def buildhhear(ctx):
setl_graph = Graph()
setl_graph.parse('hhear-ontology.setl.ttl', format="turtle")
cwd = os.getcwd()
formats = ['ttl', 'owl', 'json']
ontology_output_files = [
setl_graph.resource(URIRef('file://' + cwd + '/hhear.' + x))
for x in formats
]
print(len(setl_graph))
for filename in os.listdir(HHEAR_DIR):
if not filename.endswith('.ttl') or filename.startswith('#'):
continue
print('Adding fragment', filename)
fragment = setl_graph.resource(BNode())
for ontology_output_file in ontology_output_files:
print(ontology_output_file.identifier,
list(ontology_output_file[prov.wasGeneratedBy]))
ontology_output_file.value(prov.wasGeneratedBy).add(
prov.used, fragment)
fragment.add(RDF.type, setlr.void.Dataset)
fragment_extract = setl_graph.resource(BNode())
fragment.add(prov.wasGeneratedBy, fragment_extract)
fragment_extract.add(RDF.type, setl.Extract)
fragment_extract.add(prov.used,
URIRef('file://' + HHEAR_DIR + filename))
setlr._setl(setl_graph)
def build():
setl_graph = Graph()
setl_graph.load(SETL_FILE, format="turtle")
cwd = os.getcwd()
formats = ['ttl', 'owl', 'json']
ontology_output_files = [
setl_graph.resource(URIRef('file://' + cwd + '/hasco.' + x))
for x in formats
]
for filename in os.listdir(HASCO_DIR):
if not filename.endswith('.ttl'):
continue
print 'Adding fragment', filename
fragment = setl_graph.resource(BNode())
for ontology_output_file in ontology_output_files:
ontology_output_file.value(prov.wasGeneratedBy).add(
prov.used, fragment)
fragment.add(RDF.type, setlr.void.Dataset)
fragment_extract = setl_graph.resource(BNode())
fragment.add(prov.wasGeneratedBy, fragment_extract)
fragment_extract.add(RDF.type, setl.Extract)
fragment_extract.add(prov.used,
URIRef('file://' + HASCO_DIR + filename))
print setl_graph.serialize(format="turtle")
setlr._setl(setl_graph)
def process(self, i, o):
query_store = self.app.db.store
if hasattr(query_store, 'endpoint'):
query_store = database.create_query_store(self.app.db.store)
db_graph = rdflib.ConjunctiveGraph(store=query_store)
db_graph.NS = self.app.NS
setlr.actions[whyis.sparql] = db_graph
setlr.actions[whyis.NanopublicationManager] = self.app.nanopub_manager
setlr.actions[whyis.Nanopublication] = self.app.nanopub_manager.new
setl_graph = i.graph
# setlr.run_samples = True
resources = setlr._setl(setl_graph)
# retire old copies
old_np_map = {}
to_retire = []
for new_np, assertion, orig in self.app.db.query(
'''select distinct ?np ?assertion ?original_uri where {
?np np:hasAssertion ?assertion.
?assertion a np:Assertion;
prov:wasGeneratedBy/a ?setl;
prov:wasQuotedFrom ?original_uri.
}''',
initBindings=dict(setl=i.identifier),
initNs=dict(prov=prov, np=np)):
old_np_map[orig] = assertion
to_retire.append(new_np)
if len(to_retire) > 100:
self.app.nanopub_manager.retire(*to_retire)
to_retire = []
self.app.nanopub_manager.retire(*to_retire)
# print resources
for output_graph in setl_graph.subjects(prov.wasGeneratedBy,
i.identifier):
print(output_graph)
if setl_graph.resource(output_graph)[rdflib.RDF.type:whyis.
NanopublicationCollection]:
self.app.nanopub_manager.publish(resources[output_graph])
else:
out = resources[output_graph]
out_conjunctive = rdflib.ConjunctiveGraph(
store=out.store, identifier=output_graph)
to_publish = []
triples = 0
for new_np in self.app.nanopub_manager.prepare(
out_conjunctive):
self.explain(new_np, i, o)
to_publish.append(new_np)
# triples += len(new_np)
# if triples > 10000:
self.app.nanopub_manager.publish(*to_publish)
for resource, obj in list(resources.items()):
if hasattr(i, 'close'):
print("Closing", resource)
try:
i.close()
except:
pass
def convert_to_rdf(json_file):
setl_graph = rdflib.Graph()
setl_graph.parse(SETL_FILE,format="turtle")
cwd = os.getcwd()
extract = setl_graph.value(rdflib.URIRef('http://purl.org/twc/codegraph/setl/codegraph_json'), prov.wasGeneratedBy)
setl_graph.add((extract, prov.used,rdflib.URIRef('file://'+os.path.join(cwd,json_file))))
results = setlr._setl(setl_graph)
single_g = results[rdflib.URIRef('http://purl.org/twc/codegraph/setl/codegraph')]
print("analyzed " + json_file)
return single_g
def process(self, i, o):
setl_graph = i.graph
resources = setlr._setl(setl_graph)
# retire old copies
old_np_map = {}
for new_np, assertion, orig in self.app.db.query(
'''select distinct ?np ?assertion ?original_uri where {
?np np:hasAssertion ?assertion.
