def primer_example_alternate():
g = ProvDocument(namespaces={
'ex': 'http://example/',
'dcterms': 'http://purl.org/dc/terms/',
'foaf': 'http://xmlns.com/foaf/0.1/'
})
article = g.entity('ex:article', {'dcterms:title': "Crime rises in cities"})
articleV1 = g.entity('ex:articleV1')
articleV2 = g.entity('ex:articleV2')
dataSet1 = g.entity('ex:dataSet1')
dataSet2 = g.entity('ex:dataSet2')
regionList = g.entity('ex:regionList')
composition = g.entity('ex:composition')
chart1 = g.entity('ex:chart1')
chart2 = g.entity('ex:chart2')
blogEntry = g.entity('ex:blogEntry')
compile = g.activity('ex:compile')
compile2 = g.activity('ex:compile2')
compose = g.activity('ex:compose')
correct = g.activity('ex:correct', '2012-03-31T09:21:00', '2012-04-01T15:21:00')
illustrate = g.activity('ex:illustrate')
compose.used(dataSet1, attributes={'prov:role': "ex:dataToCompose"})
compose.used(regionList, attributes={'prov:role': "ex:regionsToAggregateBy"})
composition.wasGeneratedBy(compose)
illustrate.used(composition)
chart1.wasGeneratedBy(illustrate)
chart1.wasGeneratedBy(compile, '2012-03-02T10:30:00')
derek = g.agent('ex:derek', {
'prov:type': PROV['Person'], 'foaf:givenName': "Derek", 'foaf:mbox': "<mailto:[email protected]>"
})
compose.wasAssociatedWith(derek)
illustrate.wasAssociatedWith(derek)
chartgen = g.agent('ex:chartgen', {
'prov:type': PROV["Organization"], 'foaf:name': "Chart Generators Inc"
})
derek.actedOnBehalfOf(chartgen, compose)
chart1.wasAttributedTo(derek)
dataSet2.wasGeneratedBy(correct)
correct.used(dataSet1)
dataSet2.wasDerivedFrom(dataSet1, attributes={'prov:type': PROV['Revision']})
chart2.wasDerivedFrom(dataSet2)
blogEntry.wasDerivedFrom(article, attributes={'prov:type': PROV['Quotation']})
articleV1.specializationOf(article)
articleV1.wasDerivedFrom(dataSet1)
articleV2.specializationOf(article)
articleV2.wasDerivedFrom(dataSet2)
articleV2.alternateOf(articleV1)
return g
def add_parents(graph: ProvDocument, package: CommitModelPackage) -> ProvDocument:
"""Add link between commit activities and their parents."""
commit = package.commit
for parent in package.parent_commits:
graph.activity(*parent)
graph.activity(*commit)
graph.wasInformedBy(commit.id, parent.id)
return graph
def add_commit(graph: ProvDocument, package: CommitModelPackage) -> ProvDocument:
"""Add commit activity, agents for author and committer, relations between agents and activity."""
author, committer, commit = package.author, package.committer, package.commit
graph.agent(*author)
graph.agent(*committer)
graph.activity(*commit)
graph.wasAssociatedWith(commit.id, author.id)
graph.wasAssociatedWith(commit.id, committer.id)
return graph
def create_document():
# Create a new provenance document
document = ProvDocument() # d1 is now an empty provenance document
# Before asserting provenance statements, we need to have a way to refer to the "things"
# we want to describe provenance (e.g. articles, data sets, people). For that purpose,
# PROV uses qualified names to identify things, which essentially a shortened representation
# of a URI in the form of prefix:localpart. Valid qualified names require their prefixes defined,
# which we is going to do next.
# Declaring namespaces for various prefixes used in the example
document.add_namespace('now', 'http://www.provbook.org/nownews/')
document.add_namespace('nowpeople',
'http://www.provbook.org/nownews/people/')
document.add_namespace('bk', 'http://www.provbook.org/ns/#')
# Entity: now:employment-article-v1.html
e1 = document.entity('now:employment-article-v1.html')
e1.add_attributes({'prov:value': 'Conteudo do HTML'})
document.agent('nowpeople:Filipe')
# Attributing the article to the agent
document.wasAttributedTo(
e1, 'nowpeople:Filipe_' + str(random.randint(1000, 1070000000)))
# add more namespace declarations
document.add_namespace('govftp',
'ftp://ftp.bls.gov/pub/special.requests/oes/')
document.add_namespace('void', 'http://vocab.deri.ie/void#')
# 'now:employment-article-v1.html' was derived from at dataset at govftp
document.entity('govftp:oesm11st.zip', {
'prov:label': 'employment-stats-2011',
'prov:type': 'void:Dataset'
})
document.wasDerivedFrom('now:employment-article-v1.html',
'govftp:oesm11st.zip')
# Adding an activity
document.add_namespace('is', 'http://www.provbook.org/nownews/is/#')
document.activity('is:writeArticle')
# Usage and Generation
document.used('is:writeArticle', 'govftp:oesm11st.zip')
document.wasGeneratedBy('now:employment-article-v1.html',
'is:writeArticle')
#print("Document prepared.")
# What we have so far (in PROV-N)
logging.debug(document.serialize(indent=2))
# d1.serialize('article-prov.json') # write to file
return document
def add_resource_creation(graph: ProvDocument, package: ResourceModelPackage) -> ProvDocument:
"""Add model for resource creation."""
creator, creation, resource, resource_version = package.creation
graph.activity(*creation)
graph.entity(*resource)
graph.entity(*resource_version)
graph.agent(*creator)
graph.wasAssociatedWith(creation.id, creator.id)
graph.wasAttributedTo(resource.id, creator.id)
graph.wasAttributedTo(resource_version.id, creator.id)
graph.wasGeneratedBy(resource.id, creation.id)
graph.wasGeneratedBy(resource_version.id, creation.id)
graph.specializationOf(resource_version.id, resource.id)
return graph
def get_esmvaltool_provenance():
"""Create an esmvaltool run activity."""
provenance = ProvDocument()
namespace = 'software'
create_namespace(provenance, namespace)
attributes = {} # TODO: add dependencies with versions here
activity = provenance.activity(namespace + ':esmvaltool==' + __version__,
other_attributes=attributes)
return activity
def _create_trial_info(document: provo.ProvDocument, trial: Trial, suffix=""):
invalid_identifiers = ["."]
identifier = trial.script
for char in invalid_identifiers:
identifier = identifier.replace(char, "_")
document.agent("{}{}".format(identifier, suffix),
[(provo.PROV_TYPE, provo.PROV["SoftwareAgent"]),
("codeHash", trial.code_hash),
("script", trial.script),
("id", trial.id)])
document.activity("trial{}Execution".format(trial.id), trial.start, trial.finish,
[("nowCommand", trial.command),
("parentId", trial.parent_id),
("inheritedId", trial.inherited_id)])
document.wasAssociatedWith("trial{}Execution".format(trial.id), "{}{}".format(identifier, suffix), None,
"trial{}ExecutionByScript".format(trial.id))
def job2prov(job):
"""
Create ProvDocument based on job description
:param job: UWS job
:return: ProvDocument
"""
# job.jdl.content = {
# 'description': description,
# 'parameters': parameters,
# 'results': results,
# 'executionduration': execdur,
# 'quote': quote
# }
# parameters[pname] = {
# 'type': p.get('type'),
# 'required': p.get('required'),
# 'default': p.get('default'),
# 'description': list(p)[0].text,
# }
# results[r.get('value')] = {
# 'mediaType': r.get('mediaType'),
# 'default': r.get('default'),
# 'description': list(r)[0].text,
# }
pdoc = ProvDocument()
# Declaring namespaces for various prefixes used in the example
pdoc.add_namespace('prov', 'http://www.w3.org/ns/prov#')
pdoc.add_namespace('voprov', 'http://www.ivoa.net/ns/voprov#')
pdoc.add_namespace('cta', 'http://www.cta-observatory.org#')
pdoc.add_namespace('uwsdata', 'https://voparis-uws-test.obspm.fr/rest/' + job.jobname + '/' + job.jobid + '/')
pdoc.add_namespace('ctajobs', 'http://www.cta-observatory.org#')
# Adding an activity
ctbin = pdoc.activity('ctajobs:' + job.jobname, job.start_time, job.end_time)
