diff --git a/docker/rest-server.py b/docker/rest-server.py index 159cbb4..0a80e4b 100644 --- a/docker/rest-server.py +++ b/docker/rest-server.py @@ -17,7 +17,7 @@ class NIDMRest(Resource): def get(self, all): # noqa: A002 query_bits = [] for a in request.args.keys(): - query_bits.append("{}={}".format(a, request.args.get(a))) + query_bits.append(f"{a}={request.args.get(a)}") query = "&".join(query_bits) files = getTTLFiles() @@ -29,9 +29,7 @@ def get(self, all): # noqa: A002 output_format=RestParser.OBJECT_FORMAT, verbosity_level=5 ) - json_str = json.dumps( - restParser.run(files, "{}?{}".format(all, query)), indent=2 - ) + json_str = json.dumps(restParser.run(files, f"{all}?{query}"), indent=2) response = app.response_class( response=json_str, status=200, mimetype="application/json" ) @@ -42,9 +40,7 @@ def get(self, all): # noqa: A002 class Instructions(Resource): def get(self): return { - "message": "You probably want to start at {}projects See instructions at PyNIDM/docker/README.md for details on the API and loading data.".format( - request.url_root - ) + "message": f"You probably want to start at {request.url_root}projects See instructions at PyNIDM/docker/README.md for details on the API and loading data." } diff --git a/src/nidm/core/dot.py b/src/nidm/core/dot.py index 602d2b0..235da42 100644 --- a/src/nidm/core/dot.py +++ b/src/nidm/core/dot.py @@ -221,7 +221,7 @@ def htlm_link_if_uri(value): try: uri = value.uri - return '%s' % (uri, str(value)) + return f'{value}' except AttributeError: return str(value) @@ -279,7 +279,7 @@ def _attach_attribute_annotation(node, record): % ( attr.uri, escape(str(attr)), - ' href="%s"' % value.uri if isinstance(value, Identifier) else "", + f' href="{value.uri}"' if isinstance(value, Identifier) else "", escape( str(value) if not isinstance(value, datetime) @@ -291,7 +291,7 @@ def _attach_attribute_annotation(node, record): ann_rows.append(ANNOTATION_END_ROW) count[3] += 1 annotations = pydot.Node( - "ann%d" % count[3], label="\n".join(ann_rows), **ANNOTATION_STYLE + f"ann{count[3]}", label="\n".join(ann_rows), **ANNOTATION_STYLE ) dot.add_node(annotations) dot.add_edge(pydot.Edge(annotations, node, **ANNOTATION_LINK_STYLE)) @@ -299,58 +299,50 @@ def _attach_attribute_annotation(node, record): def _add_bundle(bundle): count[2] += 1 subdot = pydot.Cluster( - graph_name="c%d" % count[2], URL='"%s"' % bundle.identifier.uri + graph_name=f"c{count[2]}", URL=f'"{bundle.identifier.uri}"' ) if use_labels: if bundle.label == bundle.identifier: - bundle_label = '"%s"' % str(bundle.label) + bundle_label = f'"{bundle.label}"' else: # Fancier label if both are different. The label will be # the main node text, whereas the identifier will be a # kind of subtitle. bundle_label = ( - "<%s
" + f"<{bundle.label}
" '' - "%s>" + f"{bundle.identifier}>" ) - bundle_label = bundle_label % ( - str(bundle.label), - str(bundle.identifier), - ) - subdot.set_label('"%s"' % str(bundle_label)) + subdot.set_label(f'"{bundle_label}"') else: - subdot.set_label('"%s"' % str(bundle.identifier)) + subdot.set_label(f'"{bundle.identifier}"') _bundle_to_dot(subdot, bundle) dot.add_subgraph(subdot) return subdot def _add_node(record): count[0] += 1 - node_id = "n%d" % count[0] + node_id = f"n{count[0]}" if use_labels: if record.label == record.identifier: - node_label = '"%s"' % str(record.label) + node_label = f'"{record.label}"' else: # Fancier label if both are different. The label will be # the main node text, whereas the identifier will be a # kind of subtitle. node_label = ( - "<%s
" + f"<{record.label}
" '' - "%s>" - ) - node_label = node_label % ( - str(record.label), - str(record.identifier), + f"{record.identifier}>" ) else: - node_label = '"%s"' % str(record.identifier) + node_label = f'"{record.identifier}"' uri = record.identifier.uri print("record type: ", record.get_type()) style = DOT_PROVONE_STYLE[record.get_type()] print("style: ", style) - node = pydot.Node(node_id, label=node_label, URL='"%s"' % uri, **style) + node = pydot.Node(node_id, label=node_label, URL=f'"{uri}"', **style) node_map[uri] = node dot.add_node(node) @@ -360,19 +352,19 @@ def _add_node(record): def _add_generic_node(qname): count[0] += 1 - node_id = "n%d" % count[0] - node_label = '"%s"' % str(qname) + node_id = f"n{count[0]}" + node_label = f'"{qname}"' uri = qname.uri style = DOT_PROVONE_STYLE[0] - node = pydot.Node(node_id, label=node_label, URL='"%s"' % uri, **style) + node = pydot.Node(node_id, label=node_label, URL=f'"{uri}"', **style) node_map[uri] = node dot.add_node(node) return node def _get_bnode(): count[1] += 1 - bnode_id = "b%d" % count[1] + bnode_id = f"b{count[1]}" bnode = pydot.Node(bnode_id, label='""', shape="point", color="gray") dot.add_node(bnode) return bnode diff --git a/src/nidm/core/serializers/__init__.py b/src/nidm/core/serializers/__init__.py index 738c9e7..016d18f 100644 --- a/src/nidm/core/serializers/__init__.py +++ b/src/nidm/core/serializers/__init__.py @@ -73,4 +73,4 @@ def get(format_name): try: return Registry.serializers[format_name] except KeyError: - raise DoNotExist('No serializer available for the format "%s"' % format_name) + raise DoNotExist(f'No serializer available for the format "{format_name}"') diff --git a/src/nidm/core/serializers/provonerdf.py b/src/nidm/core/serializers/provonerdf.py index 1d330c7..6a29f39 100644 --- a/src/nidm/core/serializers/provonerdf.py +++ b/src/nidm/core/serializers/provonerdf.py @@ -62,7 +62,7 @@ def __init__(self): def get_anon_id(self, obj, local_prefix="id"): if obj not in self._cache: self._count += 1 - self._cache[obj] = pm.Identifier("_:%s%d" % (local_prefix, self._count)).uri + self._cache[obj] = pm.Identifier(f"_:{local_prefix}{self._count}").uri return self._cache[obj] @@ -178,7 +178,7 @@ def decode_rdf_representation(self, literal, graph): if datatype == XSD["gYearMonth"]: parsed_info = dateutil.parser.parse(literal) return pm.Literal( - "{0}-{1:02d}".format(parsed_info.year, parsed_info.month), + f"{parsed_info.year}-{parsed_info.month:02d}", datatype=self.valid_identifier(datatype), ) else: diff --git a/src/nidm/experiment/CDE.py b/src/nidm/experiment/CDE.py index ff2f763..a65b59c 100644 --- a/src/nidm/experiment/CDE.py +++ b/src/nidm/experiment/CDE.py @@ -12,7 +12,7 @@ def download_cde_files(): cde_dir = tempfile.gettempdir() for url in Constants.CDE_FILE_LOCATIONS: - urlretrieve(url, "{}/{}".format(cde_dir, url.split("/")[-1])) + urlretrieve(url, f"{cde_dir}/{url.split('/')[-1]}") return cde_dir @@ -25,7 +25,7 @@ def getCDEs(file_list=None): hasher.update(str(file_list).encode("utf-8")) h = hasher.hexdigest() - cache_file_name = tempfile.gettempdir() + "/cde_graph.{}.pickle".format(h) + cache_file_name = tempfile.gettempdir() + f"/cde_graph.{h}.pickle" if path.isfile(cache_file_name): with open(cache_file_name, "rb") as fp: @@ -50,7 +50,7 @@ def getCDEs(file_list=None): file_list = [] for f in ["ants_cde.ttl", "fs_cde.ttl", "fsl_cde.ttl"]: - fname = "{}/{}".format(cde_dir, f) + fname = f"{cde_dir}/{f}" if path.isfile(fname): file_list.append(fname) diff --git a/src/nidm/experiment/Core.py b/src/nidm/experiment/Core.py index 5af9f89..e047f84 100644 --- a/src/nidm/experiment/Core.py +++ b/src/nidm/experiment/Core.py @@ -250,8 +250,9 @@ def addLiteralAttribute( ) except KeyError as e: print( - '\nPredicate namespace identifier " %s " not found! \n' - % (str(e).split("'")[1]) + '\nPredicate namespace identifier "', + str(e).split("'")[1], + '" not found! \n', ) print( "Use addNamespace method to add namespace before adding literal attribute \n" @@ -364,7 +365,7 @@ def get_metadata_dict(self, NIDM_TYPE): uri = s if uri is None: - print("Error finding %s in NIDM-Exp Graph" % NIDM_TYPE) + print(f"Error finding {NIDM_TYPE} in NIDM-Exp Graph") return metadata # Cycle through metadata and add to json @@ -531,7 +532,7 @@ def save_DotGraph(self, filename, format=None): # noqa: A002 """ qres = rdf_graph.query(query) for row in qres: - print("project uuid = %s" % row) + print(f"project uuid = {row}") # parse uuid from project URI # project_uuid = str(row[0]).rsplit('/', 1)[-1] project_uuid = str(row[0]) @@ -557,7 +558,7 @@ def save_DotGraph(self, filename, format=None): # noqa: A002 dot.obj_dict["nodes"][key][0]["attributes"]["URL"] ): session_node = key - # print("session node = %s" %key) + # print(f"session node = {key}") # add to DOT structure edge between project_node and session_node dot.add_edge(Edge(session_node, project_node, **style)) @@ -574,7 +575,7 @@ def save_DotGraph(self, filename, format=None): # noqa: A002 ] ): acquisition_node = key - # print("acquisition node = %s" %key) + # print(f"acquisition node = {key}") dot.add_edge( Edge( diff --git a/src/nidm/experiment/Navigate.py b/src/nidm/experiment/Navigate.py index 01e2964..52f443e 100644 --- a/src/nidm/experiment/Navigate.py +++ b/src/nidm/experiment/Navigate.py @@ -538,7 +538,7 @@ def GetDataelementDetails(nidm_files_tuple, dataelement): if d in rdf_graph.subjects( predicate=isa, object=Constants.NIDM["Project"] ): - result["inProjects"].add("{} ({})".format(str(d), file)) + result["inProjects"].add(f"{d} ({file})") return result # found it, we are done diff --git a/src/nidm/experiment/Query.py b/src/nidm/experiment/Query.py index 4b09146..7f4bd80 100644 --- a/src/nidm/experiment/Query.py +++ b/src/nidm/experiment/Query.py @@ -86,9 +86,7 @@ def sparql_query_nidm(nidm_file_list, query, output_file=None, return_graph=Fals except Exception as e: print( - "Exception while communicating with blazegraph at {}: {}".format( - environ["BLAZEGRAPH_URL"], e - ) + f"Exception while communicating with blazegraph at {environ['BLAZEGRAPH_URL']}: {e}" ) # query result list @@ -231,8 +229,7 @@ def testprojectmeta(nidm_file_list): def GetProjectSessionsMetadata(nidm_file_list, project_uuid): import json - query = ( - """ + query = f""" prefix nidm: prefix rdf: @@ -240,14 +237,12 @@ def GetProjectSessionsMetadata(nidm_file_list, project_uuid): select distinct ?session_uuid ?p ?o - where { - ?session_uuid dct:isPartOf <%s> ; + where {{ + ?session_uuid dct:isPartOf <{project_uuid}> ; ?p ?o . - } + }} """ - % project_uuid - ) df = sparql_query_nidm(nidm_file_list, query, output_file=None) @@ -296,8 +291,7 @@ def GetProjectInstruments(nidm_file_list, project_id): :param project_id: identifier of project you'd like to search for unique instruments :return: Dataframe of instruments and project titles """ - query = ( - """ + query = f""" PREFIX prov: PREFIX sio: PREFIX dct: @@ -305,7 +299,7 @@ def GetProjectInstruments(nidm_file_list, project_id): prefix dctypes: SELECT DISTINCT ?project_title ?assessment_type - WHERE { + WHERE {{ ?entity rdf:type onli:assessment-instrument ; rdf:type ?assessment_type . ?entity prov:wasGeneratedBy/dct:isPartOf/dct:isPartOf ?project . @@ -314,11 +308,9 @@ def