?assertion a np:Assertion;
prov:wasGeneratedBy/a ?setl;
prov:wasQuotedFrom ?original_uri.
}''',
initBindings=dict(setl=i.identifier),
initNs=dict(prov=prov, np=np)):
old_np_map[orig] = assertion
self.app.nanopub_manager.retire(new_np)
#print resources
for output_graph in setl_graph.subjects(prov.wasGeneratedBy,
i.identifier):
out = resources[output_graph]
out_conjunctive = rdflib.ConjunctiveGraph(store=out.store,
identifier=output_graph)
#print "Generated graph", out.identifier, len(out), len(out_conjunctive)
mappings = {}
for new_np in self.app.nanopub_manager.prepare(out_conjunctive,
mappings=mappings):
self.explain(new_np, i, o)
print "Publishing", new_np.identifier
orig = [
orig for orig, new in mappings.items()
if new == new_np.assertion.identifier
]
if len(orig) == 0:
continue
orig = orig[0]
print orig
if isinstance(orig, rdflib.URIRef):
new_np.pubinfo.add((new_np.assertion.identifier,
prov.wasQuotedFrom, orig))
if orig in old_np_map:
new_np.pubinfo.add(
(new_np.assertion.identifier, prov.wasRevisionOf,
old_np_map[orig]))
print "Nanopub assertion has", len(
new_np.assertion), "statements."
self.app.nanopub_manager.publish(new_np)
print 'Published'
def convert_xml(debug=None):
setl_graph = Graph()
setl_graph.load(SETL_FILE, format="turtle")
cwd = os.getcwd()
if debug:
files = [debug]
else:
files = os.listdir(XML_DIR)[:PROCESS_FILE_COUNT]
for filename in files:
try:
print 'Processing', filename
local_setl_graph = Graph()
local_setl_graph += setl_graph
input_file_resource = local_setl_graph.resource(
URIRef('http://nanomine.tw.rpi.edu/setl/xml/nanomine_xml'))
input_file_resource.value(prov.wasGeneratedBy).set(
prov.used, URIRef('file://' + XML_DIR + filename))
output_file_resource = local_setl_graph.resource(
URIRef(OUTPUT_DIR + filename.replace('.xml', '.trig')))
output_file_resource.set(prov.used,
URIRef('file://' + OUTPUT_DIR + filename))
output_file_resource.set(dc['format'], Literal('trig'))
output_file_resource.set(RDF.type, pv.File)
generated_by = local_setl_graph.resource(BNode())
output_file_resource.set(prov.wasGeneratedBy, generated_by)
generated_by.set(RDF.type, setl.Load)
generated_by.set(
prov.used,
URIRef('http://nanomine.tw.rpi.edu/setl/xml/nanopubs'))
resources = setlr._setl(local_setl_graph)
for identifier, graph in resources.items():
if hasattr(graph, 'close'):
print "Closing", identifier
graph.close()
except Exception as e:
print e
def process(self, i, o):
query_store = database.create_query_store(self.app.db.store)
db_graph = rdflib.ConjunctiveGraph(store=query_store)
db_graph.NS = self.app.NS
setlr.actions[whyis.sparql] = db_graph
setl_graph = i.graph
#setlr.run_samples = True
resources = setlr._setl(setl_graph)
# retire old copies
old_np_map = {}
for new_np, assertion, orig in self.app.db.query(
'''select distinct ?np ?assertion ?original_uri where {
?np np:hasAssertion ?assertion.
?assertion a np:Assertion;
prov:wasGeneratedBy/a ?setl;
prov:wasQuotedFrom ?original_uri.
