build
-docs/apidocs
+readthedocs/_build
+readthedocs/api
 
 # ide
 .idea

CITATION.cff

@@ -64,7 +64,7 @@ authors:
     given-names: Maksym
     orcid: "https://orcid.org/0000-0003-2056-8018"
 
-cff-version: "1.1.0"
+cff-version: 1.2.0
 keywords:
   - Word2Vec
   - "similarity measures"

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,

conda/environment-dev.yml

@@ -3,15 +3,23 @@ channels:
   - bioconda
   - conda-forge
   - defaults
-  - nlesc
 dependencies:
-  - gensim >=4.2.0
-  - matchms >=0.6.2
-  - numba >=0.51
+  - python
+  - gensim ==4.3.2
+  - matchms >=0.14.0, <=0.26.4
+  - numba
   - numpy
   - pip
-  - python >=3.7
   - scipy
   - tqdm
-  - pip:
-    - -e ..[dev]
+  - bump2version
+  - isort>=5.1.0
+  - pylint<2.12.0
+  - prospector
+  - pytest
+  - pytest-cov
+  - sphinx>=4.0.0
+  - sphinx_rtd_theme
+  - sphinxcontrib-apidoc
+  - yapf
+

conda/meta.yaml

@@ -1,65 +1,43 @@
 {% set name = "spec2vec" %}
-{% set version = "0.8.1" %}
+{% set version = "0.8.0" %}
 
 package:
   name: {{ name|lower }}
   version: {{ version }}
 
 source:
-  path: ..
-
-extra:
-  channels:
-    - nlesc
-    - conda-forge
-    - bioconda
+  url: https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/spec2vec-{{ version }}.tar.gz
+  sha256: 0a5a4c3d79dcc4e2b22ad44bc04a67aee1f7789e42f1f0143c9a7ffef54ce5b0
 
 build:
   noarch: python
-  preserve_egg_dir: True
+  script: {{ PYTHON }} -m pip install . -vv --no-deps --no-build-isolation
   number: 0
-  skip: True # [py2k]
-  script: {{ PYTHON }} -m pip install --no-deps --ignore-installed . -vv
 
 requirements:
-  build:
-    - conda-build
-    - conda-verify
-    - pytest-runner
-    - python
-    - matchms >=0.6.2
-    - numpy {{ numpy }}
-    - setuptools
   host:
     - python >=3.7
     - pip
-    - pytest-runner
-    - setuptools
   run:
-    - gensim >=4.2.0
-    - matchms >=0.14.0, <=0.26.4
-    - numba >=0.51
-    - numpy
-    - pip
     - python >=3.7
-    - scipy <=1.10.1
+    - gensim >=4.3.3
+    - matchms >=0.27.0
     - tqdm
 
 test:
   imports:
     - spec2vec
+  commands:
+    - pip check
+  requires:
+    - pip
 
 about:
   home: https://github.com/iomega/spec2vec
+  summary: Word2Vec based similarity measure of mass spectrometry data.
   license: Apache-2.0
-  license_family: APACHE
   license_file: LICENSE
-  summary: Word2Vec based similarity measure of mass spectrometry data.
-  description: Word2Vec based similarity measure of mass spectrometry data.
-  doc_url: https://spec2vec.readthedocs.io/
-  dev_url: https://github.com/iomega/spec2vec
 
 extra:
   recipe-maintainers:
-    - fdiblen
-    - florian-huber
+    - hechth

integration-tests/test_user_workflow_spec2vec.py

@@ -2,12 +2,12 @@
 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)
 from matchms.importing import load_from_mgf
-from spec2vec import Spec2Vec, SpectrumDocument
+from spec2vec import Spec2Vec, SpectrumDocumentWithLosses
 
 
 def test_user_workflow_spec2vec():
@@ -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 = [SpectrumDocumentWithLosses(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):