# TODO: add job description, version, url, ...
# Agent
pdoc.agent('cta:consortium', other_attributes={'prov:type': "Organization"})
pdoc.wasAssociatedWith(ctbin, 'cta:consortium')
# Entities, in and out with relations
e_in = []
for pname, pdict in job.jdl.content['parameters'].iteritems():
#if pname.startswith('in'):
if any(x in pdict['type'] for x in ['file', 'xs:anyURI']):
e_in.append(pdoc.entity('uwsdata:parameters/' + pname))
# TODO: use publisher_did? add prov attributes, add voprov attributes?
ctbin.used(e_in[-1])
e_out = []
for rname, rdict in job.jdl.content['results'].iteritems():
e_out.append(pdoc.entity('uwsdata:results/' + rname))
# TODO: use publisher_did? add prov attributes, add voprov attributes?
e_out[-1].wasGeneratedBy(ctbin)
for e in e_in:
e_out[-1].wasDerivedFrom(e)
return pdoc
def gen_prov_graph(file_path, option):
'''
generates prov graph from form json file
option = "all": add attribues to nodes
'''
form_file = open(file_path, "r")
json_info = form_file.read()
form_file.close()
sf_dict = json.loads(json_info)
d1 = ProvDocument()
d1.add_namespace('subm',
'http://www.enes.org/enes_entity/data_submsission')
global_in_out = d1.entity("subm:" + "form_name_xx")
print("workflow definition: ", sf_dict['workflow'])
for [act_name, act] in sf_dict['workflow']:
print("adding entities for workflow_step: ", act_name)
entity_in_dict = sf_dict[act_name]['entity_in']
entity_out_dict = sf_dict[act_name]['entity_out']
agent_dict = sf_dict[act_name]['agent']
activity_dict = sf_dict[act_name]['activity']
# generate nodes
in_node = d1.entity("subm:" + entity_in_dict['i_name'])
out_node = d1.entity("subm:" + entity_out_dict['i_name'])
agent = d1.agent("subm:" + agent_dict['i_name'])
activity = d1.activity("subm:" + activity_dict['i_name'])
#clean up and prefix dictionaries
entity_in_dict = prefix_dict(entity_in_dict, 'subm')
entity_out_dict = prefix_dict(entity_out_dict, 'subm')
agent_dict = prefix_dict(agent_dict, 'subm')
activity_dict = prefix_dict(activity_dict, 'subm')
if option == "all":
in_node.add_attributes(entity_in_dict)
out_node.add_attributes(entity_out_dict)
agent.add_attributes(agent_dict)
activity.add_attributes(activity_dict)
# connect nodes in graph
d1.wasGeneratedBy(out_node, activity)
d1.used(activity, in_node)
d1.wasAssociatedWith(activity, agent)
d1.wasDerivedFrom(in_node, out_node)
d1.used(activity, global_in_out)
d1.wasGeneratedBy(global_in_out, activity)
return d1
def ctfToProv():
d1 = ProvDocument()
dummy = ProvDocument()
ex = Namespace('ex', 'http://example/') # namespaces do not need to be explicitly added to a document
#data = event_field(os.path.join(trace_path,'../config.yaml'))
counter = 0
counter_1 = 0
relationships = []
entities = []
activities = []
producer_events = {}
for event in trace_collection.events:
dataset = {'ex:'+k:event[k] for k in event.field_list_with_scope(
babeltrace.CTFScope.EVENT_FIELDS)}
dataset.update({'ex:'+'timestamp':(event['timestamp']/1000000000)})
#dataset.update({'ex:'+'name':event.name})
e1 = d1.entity(ex['event'+str(counter)],dataset)
entities.append(e1)
producer_agent = d1.agent('ex:'+event['producer_id'])
if event['producer_id'] not in producer_events:
producer_events[event['producer_id']] = []
else:
pel = producer_events[events['producer_id']]
d1.wasAssociatedWith(pel[len(pel)-1], e1)
pel.append(e1)
controller_agent = d1.agent('ex:'+event['controller_id'])
activity = d1.activity('ex:'+event['activity']+str(counter_1))
activities.append(activity)
d1.wasGeneratedBy(e1, activity)
# strings used to detect if the relationship already exists in the d1 document
association_relationship = str(dummy.wasAssociatedWith(activity, producer_agent))
used_relationship = str(dummy.used(controller_agent, producer_agent))
# Add activity to producer agent if it has not been added before.
d1.wasAssociatedWith(activity, producer_agent)
# if association_relationship not in relationships:
# d1.wasAssociatedWith(activity, producer_agent)
# relationships.append(association_relationship)
# Add producer agent to controller agent if it has not been added yet.
if used_relationship not in relationships:
d1.used(controller_agent, producer_agent)
relationships.append(used_relationship)
# Add temporal relationship between this event and the previous one.
# if counter > 0:
# d1.wasAssociatedWith(entities[counter - 1], e1)
counter+=1
counter_1 +=1
return d1
def ctfToProv():
d1 = ProvDocument()
dummy = ProvDocument()
ex = Namespace(
'ex', 'http://example/'
) # namespaces do not need to be explicitly added to a document
#data = event_field(os.path.join(trace_path,'../config.yaml'))
counter = 0
counter_1 = 0
relationships = []
entities = []
activities = []
for event in trace_collection.events:
dataset = {
'ex:' + k: event[k]
for k in event.field_list_with_scope(
babeltrace.CTFScope.EVENT_FIELDS)
}
dataset.update(
{'ex:' + 'timestamp': (event['timestamp'] / 1000000000)})
#dataset.update({'ex:'+'name':event.name})
e1 = d1.entity(ex['event' + str(counter)], dataset)
entities.append(e1)
producer_agent = d1.agent('ex:' + event['producer_id'])
controller_agent = d1.agent('ex:' + event['controller_id'])
activity = d1.activity('ex:' + event['activity'] + str(counter_1))
activities.append(activity)
d1.wasGeneratedBy(e1, activity)
# strings used to detect if the relationship already exists in the d1 document
association_relationship = str(
dummy.wasAssociatedWith(activity, producer_agent))
used_relationship = str(dummy.used(controller_agent, producer_agent))
# Add activity to producer agent if it has not been added before.
d1.wasAssociatedWith(activity, producer_agent)
# if association_relationship not in relationships:
# d1.wasAssociatedWith(activity, producer_agent)
# relationships.append(association_relationship)
# Add producer agent to controller agent if it has not been added yet.
if used_relationship not in relationships:
d1.used(controller_agent, producer_agent)
relationships.append(used_relationship)
# Add temporal relationship between this event and the previous one.
if counter > 0:
d1.wasAssociatedWith(entities[counter - 1], e1)
counter += 1
counter_1 += 1
return d1
def add_event_chain(graph: ProvDocument, package: ResourceModelPackage) -> ProvDocument:
"""Add chain of events beginning at the creation event."""
previous_event = previous_resource_version = None
for chain_link in package.event_chain:
user, event, resource, resource_version = chain_link
graph.entity(*resource)
graph.entity(*resource_version)
graph.activity(*event)
graph.agent(*user)
graph.wasAssociatedWith(event.id, user.id)
graph.wasAttributedTo(resource_version.id, user.id)
graph.specializationOf(resource_version.id, resource.id)
if previous_event is not None and previous_resource_version is not None:
graph.entity(*previous_resource_version)
graph.activity(*previous_event)
graph.wasGeneratedBy(resource_version.id, event.id)
graph.used(event.id, previous_resource_version.id)
graph.wasDerivedFrom(resource_version.id, previous_resource_version.id)
graph.wasInformedBy(event.id, previous_event.id)
previous_event = event
previous_resource_version = resource_version
return graph
def get_task_provenance(task, recipe_entity):
"""Create a provenance activity describing a task."""
