Skip to content

Update sssom py SSSOM version to 0.12.0 #381

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 13 commits into from
Jun 15, 2023
Merged

Update sssom py SSSOM version to 0.12.0 #381

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
21cdd42
Update Makefile
matentzn Jun 11, 2023
8bbd3b6
Updated KEY_FEATURES
hrshdhgd Jun 12, 2023
a5e007b
formatted
hrshdhgd Jun 12, 2023
1843d25
updated `semapv` prefix map as sssoms-schema
hrshdhgd Jun 12, 2023
5cf3c00
linted again
hrshdhgd Jun 13, 2023
eabad9f
cleanup
hrshdhgd Jun 13, 2023
9ef0f85
cleanup
hrshdhgd Jun 13, 2023
1af36e2
Merge branch 'Update-sssom-to-0.12.0' of https://github.com/mapping-c…
hrshdhgd Jun 13, 2023
12b6ced
Revert "linted again"
hrshdhgd Jun 13, 2023
a594856
fixed test
hrshdhgd Jun 13, 2023
26a2809
removed unnecessary variable
hrshdhgd Jun 13, 2023
4ca1b76
chnaged back to splitting negative and positive
hrshdhgd Jun 15, 2023
7316bcc
black formatted
hrshdhgd Jun 15, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
PYTHON=python
SSSOM_VERSION_TAG=0.11.0
SSSOM_VERSION_TAG=0.12.0
DEFAULT_PREFIX_MAP="https://raw.githubusercontent.com/biopragmatics/bioregistry/main/exports/contexts/obo.context.jsonld"
SSSOM_PY="https://raw.githubusercontent.com/mapping-commons/sssom/$(SSSOM_VERSION_TAG)/src/sssom_schema/datamodel/sssom_schema.py"
SSSOM_YAML="https://raw.githubusercontent.com/mapping-commons/sssom/$(SSSOM_VERSION_TAG)/src/sssom_schema/schema/sssom_schema.yaml"
Expand Down
20 changes: 6 additions & 14 deletions sssom/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,8 +100,9 @@

URI_SSSOM_MAPPINGS = f"{SSSOM_URI_PREFIX}mappings"

#: The 3 columns whose combination would be used as primary keys while merging/grouping
KEY_FEATURES = [SUBJECT_ID, PREDICATE_ID, OBJECT_ID]
#: The 4 columns whose combination would be used as primary keys while merging/grouping
KEY_FEATURES = [SUBJECT_ID, PREDICATE_ID, OBJECT_ID, PREDICATE_MODIFIER]
TRIPLE_IDS = [SUBJECT_ID, PREDICATE_ID, OBJECT_ID]


@dataclass
Expand Down Expand Up @@ -726,7 +727,6 @@ def deal_with_negation(df: pd.DataFrame) -> pd.DataFrame:
raise ValueError(
"The dataframe, after assigning default confidence, appears empty (deal_with_negation)"
)

# If s,!p,o and s,p,o , then prefer higher confidence and remove the other. ###
negation_df: pd.DataFrame
negation_df = df.loc[df[PREDICATE_MODIFIER] == PREDICATE_MODIFIER_NOT]
Expand Down Expand Up @@ -760,9 +760,9 @@ def deal_with_negation(df: pd.DataFrame) -> pd.DataFrame:

# GroupBy and SELECT ONLY maximum confidence
max_confidence_df: pd.DataFrame
max_confidence_df = combined_normalized_subset.groupby(
KEY_FEATURES, as_index=False
)[CONFIDENCE].max()
max_confidence_df = combined_normalized_subset.groupby(TRIPLE_IDS, as_index=False)[
CONFIDENCE
].max()

# If same confidence prefer "HumanCurated".
reconciled_df_subset = pd.DataFrame(columns=combined_normalized_subset.columns)
Expand Down Expand Up @@ -790,14 +790,6 @@ def deal_with_negation(df: pd.DataFrame) -> pd.DataFrame:
if len(match_condition_1[match_condition_1].index) > 1:
match_condition_1 = match_condition_1[match_condition_1].sample()