GetProjectInstruments(nidm_file_list, project_id): - FILTER( (!regex(str(?assessment_type), "http://www.w3.org/ns/prov#Entity")) && (!regex(str(?assessment_type), "http://purl.org/nidash/nidm#AcquisitionObject")) && (regex(str(?project), "%s")) ) - } + FILTER( (!regex(str(?assessment_type), "http://www.w3.org/ns/prov#Entity")) && (!regex(str(?assessment_type), "http://purl.org/nidash/nidm#AcquisitionObject")) && (regex(str(?project), "{project_id}")) ) + }} """ - % project_id - ) logging.info("Query: %s", query) df = sparql_query_nidm(nidm_file_list, query, output_file=None) results = df.to_dict() @@ -334,8 +326,7 @@ def GetInstrumentVariables(nidm_file_list, project_id): :param project_id: identifier of project you'd like to search for unique instruments :return: Dataframe of instruments, project titles, and variables """ - query = ( - """ + query = f""" PREFIX prov: PREFIX sio: PREFIX dct: @@ -343,7 +334,7 @@ def GetInstrumentVariables(nidm_file_list, project_id): prefix dctypes: SELECT DISTINCT ?project_title ?assessment_type ?variables - WHERE { + WHERE {{ ?entity rdf:type onli:assessment-instrument ; rdf:type ?assessment_type ; ?variables ?value . @@ -353,11 +344,9 @@ def GetInstrumentVariables(nidm_file_list, project_id): - FILTER( (!regex(str(?assessment_type), "http://www.w3.org/ns/prov#Entity")) && (!regex(str(?assessment_type), "http://purl.org/nidash/nidm#AcquisitionObject")) && (regex(str(?project), "%s")) ) - } + FILTER( (!regex(str(?assessment_type), "http://www.w3.org/ns/prov#Entity")) && (!regex(str(?assessment_type), "http://purl.org/nidash/nidm#AcquisitionObject")) && (regex(str(?project), "{project_id}")) ) + }} """ - % project_id - ) logging.info("Query: %s", query) df = sparql_query_nidm(nidm_file_list, query, output_file=None) results = df.to_dict() @@ -373,7 +362,7 @@ def GetParticipantIDs(nidm_file_list, output_file=None): :return: list of Constants.NIDM_PARTICIPANT UUIDs and Constants.NIDM_SUBJECTID """ - query = """ + query = f""" PREFIX prov: PREFIX sio: @@ -381,21 +370,18 @@ def GetParticipantIDs(nidm_file_list, output_file=None): PREFIX rdf: SELECT DISTINCT ?uuid ?ID - WHERE { + WHERE {{ ?activity rdf:type prov:Activity ; prov:qualifiedAssociation _:blanknode . - _:blanknode prov:hadRole %s ; + _:blanknode prov:hadRole {Constants.NIDM_PARTICIPANT} ; prov:agent ?uuid . - ?uuid %s ?ID . + ?uuid {Constants.NIDM_SUBJECTID} ?ID . - } - """ % ( - Constants.NIDM_PARTICIPANT, - Constants.NIDM_SUBJECTID, - ) + }} + """ df = sparql_query_nidm(nidm_file_list, query, output_file=output_file) @@ -413,7 +399,7 @@ def GetParticipantIDFromAcquisition(nidm_file_list, acquisition, output_file=Non :return: a dataframe subject ID and prov:Agent UUID of participant with qualified association """ - query = """ + query = f""" PREFIX prov: PREFIX sio: @@ -422,22 +408,18 @@ def GetParticipantIDFromAcquisition(nidm_file_list, acquisition, output_file=Non PREFIX prov: SELECT DISTINCT ?uuid ?ID - WHERE { + WHERE {{ - <%s> rdf:type prov:Activity ; + <{acquisition}> rdf:type prov:Activity ; prov:qualifiedAssociation _:blanknode . - _:blanknode prov:hadRole %s ; + _:blanknode prov:hadRole {Constants.NIDM_PARTICIPANT} ; prov:agent ?uuid . - ?uuid %s ?ID . + ?uuid {Constants.NIDM_SUBJECTID} ?ID . - } - """ % ( - acquisition, - Constants.NIDM_PARTICIPANT, - Constants.NIDM_SUBJECTID, - ) + }} + """ df = sparql_query_nidm(nidm_file_list, query, output_file=output_file) @@ -451,7 +433,7 @@ def GetParticipantDetails(nidm_file_list, project_id, participant_id, output_fil :return: list of Constants.NIDM_PARTICIPANT UUIDs and Constants.NIDM_SUBJECTID """ - query = """ + query = f""" PREFIX prov: PREFIX sio: @@ -462,28 +444,24 @@ def GetParticipantDetails(nidm_file_list, project_id, participant_id, output_fil SELECT DISTINCT ?uuid ?id ?activity - WHERE { + WHERE {{ ?activity rdf:type prov:Activity ; prov:qualifiedAssociation _:blanknode . - _:blanknode prov:hadRole %s ; + _:blanknode prov:hadRole {Constants.NIDM_PARTICIPANT} ; prov:agent ?uuid . - ?uuid %s ?id . + ?uuid {Constants.NIDM_SUBJECTID} ?id . ?proj a nidm:Project . ?sess dct:isPartOf ?proj . ?activity dct:isPartOf ?sess . - FILTER(regex(str(?uuid), "%s")). + FILTER(regex(str(?uuid), "{participant_id}")). - } - """ % ( - Constants.NIDM_PARTICIPANT, - Constants.NIDM_SUBJECTID, - participant_id, - ) + }} + """ df = sparql_query_nidm(nidm_file_list, query, output_file=output_file) data = df.values @@ -1209,13 +1187,11 @@ def matchPrefix(possible_URI, short=False) -> str: if short: return k else: - return "{}:{}".format(k, possible_URI.replace(n, "")) + return f"{k}:{possible_URI.replace(n, '')}" # also check the prov prefix if possible_URI.startswith("http://www.w3.org/ns/prov#"): - return "{}:{}".format( - "prov", possible_URI.replace("http://www.w3.org/ns/prov#", "") - ) + return f"prov:{possible_URI.replace('http://www.w3.org/ns/prov#', '')}" return possible_URI @@ -1405,14 +1381,14 @@ def OpenGraph(file): try: with open(file) as f: data = f.read() - logging.debug("Sending {} to blazegraph".format(file)) + logging.debug("Sending %s to blazegraph", file) requests.post( url=environ["BLAZEGRAPH_URL"], data=data, headers={"Content-type": "application/x-turtle"}, ) except Exception as e: - logging.error("Exception {} loading {} into Blazegraph.".format(e, file)) + logging.error("Exception %s loading %s into Blazegraph.", e, file) BLOCKSIZE = 65536 hasher = hashlib.md5() @@ -1423,7 +1399,7 @@ def OpenGraph(file): buf = afile.read(BLOCKSIZE) digest = hasher.hexdigest() - pickle_file = "{}/rdf_graph.{}.pickle".format(tempfile.gettempdir(), digest) + pickle_file = f"{tempfile.gettempdir()}/rdf_graph.{digest}.pickle" if path.isfile(pickle_file): with open(pickle_file, "rb") as fp: return pickle.load(fp) @@ -1491,7 +1467,7 @@ def download_cde_files(): cde_dir = tempfile.gettempdir() for url in Constants.CDE_FILE_LOCATIONS: - urlretrieve(url, "{}/{}".format(cde_dir, url.split("/")[-1])) + urlretrieve(url, f"{cde_dir}/{url.split('/')[-1]}") return cde_dir @@ -1504,7 +1480,7 @@ def getCDEs(file_list=None): hasher.update(str(file_list).encode("utf-8")) h = hasher.hexdigest() - cache_file_name = tempfile.gettempdir() + "/cde_graph.{}.pickle".format(h) + cache_file_name = tempfile.gettempdir() + f"/cde_graph.{h}.pickle" if path.isfile(cache_file_name): with open(cache_file_name, "rb") as fp: @@ -1530,7 +1506,7 @@ def getCDEs(file_list=None): # TODO: the list of file names should be it's own constant or derived from CDE_FILE_LOCATIONS file_list = [] for f in ["ants_cde.ttl", "fs_cde.ttl", "fsl_cde.ttl"]: - fname = "{}/{}".format(cde_dir, f) + fname = f"{cde_dir}/{f}" if os.path.isfile(fname): file_list.append(fname) diff --git a/src/nidm/experiment/Session.py b/src/nidm/experiment/Session.py index 3536f21..65deb16 100644 --- a/src/nidm/experiment/Session.py +++ b/src/nidm/experiment/Session.py @@ -72,7 +72,7 @@ def acquisition_exist(self, uuid): :param uuid: full uuid of acquisition :return: True if exists, False otherwise """ - # print("Query uuid: %s" %uuid) + # print(f"Query uuid: {uuid}") for acquisitions in self._acquisitions: # print(acquisitions._identifier._localpart) if str(uuid) == acquisitions._identifier._localpart: diff --git a/src/nidm/experiment/Utils.py b/src/nidm/experiment/Utils.py index 2c8aaad..73c769c 100644 --- a/src/nidm/experiment/Utils.py +++ b/src/nidm/experiment/Utils.py @@ -96,7 +96,7 @@ def read_nidm(nidmDoc): proj_id = s if proj_id is None: - print("Error reading NIDM-Exp Document %s, Must have Project Object" % nidmDoc) + print(f"Error reading NIDM-Exp Document {nidmDoc}, Must have Project Object") print() create_obj = input("Should read_nidm create a Project object for you [yes]: ") if create_obj == "yes" or create_obj == "": @@ -142,12 +142,12 @@ def read_nidm(nidmDoc): for s in rdf_graph_parse.subjects( predicate=RDF.type, object=URIRef(Constants.NIDM_SESSION.uri) ): - # print("session: %s" % s) + # print(f"session: {s}") # Split subject URI for session into namespace, uuid nm, session_uuid = split_uri(s) - # print("session uuid= %s" %session_uuid) + # print(f"session uuid= {session_uuid}") # instantiate session with this uuid session = Session(project=project, uuid=session_uuid, add_default_type=False) @@ -165,7 +165,7 @@ def read_nidm(nidmDoc): ): # Split subject URI for session into namespace, uuid nm, acq_uuid = split_uri(acq) - # print("acquisition uuid: %s" %acq_uuid) + # print(f"acquisition uuid: {acq_uuid}") # query for whether this is an AssessmentAcquisition of other Acquisition, etc. for rdf_type in rdf_graph_parse.objects(subject=acq, predicate=RDF.type): @@ -177,7 +177,7 @@ def read_nidm(nidmDoc): ): # Split subject URI for acquisition object (entity) into namespace, uuid nm, acq_obj_uuid = split_uri(acq_obj) - # print("acquisition object uuid: %s" %acq_obj_uuid) + # print(f"acquisition object uuid: {acq_obj_uuid}") # query for whether this is an MRI acquisition by way of looking at the generated entity and determining # if it has the tuple [uuid Constants.NIDM_ACQUISITION_MODALITY Constants.NIDM_MRI] @@ -233,7 +233,7 @@ def read_nidm(nidmDoc): ) in rdf_graph: # Split subject URI for associated acquisition entity for nidm:StimulusResponseFile into namespace, uuid nm, assoc_acq_uuid = split_uri(assoc_acq) - # print("associated acquisition object (stimulus file) uuid: %s" % assoc_acq_uuid) + # print(f"associated acquisition object (stimulus file) uuid: {assoc_acq_uuid}") # if so then add this entity and associate it with acquisition activity and MRI entity events_obj = AcquisitionObject( acquisition=acquisition, uuid=assoc_acq_uuid @@ -413,8 +413,7 @@ def read_nidm(nidmDoc): ) # now we need to check if there are labels for data element isAbout entries, if so add them. - query2 = ( - """ + query2 = f""" prefix nidm: prefix rdfs: @@ -422,16 +421,14 @@ def read_nidm(nidmDoc): prefix prov: select distinct ?id ?label - where { - <%s> nidm:isAbout ?id . + where {{ + <{row["uuid"]}> nidm:isAbout ?id . ?id rdf:type prov:Entity ; rdfs:label ?label . - } + }} """ - % row["uuid"] - ) # print(query2) qres2 = rdf_graph_parse.query(query2) @@ -723,70 +720,192 @@ def QuerySciCrunchElasticSearch( sys.exit(1) # Add check for internet connection, if not then skip this query...return empty dictionary - headers = { - "Content-Type": "application/json", - } - params = (("key", os.environ["INTERLEX_API_KEY"]),) if type == "cde": if anscestors: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "cde" } },\n { "terms" : { "ancestors.ilx" : ["ilx_0115066" , "ilx_0103210", "ilx_0115072", "ilx_0115070"] } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "cde"}}, + { + "terms": { + "ancestors.ilx": [ + "ilx_0115066", + "ilx_0103210", + "ilx_0115072", + "ilx_0115070", + ] + } + }, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } else: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "cde" } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "cde"}}, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } elif