Merge pull request #15 from matchms/update_to_matchms018

updates to recent matchms changes

CHANGELOG.md

@@ -7,6 +7,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.4.0] - 2023-02-03
+
+### Changed
+
+- removed network creation functions which have meanwhile been incorporated in matchms
+- switch default id fieldname form "spectrumid" to "spectrum_id" (matchms > 0.14.0)
+- adapt test to new Scores object design (matchms > 0.18.0)
+
 ## [0.3.0] - 2021-12-19
 
 ### Added
@@ -55,8 +63,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - This is the initial version mostly taken from https://github.com/iomega/spec2vec_gnps_data_analysis
 
-[Unreleased]: https://github.com/matchms/matchmsextras/compare/0.3.0...HEAD
-[0.2.3]: https://github.com/matchms/matchmsextras/compare/0.2.3...0.3.0
+[Unreleased]: https://github.com/matchms/matchmsextras/compare/0.4.0...HEAD
+[0.4.0]: https://github.com/matchms/matchmsextras/compare/0.3.0...0.4.0
+[0.3.0]: https://github.com/matchms/matchmsextras/compare/0.2.3...0.3.0
 [0.2.3]: https://github.com/matchms/matchmsextras/compare/0.2.2...0.2.3
 [0.2.2]: https://github.com/matchms/matchmsextras/compare/0.2.1...0.2.2
 [0.2.1]: https://github.com/matchms/matchmsextras/compare/0.2.0...0.2.1

matchmsextras/__version__.py

@@ -1 +1 @@
-__version__ = '0.3.0'
+__version__ = '0.4.0'

matchmsextras/networking.py

@@ -11,123 +11,12 @@
 from matplotlib import pyplot as plt
 import matplotlib
 from matchms import Spectrum, Scores
+from matchms.networking.networking_functions import get_top_hits
 
 # ----------------------------------------------------------------------------
 # ---------------- Graph / networking related functions ----------------------
 # ----------------------------------------------------------------------------
 