}''',
initBindings=dict(setl=i.identifier),
initNs=dict(prov=prov, np=np)):
old_np_map[orig] = assertion
self.app.nanopub_manager.retire(new_np)
#print resources
for output_graph in setl_graph.subjects(prov.wasGeneratedBy,
i.identifier):
out = resources[output_graph]
out_conjunctive = rdflib.ConjunctiveGraph(store=out.store,
identifier=output_graph)
#print "Generated graph", out.identifier, len(out), len(out_conjunctive)
nanopub_prepare_graph = rdflib.ConjunctiveGraph(store="Sleepycat")
nanopub_prepare_graph_tempdir = tempfile.mkdtemp()
nanopub_prepare_graph.store.open(nanopub_prepare_graph_tempdir,
True)
mappings = {}
to_publish = []
triples = 0
for new_np in self.app.nanopub_manager.prepare(
out_conjunctive,
mappings=mappings,
store=nanopub_prepare_graph.store):
self.explain(new_np, i, o)
orig = [
orig for orig, new in mappings.items()
if new == new_np.assertion.identifier
]
if len(orig) == 0:
continue
orig = orig[0]
print orig
if isinstance(orig, rdflib.URIRef):
new_np.pubinfo.add((new_np.assertion.identifier,
prov.wasQuotedFrom, orig))
if orig in old_np_map:
new_np.pubinfo.add(
(new_np.assertion.identifier, prov.wasRevisionOf,
old_np_map[orig]))
print "Publishing %s with %s assertions." % (
new_np.identifier, len(new_np.assertion))
to_publish.append(new_np)
#triples += len(new_np)
#if triples > 10000:
self.app.nanopub_manager.publish(*to_publish)
print 'Published'
def sdd2owl(c, inputfile, ontology, outputfile, infosheet="InfoSheet"):
import openpyxl
import re
import pandas as pd
import json
cwd = os.getcwd()
setl_graph = Graph()
setl_graph.parse('sdd_owl_semantics.setl.ttl', format="turtle")
sddns = rdflib.Namespace('http://purl.org/twc/sdd/setl/')
tab_config = {
"Data_Dictionary": sddns.dm_table,
"Codebook": sddns.codebook_table,
"Code_Mappings": sddns.codemapping_table,
"Timeline": sddns.timeline_table
}
wb = openpyxl.load_workbook(inputfile)
infosheet_tab = wb[infosheet]
infosheet_dict = dict([(row[0].value, row[1].value)
for row in infosheet_tab])
infosheet_resource = setl_graph.resource(sddns.info_sheet)
infosheet_resource.add(rdflib.RDF.type, setl.Excel)
infosheet_resource.add(setl.sheetname, rdflib.Literal(infosheet))
gen = infosheet_resource.value(prov.wasGeneratedBy)
gen.add(prov.used, URIRef('file://' + os.path.join(cwd, inputfile)))
for entry, uri in tab_config.items():
res = setl_graph.resource(uri)
sheet = infosheet_dict[entry]
gen = res.value(prov.wasGeneratedBy)
if sheet.startswith('#'):
res.add(rdflib.RDF.type, setl.Excel)
res.add(setl.sheetname, rdflib.Literal(sheet[1:]))
gen.add(prov.used,
URIRef('file://' + os.path.join(cwd, inputfile)))
else:
res.add(rdflib.RDF.type, csvw.Table)
gen.add(prov.used, URIRef(sheet))
context = {
"@base": "http://purl.org/twc/ctxid/",
"sio": "http://semanticscience.org/resource/",
"chear": "http://hadatac.org/ont/chear#",
"skos": "http://www.w3.org/2004/02/skos/core#",
"prov": "http://www.w3.org/ns/prov#",
"dc": "http://purl.org/dc/terms/",
"cmo": "http://purl.obolibrary.org/obo/CMO_",
"doid": "http://purl.obolibrary.org/obo/DOID_",
"owl": "http://www.w3.org/2002/07/owl#",
"rdfs": "http://www.w3.org/2000/01/rdf-schema#",
"rdfs": "http://www.w3.org/2000/01/rdf-schema#",
"chebi": "http://purl.obolibrary.org/obo/CHEBI_",
"stato": "http://purl.obolibrary.org/obo/STATO_",
"obo": "http://purl.obolibrary.org/obo/",
"pubchem": "http://rdf.ncbi.nlm.nih.gov/pubchem/compound/",
"dc": "http://purl.org/dc/terms/",
"hasco": "http://hadatac.org/ont/hasco#",
"vstoi": "http://hadatac.org/ont/vstoi#",
"hasneto": "http://hadatac.org/ont/hasneto#",
"uberon": "http://purl.obolibrary.org/obo/UBERON_",
"prv": "http://hadatac.org/ont/prov#"
}
namespaces = load_namespaces()
context.update(namespaces)
setl_graph.add((sddns.metadata_transform, setl.hasContext,
Literal(json.dumps(context))))
setl_graph.add((sddns.namespaces, prov.value,
Literal("result = %s" % json.dumps(context))))
resources = setlr._setl(setl_graph)
ont = resources[sddns.metadata]
prefix = "http://purl.org/twc/ctxid/"
mappings = {}
for cls, identifier in ont.query('''select ?cls ?identifier where {
?cls a owl:Class; dc:identifier ?identifier.
}''',
initNs={
"owl": rdflib.OWL,
"dc": dc
}):
if prefix in str(cls):
id = cls.replace(prefix, '')
integer_id = int(id, 16)
ont.add((cls, skos.notation, rdflib.Literal(integer_id)))
column, code = identifier.split('||||')
print("Mapping (%s, %s) => %s" % (column, code, cls))
mappings[(column, code)] = "ctxid:" + id
with open(ontology, 'wb') as o:
ont.serialize(o, format="turtle")
codebook = wb[infosheet_dict['Codebook'][1:]]
header = None
code_col = None
class_col = None
column_col = None
for row in codebook.rows:
if header is None:
header = row
for cell in header:
if cell.value == "Code":
code_col = cell.column - 1
if cell.value == "Class":
class_col = cell.column - 1
if cell.value == "Column":
column_col = cell.column - 1
print('Found Column Headers: Code==%s Class==%s Column=%s' %
(code_col, class_col, column_col))
continue
if (row[column_col].value == None): continue
column = str(row[column_col].value)
code = str(row[code_col].value)
if (column, code) in mappings:
print("%s.%s = %s" % (column, code, mappings[(column, code)]))
row[class_col].value = mappings[(column, code)]
wb.save(outputfile)