type == "pde": if anscestors: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "pde" } },\n { "terms" : { "ancestors.ilx" : ["ilx_0115066" , "ilx_0103210", "ilx_0115072", "ilx_0115070"] } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "pde"}}, + { + "terms": { + "ancestors.ilx": [ + "ilx_0115066", + "ilx_0103210", + "ilx_0115072", + "ilx_0115070", + ] + } + }, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } else: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "pde" } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "pde"}}, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } elif type == "fde": if anscestors: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "fde" } },\n { "terms" : { "ancestors.ilx" : ["ilx_0115066" , "ilx_0103210", "ilx_0115072", "ilx_0115070"] } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "fde"}}, + { + "terms": { + "ancestors.ilx": [ + "ilx_0115066", + "ilx_0103210", + "ilx_0115072", + "ilx_0115070", + ] + } + }, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } else: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "fde" } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "fde"}}, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } elif type == "term": if anscestors: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "term" } },\n { "terms" : { "ancestors.ilx" : ["ilx_0115066" , "ilx_0103210", "ilx_0115072", "ilx_0115070"] } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "term"}}, + { + "terms": { + "ancestors.ilx": [ + "ilx_0115066", + "ilx_0103210", + "ilx_0115072", + "ilx_0115070", + ] + } + }, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } else: - data = ( - '\n{\n "query": {\n "bool": {\n "must" : [\n { "term" : { "type" : "term" } },\n { "multi_match" : {\n "query": "%s", \n "fields": [ "label", "definition" ] \n } }\n]\n }\n }\n}\n' - % query_string - ) + data = { + "query": { + "bool": { + "must": [ + {"term": {"type": "term"}}, + { + "multi_match": { + "query": query_string, + "fields": ["label", "definition"], + } + }, + ] + } + } + } else: print( - "ERROR: Valid types for SciCrunch query are 'cde','pde', or 'fde'. You set type: %s " - % type + f"ERROR: Valid types for SciCrunch query are 'cde','pde', or 'fde'. You set type: {type} " ) print("ERROR: in function Utils.py/QuerySciCrunchElasticSearch") exit(1) response = requests.post( "https://scicrunch.org/api/1/elastic-ilx/interlex/term/_search#", - headers=headers, params=params, - data=data, + json=data, ) return json.loads(response.text) @@ -969,7 +1088,7 @@ def load_nidm_terms_concepts(): r.raise_for_status() concept_graph = r.json() except Exception: - logging.info("Error opening %s used concepts file..continuing" % concept_url) + logging.info("Error opening %s used concepts file..continuing", concept_url) return None return concept_graph @@ -1015,7 +1134,7 @@ def load_nidm_owl_files(): # union_graph=union_graph+temp_graph # # except Exception: - # logging.info("Error opening %s import file..continuing" %os.path.join(imports_path,resource)) + # logging.info("Error opening %s import file..continuing", os.path.join(imports_path,resource)) # continue owls = [ @@ -1041,7 +1160,7 @@ def load_nidm_owl_files(): temp_graph.parse(location=resource, format="turtle") union_graph = union_graph + temp_graph except Exception: - logging.info("Error opening %s owl file..continuing" % resource) + logging.info("Error opening %s owl file..continuing", resource) continue return union_graph @@ -1186,7 +1305,7 @@ def getSubjIDColumn(column_to_terms, df): if id_field is None: option = 1 for column in df.columns: - print("%d: %s" % (option, column)) + print(f"{option}: {column}") option = option + 1 selection = input("Please select the subject ID field from the list above: ") id_field = df.columns[int(selection) - 1] @@ -1330,7 +1449,7 @@ def map_variables_to_terms( with open(json_source, "r") as f: json_map = json.load(f) else: - print("ERROR: Can't open json mapping file: %s" % (json_source)) + print(f"ERROR: Can't open json mapping file: {json_source}") exit() except Exception: # if not then it's a json structure already @@ -1417,8 +1536,7 @@ def map_variables_to_terms( column_to_terms[current_tuple]["label"] = "" print( "No label or source_variable or sourceVariable keys found in json mapping file for variable " - "%s. Consider adding these to the json file as they are important" - % json_key[0] + f"{json_key[0]}. Consider adding these to the json file as they are important" ) else: column_to_terms[current_tuple]["label"] = json_map[json_key[0]][ @@ -1440,67 +1558,63 @@ def map_variables_to_terms( print("\n" + ("*" * 85)) print( - "Column %s already annotated in user supplied JSON mapping file" - % column - ) - print("label: %s" % column_to_terms[current_tuple]["label"]) - print( - "description: %s" - % column_to_terms[current_tuple]["description"] + f"Column {column} already annotated in user supplied JSON mapping file" ) + print("label:", column_to_terms[current_tuple]["label"]) + print("description:", column_to_terms[current_tuple]["description"]) if "url" in json_map[json_key[0]]: column_to_terms[current_tuple]["url"] = json_map[json_key[0]][ "url" ] - print("url: %s" % column_to_terms[current_tuple]["url"]) - # print("Variable: %s" %column_to_terms[current_tuple]['variable']) + print("url:", column_to_terms[current_tuple]["url"]) + # print("Variable:", column_to_terms[current_tuple]['variable']) if "sameAs" in json_map[json_key[0]]: column_to_terms[current_tuple]["sameAs"] = json_map[ json_key[0] ]["sameAs"] - print("sameAs: %s" % column_to_terms[current_tuple]["sameAs"]) + print("sameAs:", column_to_terms[current_tuple]["sameAs"]) if "url" in json_map[json_key[0]]: column_to_terms[current_tuple]["url"] = json_map[json_key[0]][ "url" ] - print("url: %s" % column_to_terms[current_tuple]["url"]) + print("url:", column_to_terms[current_tuple]["url"]) if "source_variable" in json_map[json_key[0]]: column_to_terms[current_tuple]["source_variable"] = json_map[ json_key[0] ]["source_variable"] print( - "source variable: %s" - % column_to_terms[current_tuple]["source_variable"] + "source variable:", + column_to_terms[current_tuple]["source_variable"], ) elif "sourceVariable" in json_map[json_key[0]]: column_to_terms[current_tuple]["source_variable"] = json_map[ json_key[0] ]["sourceVariable"] print( - "source variable: %s" - % column_to_terms[current_tuple]["source_variable"] + "source variable:", + column_to_terms[current_tuple]["source_variable"], ) else: # add source variable if not there... column_to_terms[current_tuple]["source_variable"] = str(column) - print("Added source variable (%s) to annotations" % column) + print(f"Added source variable ({column}) to annotations") if "associatedWith" in json_map[json_key[0]]: column_to_terms[current_tuple]["associatedWith"] = json_map[ json_key[0] ]["associatedWith"] print( - "associatedWith: %s" - % column_to_terms[current_tuple]["associatedWith"] + "associatedWith:", + column_to_terms[current_tuple]["associatedWith"], ) if "allowableValues" in json_map[json_key[0]]: column_to_terms[current_tuple]["allowableValues"] = json_map[ json_key[0] ]["allowableValues"] print( - "allowableValues: %s" - % column_to_terms[current_tuple]["allowableValues"] + "allowableValues:", + column_to_terms[current_tuple]["allowableValues"], ) # added to support ReproSchema json format @@ -1523,10 +1637,10 @@ def map_variables_to_terms( "valueType" ] print( - "valueType: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "valueType:", + column_to_terms[current_tuple]["responseOptions"][ "valueType" - ] + ], ) elif "minValue" in subkey: @@ -1542,10 +1656,10 @@ def map_variables_to_terms( "minValue" ] = json_map[json_key[0]]["responseOptions"]["minValue"] print( - "minValue: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "minValue:", + column_to_terms[current_tuple]["responseOptions"][ "minValue" - ] + ], ) elif "maxValue" in subkey: @@ -1561,10 +1675,10 @@ def map_variables_to_terms( "maxValue" ] = json_map[json_key[0]]["responseOptions"]["maxValue"] print( - "maxValue: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "maxValue:", + column_to_terms[current_tuple]["responseOptions"][ "maxValue" - ] + ], ) elif "choices" in subkey: if ( @@ -1579,10 +1693,10 @@ def map_variables_to_terms( "choices" ] = json_map[json_key[0]]["responseOptions"]["choices"] print( - "levels: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "levels:", + column_to_terms[current_tuple]["responseOptions"][ "choices" - ] + ], ) elif "hasUnit" in subkey: if ( @@ -1597,10 +1711,10 @@ def map_variables_to_terms( "unitCode" ] = json_map[json_key[0]]["responseOptions"]["hasUnit"] print( - "units: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "units:", + column_to_terms[current_tuple]["responseOptions"][ "unitCode" - ] + ], ) elif "unitCode" in subkey: if ( @@ -1615,10 +1729,10 @@ def map_variables_to_terms( "unitCode" ] = json_map[json_key[0]]["responseOptions"]["unitCode"] print( - "units: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "units:", + column_to_terms[current_tuple]["responseOptions"][ "unitCode" - ] + ], ) if "levels" in json_map[json_key[0]]: @@ -1632,10 +1746,10 @@ def map_variables_to_terms( "choices" ] = json_map[json_key[0]]["levels"] print( - "choices: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "choices:", + column_to_terms[current_tuple]["responseOptions"][ "choices" - ] + ], ) elif "Levels" in json_map[json_key[0]]: # upgrade 'levels' to 'responseOptions'->'choices' @@ -1648,10 +1762,10 @@ def map_variables_to_terms( "choices" ] = json_map[json_key[0]]["Levels"] print( - "levels: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "levels:", + column_to_terms[current_tuple]["responseOptions"][ "choices" - ] + ], ) if "valueType" in json_map[json_key[0]]: @@ -1665,10 +1779,10 @@ def map_variables_to_terms( "valueType" ] = json_map[json_key[0]]["valueType"] print( - "valueType: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "valueType:", + column_to_terms[current_tuple]["responseOptions"][ "valueType" - ] + ], ) if "minValue" in json_map[json_key[0]]: @@ -1682,10 +1796,10 @@ def map_variables_to_terms( "minValue" ] = json_map[json_key[0]]["minValue"] print( - "minValue: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "minValue:", + column_to_terms[current_tuple]["responseOptions"][ "minValue" - ] + ], ) elif "minimumValue" in json_map[json_key[0]]: # upgrade 'minValue' to 'responseOptions'->'minValue @@ -1698,10 +1812,10 @@ def map_variables_to_terms( "minValue" ] = json_map[json_key[0]]["minimumValue"] print( - "minValue: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "minValue:", + column_to_terms[current_tuple]["responseOptions"][ "minValue" - ] + ], ) if "maxValue" in json_map[json_key[0]]: @@ -1715,10 +1829,10 @@ def