-def get_top_hits(scores, identifier: str = "spectrum_id",
-                 top_n: int = 25, search_by: str = "queries") -> Tuple[dict, dict]:
-    """Get top_n highest scores (and indices) for every entry.
-
-    Args:
-    --------
-    scores
-        Matchms Scores object containing all Spec2Vec similarities.
-    identifier
-        Unique intentifier for each spectrum in scores. Will also be used for
-        node names.
-    top_n
-        Return the indexes and scores for the top_n highest scores.
-    search_by
-        Chose between 'queries' or 'references' which decides if the top_n matches
-        for every spectrum in scores.queries or in scores.references will be
-        collected and returned
-    """
-    assert search_by in ["queries", "references"], \
-        "search_by must be 'queries' or 'references"
-    if top_n < 2:
-        top_n = 2
-        print("Set top_n to minimum value of 2")
-    #dim1 = len(scores.references) if search_by=="references" else len(scores.queries)
-    #dim2 = min(top_n, len(scores.queries) if search_by=="references" else len(scores.references))
-
-    similars_idx = dict()
-    similars_scores = dict()
-
-    if search_by=="queries":
-        for i, spec in enumerate(scores.queries):
-            spec_id = spec.get(identifier)
-            similars_idx[spec_id] = scores.scores[:, i].argsort()[::-1][:top_n]
-            similars_scores[spec_id] = scores.scores[similars_idx[spec_id], i]
-    elif search_by=="references":
-        for i, spec in enumerate(scores.references):
-            spec_id = spec.get(identifier)
-            similars_idx[spec_id] = scores.scores[i, :].argsort()[::-1][:top_n]
-            similars_scores[spec_id] = scores.scores[i, similars_idx[spec_id]]
-    return similars_idx, similars_scores
-
-
-def create_network(scores: Scores,
-                   identifier: str = "spectrum_id",
-                   top_n: int = 20,
-                   max_links: int = 10,
-                   cutoff: float = 0.7,
-                   link_method: str = 'single') -> nx.Graph:
-    """
-    Function to create network from given top-n similarity values. Expects that
-    similarities given in scores are from an all-vs-all comparison including all
-    possible pairs.
-
-    Args:
-    --------
-    scores
-        Matchms Scores object containing all Spec2Vec similarities.
-    identifier
-        Unique intentifier for each spectrum in scores. Will also be used for
-        node names.
-    top_n
-        Consider edge between spectrumA and spectrumB if score falls into
-        top_n for spectrumA or spectrumB (link_method="single"), or into
-        top_n for spectrumA and spectrumB (link_method="mutual"). From those
-        potential links, only max_links will be kept, so top_n must be >= max_links.
-    max_links
-        Maximum number of links to add per node. Default = 10.
-        Due to incoming links, total number of links per node can be higher.
-    cutoff
-        Threshold for given similarities. Edges/Links will only be made for
-        similarities > cutoff. Default = 0.7.
-    link_method
-        Chose between 'single' and 'mutual'. 'single will add all links based
-        on individual nodes. 'mutual' will only add links if that link appears
-        in the given top-n list for both nodes.
-    """
-    assert top_n >= max_links, "top_n must be >= max_links"
-    assert np.all(scores.queries == scores.references), \
-        "Expected symmetric scores object with queries==references"
-    unique_ids = list({s.get(identifier) for s in scores.queries})
-    dimension = len(unique_ids)
-
-    # Initialize network graph, add nodes
-    msnet = nx.Graph()
-    msnet.add_nodes_from(unique_ids)
-
-    # Collect location and score of highest scoring candidates for queries and references
-    similars_idx, similars_scores = get_top_hits(scores, top_n=top_n,
-                                                 search_by="queries")
-
-    # Add edges based on global threshold (cutoff) for weights
-    for i, spec in enumerate(scores.queries):
-        query_id = spec.get(identifier)
-
-        ref_candidates = np.array([scores.references[x].get(identifier)
-                                   for x in similars_idx[query_id]])
-        idx = np.where((similars_scores[query_id] >= cutoff) & (ref_candidates != query_id))[0][:max_links]
-        if link_method == "single":
-            new_edges = [(query_id, str(ref_candidates[x]),
-                          float(similars_scores[query_id][x])) for x in idx]
-        elif link_method == "mutual":
-            new_edges = [(query_id, str(ref_candidates[x]),
-                          float(similars_scores[query_id][x]))
-                         for x in idx if i in similars_idx[ref_candidates[x]][:]]
-        else:
-            raise ValueError("Link method not kown")
-
-        msnet.add_weighted_edges_from(new_edges)
-
-    return msnet
-
-
 def create_network_asymmetric(scores: Scores,
                               identifier: str = "spectrum_id",
                               add_links_from_queries: bool = True,

matchmsextras/pubchem_lookup.py

@@ -2,7 +2,7 @@
 import re
 import pubchempy as pcp
 import numpy as np
-from matchms.utils import is_valid_inchikey
+from matchms.metadata_utils import is_valid_inchikey
 
 
 logger = logging.getLogger("matchms")

tests/test_networking.py

@@ -1,9 +1,9 @@
 import pytest
 import numpy as np
 from matchms import Spectrum, calculate_scores
+from matchms.networking import SimilarityNetwork
 from matchms.similarity import FingerprintSimilarity
-from matchmsextras.networking import create_network, create_network_asymmetric
-from matchmsextras.networking import get_top_hits
+from matchmsextras.networking import create_network_asymmetric
 from matchmsextras.networking import dilate_cluster
 from matchmsextras.networking import extract_networking_metadata
 