provenance = ProvDocument()
create_namespace(provenance, 'task')
activity = provenance.activity('task:' + task.name)
trigger = recipe_entity
update_without_duplicating(provenance, recipe_entity.bundle)
starter = ESMVALTOOL_PROVENANCE
update_without_duplicating(provenance, starter.bundle)
activity.wasStartedBy(trigger, starter)
return activity
def transform_to_prov(context_model):
from prov.model import ProvDocument
from prov.dot import prov_to_dot
doc = ProvDocument()
doc.add_namespace('is', 'http://www.provbook.org/nownews/is/#')
doc.add_namespace('void', 'http://vocab.deri.ie/void#')
doc.add_namespace('nowpeople', 'http://www.provbook.org/nownews/people/')
input_data = doc.entity("void:Inputdata")
backend_agent = doc.agent("nowpeople:EODC")
user_agent = doc.agent("nowpeople:OpenEO-User")
doc.wasAttributedTo(input_data, backend_agent)
process_details = context_model["process_details"]
prev_key = input_data
for key in process_details:
key_entity = doc.entity("void:" + key + "_output")
key_activity = doc.activity('is:' + key)
doc.used(key_activity, prev_key)
doc.wasDerivedFrom(key_entity, prev_key)
doc.wasGeneratedBy(key_entity,
key_activity,
time=process_details[key]["timing"]["end"])
doc.wasStartedBy(key_activity,
user_agent,
time=process_details[key]["timing"]["start"])
prev_key = key_entity
dot = prov_to_dot(doc)
dot.write_png('output-prov.png')
return doc
def release_tag_model(graph: ProvDocument, packages: ReleaseTagPackage):
for package in packages:
if package.release_package is not None:
r_user, release, release_event, release_evidence, assets = package.release_package
graph.agent(*r_user)
graph.entity(*release)
graph.activity(*release_event)
graph.entity(*release_evidence)
for asset in assets:
graph.entity(*asset)
graph.hadMember(asset.id, release.id)
graph.hadMember(release_evidence.id, release.id)
graph.wasGeneratedBy(release.id, release_event.id)
graph.wasAttributedTo(release.id, r_user.id)
graph.wasAssociatedWith(release_event.id, r_user.id)
if package.tag_package is not None:
t_user, tag, tag_event = package.tag_package
graph.agent(*t_user)
graph.entity(*tag)
graph.activity(*tag_event)
if package.release_package is not None:
graph.hadMember(tag.id, release.id)
graph.wasGeneratedBy(tag.id, tag_event.id)
graph.wasAttributedTo(tag.id, t_user.id)
graph.wasAssociatedWith(tag_event.id, t_user.id)
if package.commit_package is not None:
author, commit_event, _, commit, _ = package.commit_package
graph.agent(*author)
graph.activity(*commit_event)
graph.entity(*commit)
if package.tag_package is not None:
graph.hadMember(commit.id, tag.id)
graph.wasGeneratedBy(commit.id, commit_event.id)
graph.wasAttributedTo(commit.id, author.id)
graph.wasAssociatedWith(commit_event.id, author.id)
return graph
def document_2(self):
d2 = ProvDocument()
ns_ex = d2.add_namespace('ex', EX2_URI)
d2.activity(ns_ex['a1'])
return d2
def primer_example():
# https://github.com/lucmoreau/ProvToolbox/blob/master/prov-n/src/test/resources/prov/primer.pn
#===========================================================================
# document
g = ProvDocument()
# prefix ex <http://example/>
# prefix dcterms <http://purl.org/dc/terms/>
# prefix foaf <http://xmlns.com/foaf/0.1/>
ex = Namespace('ex', 'http://example/') # namespaces do not need to be explicitly added to a document
g.add_namespace("dcterms", "http://purl.org/dc/terms/")
g.add_namespace("foaf", "http://xmlns.com/foaf/0.1/")
# entity(ex:article, [dcterms:title="Crime rises in cities"])
# first time the ex namespace was used, it is added to the document automatically
g.entity(ex['article'], {'dcterms:title': "Crime rises in cities"})
# entity(ex:articleV1)
g.entity(ex['articleV1'])
# entity(ex:articleV2)
g.entity(ex['articleV2'])
# entity(ex:dataSet1)
g.entity(ex['dataSet1'])
# entity(ex:dataSet2)
g.entity(ex['dataSet2'])
# entity(ex:regionList)
g.entity(ex['regionList'])
# entity(ex:composition)
g.entity(ex['composition'])
# entity(ex:chart1)
g.entity(ex['chart1'])
# entity(ex:chart2)
g.entity(ex['chart2'])
# entity(ex:blogEntry)
g.entity(ex['blogEntry'])
# activity(ex:compile)
g.activity('ex:compile') # since ex is registered, it can be used like this
# activity(ex:compile2)
g.activity('ex:compile2')
# activity(ex:compose)
g.activity('ex:compose')
# activity(ex:correct, 2012-03-31T09:21:00, 2012-04-01T15:21:00)
g.activity('ex:correct', '2012-03-31T09:21:00', '2012-04-01T15:21:00') # date time can be provided as strings
# activity(ex:illustrate)
g.activity('ex:illustrate')
# used(ex:compose, ex:dataSet1, -, [ prov:role = "ex:dataToCompose"])
g.used('ex:compose', 'ex:dataSet1', other_attributes={'prov:role': "ex:dataToCompose"})
# used(ex:compose, ex:regionList, -, [ prov:role = "ex:regionsToAggregateBy"])
g.used('ex:compose', 'ex:regionList', other_attributes={'prov:role': "ex:regionsToAggregateBy"})
# wasGeneratedBy(ex:composition, ex:compose, -)
g.wasGeneratedBy('ex:composition', 'ex:compose')
# used(ex:illustrate, ex:composition, -)
g.used('ex:illustrate', 'ex:composition')
# wasGeneratedBy(ex:chart1, ex:illustrate, -)
g.wasGeneratedBy('ex:chart1', 'ex:illustrate')
# wasGeneratedBy(ex:chart1, ex:compile, 2012-03-02T10:30:00)
g.wasGeneratedBy('ex:chart1', 'ex:compile', '2012-03-02T10:30:00')
# wasGeneratedBy(ex:chart2, ex:compile2, 2012-04-01T15:21:00)
#
#
# agent(ex:derek, [ prov:type="prov:Person", foaf:givenName = "Derek",
# foaf:mbox= "<mailto:[email protected]>"])
g.agent('ex:derek', {
'prov:type': PROV["Person"], 'foaf:givenName': "Derek", 'foaf:mbox': "<mailto:[email protected]>"
})
# wasAssociatedWith(ex:compose, ex:derek, -)
g.wasAssociatedWith('ex:compose', 'ex:derek')
# wasAssociatedWith(ex:illustrate, ex:derek, -)
g.wasAssociatedWith('ex:illustrate', 'ex:derek')
#
# agent(ex:chartgen, [ prov:type="prov:Organization",
# foaf:name = "Chart Generators Inc"])
g.agent('ex:chartgen', {'prov:type': PROV["Organization"], 'foaf:name': "Chart Generators Inc"})
# actedOnBehalfOf(ex:derek, ex:chartgen, ex:compose)
g.actedOnBehalfOf('ex:derek', 'ex:chartgen', 'ex:compose')
# wasAttributedTo(ex:chart1, ex:derek)
g.wasAttributedTo('ex:chart1', 'ex:derek')
# wasGeneratedBy(ex:dataSet2, ex:correct, -)
g.wasGeneratedBy('ex:dataSet2', 'ex:correct')
# used(ex:correct, ex:dataSet1, -)
g.used('ex:correct', 'ex:dataSet1')
# wasDerivedFrom(ex:dataSet2, ex:dataSet1, [prov:type='prov:Revision'])
g.wasDerivedFrom('ex:dataSet2', 'ex:dataSet1', other_attributes={'prov:type': PROV['Revision']})
# wasDerivedFrom(ex:chart2, ex:dataSet2)
g.wasDerivedFrom('ex:chart2', 'ex:dataSet2')
# wasDerivedFrom(ex:blogEntry, ex:article, [prov:type='prov:Quotation'])
g.wasDerivedFrom('ex:blogEntry', 'ex:article', other_attributes={'prov:type': PROV['Quotation']})
# specializationOf(ex:articleV1, ex:article)
g.specializationOf('ex:articleV1', 'ex:article')
# wasDerivedFrom(ex:articleV1, ex:dataSet1)
g.wasDerivedFrom('ex:articleV1', 'ex:dataSet1')
# specializationOf(ex:articleV2, ex:article)
g.specializationOf('ex:articleV2', 'ex:article')
# wasDerivedFrom(ex:articleV2, ex:dataSet2)
g.wasDerivedFrom('ex:articleV2', 'ex:dataSet2')
# alternateOf(ex:articleV2, ex:articleV1)
g.alternateOf('ex:articleV2', 'ex:articleV1')
# endDocument
return g
def document_2(self):
d2 = ProvDocument()
ns_ex = d2.add_namespace('ex', EX2_URI)
d2.activity(ns_ex['a1'])
return d2
def w3c_publication_1():
# https://github.com/lucmoreau/ProvToolbox/blob/master/asn/src/test/resources/prov/w3c-publication1.prov-asn
#===========================================================================