# FutureWarning: The frame.append method is deprecated and will be removed
# from pandas in a future version. Use pandas.concat instead.
# reconciled_df_subset = reconciled_df_subset.append(
# combined_normalized_subset.loc[
# match_condition_1[match_condition_1].index, :
# ],
# ignore_index=True,
# )
reconciled_df_subset = pd.concat(
[
reconciled_df_subset,
Expand Down
2 changes: 1 addition & 1 deletion tests/data/bad_basic.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
# d: "http://example.org/d/"
# rdfs: "http://www.w3.org/2000/01/rdf-schema#"
# owl: "http://www.w3.org/2002/07/owl#"
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
c:something YYYYY owl:equivalentClass b:something yyyyyy Lexical c d rdf_matcher 0.81 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity xxxxx mock data
d:something YYYYY owl:equivalentClass Not a:something yyyyyy Lexical d a rdf_matcher 0.82 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity xxxxx mock data
Expand Down
2 changes: 1 addition & 1 deletion tests/data/basic.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@
# c: "http://example.org/c/"
# d: "http://example.org/d/"
# orcid: "https://orcid.org/my-orcid?orcid="
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
x:appendage appendage owl:equivalentClass y:appendage appendages semapv:ManualMappingCuration x:example y:example rdf_matcher 0.840714406 rdfs:label|skos:prefLabel rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity appendag .
x:appendage appendage owl:equivalentClass z:appendage APPENDAGE semapv:ManualMappingCuration x:example z:example rdf_matcher 0.840714406 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity appendag .
Expand Down
2 changes: 1 addition & 1 deletion tests/data/basic2.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
# c: "http://example.org/c/"
# d: "http://example.org/d/"
# orcid: "https://orcid.org/my-orcid?orcid="
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
x:FOO FOO owl:equivalentClass y:FOO FOO semapv:SemanticSimilarityThresholdMatching x:example y:example rdf_matcher 0.840714406 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity foo .
x:appendage appendage owl:equivalentClass y:appendage appendages semapv:ManualMappingCuration x:example y:example rdf_matcher 0.840714406 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity appendag .
Expand Down
2 changes: 1 addition & 1 deletion tests/data/basic3.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
# rdfs: "http://www.w3.org/2000/01/rdf-schema#"
# owl: "http://www.w3.org/2002/07/owl#"
# orcid: "https://orcid.org/my-orcid?orcid="
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
c:something YYYYY owl:equivalentClass b:something yyyyyy semapv:LexicalMatching c:example d:example rdf_matcher 0.81 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity xxxxx mock data
d:something YYYYY owl:equivalentClass Not a:something yyyyyy semapv:LexicalMatching d:example a:example rdf_matcher 0.82 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity xxxxx mock data
Expand Down
2 changes: 1 addition & 1 deletion tests/data/basic4.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
# b2: "http://example.org/b2/"
# c2: "http://example.org/c2/"
# d2: "http://example.org/d2/"
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
x2:appendage appendage owl:equivalentClass y2:appendage appendages semapv:SemanticSimilarityThresholdMatching x y rdf_matcher 0.840714406 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity appendag .
x2:appendage appendage owl:equivalentClass z2:appendage APPENDAGE semapv:SemanticSimilarityThresholdMatching x z rdf_matcher 0.840714406 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity appendag .
Expand Down
2 changes: 1 addition & 1 deletion tests/data/basic5.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
# b1: "http://example.org/b1/"
# c1: "http://example.org/c1/"
# d1: "http://example.org/d1/"
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
x1:appendage appendage owl:equivalentClass y1:appendage appendages semapv:LexicalMatching x z rdf_matcher 0.840714406 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity organ .
x1:appendage appendage owl:equivalentClass z1:appendage APPENDAGE semapv:LexicalMatching x y rdf_matcher 0.840714406 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity region .
Expand Down