@@ -50,61 +50,14 @@ def create_dummy_scores_symmetric():
     return scores
 
 
-def test_get_top_hits_by_references():
-    scores = create_dummy_scores()
-    idx_ref, scores_ref = get_top_hits(scores, top_n=10, search_by="references")
-
-    expected_scores_ref = {'ref_spec_0': np.array([0.66666667, 0.5       , 0.        ]),
-                           'ref_spec_1': np.array([0.66666667, 0.5       , 0.        ]),
-                           'ref_spec_2': np.array([0.66666667, 0.66666667, 0.5       ]),
-                           'ref_spec_3': np.array([0.8, 0.5, 0.5]),
-                           'ref_spec_4': np.array([1. , 0.8, 0.5])}
-    expected_idx_ref = {'ref_spec_0': np.array([0, 2, 1], dtype=np.int64),
-                        'ref_spec_1': np.array([1, 2, 0], dtype=np.int64),
-                        'ref_spec_2': np.array([1, 0, 2], dtype=np.int64),
-                        'ref_spec_3': np.array([2, 1, 0], dtype=np.int64),
-                        'ref_spec_4': np.array([0, 2, 1], dtype=np.int64)}
-    for key in scores_ref.keys():
-        assert np.allclose(scores_ref[key], expected_scores_ref[key], atol=1e-5), \
-            "Expected different selected scores"
-    for key in idx_ref.keys():
-        assert np.allclose(idx_ref[key], expected_idx_ref[key], atol=1e-5), \
-            "Expected different selected indices"
-
-    # Test lower top_n
-    idx_ref, scores_ref = get_top_hits(scores, top_n=2, search_by="references")
-    for key in scores_ref.keys():
-        assert np.allclose(scores_ref[key], expected_scores_ref[key][:2], atol=1e-5), \
-            "Expected different selected scores"
-    for key in idx_ref.keys():
-        assert np.allclose(idx_ref[key], expected_idx_ref[key][:2], atol=1e-5), \
-            "Expected different selected indices"
-
-def test_get_top_hits_by_queries():
-    scores = create_dummy_scores()
-    idx_query, scores_query = get_top_hits(scores, top_n=10, search_by="queries")
-
-    expected_scores_query = {'query_spec_0': np.array([1.        , 0.66666667, 0.66666667, 0.5       , 0.        ]),
-                             'query_spec_1': np.array([0.66666667, 0.66666667, 0.5       , 0.5       , 0.        ]),
-                             'query_spec_2': np.array([0.8, 0.8, 0.5, 0.5, 0.5])}
-    expected_idx_query = {'query_spec_0': np.array([4, 2, 0, 3, 1], dtype=np.int64),
-                          'query_spec_1': np.array([2, 1, 4, 3, 0], dtype=np.int64),
-                          'query_spec_2': np.array([4, 3, 2, 1, 0], dtype=np.int64)}
-    for key in scores_query.keys():
-        assert np.allclose(scores_query[key], expected_scores_query[key], atol=1e-5), \
-            "Expected different selected scores"
-    for key in idx_query.keys():
-        assert np.allclose(idx_query[key], expected_idx_query[key], atol=1e-5), \
-            "Expected different selected indices"
-
-    # Test lower top_n
-    idx_query, scores_query = get_top_hits(scores, top_n=2, search_by="queries")
-    for key in scores_query.keys():
-        assert np.allclose(scores_query[key], expected_scores_query[key][:2], atol=1e-5), \
-            "Expected different selected scores"
-    for key in idx_query.keys():
-        assert np.allclose(idx_query[key], expected_idx_query[key][:2], atol=1e-5), \
-            "Expected different selected indices"
+@pytest.fixture()
+def network_symmetric():
+    """Test creating a graph from a symmetric Scores object"""
+    cutoff = 0.7
+    scores = create_dummy_scores_symmetric()
+    msnet = SimilarityNetwork(score_cutoff=cutoff)
+    msnet.create_network(scores)
+    return msnet.graph
 
 
 def test_create_network_asymmetric():
@@ -127,7 +80,7 @@ def test_create_network_asymmetric():
                         'ref_spec_3',
                         'ref_spec_4',
                         'ref_spec_4']
-    assert len(edges_list) == np.sum(scores.scores > cutoff), \
+    assert len(edges_list) == np.sum(scores.scores.to_array() > cutoff), \
         "Expected different number of edges"
     assert np.all([(x[0] in nodes_with_edges) for x in edges_list]), "Expected different edges in graph"
     assert np.all([(x[1] in nodes_with_edges) for x in edges_list]), "Expected different edges in graph"
@@ -137,96 +90,14 @@ def test_create_network_asymmetric():
         "Expected different edge weight"
 