# bundle
#
# prefix ex <http://example.org/>
#
# prefix w3 <http://www.w3.org/>
# prefix tr <http://www.w3.org/TR/2011/>
# prefix process <http://www.w3.org/2005/10/Process-20051014/tr.html#>
# prefix email <https://lists.w3.org/Archives/Member/w3c-archive/>
# prefix chairs <https://lists.w3.org/Archives/Member/chairs/>
# prefix trans <http://www.w3.org/2005/08/01-transitions.html#>
# prefix rec54 <http://www.w3.org/2001/02pd/rec54#>
#
#
# entity(tr:WD-prov-dm-20111018, [ prov:type='rec54:WD' ])
# entity(tr:WD-prov-dm-20111215, [ prov:type='rec54:WD' ])
# entity(process:rec-advance, [ prov:type='prov:Plan' ])
#
#
# entity(chairs:2011OctDec/0004, [ prov:type='trans:transreq' ])
# entity(email:2011Oct/0141, [ prov:type='trans:pubreq' ])
# entity(email:2011Dec/0111, [ prov:type='trans:pubreq' ])
#
#
# wasDerivedFrom(tr:WD-prov-dm-20111215, tr:WD-prov-dm-20111018)
#
#
# activity(ex:act1,-,-,[prov:type="publish"])
# activity(ex:act2,-,-,[prov:type="publish"])
#
# wasGeneratedBy(tr:WD-prov-dm-20111018, ex:act1, -)
# wasGeneratedBy(tr:WD-prov-dm-20111215, ex:act2, -)
#
# used(ex:act1, chairs:2011OctDec/0004, -)
# used(ex:act1, email:2011Oct/0141, -)
# used(ex:act2, email:2011Dec/0111, -)
#
# agent(w3:Consortium, [ prov:type='prov:Organization' ])
#
# wasAssociatedWith(ex:act1, w3:Consortium, process:rec-advance)
# wasAssociatedWith(ex:act2, w3:Consortium, process:rec-advance)
#
# endBundle
#===========================================================================
g = ProvDocument()
g.add_namespace('ex', 'http://example.org/')
g.add_namespace('w3', 'http://www.w3.org/')
g.add_namespace('tr', 'http://www.w3.org/TR/2011/')
g.add_namespace('process', 'http://www.w3.org/2005/10/Process-20051014/tr.html#')
g.add_namespace('email', 'https://lists.w3.org/Archives/Member/w3c-archive/')
g.add_namespace('chairs', 'https://lists.w3.org/Archives/Member/chairs/')
g.add_namespace('trans', 'http://www.w3.org/2005/08/01-transitions.html#')
g.add_namespace('rec54', 'http://www.w3.org/2001/02pd/rec54#')
g.entity('tr:WD-prov-dm-20111018', {'prov:type': 'rec54:WD'})
g.entity('tr:WD-prov-dm-20111215', {'prov:type': 'rec54:WD'})
g.entity('process:rec-advance', {'prov:type': 'prov:Plan'})
g.entity('chairs:2011OctDec/0004', {'prov:type': 'trans:transreq'})
g.entity('email:2011Oct/0141', {'prov:type': 'trans:pubreq'})
g.entity('email:2011Dec/0111', {'prov:type': 'trans:pubreq'})
g.wasDerivedFrom('tr:WD-prov-dm-20111215', 'tr:WD-prov-dm-20111018')
g.activity('ex:act1', other_attributes={'prov:type': "publish"})
g.activity('ex:act2', other_attributes={'prov:type': "publish"})
g.wasGeneratedBy('tr:WD-prov-dm-20111018', 'ex:act1')
g.wasGeneratedBy('tr:WD-prov-dm-20111215', 'ex:act2')
g.used('ex:act1', 'chairs:2011OctDec/0004')
g.used('ex:act1', 'email:2011Oct/0141')
g.used('ex:act2', 'email:2011Dec/0111')
g.agent('w3:Consortium', other_attributes={'prov:type': "Organization"})
g.wasAssociatedWith('ex:act1', 'w3:Consortium', 'process:rec-advance')
g.wasAssociatedWith('ex:act2', 'w3:Consortium', 'process:rec-advance')
return g
def w3c_publication_2():
# https://github.com/lucmoreau/ProvToolbox/blob/master/asn/src/test/resources/prov/w3c-publication2.prov-asn
#===========================================================================
# bundle
#
# prefix ex <http://example.org/>
# prefix rec <http://example.org/record>
#
# prefix w3 <http://www.w3.org/TR/2011/>
# prefix hg <http://dvcs.w3.org/hg/prov/raw-file/9628aaff6e20/model/releases/WD-prov-dm-20111215/>
#
#
# entity(hg:Overview.html, [ prov:type="file in hg" ])
# entity(w3:WD-prov-dm-20111215, [ prov:type="html4" ])
#
#
# activity(ex:rcp,-,-,[prov:type="copy directory"])
#
# wasGeneratedBy(rec:g; w3:WD-prov-dm-20111215, ex:rcp, -)
#
# entity(ex:req3, [ prov:type="http://www.w3.org/2005/08/01-transitions.html#pubreq" %% xsd:anyURI ])
#
# used(rec:u; ex:rcp,hg:Overview.html,-)
# used(ex:rcp, ex:req3, -)
#
#
# wasDerivedFrom(w3:WD-prov-dm-20111215, hg:Overview.html, ex:rcp, rec:g, rec:u)
#
# agent(ex:webmaster, [ prov:type='prov:Person' ])
#
# wasAssociatedWith(ex:rcp, ex:webmaster, -)
#
# endBundle
#===========================================================================
ex = Namespace('ex', 'http://example.org/')
rec = Namespace('rec', 'http://example.org/record')
w3 = Namespace('w3', 'http://www.w3.org/TR/2011/')
hg = Namespace('hg', 'http://dvcs.w3.org/hg/prov/raw-file/9628aaff6e20/model/releases/WD-prov-dm-20111215/')
g = ProvDocument()
g.entity(hg['Overview.html'], {'prov:type': "file in hg"})
g.entity(w3['WD-prov-dm-20111215'], {'prov:type': "html4"})
g.activity(ex['rcp'], None, None, {'prov:type': "copy directory"})
g.wasGeneratedBy('w3:WD-prov-dm-20111215', 'ex:rcp', identifier=rec['g'])
g.entity('ex:req3', {'prov:type': Identifier("http://www.w3.org/2005/08/01-transitions.html#pubreq")})
g.used('ex:rcp', 'hg:Overview.html', identifier='rec:u')
g.used('ex:rcp', 'ex:req3')
g.wasDerivedFrom('w3:WD-prov-dm-20111215', 'hg:Overview.html', 'ex:rcp', 'rec:g', 'rec:u')
g.agent('ex:webmaster', {'prov:type': "Person"})
g.wasAssociatedWith('ex:rcp', 'ex:webmaster')
return g
def primer_example_alternate():
g = ProvDocument(
namespaces={
"ex": "http://example/",
"dcterms": "http://purl.org/dc/terms/",
"foaf": "http://xmlns.com/foaf/0.1/",
})
article = g.entity("ex:article",
{"dcterms:title": "Crime rises in cities"})
articleV1 = g.entity("ex:articleV1")
articleV2 = g.entity("ex:articleV2")
dataSet1 = g.entity("ex:dataSet1")
dataSet2 = g.entity("ex:dataSet2")
regionList = g.entity("ex:regionList")
composition = g.entity("ex:composition")
chart1 = g.entity("ex:chart1")
chart2 = g.entity("ex:chart2")
blogEntry = g.entity("ex:blogEntry")
compile = g.activity("ex:compile")
compile2 = g.activity("ex:compile2")
compose = g.activity("ex:compose")
correct = g.activity("ex:correct", "2012-03-31T09:21:00",
"2012-04-01T15:21:00")
illustrate = g.activity("ex:illustrate")
compose.used(dataSet1, attributes={"prov:role": "ex:dataToCompose"})
compose.used(regionList,
attributes={"prov:role": "ex:regionsToAggregateBy"})
composition.wasGeneratedBy(compose)
illustrate.used(composition)
chart1.wasGeneratedBy(illustrate)
chart1.wasGeneratedBy(compile, "2012-03-02T10:30:00")
derek = g.agent(
"ex:derek",
{
"prov:type": PROV["Person"],
"foaf:givenName": "Derek",
"foaf:mbox": "<mailto:[email protected]>",
},
)
compose.wasAssociatedWith(derek)
illustrate.wasAssociatedWith(derek)
chartgen = g.agent(
"ex:chartgen",
{
"prov:type": PROV["Organization"],
"foaf:name": "Chart Generators Inc"
},
)
derek.actedOnBehalfOf(chartgen, compose)
chart1.wasAttributedTo(derek)
dataSet2.wasGeneratedBy(correct)
correct.used(dataSet1)
dataSet2.wasDerivedFrom(dataSet1,
attributes={"prov:type": PROV["Revision"]})
chart2.wasDerivedFrom(dataSet2)
blogEntry.wasDerivedFrom(article,
attributes={"prov:type": PROV["Quotation"]})
articleV1.specializationOf(article)
articleV1.wasDerivedFrom(dataSet1)
articleV2.specializationOf(article)
articleV2.wasDerivedFrom(dataSet2)
articleV2.alternateOf(articleV1)
return g
def get_provenance_history(uuid, normalized_provenance_dict):
prov_doc = ProvDocument()
# The 'prov' prefix is build-in namespace, no need to redefine here
prov_doc.add_namespace(HUBMAP_NAMESPACE, 'https://hubmapconsortium.org/')
# A bit validation
if 'relationships' not in normalized_provenance_dict:
raise LookupError(
f'Missing "relationships" key from the normalized_provenance_dict for Entity of uuid: {uuid}'
)
if 'nodes' not in normalized_provenance_dict:
raise LookupError(
f'Missing "nodes" key from the normalized_provenance_dict for Entity of uuid: {uuid}'
)
# Pack the nodes into a dictionary using the uuid as key
nodes_dict = {}
for node in normalized_provenance_dict['nodes']:
nodes_dict[node['uuid']] = node
# Loop through the relationships and build the provenance document
for rel_dict in normalized_provenance_dict['relationships']:
# (Activity) - [ACTIVITY_OUTPUT] -> (Entity)
if rel_dict['rel_data']['type'] == 'ACTIVITY_OUTPUT':
activity_uuid = rel_dict['fromNode']['uuid']
entity_uuid = rel_dict['toNode']['uuid']
# (Entity) - [ACTIVITY_INPUT] -> (Activity)
elif rel_dict['rel_data']['type'] == 'ACTIVITY_INPUT':
entity_uuid = rel_dict['fromNode']['uuid']
activity_uuid = rel_dict['toNode']['uuid']
activity_node = nodes_dict[activity_uuid]
entity_node = nodes_dict[entity_uuid]
activity_uri = None
entity_uri = None
# Skip Lab nodes for agent and organization
if entity_node['entity_type'] != 'Lab':
# Get the agent information from the entity node
agent_record = get_agent_record(entity_node)