2 changes: 1 addition & 1 deletion tests/data/basic7.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
# rdfs: "http://www.w3.org/2000/01/rdf-schema#"
# owl: "http://www.w3.org/2002/07/owl#"
# orcid: "https://orcid.org/my-orcid?orcid="
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
# skos: "http://www.w3.org/2004/02/skos/core#"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
a:something YYYYY owl:equivalentClass b:something yyyyyy semapv:LexicalMatching c:example d:example rdf_matcher 0.8 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity xxxxx mock data
Expand Down
2 changes: 1 addition & 1 deletion tests/data/cob-to-external.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
# rdfs: "http://www.w3.org/2000/01/rdf-schema#"
# skos: "http://www.w3.org/2004/02/skos/core#"
# owl: "http://www.w3.org/2002/07/owl#"
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
# BFO: "http://purl.obolibrary.org/obo/BFO_"
# CARO: "http://purl.obolibrary.org/obo/CARO_"
# CHEBI: "http://purl.obolibrary.org/obo/CHEBI_"
Expand Down
2 changes: 1 addition & 1 deletion tests/data/reconcile_1.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
# owl: http://www.w3.org/2002/07/owl#
# rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
# rdfs: http://www.w3.org/2000/01/rdf-schema#
# semapv: https://w3id.org/semapv/
# semapv: https://w3id.org/semapv/vocab/
# skos: http://www.w3.org/2004/02/skos/core#
# sssom: https://w3id.org/sssom/
# license: https://w3id.org/sssom/license/unspecified
Expand Down
2 changes: 1 addition & 1 deletion tests/data/reconcile_2.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
# owl: http://www.w3.org/2002/07/owl#
# rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
# rdfs: http://www.w3.org/2000/01/rdf-schema#
# semapv: https://w3id.org/semapv/
# semapv: https://w3id.org/semapv/vocab/
# skos: http://www.w3.org/2004/02/skos/core#
# sssom: https://w3id.org/sssom/
# license: https://w3id.org/sssom/license/unspecified
Expand Down
2 changes: 1 addition & 1 deletion tests/data/test_annotate_sssom.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
# owl: http://www.w3.org/2002/07/owl#
# rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
# rdfs: http://www.w3.org/2000/01/rdf-schema#
# semapv: https://w3id.org/semapv/
# semapv: https://w3id.org/semapv/vocab/
# skos: http://www.w3.org/2004/02/skos/core#
# sssom: https://w3id.org/sssom/
# x: http://example.org/x/
Expand Down
2 changes: 1 addition & 1 deletion tests/data/test_clean_prefix.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
# rdfs: "http://www.w3.org/2000/01/rdf-schema#"
# owl: "http://www.w3.org/2002/07/owl#"
# orcid: "https://orcid.org/my-orcid?orcid="
# semapv: "https://w3id.org/semapv/"
# semapv: "https://w3id.org/semapv/vocab/"
subject_id subject_label predicate_id predicate_modifier object_id object_label mapping_justification subject_source object_source mapping_tool confidence subject_match_field object_match_field subject_category object_category match_string comment
c:something YYYYY owl:equivalentClass b:something yyyyyy semapv:LexicalMatching c:example d:example rdf_matcher 0.81 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity xxxxx mock data
d:something YYYYY owl:equivalentClass Not a:something yyyyyy semapv:LexicalMatching d:example a:example rdf_matcher 0.82 rdfs:label rdfs:label biolink:AnatomicalEntity biolink:AnatomicalEntity xxxxx mock data
Expand Down
2 changes: 1 addition & 1 deletion tests/data/test_filter_sssom.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
# owl: http://www.w3.org/2002/07/owl#
# rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
# rdfs: http://www.w3.org/2000/01/rdf-schema#
# semapv: https://w3id.org/semapv/
# semapv: https://w3id.org/semapv/vocab/
# skos: http://www.w3.org/2004/02/skos/core#
# sssom: https://w3id.org/sssom/
# x: http://example.org/x/
Expand Down
2 changes: 1 addition & 1 deletion tests/data/test_inject_metadata_msdf.tsv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
# owl: http://www.w3.org/2002/07/owl#
# rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
# rdfs: http://www.w3.org/2000/01/rdf-schema#
# semapv: https://w3id.org/semapv/
# semapv: https://w3id.org/semapv/vocab/
# skos: http://www.w3.org/2004/02/skos/core#
# sssom: https://w3id.org/sssom/
# license: https://creativecommons.org/licenses/by-nc/4.0/
Expand Down