map_variables_to_terms( "maxValue" ] = json_map[json_key[0]]["maxValue"] print( - "maxValue: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "maxValue:", + column_to_terms[current_tuple]["responseOptions"][ "maxValue" - ] + ], ) elif "maximumValue" in json_map[json_key[0]]: # upgrade 'maxValue' to 'responseOptions'->'maxValue @@ -1731,10 +1845,10 @@ def map_variables_to_terms( "maxValue" ] = json_map[json_key[0]]["maximumValue"] print( - "maxValue: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "maxValue:", + column_to_terms[current_tuple]["responseOptions"][ "maxValue" - ] + ], ) if "hasUnit" in json_map[json_key[0]]: # upgrade 'hasUnit' to 'responseOptions'->'unitCode @@ -1747,10 +1861,10 @@ def map_variables_to_terms( "unitCode" ] = json_map[json_key[0]]["hasUnit"] print( - "unitCode: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "unitCode:", + column_to_terms[current_tuple]["responseOptions"][ "unitCode" - ] + ], ) elif "Units" in json_map[json_key[0]]: # upgrade 'Units' to 'responseOptions'->'unitCode @@ -1763,10 +1877,10 @@ def map_variables_to_terms( "unitCode" ] = json_map[json_key[0]]["Units"] print( - "unitCode: %s" - % column_to_terms[current_tuple]["responseOptions"][ + "unitCode:", + column_to_terms[current_tuple]["responseOptions"][ "unitCode" - ] + ], ) if "isAbout" in json_map[json_key[0]]: @@ -1805,24 +1919,16 @@ def map_variables_to_terms( } ) print( - "isAbout: %s = %s, %s = %s" - % ( - "@id", - subdict["@id"], - "label", - subdict["label"], - ) + f"isAbout: @id = {subdict['@id']}, label = {subdict['label']}" ) else: column_to_terms[current_tuple][ "isAbout" ].append({"@id": subdict["@id"]}) - print( - "isAbout: %s = %s" % ("@id", subdict["@id"]) - ) + print(f"isAbout: @id = {subdict['@id']}") # for isabout_key,isabout_value in subdict.items(): # column_to_terms[current_tuple]['isAbout'].append({isabout_key:isabout_value}) - # print("isAbout: %s = %s" %(isabout_key, isabout_value)) + # print(f"isAbout: {isabout_key} = {isabout_value}") # if isAbout is a dictionary then we only have 1 isAbout...we'll upgrade it to a list # to be consistent moving forward else: @@ -1861,13 +1967,7 @@ def map_variables_to_terms( ) print( - "isAbout: %s = %s, %s = %s" - % ( - "@id", - column_to_terms[current_tuple]["isAbout"]["@id"], - "label", - column_to_terms[current_tuple]["isAbout"]["label"], - ) + f"isAbout: @id = {column_to_terms[current_tuple]['isAbout']['@id']}, label = {column_to_terms[current_tuple]['isAbout']['label']}" ) else: # if user ran in mode where they want to associate concepts and this isn't the participant @@ -1936,15 +2036,12 @@ def map_variables_to_terms( # column_to_terms[subjid_tuple]['variable'] = str(column) print( - "Variable %s automatically mapped to participant/subject identifier" - % search_term - ) - print("Label: %s" % column_to_terms[subjid_tuple]["label"]) - print("Description: %s" % column_to_terms[subjid_tuple]["description"]) - # print("Url: %s" %column_to_terms[subjid_tuple]['url']) - print( - "Source Variable: %s" % column_to_terms[subjid_tuple]["source_variable"] + f"Variable {search_term} automatically mapped to participant/subject identifier" ) + print("Label:", column_to_terms[subjid_tuple]["label"]) + print("Description:", column_to_terms[subjid_tuple]["description"]) + # print("Url:", column_to_terms[subjid_tuple]['url']) + print("Source Variable:", column_to_terms[subjid_tuple]["source_variable"]) print("-" * 87) continue # if we haven't already found an annotation for this column then have user create one. @@ -2063,7 +2160,7 @@ def write_json_mapping_file(source_variable_annotations, output_file, bids=False ) as fp: json.dump(new_dict, fp, indent=4) else: - # logging.info("saving json mapping file: %s" %os.path.join(os.path.basename(output_file), \ + # logging.info("saving json mapping file: %s", os.path.join(os.path.basename(output_file), \ # os.path.splitext(output_file)[0]+".json")) with open( os.path.join( @@ -2123,7 +2220,7 @@ def find_concept_interactive( option = 1 print() print("Concept Association") - print("Query String: %s " % search_term) + print(f"Query String: {search_term} ") # modified by DBK 5/14/21 to start with nidm-terms used concepts if nidmterms_concepts is not None: @@ -2140,13 +2237,12 @@ def find_concept_interactive( first_nidm_term = False print( - "%d: Label: %s \t Definition: %s \t URL: %s" - % ( - option, - nidmterms_concepts_query[key]["label"], - nidmterms_concepts_query[key]["definition"], - nidmterms_concepts_query[key]["url"], - ) + f"{option}: Label:", + nidmterms_concepts_query[key]["label"], + "\t Definition:", + nidmterms_concepts_query[key]["definition"], + "\t URL:", + nidmterms_concepts_query[key]["url"], ) search_result[key] = {} search_result[key]["label"] = nidmterms_concepts_query[key]["label"] @@ -2167,20 +2263,19 @@ def find_concept_interactive( ) # temp = ilx_result.copy() - # print("Search Term: %s" %search_term) + # print("Search Term:", search_term) if len(ilx_result) != 0: print("InterLex:") print() # print("Search Results: ") for key, _ in ilx_result.items(): print( - "%d: Label: %s \t Definition: %s \t Preferred URL: %s " - % ( - option, - ilx_result[key]["label"], - ilx_result[key]["definition"], - ilx_result[key]["preferred_url"], - ) + f"{option}: Label:", + ilx_result[key]["label"], + "\t Definition:", + ilx_result[key]["definition"], + "\t Preferred URL:", + ilx_result[key]["preferred_url"], ) search_result[key] = {} @@ -2207,14 +2302,10 @@ def find_concept_interactive( first_cogatlas_concept = False print( - "%d: Label: %s \t Definition: %s " - % ( - option, - cogatlas_concepts_query[key]["label"], - cogatlas_concepts_query[key]["definition"].rstrip( - "\r\n" - ), - ) + f"{option}: Label:", + cogatlas_concepts_query[key]["label"], + "\t Definition: ", + cogatlas_concepts_query[key]["definition"].rstrip("\r\n"), ) search_result[key] = {} search_result[key]["label"] = cogatlas_concepts_query[key][ @@ -2239,14 +2330,10 @@ def find_concept_interactive( for key, _ in cogatlas_disorders_query.items(): if cogatlas_disorders_query[key]["score"] > min_match_score + 20: print( - "%d: Label: %s \t Definition: %s " - % ( - option, - cogatlas_disorders_query[key]["label"], - cogatlas_disorders_query[key]["definition"].rstrip( - "\r\n" - ), - ) + f"{option}: Label:", + cogatlas_disorders_query[key]["label"], + "\t Definition: ", + cogatlas_disorders_query[key]["definition"].rstrip("\r\n"), ) search_result[key] = {} search_result[key]["label"] = cogatlas_disorders_query[key][ @@ -2281,13 +2368,12 @@ def find_concept_interactive( first_nidm_term = False print( - "%d: Label: %s \t Definition: %s \t URL: %s" - % ( - option, - nidm_constants_query[key]["label"], - nidm_constants_query[key]["definition"], - nidm_constants_query[key]["url"], - ) + f"{option}: Label:", + nidm_constants_query[key]["label"], + "\t Definition:", + nidm_constants_query[key]["definition"], + "\t URL:", + nidm_constants_query[key]["url"], ) search_result[key] = {} search_result[key]["label"] = nidm_constants_query[key]["label"] @@ -2304,37 +2390,35 @@ def find_concept_interactive( if ancestor: # Broaden Interlex search print( - "%d: Broaden Search (includes interlex, cogatlas, and nidm ontology) " - % option + f"{option}: Broaden Search (includes interlex, cogatlas, and nidm ontology) " ) else: # Narrow Interlex search print( - "%d: Narrow Search (includes nidm-terms previously used concepts) " - % option + f"{option}: Narrow Search (includes nidm-terms previously used concepts) " ) option = option + 1 # Add option to change query string - print('%d: Change query string from: "%s"' % (option, search_term)) + print(f'{option}: Change query string from: "{search_term}"') # ####### DEFINE NEW CONCEPT COMMENTED OUT RIGHT NOW ################## # # Add option to define your own term # option = option + 1 - # print("%d: Define my own concept for this variable" % option) + # print(f"{option}: Define my own concept for this variable") # ####### DEFINE NEW CONCEPT COMMENTED OUT RIGHT NOW ################## # Add option to define your own term option = option + 1 - print("%d: No concept needed for this variable" % option) + print(f"{option}: No concept needed for this variable") print("*" * 87) # Wait for user input - selection = input("Please select an option (1:%d) from above: \t" % option) + selection = input(f"Please select an option (1:{option}) from above: \t") # Make sure user selected one of the options. If not present user with selection input again while (not selection.isdigit()) or (int(selection) > int(option)): # Wait for user input - selection = input("Please select an option (1:%d) from above: \t" % option) + selection = input(f"Please select an option (1:{option}) from above: \t") # toggle use of ancestors in interlex query or not if int(selection) == (option - 2): @@ -2343,8 +2427,7 @@ def find_concept_interactive( elif int(selection) == (option - 1): # ask user for new search string search_term = input( - "Please input new search string for CSV column: %s \t:" - % source_variable + f"Please input new search string for CSV column: {source_variable} \t:" ) print("*" * 87) @@ -2372,19 +2455,17 @@ def find_concept_interactive( "label": search_result[search_result[selection]]["label"], } ) - print( - "\nConcept annotation added for source variable: %s" % source_variable - ) + print("\nConcept annotation added for source variable:", source_variable) go_loop = False def define_new_concept(source_variable, ilx_obj): # user wants to define their own term. Ask for term label and definition - print("\nYou selected to enter a new concept for CSV column: %s" % source_variable) + print("\nYou selected to enter a new concept for CSV column:", source_variable) # collect term information from user concept_label = input( - "Please enter a label for the new concept [%s]:\t" % source_variable + f"Please enter a label for the new concept [{source_variable}]:\t" ) concept_definition = input("Please enter a definition for this concept:\t") @@ -2408,13 +2489,13 @@ def annotate_data_element(source_variable, current_tuple, source_variable_annota # user instructions print( - "\nYou will now be asked a series of questions to annotate your term: %s" - % source_variable + "\nYou will now be asked a series of questions to annotate your term:", + source_variable, ) # collect term information from user term_label = input( - "Please enter a full name to associate with the term [%s]:\t" % source_variable + f"Please enter a full name to associate with the term [{source_variable}]:\t" ) if term_label == "": term_label = source_variable @@ -2501,11 +2582,10 @@ def annotate_data_element(source_variable, current_tuple, source_variable_annota for category in range(1, int(num_categories) + 1): # term category dictionary has labels as keys and value associated with label as value cat_label = input( - "Please enter the text string label for