# Use 'created_by_user_sub' as agent ID if presents
# Otherwise, fall back to use email by replacing @ and .
created_by_user_sub_prov_key = f'{HUBMAP_NAMESPACE}:userUUID'
created_by_user_email_prov_key = f'{HUBMAP_NAMESPACE}:userEmail'
if created_by_user_sub_prov_key in agent_record:
agent_id = agent_record[created_by_user_sub_prov_key]
elif created_by_user_email_prov_key in agent_record:
agent_id = str(
agent_record[created_by_user_email_prov_key]).replace(
'@', '-')
agent_id = str(agent_id).replace('.', '-')
else:
msg = f"Both 'created_by_user_sub' and 'created_by_user_email' are missing form entity of uuid: {entity_node['uuid']}"
logger.error(msg)
raise LookupError(msg)
# Build the agent uri
agent_uri = build_uri(HUBMAP_NAMESPACE, 'agent', agent_id)
# Only add the same agent once
# Multiple entities can be associated to the same agent
agent = prov_doc.get_record(agent_uri)
if len(agent) == 0:
doc_agent = prov_doc.agent(agent_uri, agent_record)
else:
doc_agent = agent[0]
# Organization
# Get the organization information from the entity node
org_record = get_organization_record(entity_node)
# Build the organization uri
group_uuid_prov_key = f'{HUBMAP_NAMESPACE}:groupUUID'
org_uri = build_uri(HUBMAP_NAMESPACE, 'organization',
org_record[group_uuid_prov_key])
# Only add the same organization once
# Multiple entities can be associated to different agents who are from the same organization
org = prov_doc.get_record(org_uri)
if len(org) == 0:
doc_org = prov_doc.agent(org_uri, org_record)
else:
doc_org = org[0]
# Build the activity uri
activity_uri = build_uri(HUBMAP_NAMESPACE, 'activities',
activity_node['uuid'])
# Register activity if not already registered
activity = prov_doc.get_record(activity_uri)
if len(activity) == 0:
# Shared attributes to be added to the PROV document
activity_attributes = {'prov:type': 'Activity'}
# Convert the timestampt integer to datetime string
# Note: in our case, prov:startTime is the same as prov:endTime
activity_time = timestamp_to_datetime(
activity_node['created_timestamp'])
# Add prefix to all other attributes
for key in activity_node:
prov_key = f'{HUBMAP_NAMESPACE}:{key}'
# Use datetime string instead of timestamp integer
if key == 'created_timestamp':
activity_attributes[prov_key] = activity_time
else:
activity_attributes[prov_key] = activity_node[key]
# Register activity
doc_activity = prov_doc.activity(activity_uri, activity_time,
activity_time,
activity_attributes)
# Relationship: the agent actedOnBehalfOf the org
prov_doc.actedOnBehalfOf(doc_agent, doc_org, doc_activity)
else:
doc_activity = activity[0]
# Build the entity uri
entity_uri = build_uri(HUBMAP_NAMESPACE, 'entities',
entity_node['uuid'])
# Register entity is not already registered
if len(prov_doc.get_record(entity_uri)) == 0:
# Shared attributes to be added to the PROV document
entity_attributes = {'prov:type': 'Entity'}
# Add prefix to all other attributes
for key in entity_node:
# Entity property values can be list or dict, skip
# And list and dict are unhashable types when calling `prov_doc.entity()`
if not isinstance(entity_node[key], (list, dict)):
prov_key = f'{HUBMAP_NAMESPACE}:{key}'
# Use datetime string instead of timestamp integer
if key in [
'created_timestamp', 'last_modified_timestamp',
'published_timestamp'
]:
entity_attributes[prov_key] = activity_time
else:
entity_attributes[prov_key] = entity_node[key]
# Register entity
prov_doc.entity(entity_uri, entity_attributes)
# Build activity uri and entity uri if not already built
# For the Lab nodes
if activity_uri is None:
activity_uri = build_uri(HUBMAP_NAMESPACE, 'activities',
activity_node['uuid'])
if entity_uri is None:
entity_uri = build_uri(HUBMAP_NAMESPACE, 'entities',
entity_node['uuid'])
# The following relationships apply to all node including Lab entity nodes
# (Activity) - [ACTIVITY_OUTPUT] -> (Entity)
if rel_dict['rel_data']['type'] == 'ACTIVITY_OUTPUT':
# Relationship: the entity wasGeneratedBy the activity
prov_doc.wasGeneratedBy(entity_uri, activity_uri)
# (Entity) - [ACTIVITY_INPUT] -> (Activity)
elif rel_dict['rel_data']['type'] == 'ACTIVITY_INPUT':
# Relationship: the activity used the entity
prov_doc.used(activity_uri, entity_uri)
# Format into json string based on the PROV-JSON Serialization
# https://www.w3.org/Submission/prov-json/
serialized_json = prov_doc.serialize()
return serialized_json
def document_2(self):
d2 = ProvDocument()
ns_ex = d2.add_namespace("ex", EX2_URI)
d2.activity(ns_ex["a1"])
return d2
class Context(object):
"""
Context is a singlton storing all
of the run specific data.
"""
def __init__(self):
# Warning;
# If new data is added with a site dimension the
# clip exposure function may need to be updated
# so the site data stays consistent.
# -------------- These variables are saved ----
# If new variables are added the save functions
# will need to be modified.
# Latitude and longitude values of the exposure data
# Has a site dimension
self.exposure_lat = None
self.exposure_long = None
# Data with a site dimension
# key - data name
# value - A numpy array. First dimension is site. (0 axis)
# Has a site dimension
self.exposure_att = None
# Data for aggregation across sites
self.exposure_agg = None
#
# -------------- The above variables are saved ----
# key - intensity measure
# value - One instance of RealisedVulnerabilityCurves. An att in this
# class has a site dimension.
self.exposure_vuln_curves = None
# A dictionary of the vulnerability sets.
# Not associated with exposures.
# key - vulnerability set ID
# value - vulnerability set instance
self.vulnerability_sets = {}
# A dictionary with keys being vulnerability_set_ids and
# value being the exposure attribute who's values are vulnerability
# function ID's.
self.vul_function_titles = {}
# A `prov.ProvDocument` to manage provenance information, including
# adding required namespaces
self.prov = ProvDocument()
self.prov.set_default_namespace("")
self.prov.add_namespace('prov', 'http://www.w3.org/ns/prov#')
self.prov.add_namespace('xsd', 'http://www.w3.org/2001/XMLSchema#')
self.prov.add_namespace('foaf', 'http://xmlns.com/foaf/0.1/')
self.prov.add_namespace('void', 'http://vocab.deri.ie/void#')
self.prov.add_namespace('dcterms', 'http://purl.org/dc/terms/')
commit, branch, dt = misc.get_git_commit()
# Create the fundamental software agent that is this code:
self.prov.agent(
":hazimp", {
"prov:type": "prov:SoftwareAgent",
"prov:Revision": commit,
"prov:branch": branch,
"prov:date": dt
})
self.prov.agent(f":{getpass.getuser()}", {"prov:type": "foaf:Person"})
self.prov.actedOnBehalfOf(":hazimp", f":{getpass.getuser()}")
self.provlabel = ''
def set_prov_label(self, label, title="HazImp analysis"):
"""
Set the qualified label for the provenance data
"""
self.provlabel = f":{label}"
self.prov.activity(f":{label}",
datetime.now().strftime(DATEFMT), None, {
"dcterms:title": title,
"prov:type": "void:Analysis"
})
self.prov.wasAttributedTo(self.provlabel, ":hazimp")
def get_site_shape(self):
"""
Get the numpy shape of sites the context is storing.
