Merge pull request #88 from iomega/matchms_0_18

Move to matchms >=0.18.0

Author: florian-huber

CHANGELOG.md

@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.8.0] - 2022-01-06
+
+### Changed
+
+- Minor changes to make tests pass with new matchms versions (>=0.18.0). Should nearly always be backwards compatible though.
+- Now dependency requirement is set to `matchms>=0.14.0`
+
 ## [0.7.0] - 2022-10-01
 
 ### Added
@@ -135,7 +142,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fossa configuration
 - Flowchart
 
-[Unreleased]: https://github.com/iomega/spec2vec/compare/0.7.0...HEAD
+[Unreleased]: https://github.com/iomega/spec2vec/compare/0.8.0...HEAD
+[0.8.0]: https://github.com/iomega/spec2vec/compare/0.6.0...0.7.0
 [0.7.0]: https://github.com/iomega/spec2vec/compare/0.6.0...0.7.0
 [0.6.0]: https://github.com/iomega/spec2vec/compare/0.5.0...0.6.0
 [0.5.0]: https://github.com/iomega/spec2vec/compare/0.4.0...0.5.0

conda/meta.yaml

@@ -1,5 +1,5 @@
 {% set name = "spec2vec" %}
-{% set version = "0.7.0" %}
+{% set version = "0.8.0" %}
 
 package:
   name: {{ name|lower }}
@@ -37,7 +37,7 @@ requirements:
     - setuptools
   run:
     - gensim >=4.2.0
-    - matchms >=0.6.0
+    - matchms >=0.14.0
     - numba >=0.51
     - numpy
     - pip

integration-tests/test_user_workflow_spec2vec.py

@@ -1,6 +1,6 @@
 import os
 import gensim
-import pytest
+import numpy as np
 from matchms import calculate_scores
 from matchms.filtering import (add_losses, add_parent_mass, default_filters,
                                normalize_intensities,
@@ -68,16 +68,18 @@ def apply_my_filters(s):
     actual_top10 = sorted_by_score[:10]
 
     expected_top10 = [
-        (documents[19], documents[25], pytest.approx(0.9999121928249473, rel=1e-9)),
-        (documents[20], documents[25], pytest.approx(0.9998846890269892, rel=1e-9)),
-        (documents[20], documents[45], pytest.approx(0.9998756073673759, rel=1e-9)),
-        (documents[25], documents[45], pytest.approx(0.9998750427994474, rel=1e-9)),
-        (documents[19], documents[27], pytest.approx(0.9998722768460854, rel=1e-9)),
-        (documents[22], documents[27], pytest.approx(0.9998633023352553, rel=1e-9)),
-        (documents[18], documents[27], pytest.approx(0.9998616961532616, rel=1e-9)),
-        (documents[19], documents[45], pytest.approx(0.9998528723697396, rel=1e-9)),
-        (documents[14], documents[71], pytest.approx(0.9998404364805897, rel=1e-9)),
-        (documents[20], documents[27], pytest.approx(0.9998336807761137, rel=1e-9))
+        (documents[19], documents[25], 0.9999121928249473),
+        (documents[20], documents[25], 0.9998846890269892),
+        (documents[20], documents[45], 0.9998756073673759),
+        (documents[25], documents[45], 0.9998750427994474),
+        (documents[19], documents[27], 0.9998722768460854),
+        (documents[22], documents[27], 0.9998633023352553),
+        (documents[18], documents[27], 0.9998616961532616),
+        (documents[19], documents[45], 0.9998528723697396),
+        (documents[14], documents[71], 0.9998404364805897),
+        (documents[20], documents[27], 0.9998336807761137)
     ]
 
-    assert actual_top10 == expected_top10, "Expected different top 10 table."
+    assert [x[0] for x in actual_top10] == [x[0] for x in expected_top10]
+    assert [x[1] for x in actual_top10] == [x[1] for x in expected_top10]
+    assert np.allclose([x[2][0] for x in actual_top10], [x[2] for x in expected_top10]), "Expected different top 10 table."

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.7.0
+current_version = 0.8.0
 
 [bumpversion:file:conda/meta.yaml]
 search = set version = "{current_version}"

setup.py

@@ -47,7 +47,7 @@
     python_requires='>=3.7',
     install_requires=[
         "gensim >=4.2.0",
-        "matchms <0.18.0",
+        "matchms >=0.14.0",
         "numba >=0.51",
         "numpy",
         "scipy",

spec2vec/Spec2Vec.py

@@ -134,6 +134,7 @@ def pair(self, reference: Union[SpectrumDocument, Spectrum],
 
     def matrix(self, references: Union[List[SpectrumDocument], List[Spectrum]],
                queries: Union[List[SpectrumDocument], List[Spectrum]],
+               array_type: str = "numpy",
                is_symmetric: bool = False) -> np.ndarray:
         """Calculate the spec2vec similarities between all references and queries.
 
@@ -143,6 +144,10 @@ def matrix(self, references: Union[List[SpectrumDocument], List[Spectrum]],
             Reference spectrums or spectrum documents.
         queries:
             Query spectrums or spectrum documents.
+        array_type
+            Specify the output array type. Can be "numpy" or "sparse".
+            Currently, only "numpy" is supported and will return a numpy array.
+            Future versions will include "sparse" as option to return a COO-sparse array.
         is_symmetric:
             Set to True if references == queries to speed up calculation about 2x.
             Uses the fact that in this case score[i, j] = score[j, i]. Default is False.

spec2vec/__version__.py

@@ -1 +1 @@
-__version__ = '0.7.0'
+__version__ = '0.8.0'

spec2vec/serialization/model_importing.py

@@ -38,9 +38,12 @@ def build(self) -> KeyedVectors:
 
         def from_dict(self, dictionary: dict):
             expected_keys = {"vector_size", "__numpys", "__scipys", "__ignoreds", "__recursive_saveloads",
-                             "index_to_key", "norms", "key_to_index", "next_index", "__weights_format"}
+                             "index_to_key", "norms", "key_to_index", "__weights_format"}
             if dictionary.keys() == expected_keys:
                 self.__dict__ = dictionary
+            elif expected_keys.symmetric_difference(dictionary.keys()) == {"next_index"}:  # backward compatibility
+                dictionary.pop("next_index")
+                self.__dict__ = dictionary
             else:
                 raise ValueError("The keys of model's dictionary representation do not match the expected keys.")
             return self