the category %d:\t" - % category + f"Please enter the text string label for the category {category}:\t" ) cat_value = input( - 'Please enter the value associated with label "%s":\t' % cat_label + f'Please enter the value associated with label "{cat_label}":\t' ) term_category[cat_label] = cat_value @@ -2515,8 +2595,7 @@ def annotate_data_element(source_variable, current_tuple, source_variable_annota for category in range(1, int(num_categories) + 1): # term category dictionary has labels as keys and value associated with label as value cat_label = input( - "Please enter the text string label for the category %d:\t" - % category + f"Please enter the text string label for the category {category}:\t" ) term_category.append(cat_label) @@ -2580,39 +2659,39 @@ def annotate_data_element(source_variable, current_tuple, source_variable_annota # print mappings print("\n" + ("*" * 85)) - print("Stored mapping: %s -> " % source_variable) - print("label: %s" % source_variable_annotations[current_tuple]["label"]) + print(f"Stored mapping: {source_variable} -> ") + print("label:", source_variable_annotations[current_tuple]["label"]) print( - "source variable: %s" - % source_variable_annotations[current_tuple]["source_variable"] + "source variable:", + source_variable_annotations[current_tuple]["source_variable"], ) - print("description: %s" % source_variable_annotations[current_tuple]["description"]) + print("description:", source_variable_annotations[current_tuple]["description"]) print( - "valueType: %s" - % source_variable_annotations[current_tuple]["responseOptions"]["valueType"] + "valueType:", + source_variable_annotations[current_tuple]["responseOptions"]["valueType"], ) # left for legacy purposes if "hasUnit" in source_variable_annotations[current_tuple]: - print("hasUnit: %s" % source_variable_annotations[current_tuple]["hasUnit"]) + print("hasUnit:", source_variable_annotations[current_tuple]["hasUnit"]) elif "unitCode" in source_variable_annotations[current_tuple]["responseOptions"]: print( - "hasUnit: %s" - % source_variable_annotations[current_tuple]["responseOptions"]["unitCode"] + "hasUnit:", + source_variable_annotations[current_tuple]["responseOptions"]["unitCode"], ) if "minValue" in source_variable_annotations[current_tuple]["responseOptions"]: print( - "minimumValue: %s" - % source_variable_annotations[current_tuple]["responseOptions"]["minValue"] + "minimumValue:", + source_variable_annotations[current_tuple]["responseOptions"]["minValue"], ) if "maxValue" in source_variable_annotations[current_tuple]["responseOptions"]: print( - "maximumValue: %s" - % source_variable_annotations[current_tuple]["responseOptions"]["maxValue"] + "maximumValue:", + source_variable_annotations[current_tuple]["responseOptions"]["maxValue"], ) if term_datatype == URIRef(Constants.XSD["complexType"]): print( - "choices: %s" - % source_variable_annotations[current_tuple]["responseOptions"]["choices"] + "choices:", + source_variable_annotations[current_tuple]["responseOptions"]["choices"], ) print("-" * 87) @@ -2888,7 +2967,7 @@ def addGitAnnexSources(obj, bids_root, filepath=None): return len(sources) except Exception: # if "No annex found at" not in str(e): - # print("Warning, error with AnnexRepo (Utils.py, addGitAnnexSources): %s" %str(e)) + # print("Warning, error with AnnexRepo (Utils.py, addGitAnnexSources):", e) return 0 diff --git a/src/nidm/experiment/tools/bidsmri2nidm.py b/src/nidm/experiment/tools/bidsmri2nidm.py index ebad76a..b3b9985 100755 --- a/src/nidm/experiment/tools/bidsmri2nidm.py +++ b/src/nidm/experiment/tools/bidsmri2nidm.py @@ -159,7 +159,7 @@ def main(): level=logging.DEBUG, ) # add some logging info - logging.info("bidsmri2nidm %s" % args) + logging.info("bidsmri2nidm %s", args) # if args.owl is None: # args.owl = 'nidm' @@ -234,7 +234,7 @@ def main(): def addbidsignore(directory, filename_to_add): - logging.info("Adding file %s to %s/.bidsignore..." % (filename_to_add, directory)) + logging.info("Adding file %s to %s/.bidsignore...", filename_to_add, directory) # adds filename_to_add to .bidsignore file in directory if not isfile(os.path.join(directory, ".bidsignore")): with open(os.path.join(directory, ".bidsignore"), "w") as text_file: @@ -309,8 +309,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image contrast type found in BIDS_Constants.py for %s" - % file_tpl.entities["suffix"] + "WARNING: No matching image contrast type found in BIDS_Constants.py for %s", + file_tpl.entities["suffix"], ) # add image usage type @@ -324,8 +324,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image usage type found in BIDS_Constants.py for %s" - % file_tpl.entities["datatype"] + "WARNING: No matching image usage type found in BIDS_Constants.py for %s", + file_tpl.entities["datatype"], ) # add file link # make relative link to @@ -364,8 +364,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." - % join(directory, file_tpl.dirname, file_tpl.filename) + "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files...", + join(directory, file_tpl.dirname, file_tpl.filename), ) # get associated JSON file if exists # There is T1w.json file with information @@ -419,7 +419,7 @@ def addimagingsessions( else: logging.critical( - "Error: BIDS directory %s does not exist!" % os.path.join(directory) + "Error: BIDS directory %s does not exist!", os.path.join(directory) ) exit(-1) @@ -450,8 +450,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image contrast type found in BIDS_Constants.py for %s" - % file_tpl.entities["suffix"] + "WARNING: No matching image contrast type found in BIDS_Constants.py for %s", + file_tpl.entities["suffix"], ) # add image usage type @@ -465,8 +465,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image usage type found in BIDS_Constants.py for %s" - % file_tpl.entities["datatype"] + "WARNING: No matching image usage type found in BIDS_Constants.py for %s", + file_tpl.entities["datatype"], ) # make relative link to acq_obj.add_attributes( @@ -505,8 +505,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." - % join(directory, file_tpl.dirname, file_tpl.filename) + "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files...", + join(directory, file_tpl.dirname, file_tpl.filename), ) if "run" in file_tpl.entities: @@ -614,7 +614,7 @@ def addimagingsessions( dataset = {} else: logging.critical( - "Error: BIDS directory %s does not exist!" % os.path.join(directory) + "Error: BIDS directory %s does not exist!", os.path.join(directory) ) exit(-1) @@ -650,8 +650,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image contrast type found in BIDS_Constants.py for %s" - % file_tpl.entities["suffix"] + "WARNING: No matching image contrast type found in BIDS_Constants.py for %s", + file_tpl.entities["suffix"], ) # add image usage type if file_tpl.entities["datatype"] in BIDS_Constants.scans: @@ -660,8 +660,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image usage type found in BIDS_Constants.py for %s" - % file_tpl.entities["datatype"] + "WARNING: No matching image usage type found in BIDS_Constants.py for %s", + file_tpl.entities["datatype"], ) # make relative link to acq_obj.add_attributes( @@ -682,8 +682,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." - % join(directory, file_tpl.dirname, file_tpl.filename) + "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files...", + join(directory, file_tpl.dirname, file_tpl.filename), ) # add git-annex/datalad info if exists @@ -749,8 +749,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image contrast type found in BIDS_Constants.py for %s" - % file_tpl.entities["suffix"] + "WARNING: No matching image contrast type found in BIDS_Constants.py for %s", + file_tpl.entities["suffix"], ) # add image usage type @@ -760,8 +760,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING: No matching image usage type found in BIDS_Constants.py for %s" - % file_tpl.entities["datatype"] + "WARNING: No matching image usage type found in BIDS_Constants.py for %s", + file_tpl.entities["datatype"], ) # make relative link to acq_obj.add_attributes( @@ -782,8 +782,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." - % join(directory, file_tpl.dirname, file_tpl.filename) + "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files...", + join(directory, file_tpl.dirname, file_tpl.filename), ) # add git-annex/datalad info if exists @@ -883,8 +883,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." - % join(directory, file_tpl.dirname, file_tpl.filename) + "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files...", + join(directory, file_tpl.dirname, file_tpl.filename), ) acq_obj_bvec = AcquisitionObject(acq) acq_obj_bvec.add_attributes({PROV_TYPE: BIDS_Constants.scans["bvec"]}) @@ -938,8 +938,8 @@ def addimagingsessions( ) else: logging.info( - "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files..." - % join(directory, file_tpl.dirname, file_tpl.filename) + "WARNING file %s doesn't exist! No SHA512 sum stored in NIDM files...", + join(directory, file_tpl.dirname, file_tpl.filename), ) # link bval and bvec acquisition object entities together or is their association with DWI scan... @@ -961,7 +961,7 @@ def bidsmri2project(directory, args): exit("-1") else: logging.critical( - "Error: BIDS directory %s does not exist!" % os.path.join(directory) + "Error: BIDS directory %s does not exist!", os.path.join(directory) ) exit("-1") @@ -1279,7 +1279,7 @@ def bidsmri2project(directory, args): # create acquisition objects for each scan for each subject # loop through all subjects in dataset for subject_id in bids_layout.get_subjects(): - logging.info("Converting subject: %s" % subject_id) + logging.info("Converting subject: %s", subject_id) # skip .git directories...added to support datalad datasets if subject_id.startswith("."): continue diff --git a/src/nidm/experiment/tools/csv2nidm.py b/src/nidm/experiment/tools/csv2nidm.py index 76251a1..f5af966 100644 --- a/src/nidm/experiment/tools/csv2nidm.py +++ b/src/nidm/experiment/tools/csv2nidm.py @@ -195,7 +195,7 @@ def main(): level=logging.DEBUG, ) # add some logging info - logging.info("csv2nidm %s" % args) + logging.info("csv2nidm %s", args) # If user has added an existing NIDM file as a command line parameter then add to existing file for subjects who exist in the NIDM file if args.nidm_file: @@ -232,7 +232,7 @@ def main(): if id_field is None: option = 1 for column in df.columns: - print("%d: %s" % (option, column)) + print(f"{option}: {column}") option = option + 1 selection = input( "Please select the subject ID field from the list above: " @@ -242,7 +242,6 @@ def main(): # Wait for user input selection = input( "Please select the subject ID field from the list above: \t" - % option ) id_field = df.columns[int(selection) - 1] # make sure id_field is a string for zero-padded subject ids @@ -269,7 +268,7 @@ def main(): # qres = rdf_graph.query(query) for _, row in qres.iterrows(): - logging.info("participant in NIDM file %s \t %s" % (row[0], row[1])) + logging.info("participant in NIDM file %s \t %s", row[0], row[1]) # find row in CSV file with subject id matching agent from NIDM file # csv_row = df.loc[df[id_field]==type(df[id_field][0])(row[1])] @@ -390,7 +389,7 @@ def main(): if id_field is None: option = 1 for column in df.columns: - print("%d: %s" % (option, column)) + print(f"{option}: {column}") option = option + 1 selection = input( "Please select the subject ID field from the list above: " @@ -400,7 +399,6 @@ def main(): # Wait for user input selection = input( "Please select the subject ID field from the list above: \t" - % option ) id_field = df.columns[int(selection) - 1] # make sure id_field is a string for zero-padded subject ids diff --git a/src/nidm/experiment/tools/nidm2bids.py b/src/nidm/experiment/tools/nidm2bids.py index 0e19fa0..aa4774b 100644 --- a/src/nidm/experiment/tools/nidm2bids.py +++ b/src/nidm/experiment/tools/nidm2bids.py @@ -41,7 +41,6 @@ from os import mkdir, system from os.path import basename, isdir, isfile, join, splitext from shutil import copyfile -import sys import tempfile import urllib.parse import datalad.api as dl @@ -69,7 +68,7 @@ def GetImageFromAWS(location, output_file, args): :return: None if file not downloaded else will return True """ - print("Trying AWS S3 for dataset: %s" % location) + print(f"Trying AWS S3 for dataset: {location}") # modify location to remove everything before the dataset name # problem is we don't know the dataset identifier inside the path string because # it doesn't have any constraints. For openneuro datasets they start with "ds" so @@ -154,7 +153,7 @@ def GetImageFromURL(url): temp.flush() return temp.name except Exception: - print("ERROR! Can't open url: %s" % url) + print(f"ERROR! Can't open url: {url}") return -1 @@ -165,22 +164,19 @@ def GetDataElementMetadata(nidm_graph, de_uuid): """ # query nidm_graph for Constants.NIIRI[de_uuid] rdf:type PersonalDataElement - query = ( - """ + query = f""" PREFIX rdf: PREFIX prov: PREFIX niiri: PREFIX nidm: select distinct ?p ?o - where { + where {{ - <%s> rdf:type nidm:PersonalDataElement ; + <{Constants.NIIRI[de_uuid]}> rdf:type nidm:PersonalDataElement ; ?p ?o . - } + }} """ - % Constants.NIIRI[de_uuid] - ) # print(query) qres = nidm_graph.query(query) @@ -220,21 +216,18 @@ def GetDataElementMetadata(nidm_graph, de_uuid): # if this is a list we have to loop through the entries and store the url and labels for entry in value: # query for label for this isAbout URL - query = ( - """ + query = f""" prefix prov: prefix rdfs: prefix rdf: select distinct ?label - where { - <%s> rdf:type prov:Entity ; + where {{ + <{entry}> rdf:type prov:Entity ; rdfs:label ?label . - } + }} """ - % entry - ) # print(query) qres = nidm_graph.query(query) @@ -245,21 +238,18 @@ def GetDataElementMetadata(nidm_graph, de_uuid): else: # only 1 isAbout entry # query for label for this isAbout URL - query = ( - """ + query = f""" prefix prov: prefix rdfs: prefix rdf: select distinct ?label - where { - <%s> rdf:type prov:Entity ; + where {{ + <{value}> rdf:type prov:Entity ; rdfs:label ?label . - } + }} """ - % value - ) # print(query) qres = nidm_graph.query(query) for row in qres: @@ -348,7 +338,7 @@ def CreateBIDSParticipantFile(nidm_graph, output_file, participant_fields): # # Steps(1):(3) - query = """ + query = f""" PREFIX rdf: PREFIX prov: PREFIX onli: @@ -356,20 +346,17 @@ def CreateBIDSParticipantFile(nidm_graph, output_file, participant_fields): PREFIX niiri: SELECT DISTINCT ?pred ?value - WHERE { + WHERE {{ ?asses_activity prov:qualifiedAssociation ?_blank . ?_blank rdf:type prov:Association ; - prov:agent <%s> ; + prov:agent <{subj_uri}> ; prov:hadRole sio:Subject . ?entities prov:wasGeneratedBy ?asses_activity ; rdf:type onli:assessment-instrument ; ?pred ?value . - FILTER (regex(str(?pred) ,"%s","i" )) - }""" % ( - subj_uri, - fields, - ) + FILTER (regex(str(?pred) ,"{fields}","i" )) + }}""" # print(query) qres = nidm_graph.query(query) @@ -431,8 +418,8 @@ def NIDMProject2BIDSDatasetDescriptor(nidm_graph, output_directory): # iterate over the temporary dictionary and delete items from the original for proj_key, _ in project_metadata_tmp.items(): key_found = 0 - # print("proj_key = %s " % proj_key) - # print("project_metadata[proj_key] = %s" %project_metadata[proj_key]) + # print(f"proj_key = {proj_key} ") + # print(f"project_metadata[proj_key] = {project_metadata[proj_key]}") for key, _ in BIDS_Constants.dataset_description.items(): if BIDS_Constants.dataset_description[key]._uri == proj_key: @@ -464,15 +451,12 @@ def AddMetadataToImageSidecar(graph_entity, graph, output_directory, image_filen """ # query graph for metadata associated with graph_entity - query = ( - """ + query = f""" Select DISTINCT ?p ?o - WHERE { - <%s> ?p ?o . - } + WHERE {{ + <{graph_entity}> ?p ?o . + }} """ - % graph_entity - ) qres = graph.query(query) # dictionary to store metadata @@ -560,12 +544,11 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): ret = GetImageFromURL(location) if ret == -1: print( - "ERROR! Can't download file: %s from url: %s, trying to copy locally...." - % (filename, location) + f"ERROR! Can't download file: {filename} from url: {location}, trying to copy locally...." ) if "file" in location: location = str(location).lstrip("file:") - print("Trying to copy file from %s" % (location)) + print(f"Trying to copy file from {location}") try: copyfile( location, @@ -579,23 +562,20 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): except Exception: print( - "ERROR! Failed to find file %s on filesystem..." - % location + f"ERROR! Failed to find file {location} on filesystem..." ) if not args.no_downloads: try: print( - "Running datalad get command on dataset: %s" - % location + f"Running datalad get command on dataset: {location}" ) dl.Dataset(os.path.dirname(location)).get( recursive=True, jobs=1 ) - except Exception: + except Exception as e: print( - "ERROR! Datalad returned error: %s for dataset %s." - % (sys.exc_info()[0], location) + f"ERROR! Datalad returned error: {type(e)} for dataset {location}." ) GetImageFromAWS( location=location, @@ -635,19 +615,16 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): # if this is a DWI scan then we should copy over the b-value and b-vector files if bids_ext == "dwi": # search for entity uuid with rdf:type nidm:b-value that was generated by activity - query = ( - """ + query = f""" PREFIX rdf: PREFIX prov: PREFIX nidm: SELECT DISTINCT ?entity - WHERE { + WHERE {{ ?entity rdf:type ; - prov:wasGeneratedBy <%s> . - }""" - % activity - ) + prov:wasGeneratedBy <{activity}> . + }}""" # print(query) qres = graph.query(query) @@ -663,12 +640,11 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): ret = GetImageFromURL(location) if ret == -1: print( - "ERROR! Can't download file: %s from url: %s, trying to copy locally...." - % (filename, location) + f"ERROR! Can't download file: {filename} from url: {location}, trying to copy locally...." ) if "file" in location: location = str(location).lstrip("file:") - print("Trying to copy file from %s" % (location)) + print(f"Trying to copy file from {location}") try: copyfile( location, @@ -681,23 +657,20 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): ) except Exception: print( - "ERROR! Failed to find file %s on filesystem..." - % location + f"ERROR! Failed to find file {location} on filesystem..." ) if not args.no_downloads: try: print( - "Running datalad get command on dataset: %s" - % location + f"Running datalad get command on dataset: {location}" ) dl.Dataset(os.path.dirname(location)).get( recursive=True, jobs=1 ) - except Exception: + except Exception as e: print( - "ERROR! Datalad returned error: %s for dataset %s." - % (sys.exc_info()[0], location) + f"ERROR! Datalad returned error: {type(e)} for dataset {location}." ) GetImageFromAWS( location=location, @@ -710,19 +683,16 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): args=args, ) # search for entity uuid with rdf:type nidm:b-value that was generated by activity - query = ( - """ + query = f""" PREFIX rdf: PREFIX prov: PREFIX nidm: SELECT DISTINCT ?entity - WHERE { + WHERE {{ ?entity rdf:type ; - prov:wasGeneratedBy <%s> . - }""" - % activity - ) + prov:wasGeneratedBy <{activity}> . + }}""" # print(query) qres = graph.query(query) @@ -738,12 +708,11 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): ret = GetImageFromURL(location) if ret == -1: print( - "ERROR! Can't download file: %s from url: %s, trying to copy locally...." - % (filename, location) + f"ERROR! Can't download file: {filename} from url: {location}, trying to copy locally...." ) if "file" in location: location = str(location).lstrip("file:") - print("Trying to copy file from %s" % (location)) + print(f"Trying to copy file from {location}") try: copyfile( location, @@ -756,23 +725,20 @@ def ProcessFiles(graph, scan_type, output_directory, project_location, args): ) except Exception: print( - "ERROR! Failed to find file %s on filesystem..." - % location + f"ERROR! Failed to find file {location} on filesystem..." ) if not args.no_downloads: try: print( - "Running datalad get command on dataset: %s" - % location + f"Running datalad get command on dataset: {location}" ) dl.Dataset(os.path.dirname(location)).get( recursive=True, jobs=1 ) - except Exception: + except Exception as e: print( - "ERROR! Datalad returned error: %s for dataset %s." - % (sys.exc_info()[0], location) + f"ERROR! Datalad returned error: {type(e)} for dataset {location}." ) GetImageFromAWS( location=location, @@ -897,7 +863,7 @@ def main(): format_found = False for fmt in "turtle", "xml", "n3", "trix", "rdfa": try: - print("Reading RDF file as %s..." % fmt) + print(f"Reading RDF file as {fmt}...") # load NIDM graph into NIDM-Exp API objects nidm_project = read_nidm(rdf_file) # temporary save nidm_project @@ -907,7 +873,7 @@ def main(): format_found = True break except Exception: - print("File: %s appears to be an invalid %s RDF file" % (rdf_file, fmt)) + print(f"File: {rdf_file} appears to be an invalid {fmt} RDF file") if not format_found: print( diff --git a/src/nidm/experiment/tools/nidm_affinity_propagation.py b/src/nidm/experiment/tools/nidm_affinity_propagation.py index f10bcc5..c3a8020 100644 --- a/src/nidm/experiment/tools/nidm_affinity_propagation.py +++ b/src/nidm/experiment/tools/nidm_affinity_propagation.py @@ -366,7 +366,7 @@ def ap(): labels = af.labels_ n_clusters_ = len(cluster_center_indices) - print("Estimated number of clusters: %d" % n_clusters_) + print(f"Estimated number of clusters: {n_clusters_}") # print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels)) # print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels)) # print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels)) diff --git a/src/nidm/experiment/tools/nidm_linreg.py b/src/nidm/experiment/tools/nidm_linreg.py index 064b107..1af6d6f 100644 --- a/src/nidm/experiment/tools/nidm_linreg.py +++ b/src/nidm/experiment/tools/nidm_linreg.py @@ -650,7 +650,7 @@ def contrasting(): # Defining the Simple class def _name_levels(prefix, levels): - return ["[%s%s]" % (prefix, level) for level in levels] + return [f"[{prefix}{level}]" for level in levels] class Simple(object): def _simple_contrast(self, levels): @@ -789,10 +789,9 @@ def regularizing(): lassoModelChosen.fit(X, y) print("\nLasso regression model:") print( - "Alpha with maximum likelihood (range: 1 to %d) = %f" - % (MAX_ALPHA, max_cross_val_alpha) + f"Alpha with maximum likelihood (range: 1 to {MAX_ALPHA}) = {max_cross_val_alpha}" ) - print("Current Model Score = %f" % (lassoModelChosen.score(X, y))) + print(f"Current Model Score = {lassoModelChosen.score(X, y)}") index = 0 print("\nCoefficients:") if o is not None: @@ -800,21 +799,20 @@ def regularizing(): with open(o, "a") as f: f.write("\n\nLasso regression model:") f.write( - "\nAlpha with maximum likelihood (range: 1 to %d) = %f" - % (MAX_ALPHA, max_cross_val_alpha) + f"\nAlpha with maximum likelihood (range: 1 to {MAX_ALPHA}) = {max_cross_val_alpha}" ) - f.write("\nCurrent Model Score = %f" % (lassoModelChosen.score(X, y))) + f.write(f"\nCurrent Model Score = {lassoModelChosen.score(X, y)}") f.write("\n\nCoefficients:") for var in full_model_variable_list: - print("%s \t %f" % (var, lassoModelChosen.coef_[index])) + print(f"{var} \t {lassoModelChosen.coef_[index]}") if o is not None: with open(o, "a") as f: - f.write("\n%s \t %f" % (var, lassoModelChosen.coef_[index])) + f.write(f"\n{var} \t {lassoModelChosen.coef_[index]}") index = index + 1 - print("Intercept: %f" % (lassoModelChosen.intercept_)) + print(f"Intercept: {lassoModelChosen.intercept_}") if o is not None: with open(o, "a") as f: - f.write("\nIntercept: %f" % (lassoModelChosen.intercept_)) + f.write(f"\nIntercept: {lassoModelChosen.intercept_}") print() if r == ("L2" or "Ridge" or "l2" or "Ridge") and not ( @@ -840,10 +838,9 @@ def regularizing(): ridgeModelChosen.fit(X, y) print("\nRidge regression model:") print( - "Alpha with maximum likelihood (range: 1 to %d) = %f" - % (MAX_ALPHA, max_cross_val_alpha) + f"Alpha with maximum likelihood (range: 1 to {MAX_ALPHA}) = {max_cross_val_alpha}" ) - print("Current Model Score = %f" % (ridgeModelChosen.score(X, y))) + print(f"Current Model Score = {ridgeModelChosen.score(X, y)}") index = 0 """This numpy_conversion part was necessary because for the ridge model, all the coefficients get stored in a numpy array, and the conversion is necessary to get the coefficients. However, it is only needed if the model @@ -857,37 +854,36 @@ def regularizing(): with open(o, "a") as f: f.write("\n\nRidge regression model:") f.write( - "\nAlpha with maximum likelihood (range: 1 to %d) = %f" - % (MAX_ALPHA, max_cross_val_alpha) + f"\nAlpha with maximum likelihood (range: 1 to {MAX_ALPHA}) = {max_cross_val_alpha}" ) - f.write("\nCurrent Model Score = %f" % (ridgeModelChosen.score(X, y))) + f.write(f"\nCurrent Model Score = {ridgeModelChosen.score(X, y)}") f.write("\n\nCoefficients:") print("\nCoefficients:") if numpy_conversion: coeff_list = ridgeModelChosen.coef_[index].tolist() coeff_list.pop(0) for var in full_model_variable_list: - print("%s \t %f" % (var, coeff_list[index])) + print(f"{var} \t {coeff_list[index]}") if o is not None: with open(o, "a") as f: - f.write("\n%s \t %f" % (var, coeff_list[index])) + f.write(f"\n{var} \t {coeff_list[index]}") index = index + 1 - print("Intercept: %f" % (ridgeModelChosen.intercept_)) + print(f"Intercept: {ridgeModelChosen.intercept_}") if o is not None: with open(o, "a") as f: - f.write("\nIntercept: %f" % (ridgeModelChosen.intercept_)) + f.write(f"\nIntercept: {ridgeModelChosen.intercept_}") print() else: for var in full_model_variable_list: - print("%s \t %f" % (var, ridgeModelChosen.coef_[index])) + print(f"{var} \t {ridgeModelChosen.coef_[index]}") if o is not None: with open(o, "a") as f: - f.write("\n%s \t %f" % (var, ridgeModelChosen.coef_[index])) + f.write(f"\n{var} \t {ridgeModelChosen.coef_[index]}") index = index + 1 - print("Intercept: %f" % (ridgeModelChosen.intercept_)) + print(f"Intercept: {ridgeModelChosen.intercept_}") if o is not None: with open(o, "a") as f: - f.write("\nIntercept: %f" % (ridgeModelChosen.intercept_)) + f.write(f"\nIntercept: {ridgeModelChosen.intercept_}") print() diff --git a/src/nidm/experiment/tools/nidm_merge.py b/src/nidm/experiment/tools/nidm_merge.py index 3b0bd7f..9e78940 100644 --- a/src/nidm/experiment/tools/nidm_merge.py +++ b/src/nidm/experiment/tools/nidm_merge.py @@ -86,8 +86,7 @@ def merge(nidm_file_list, s, out_file): # for each UUID / subject ID look in graph and see if you can find the same ID. If so get the UUID of # that prov:agent and change all the UUIDs in nidm_file to match then concatenate the two graphs. - query = ( - """ + query = f""" PREFIX prov: PREFIX sio: @@ -96,14 +95,12 @@ def merge(nidm_file_list, s, out_file): PREFIX prov: SELECT DISTINCT ?uuid ?ID - WHERE { + WHERE {{ ?uuid a prov:Agent ; - %s ?ID . + {Constants.NIDM_SUBJECTID} ?ID . FILTER(?ID = """ - % Constants.NIDM_SUBJECTID - ) # add filters to above query to only look for subject IDs which are in the first file to merge into temp = True @@ -135,15 +132,15 @@ def merge(nidm_file_list, s, out_file): for s, p, o in graph.triples((None, None, None)): if s == row["uuid"]: - # print("replacing subject in triple %s %s %s with %s" %(s,p,o,uuid_to_replace)) + # print(f"replacing subject in triple {s} {p} {o} with {uuid_to_replace}") graph.add((uuid_replacement, p, o)) graph.remove((row["uuid"], p, o)) elif o == row["uuid"]: - # print("replacing object in triple %s %s %s with %s" %(s,p,o,uuid_to_replace)) + # print(f"replacing object in triple {s} {p} {o} with {uuid_to_replace}") graph.add((s, p, uuid_replacement)) graph.remove((s, p, row["uuid"])) elif p == row["uuid"]: - # print("replacing predicate in triple %s %s %s with %s" %(s,p,o,uuid_to_replace)) + # print(f"replacing predicate in triple {s} {p} {o} with {uuid_to_replace}") graph.add((s, uuid_replacement, o)) graph.remove((s, row["uuid"], o)) diff --git a/src/nidm/experiment/tools/nidm_query.py b/src/nidm/experiment/tools/nidm_query.py index 00921e4..358dffe 100644 --- a/src/nidm/experiment/tools/nidm_query.py +++ b/src/nidm/experiment/tools/nidm_query.py @@ -167,7 +167,7 @@ def query( if blaze: os.environ["BLAZEGRAPH_URL"] = blaze - print("setting BLAZEGRAPH_URL to {}".format(blaze)) + print(f"setting BLAZEGRAPH_URL to {blaze}") if get_participants: df = GetParticipantIDs(nidm_file_list.split(","), output_file=output_file) diff --git a/src/nidm/experiment/tools/nidm_version.py b/src/nidm/experiment/tools/nidm_version.py index fbfd3f9..99d1830 100644 --- a/src/nidm/experiment/tools/nidm_version.py +++ b/src/nidm/experiment/tools/nidm_version.py @@ -8,7 +8,7 @@ def version(): """ This function will print the version of pynidm. """ - print("PyNIDM Version: %s" % __version__) + print(f"PyNIDM Version: {__version__}") if __name__ == "__main__": diff --git a/src/nidm/experiment/tools/repronim_simple2_brainvolumes.py b/src/nidm/experiment/tools/repronim_simple2_brainvolumes.py index aab74a1..5348696 100644 --- a/src/nidm/experiment/tools/repronim_simple2_brainvolumes.py +++ b/src/nidm/experiment/tools/repronim_simple2_brainvolumes.py @@ -289,7 +289,7 @@ def add_brainvolume_data( qres = rdf_graph_parse.query(query) for row in qres: - print("%s \t %s" % (row[2], row[1])) + print(f"{row[2]} \t {row[1]}") # find row in CSV file with subject id matching agent from NIDM file # csv_row = df.loc[df[id_field]==type(df[id_field][0])(row[1])] @@ -304,7 +304,7 @@ def add_brainvolume_data( # if there was data about this subject in the NIDM file already (i.e. an agent already exists with this subject id) # then add this brain volumes data to NIDM file, else skip it.... if not (len(csv_row.index) == 0): - print("found other data for participant %s" % row[1]) + print(f"found other data for participant {row[1]}") # Here we're sure we have an agent in the NIDM graph that corresponds to the participant in the # brain volumes data. We don't know which AcquisitionObject (entity) describes the T1-weighted scans @@ -325,7 +325,7 @@ def add_brainvolume_data( if row_variable == id_field: # store participant id for later use in processing the data for this row participant_id = row_data.values[0] - print("participant id: %s" % participant_id) + print(f"participant id: {participant_id}") continue else: # get source software matching this column deal with duplicate variables in source_row and pandas changing duplicate names @@ -691,7 +691,7 @@ def main(): # qres = rdf_graph_parse.query(query) # for row in qres: - # print('%s \t %s' %(row[0],row[1])) + # print(f'{row[0]} \t {row[1]}') # #find row in CSV file with subject id matching agent from NIDM file # #csv_row = df.loc[df[id_field]==type(df[id_field][0])(row[1])] diff --git a/src/nidm/experiment/tools/rest.py b/src/nidm/experiment/tools/rest.py index cec4aba..9627bd3 100644 --- a/src/nidm/experiment/tools/rest.py +++ b/src/nidm/experiment/tools/rest.py @@ -34,11 +34,11 @@ class RestParser: def __init__(self, verbosity_level=0, output_format=0): self.verbosity_level = verbosity_level self.output_format = output_format - self.restLog("Setting output format {}".format(self.output_format), 4) + self.restLog(f"Setting output format {self.output_format}", 4) def setOutputFormat(self, output_format): self.output_format = output_format - self.restLog("Setting output format {}".format(self.output_format), 4) + self.restLog(f"Setting output format {self.output_format}", 4) ##################### # Standard formatters @@ -191,7 +191,7 @@ def projectSummaryFormat(self, result): ] field_table = tabulate(fh_rows, fh_header) # added by DBK, if they asked for fields then just give them the fields - return "{}".format(field_table) + return str(field_table) else: field_table = "" @@ -222,9 +222,7 @@ def projectSummaryFormat(self, result): return self.format(result) def formatDerivatives(self, derivative): - self.restLog( - "formatting derivatives in format {}".format(self.output_format), 5 - ) + self.restLog(f"formatting derivatives in format {self.output_format}", 5) if self.output_format == self.CLI_FORMAT: table = [] for uri in derivative: @@ -335,7 +333,7 @@ def subjectSummaryFormat(self, result): ) derivatives = self.formatDerivatives(result["derivatives"]) - return "{}\n\n{}\n\n{}".format(tabulate(toptable), derivatives, instruments) + return f"{tabulate(toptable)}\n\n{derivatives}\n\n{instruments}" else: return self.format(result) @@ -365,7 +363,7 @@ def subjectSummaryFormat_v2(self, result): instruments = self.activityDataTableFormat(result["instruments"]) derivatives = self.activityDataTableFormat(result["derivatives"]) - return "{}\n\n{}\n\n{}".format(tabulate(toptable), derivatives, instruments) + return f"{tabulate(toptable)}\n\n{derivatives}\n\n{instruments}" else: return self.format(result) @@ -413,7 +411,7 @@ def projects(self): if "fields" in self.query and len(self.query["fields"]) > 0: subjects_set = set() dataelements_set = set() - self.restLog("Using fields {}".format(self.query["fields"]), 2) + self.restLog(f"Using fields {self.query['fields']}", 2) # result['field_values'] = [] for proj in projects: @@ -533,7 +531,7 @@ def projectStats(self): match = re.match(r"^/?statistics/projects/([^/]+)\??