It is based on the shape of exposure_long.
:return: The numpy shape of sites the context is storing.
"""
if self.exposure_long is None:
shape = (0)
else:
shape = self.exposure_long.shape
return shape
def clip_exposure(self, min_long, min_lat, max_long, max_lat):
""" min_long, min_lat, max_long, max_lat
Clip the exposure data so only the exposure values within
the rectangle formed by max_lat, min_lat, max_long and
min_long are included.
Note: This must be called before the exposure_vuln_curves
are determined, since the curves have a site dimension.
"""
assert self.exposure_vuln_curves is None
bad_indexes = set()
bad_indexes = bad_indexes.union(
numpy.where(self.exposure_long < min_long)[0])
bad_indexes = bad_indexes.union(
numpy.where(self.exposure_long > max_long)[0])
bad_indexes = bad_indexes.union(
numpy.where(self.exposure_lat < min_lat)[0])
bad_indexes = bad_indexes.union(
numpy.where(self.exposure_lat > max_lat)[0])
good_indexes = numpy.array(list(
set(range(self.exposure_lat.size)).difference(bad_indexes)),
dtype=int)
if good_indexes.shape[0] == 0:
self.exposure_lat = numpy.array([])
self.exposure_long = numpy.array([])
else:
self.exposure_lat = self.exposure_lat[good_indexes]
self.exposure_long = self.exposure_long[good_indexes]
if isinstance(self.exposure_att, dict):
for key in self.exposure_att:
if good_indexes.shape[0] == 0:
exp_att = numpy.array([])
else:
exp_att = self.exposure_att[key][good_indexes]
self.exposure_att[key] = exp_att
else:
self.exposure_att = self.exposure_att.take(good_indexes)
def save_exposure_atts(self, filename, use_parallel=True):
"""
Save the exposure attributes, including latitude and longitude.
The file type saved is based on the filename extension.
Options
'.npz': Save the arrays into a single file in uncompressed .npz
format.
:param use_parallel: Set to True for parallel behaviour
Which is only node 0 writing to file.
:param filename: The file to be written.
:return write_dict: The whole dictionary, returned for testing.
"""
[filename, bucket_name, bucket_key] = \
misc.create_temp_file_path_for_s3(filename)
s1 = self.prov.entity(
":HazImp output file", {
"prov:label": "Full HazImp output file",
"prov:type": "void:Dataset",
"prov:atLocation": os.path.basename(filename)
})
a1 = self.prov.activity(":SaveImpactData",
datetime.now().strftime(DATEFMT), None)
self.prov.wasGeneratedBy(s1, a1)
self.prov.wasInformedBy(a1, self.provlabel)
write_dict = self.exposure_att.copy()
write_dict[EX_LAT] = self.exposure_lat
write_dict[EX_LONG] = self.exposure_long
if use_parallel:
assert misc.INTID in write_dict
write_dict = parallel.gather_dict(write_dict,
write_dict[misc.INTID])
if parallel.STATE.rank == 0 or not use_parallel:
if filename[-4:] == '.csv':
save_csv(write_dict, filename)
else:
numpy.savez(filename, **write_dict)
misc.upload_to_s3_if_applicable(filename, bucket_name, bucket_key)
# The write_dict is returned for testing
# When running in paralled this is a way of getting all
# of the context info
return write_dict
def save_exposure_aggregation(self, filename, use_parallel=True):
"""
Save the aggregated exposure attributes.
The file type saved is based on the filename extension.
Options
'.npz': Save the arrays into a single file in uncompressed .npz
format.
:param use_parallel: Set to True for parallel behaviour which
is only node 0 writing to file.
:param filename: The file to be written.
:return write_dict: The whole dictionary, returned for testing.
"""
write_dict = self.exposure_agg.copy()
s1 = self.prov.entity(
":Aggregated HazImp output file", {
"prov:label": "Aggregated HazImp output file",
"prov:type": "void:Dataset",
"prov:atLocation": os.path.basename(filename)
})
a1 = self.prov.activity(":SaveAggregatedImpactData",
datetime.now().strftime(DATEFMT), None)
self.prov.wasGeneratedBy(s1, a1)
self.prov.wasInformedBy(a1, self.prov.activity(":AggregateLoss"))
if parallel.STATE.rank == 0 or not use_parallel:
if filename[-4:] == '.csv':
save_csv_agg(write_dict, filename)
else:
numpy.savez(filename, **write_dict)
# The write_dict is returned for testing
# When running in paralled this is a way of getting all
# of the context info
return write_dict
def save_aggregation(self,
filename,
boundaries,
impactcode,
boundarycode,
categories,
use_parallel=True):
"""
Save data aggregated to geospatial regions
:param str filename: Destination filename
:param bool use_parallel: True for parallel behaviout, which
is only node 0 writing to file
"""
LOGGER.info("Saving aggregated data")
boundaries = misc.download_file_from_s3_if_needed(boundaries)
[filename, bucket_name, bucket_key] = \
misc.create_temp_file_path_for_s3(filename)
write_dict = self.exposure_att.copy()
dt = datetime.now().strftime(DATEFMT)
atts = {
"prov:type": "void:Dataset",
"prov:atLocation": os.path.basename(boundaries),
"prov:generatedAtTime": misc.get_file_mtime(boundaries),
"void:boundary_code": boundarycode
}
bdyent = self.prov.entity(":Aggregation boundaries", atts)
aggact = self.prov.activity(":AggregationByRegions", dt, None,
{'prov:type': "Spatial aggregation"})
aggatts = {
"prov:type": "void:Dataset",
"prov:atLocation": os.path.basename(filename),
"prov:generatedAtTime": dt
}
aggfileent = self.prov.entity(":AggregationFile", aggatts)
self.prov.used(aggact, bdyent)
self.prov.wasInformedBy(aggact, self.provlabel)
self.prov.wasGeneratedBy(aggfileent, aggact)
if parallel.STATE.rank == 0 or not use_parallel:
aggregate.choropleth(write_dict, boundaries, impactcode,
boundarycode, filename, categories)
misc.upload_to_s3_if_applicable(filename, bucket_name, bucket_key)
if (bucket_name is not None and bucket_key is not None
and bucket_key.endswith('.shp')):
[rootname, ext] = os.path.splitext(filename)
base_bucket_key = bucket_key[:-len(ext)]
misc.upload_to_s3_if_applicable(rootname + '.dbf', bucket_name,
base_bucket_key + '.dbf')
misc.upload_to_s3_if_applicable(rootname + '.shx', bucket_name,
base_bucket_key + '.shx')
misc.upload_to_s3_if_applicable(rootname + '.prj', bucket_name,
base_bucket_key + '.prj')
misc.upload_to_s3_if_applicable(rootname + '.cpg', bucket_name,
base_bucket_key + '.cpg', True)
else:
pass
def aggregate_loss(self, groupby=None, kwargs=None):
"""
Aggregate data by the `groupby` attribute, using the `kwargs` to
perform any arithmetic aggregation on fields (e.g. summation,
mean, etc.)
:param str groupby: A column in the `DataFrame` that corresponds to
regions by which to aggregate data
:param dict kwargs: A `dict` with keys of valid column names (from the
`DataFrame`) and values being lists of aggregation functions to apply
to the columns.