 
-def test_create_network_symmetric_wrong_input():
-    """Test if function is used with non-symmetric scores object"""
-    scores = create_dummy_scores()
-    with pytest.raises(AssertionError) as msg:
-        _ = create_network(scores)
-
-    expected_msg = "Expected symmetric scores object with queries==references"
-    assert expected_msg in str(msg), "Expected different exception"
-
-
-def test_create_network_symmetric():
-    """Test creating a graph from a symmetric Scores object"""
-    cutoff=0.7
-    scores = create_dummy_scores_symmetric()
-    msnet = create_network(scores, cutoff=cutoff)
-
-    edges_list = list(msnet.edges())
-    edges_list.sort()
-    nodes_without_edges = ['ref_spec_0',
-                           'ref_spec_1',
-                           'ref_spec_2']
-    assert len(edges_list) == 5, "Expected different number of edges"
-    assert np.all([(x[0] not in nodes_without_edges) for x in edges_list]), \
-        "Expected this node to have no edges"
-    assert np.all([(x[1] not in nodes_without_edges) for x in edges_list]), \
-        "Expected this node to have no edges"
-
-
-def test_create_network_symmetric_higher_cutoff():
-    cutoff=0.9
-    scores = create_dummy_scores_symmetric()
-    msnet = create_network(scores, cutoff=cutoff)
-
-    edges_list = list(msnet.edges())
-    edges_list.sort()
-    assert len(edges_list) == 1, "Expected only one link"
-    assert edges_list[0][0] in ['query_spec_0', 'ref_spec_4'], \
-        "Expected different node to have a link"
-    assert edges_list[0][1] in ['query_spec_0', 'ref_spec_4'], \
-        "Expected different node to have a link"
-
-
-def test_create_network_symmetric_mutual_method():
-    """Test creating a graph from a Scores object"""
-    cutoff=0.7
-    scores = create_dummy_scores_symmetric()
-    # change some scores
-    scores._scores[7, 6] = scores._scores[6, 7] = 0.85
-    scores._scores[7, 5] = scores._scores[5, 7] = 0.75
-    scores._scores[7, 3] = scores._scores[3, 7] = 0.7
-
-    msnet = create_network(scores, cutoff=cutoff, top_n=3,
-                           max_links=3, link_method="mutual")
-    nodes_with_edges = ['query_spec_0', 'query_spec_1', 'query_spec_2', 'ref_spec_4']
-    edges_list = list(msnet.edges())
-    edges_list.sort()
-    assert len(edges_list) == 3, "Expected only four link"
-    assert np.all([(x[0] in nodes_with_edges) for x in edges_list]), "Expected different edges in graph"
-    assert np.all([(x[1] in nodes_with_edges) for x in edges_list]), "Expected different edges in graph"
-
-
-def test_create_network_symmetric_max_links_1():
-    """Test creating a graph from a Scores object using max_links=1"""
-    cutoff=0.7
-    scores = create_dummy_scores_symmetric()
-    msnet = create_network(scores, cutoff=cutoff, max_links=1, link_method="single")
-
-    edges_list = list(msnet.edges())
-    edges_list.sort()
-    nodes_without_edges = ['ref_spec_0',
-                           'ref_spec_1',
-                           'ref_spec_2',]
-    assert len(edges_list) == 3, "Expected different number of edges"
-    assert np.all([(x[0] not in nodes_without_edges) for x in edges_list]), \
-        "Expected this node to have no edges"
-    assert np.all([(x[1] not in nodes_without_edges) for x in edges_list]), \
-        "Expected this node to have no edges"
-
-
-def test_dilate_cluster():
-    # Create graph
-    cutoff=0.7
+def test_dilate_cluster(network_symmetric):
     scores = create_dummy_scores_symmetric()
-    msnet = create_network(scores, cutoff=cutoff, top_n=3, max_links=3)
-    assert len(msnet.edges()) == 5, \
+    assert len(network_symmetric.edges()) == 5, \
         "Expected different number of edges before dilating"
 
     # Dilation step
-    msnet_dilated, links_added = dilate_cluster(msnet, scores)
-    assert len(msnet.edges()) == 12, \
+    msnet_dilated, _ = dilate_cluster(network_symmetric, scores)
+    assert len(msnet_dilated.edges()) == 12, \
         "Expected different number of edges after dilating"