$", path) id_ = parse.unquote(str(match.group(1))) - self.restLog("Returning project {} stats metadata".format(id_), 2) + self.restLog(f"Returning project {id_} stats metadata", 2) meta_data = Query.GetProjectsMetadata(self.nidm_files) self.ExpandProjectMetaData(meta_data) @@ -639,7 +637,7 @@ def addFieldStats(self, result, project, subjects, field, type): # noqa: A002 def projectSummary(self): match = re.match(r"^/?projects/([^/]+)$", self.command) pid = parse.unquote(str(match.group(1))) - self.restLog("Returning project {} summary".format(pid), 2) + self.restLog(f"Returning project {pid} summary", 2) result = nidm.experiment.Navigate.GetProjectAttributes( self.nidm_files, project_id=pid @@ -654,7 +652,7 @@ def projectSummary(self): # if we got fields, drill into each subject and pull out the field data # subject details -> derivatives / instrument -> values -> element if "fields" in self.query and len(self.query["fields"]) > 0: - self.restLog("Using fields {}".format(self.query["fields"]), 2) + self.restLog(f"Using fields {self.query['fields']}", 2) result["field_values"] = [] # get all the synonyms for all the fields field_synonyms = functools.reduce( @@ -687,9 +685,7 @@ def subjectsList(self): match = re.match(r"^/?projects/([^/]+)/subjects/?$", self.command) project = match.group((1)) self.restLog( - "Returning all agents matching filter '{}' for project {}".format( - self.query["filter"], project - ), + f"Returning all agents matching filter '{self.query['filter']}' for project {project}", 2, ) # result = Query.GetParticipantUUIDsForProject(self.nidm_files, project, self.query['filter'], None) @@ -712,7 +708,7 @@ def subjectsList(self): def projectSubjectSummary(self): match = re.match(r"^/?projects/([^/]+)/subjects/([^/]+)/?$", self.command) subject = Navigate.normalizeSingleSubjectToUUID(self.nidm_files, match.group(2)) - self.restLog("Returning info about subject {}".format(match.group(2)), 2) + self.restLog(f"Returning info about subject {match[2]}", 2) return self.subjectSummaryFormat( Query.GetParticipantDetails(self.nidm_files, match.group(1), subject) ) @@ -782,7 +778,7 @@ def subjects(self): def subjectSummary(self): match = re.match(r"^/?subjects/([^/]+)/?$", self.command) - self.restLog("Returning info about subject {}".format(match.group(1)), 2) + self.restLog(f"Returning info about subject {match[1]}", 2) sid = match.group(1) # if we were passed in a sub_id rather than a UUID, lookup the associated UUID. (we might get multiple!) @@ -816,7 +812,7 @@ def instrumentsList(self): match = re.match( r"^/?projects/([^/]+)/subjects/([^/]+)/instruments/?$", self.command ) - self.restLog("Returning instruments in subject {}".format(match.group(2)), 2) + self.restLog(f"Returning instruments in subject {match[2]}", 2) subject = Navigate.normalizeSingleSubjectToUUID(self.nidm_files, match.group(2)) instruments = Query.GetParticipantInstrumentData( self.nidm_files, match.group(1), subject @@ -830,9 +826,7 @@ def instrumentSummary(self): r"^/?projects/([^/]+)/subjects/([^/]+)/instruments/([^/]+)$", self.command ) self.restLog( - "Returning instrument {} in subject {}".format( - match.group(3), match.group(2) - ), + f"Returning instrument {match[3]} in subject {match[2]}", 2, ) subject = Navigate.normalizeSingleSubjectToUUID(self.nidm_files, match.group(2)) @@ -844,7 +838,7 @@ def instrumentSummary(self): def derivativesList(self): result = [] match = re.match(r"^/?projects/([^/]+)/subjects/([^/]+)", self.command) - self.restLog("Returning derivatives in subject {}".format(match.group(2)), 2) + self.restLog(f"Returning derivatives in subject {match[2]}", 2) subject = Navigate.normalizeSingleSubjectToUUID(self.nidm_files, match.group(2)) derivatives = Query.GetDerivativesDataForSubject( self.nidm_files, match.group(1), subject @@ -859,7 +853,7 @@ def derivativeSummary(self): ) subject = Navigate.normalizeSingleSubjectToUUID(self.nidm_files, match.group(2)) uri = match.group(3) - self.restLog("Returning stat {} in subject {}".format(uri, match.group(2)), 2) + self.restLog(f"Returning stat {uri} in subject {match[2]}", 2) derivatives = Query.GetDerivativesDataForSubject( self.nidm_files, match.group(1), subject ) @@ -874,9 +868,7 @@ def run(self, nidm_files, command): try: self.restLog("parsing command " + command, 1) self.restLog("Files to read:" + str(nidm_files), 1) - self.restLog( - "Using {} as the graph cache directory".format(gettempdir()), 1 - ) + self.restLog(f"Using {gettempdir()} as the graph cache directory", 1) self.nidm_files = tuple(nidm_files) # replace # marks with %23 - they are sometimes used in the is_about terms @@ -898,7 +890,7 @@ def run(self, nidm_files, command): return self.route() except ValueError as ve: - logging.error("Exception: {}".format(ve)) + logging.error("Exception: %s", ve) return self.format( {"error": "One of the supplied field terms was not found."} ) diff --git a/tests/experiment/read_nidm.py b/tests/experiment/read_nidm.py index 756e602..c69b656 100644 --- a/tests/experiment/read_nidm.py +++ b/tests/experiment/read_nidm.py @@ -13,29 +13,29 @@ def main(): project = read_nidm(args.nidm_file) - print("Project: \n %s" % project.get_uuid()) + print(f"Project: \n {project.get_uuid()}") sessions = project.get_sessions() - print("Sessions:\n %s" % sessions) + print(f"Sessions:\n {sessions}") acquisitions = [] for session in sessions: acquisitions = session.get_acquisitions() - print("Acquisitions:\n %s" % acquisitions) + print(f"Acquisitions:\n {acquisitions}") for acq in acquisitions: acquisition_objects = acq.get_acquisition_objects() - print("Acquisition Objects:\n %s" % acquisition_objects) + print(f"Acquisition Objects:\n {acquisition_objects}") # check for data elements - print("Data Elements: \n %s" % project.get_dataelements()) + print(f"Data Elements: \n {project.get_dataelements()}") # derivatives # and for derivatives - print("Derivatives: \n %s" % project.get_derivatives()) + print(f"Derivatives: \n {project.get_derivatives()}") for deriv in project.get_derivatives(): derivobj = deriv.get_derivative_objects() - print("Derivative Objects: \n %s" % derivobj) + print(f"Derivative Objects: \n {derivobj}") with open(args.outfile, "w") as f: # serialize project for comparison with the original diff --git a/tests/experiment/termsearch.py b/tests/experiment/termsearch.py index c8b3759..0b5fe78 100644 --- a/tests/experiment/termsearch.py +++ b/tests/experiment/termsearch.py @@ -38,7 +38,7 @@ def main(): # for items in term['_source']['existing_ids']: # if items['preferred']=='1': # preferred_url=items['iri'] - # print("Label = %s \t Definition = %s \t Preferred URL = %s " %(term['_source']['label'],term['_source']['definition'],preferred_url)) + # print(f"Label = {term['_source']['label']} \t Definition = {term['_source']['definition']} \t Preferred URL = {preferred_url} ") # example of uber elastic search query returns dictionary of label, definition, and preferred_url print("\n\n-------------------------------------------") @@ -46,12 +46,7 @@ def main(): results = Utils.GetNIDMTermsFromSciCrunch(args.key, args.query_string) for key, _ in results.items(): print( - "Label: %s \t Definition: %s \t Preferred URL: %s " - % ( - results[key]["label"], - results[key]["definition"], - results[key]["preferred_url"], - ) + f"Label: {results[key]['label']} \t Definition: {results[key]['definition']} \t Preferred URL: {results[key]['preferred_url']} " ) diff --git a/tests/experiment/test_query.py b/tests/experiment/test_query.py index 9c9d111..4899f53 100644 --- a/tests/experiment/test_query.py +++ b/tests/experiment/test_query.py @@ -203,7 +203,7 @@ def saveProject(file_name, project): # save a turtle file with open(file_name, "w") as f: f.write(project.serializeTurtle()) - return "nidm:_123_{}".format(file_name) + return f"nidm:_123_{file_name}" def makeProjectTestFile(filename): diff --git a/tests/experiment/tools/test_rest.py b/tests/experiment/tools/test_rest.py index 1c82f67..aae13fd 100644 --- a/tests/experiment/tools/test_rest.py +++ b/tests/experiment/tools/test_rest.py @@ -396,7 +396,7 @@ def test_CheckSubjectMatchesFilter(brain_vol: BrainVol) -> None: break # find an actual stat and build a matching filter to make sure our matcher passes it - filter_str = "derivatives.{} eq {}".format(dt, val) + filter_str = f"derivatives.{dt} eq {val}" assert Query.CheckSubjectMatchesFilter( brain_vol.files, project, subject, filter_str ) diff --git a/tests/experiment/tools/test_rest_dataelements.py b/tests/experiment/tools/test_rest_dataelements.py index 3142de2..a53a0c0 100644 --- a/tests/experiment/tools/test_rest_dataelements.py +++ b/tests/experiment/tools/test_rest_dataelements.py @@ -85,7 +85,7 @@ def test_dataelement_details(openneuro_files: list[str]) -> None: rest_parser = RestParser(output_format=RestParser.OBJECT_FORMAT) # result = rest_parser.run(openneuro_files, '/dataelements') # - # dti = rest_parser.run(openneuro_files, '/dataelements/{}'.format(result["data_elements"]["label"][0])) + # dti = rest_parser.run(openneuro_files, f'/dataelements/{result["data_elements"]["label"][0]}') # # assert "label" in dti # assert "description" in dti @@ -94,7 +94,7 @@ def test_dataelement_details(openneuro_files: list[str]) -> None: # # # make sure the text formatter doesn't fail horribly # rest_parser.setOutputFormat(RestParser.CLI_FORMAT) - # txt = rest_parser.run(openneuro_files, '/dataelements/{}'.format(result["data_elements"]["label"][0])) + # txt = rest_parser.run(openneuro_files, f'/dataelements/{result["data_elements"]["label"][0]}') # dti = rest_parser.run( @@ -106,7 +106,7 @@ def test_dataelement_details(openneuro_files: list[str]) -> None: def test_dataelement_details_in_projects_field(brain_vol_files: list[str]) -> None: rest_parser = RestParser(output_format=RestParser.OBJECT_FORMAT) # result = rest_parser.run(openneuro_files, '/dataelements') - # dti = rest_parser.run(openneuro_files, '/dataelements/{}'.format(result["data_elements"]["label"][0])) + # dti = rest_parser.run(openneuro_files, f'/dataelements/{result["data_elements"]["label"][0]}') # assert len(dti['inProjects']) >= 1 # find a data element that we are using for at least one subject