For example::
kwargs = {'REPLACEMENT_VALUE': ['mean', 'sum'],
'structural_loss_ratio': ['mean', 'std']}
See
https://pandas.pydata.org/pandas-docs/stable/user_guide/groupby.html#aggregation
for more guidance on using aggregation with `DataFrames`
"""
LOGGER.info(f"Aggregating loss using {groupby} attribute")
a1 = self.prov.activity(":AggregateLoss",
datetime.now().strftime(DATEFMT), None, {
"prov:type": "Aggregation",
"void:aggregator": repr(groupby)
})
self.prov.wasInformedBy(a1, self.provlabel)
self.exposure_agg = aggregate.aggregate_loss_atts(
self.exposure_att, groupby, kwargs)
def categorise(self, bins, labels, field_name):
"""
Bin values into discrete intervals.
:param list bins: Monotonically increasing array of bin edges,
including the rightmost edge, allowing for
non-uniform bin widths.
:param labels: Specifies the labels for the returned
bins. Must be the same length as the resulting bins.
:param str field_name: Name of the new column in the `exposure_att`
`DataFrame`
"""
for intensity_key in self.exposure_vuln_curves:
vc = self.exposure_vuln_curves[intensity_key]
lct = vc.loss_category_type
LOGGER.info(f"Categorising {lct} values into {len(labels)} categories")
self.exposure_att[field_name] = pd.cut(self.exposure_att[lct],
bins,
right=False,
labels=labels)
def tabulate(self, file_name, index=None, columns=None, aggfunc=None):
"""
Reshape data (produce a "pivot" table) based on column values. Uses
unique values from specified `index` / `columns` to form axes of the
resulting DataFrame, then writes to an Excel file. This function does
not support data aggregation - multiple values will result in a
MultiIndex in the columns.
See
https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.pivot_table.html
for further details.
Parameters
----------
file_name : destination for the pivot table
index : column or list of columns
Keys to group by on the pivot table index. If an array is passed,
it is being used as the same manner as column values.
columns : column, or list of the columns
Keys to group by on the pivot table column. If an array is passed,
it is being used as the same manner as column values.
aggfunc : function, list of functions, dict, default numpy.mean
If list of functions passed, the resulting pivot table will have
hierarchical columns whose top level are the function names
(inferred from the function objects themselves)
If dict is passed, the key is column to aggregate and value
is function or list of functions.
"""
if index not in self.exposure_att.columns:
LOGGER.error(f"Cannot tabulate data using {index} as index")
LOGGER.error(f"{index} is not an attribute of the exposure data")
return
if columns not in self.exposure_att.columns:
LOGGER.error(
f"Required attribute(s) {columns} not in the exposure data")
LOGGER.error(
"Maybe you need to run a categorise job before this one?")
return
dt = datetime.now().strftime(DATEFMT)
a1 = self.prov.activity(
":Tabulate", dt, None, {
"prov:type": "Tabulation",
"void:aggregator": repr(index),
"void:attributes": repr(columns),
"void:aggregation": repr(aggfunc)
})
tblatts = {
"prov:type": "void:Dataset",
"prov:atLocation": os.path.basename(file_name),
"prov:generatedAtTime": dt
}
tblfileent = self.prov.entity(":TabulationFile", tblatts)
self.pivot = self.exposure_att.pivot_table(index=index,
columns=columns,
aggfunc=aggfunc,
fill_value=0)
try:
self.pivot.to_excel(file_name)
except TypeError as te:
LOGGER.error(te)
raise
except KeyError as ke:
LOGGER.error(ke)
raise
except ValueError as ve:
LOGGER.error(f"Unable to save tabulated data to {file_name}")
LOGGER.error(ve)
else:
self.prov.wasGeneratedBy(tblfileent, a1)
self.prov.wasInformedBy(a1, self.provlabel)
def w3c_publication_2():
# https://github.com/lucmoreau/ProvToolbox/blob/master/asn/src/test/resources/prov/w3c-publication2.prov-asn
# ===========================================================================
# bundle
#
# prefix ex <http://example.org/>
# prefix rec <http://example.org/record>
#
# prefix w3 <http://www.w3.org/TR/2011/>
# prefix hg <http://dvcs.w3.org/hg/prov/raw-file/9628aaff6e20/model/releases/WD-prov-dm-20111215/>
#
#
# entity(hg:Overview.html, [ prov:type="file in hg" ])
# entity(w3:WD-prov-dm-20111215, [ prov:type="html4" ])
#
#
# activity(ex:rcp,-,-,[prov:type="copy directory"])
#
# wasGeneratedBy(rec:g; w3:WD-prov-dm-20111215, ex:rcp, -)
#
# entity(ex:req3, [ prov:type="http://www.w3.org/2005/08/01-transitions.html#pubreq" %% xsd:anyURI ])
#
# used(rec:u; ex:rcp,hg:Overview.html,-)
# used(ex:rcp, ex:req3, -)
#
#
# wasDerivedFrom(w3:WD-prov-dm-20111215, hg:Overview.html, ex:rcp, rec:g, rec:u)
#
# agent(ex:webmaster, [ prov:type='prov:Person' ])
#
# wasAssociatedWith(ex:rcp, ex:webmaster, -)
#
# endBundle
# ===========================================================================
ex = Namespace("ex", "http://example.org/")
rec = Namespace("rec", "http://example.org/record")
w3 = Namespace("w3", "http://www.w3.org/TR/2011/")
hg = Namespace(
"hg",
"http://dvcs.w3.org/hg/prov/raw-file/9628aaff6e20/model/releases/WD-prov-dm-20111215/",
)
g = ProvDocument()
g.entity(hg["Overview.html"], {"prov:type": "file in hg"})
g.entity(w3["WD-prov-dm-20111215"], {"prov:type": "html4"})
g.activity(ex["rcp"], None, None, {"prov:type": "copy directory"})
g.wasGeneratedBy("w3:WD-prov-dm-20111215", "ex:rcp", identifier=rec["g"])
g.entity(
"ex:req3",
{
"prov:type":
Identifier("http://www.w3.org/2005/08/01-transitions.html#pubreq")
},
)
g.used("ex:rcp", "hg:Overview.html", identifier="rec:u")
g.used("ex:rcp", "ex:req3")
g.wasDerivedFrom("w3:WD-prov-dm-20111215", "hg:Overview.html", "ex:rcp",
"rec:g", "rec:u")
g.agent("ex:webmaster", {"prov:type": "Person"})
g.wasAssociatedWith("ex:rcp", "ex:webmaster")
return g
class NIDMExporter():
"""
Generic class to parse a result directory to extract the pieces of
information to be stored in NIDM-Results and to generate a NIDM-Results
export.
"""
def __init__(self, version, out_dir, zipped=True):
out_dirname = os.path.basename(out_dir)
out_path = os.path.dirname(out_dir)
# Create output path from output name
self.zipped = zipped
if not self.zipped:
out_dirname = out_dirname+".nidm"
else:
out_dirname = out_dirname+".nidm.zip"
out_dir = os.path.join(out_path, out_dirname)
# Quit if output path already exists and user doesn't want to overwrite
# it
if os.path.exists(out_dir):
msg = out_dir+" already exists, overwrite?"
if not input("%s (y/N) " % msg).lower() == 'y':
quit("Bye.")
if os.path.isdir(out_dir):
shutil.rmtree(out_dir)
else:
os.remove(out_dir)
self.out_dir = out_dir
if version == "dev":
self.version = {'major': 10000, 'minor': 0, 'revision': 0,
'num': version}
else:
major, minor, revision = version.split(".")
if "-rc" in revision:
revision, rc = revision.split("-rc")
else:
rc = -1
self.version = {'major': int(major), 'minor': int(minor),
'revision': int(revision), 'rc': int(rc),
'num': version}
# Initialise prov document
self.doc = ProvDocument()
self._add_namespaces()
# A temp directory that will contain the exported data
self.export_dir = tempfile.mkdtemp(prefix="nidm-", dir=out_path)
self.prepend_path = ''
def parse(self):
"""
Parse a result directory to extract the pieces information to be
stored in NIDM-Results.
"""
try:
# Methods: find_software, find_model_fitting, find_contrasts and
# find_inferences should be defined in the children classes and
# return a list of NIDM Objects as specified in the objects module
# Object of type Software describing the neuroimaging software
# package used for the analysis
self.software = self._find_software()
# List of objects of type ModelFitting describing the
# model fitting step in NIDM-Results (main activity: Model
# Parameters Estimation)
self.model_fittings = self._find_model_fitting()
# Dictionary of (key, value) pairs where where key is a tuple
# containing the identifier of a ModelParametersEstimation object
# and a tuple of identifiers of ParameterEstimateMap objects and
# value is an object of type Contrast describing the contrast
# estimation step in NIDM-Results (main activity: Contrast
# Estimation)
self.contrasts = self._find_contrasts()
# Inference activity and entities
# Dictionary of (key, value) pairs where key is the identifier of a
# ContrastEstimation object and value is an object of type
# Inference describing the inference step in NIDM-Results (main
# activity: Inference)
self.inferences = self._find_inferences()
except Exception:
self.cleanup()
raise
def cleanup(self):
if os.path.isdir(self.export_dir):
shutil.rmtree(self.export_dir)
def add_object(self, nidm_object, export_file=True):
"""
Add a NIDMObject to a NIDM-Results export.
"""
if not export_file:
export_dir = None
else:
export_dir = self.export_dir
if not isinstance(nidm_object, NIDMFile):
nidm_object.export(self.version, export_dir)
else:
nidm_object.export(self.version, export_dir, self.prepend_path)
# ProvDocument: add object to the bundle
if nidm_object.prov_type == PROV['Activity']:
self.bundle.activity(nidm_object.id,
other_attributes=nidm_object.attributes)
elif nidm_object.prov_type == PROV['Entity']:
self.bundle.entity(nidm_object.id,
other_attributes=nidm_object.attributes)
elif nidm_object.prov_type == PROV['Agent']:
self.bundle.agent(nidm_object.id,
other_attributes=nidm_object.attributes)
# self.bundle.update(nidm_object.p)
def export(self):
"""
Generate a NIDM-Results export.
"""
try:
if not os.path.isdir(self.export_dir):
os.mkdir(self.export_dir)
# Initialise main bundle
self._create_bundle(self.version)
self.add_object(self.software)
# Add model fitting steps
if not isinstance(self.model_fittings, list):
self.model_fittings = list(self.model_fittings.values())
for model_fitting in self.model_fittings:
# Design Matrix
# model_fitting.activity.used(model_fitting.design_matrix)
self.bundle.used(model_fitting.activity.id,
model_fitting.design_matrix.id)
self.add_object(model_fitting.design_matrix)
# *** Export visualisation of the design matrix
self.add_object(model_fitting.design_matrix.image)
if model_fitting.design_matrix.image.file is not None:
self.add_object(model_fitting.design_matrix.image.file)
if model_fitting.design_matrix.hrf_models is not None:
# drift model
self.add_object(model_fitting.design_matrix.drift_model)
if self.version['major'] > 1 or \
(self.version['major'] == 1 and
self.version['minor'] >= 3):
# Machine
# model_fitting.data.wasAttributedTo(model_fitting.machine)
self.bundle.wasAttributedTo(model_fitting.data.id,
model_fitting.machine.id)
self.add_object(model_fitting.machine)
# Imaged subject or group(s)
for sub in model_fitting.subjects:
self.add_object(sub)
# model_fitting.data.wasAttributedTo(sub)
self.bundle.wasAttributedTo(model_fitting.data.id,
sub.id)
# Data
# model_fitting.activity.used(model_fitting.data)
self.bundle.used(model_fitting.activity.id,
model_fitting.data.id)
self.add_object(model_fitting.data)
# Error Model
# model_fitting.activity.used(model_fitting.error_model)
self.bundle.used(model_fitting.activity.id,
model_fitting.error_model.id)
self.add_object(model_fitting.error_model)
# Parameter Estimate Maps
for param_estimate in model_fitting.param_estimates:
# param_estimate.wasGeneratedBy(model_fitting.activity)
self.bundle.wasGeneratedBy(param_estimate.id,
model_fitting.activity.id)
self.add_object(param_estimate)
self.add_object(param_estimate.coord_space)
self.add_object(param_estimate.file)
if param_estimate.derfrom is not None:
self.bundle.wasDerivedFrom(param_estimate.id,
param_estimate.derfrom.id)
self.add_object(param_estimate.derfrom)
self.add_object(param_estimate.derfrom.file,
export_file=False)
# Residual Mean Squares Map
# model_fitting.rms_map.wasGeneratedBy(model_fitting.activity)
self.add_object(model_fitting.rms_map)
self.bundle.wasGeneratedBy(model_fitting.rms_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.rms_map.coord_space)
self.add_object(model_fitting.rms_map.file)
if model_fitting.rms_map.derfrom is not None:
self.bundle.wasDerivedFrom(
model_fitting.rms_map.id,
model_fitting.rms_map.derfrom.id)
self.add_object(model_fitting.rms_map.derfrom)
self.add_object(model_fitting.rms_map.derfrom.file,
export_file=False)
# Resels per Voxel Map
if model_fitting.rpv_map is not None:
self.add_object(model_fitting.rpv_map)
self.bundle.wasGeneratedBy(model_fitting.rpv_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.rpv_map.coord_space)
self.add_object(model_fitting.rpv_map.file)
if model_fitting.rpv_map.inf_id is not None:
self.bundle.used(model_fitting.rpv_map.inf_id,
model_fitting.rpv_map.id)
if model_fitting.rpv_map.derfrom is not None:
self.bundle.wasDerivedFrom(
model_fitting.rpv_map.id,
model_fitting.rpv_map.derfrom.id)
self.add_object(model_fitting.rpv_map.derfrom)
self.add_object(model_fitting.rpv_map.derfrom.file,
export_file=False)
# Mask
# model_fitting.mask_map.wasGeneratedBy(model_fitting.activity)
self.bundle.wasGeneratedBy(model_fitting.mask_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.mask_map)
if model_fitting.mask_map.derfrom is not None:
self.bundle.wasDerivedFrom(
model_fitting.mask_map.id,
model_fitting.mask_map.derfrom.id)
self.add_object(model_fitting.mask_map.derfrom)
self.add_object(model_fitting.mask_map.derfrom.file,
export_file=False)
# Create coordinate space export
self.add_object(model_fitting.mask_map.coord_space)
# Create "Mask map" entity
self.add_object(model_fitting.mask_map.file)
# Grand Mean map
# model_fitting.grand_mean_map.wasGeneratedBy(model_fitting.activity)
self.bundle.wasGeneratedBy(model_fitting.grand_mean_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.grand_mean_map)
# Coordinate space entity
self.add_object(model_fitting.grand_mean_map.coord_space)
# Grand Mean Map entity
self.add_object(model_fitting.grand_mean_map.file)
# Model Parameters Estimation activity
self.add_object(model_fitting.activity)
self.bundle.wasAssociatedWith(model_fitting.activity.id,
self.software.id)
# model_fitting.activity.wasAssociatedWith(self.software)
# self.add_object(model_fitting)
# Add contrast estimation steps
analysis_masks = dict()
for (model_fitting_id, pe_ids), contrasts in list(
self.contrasts.items()):
for contrast in contrasts:
model_fitting = self._get_model_fitting(model_fitting_id)
# for contrast in contrasts:
# contrast.estimation.used(model_fitting.rms_map)
self.bundle.used(contrast.estimation.id,
model_fitting.rms_map.id)
# contrast.estimation.used(model_fitting.mask_map)
self.bundle.used(contrast.estimation.id,
model_fitting.mask_map.id)
analysis_masks[contrast.estimation.id] = \
model_fitting.mask_map.id
self.bundle.used(contrast.estimation.id,
contrast.weights.id)
self.bundle.used(contrast.estimation.id,
model_fitting.design_matrix.id)
# contrast.estimation.wasAssociatedWith(self.software)
self.bundle.wasAssociatedWith(contrast.estimation.id,
self.software.id)
for pe_id in pe_ids:
# contrast.estimation.used(pe_id)
self.bundle.used(contrast.estimation.id, pe_id)
# Create estimation activity
self.add_object(contrast.estimation)
# Create contrast weights
self.add_object(contrast.weights)
if contrast.contrast_map is not None:
# Create contrast Map
# contrast.contrast_map.wasGeneratedBy(contrast.estimation)
self.bundle.wasGeneratedBy(contrast.contrast_map.id,
contrast.estimation.id)
self.add_object(contrast.contrast_map)
self.add_object(contrast.contrast_map.coord_space)
# Copy contrast map in export directory
self.add_object(contrast.contrast_map.file)
if contrast.contrast_map.derfrom is not None:
self.bundle.wasDerivedFrom(
contrast.contrast_map.id,
contrast.contrast_map.derfrom.id)
self.add_object(contrast.contrast_map.derfrom)
self.add_object(contrast.contrast_map.derfrom.file,
export_file=False)
# Create Std Err. Map (T-tests) or Explained Mean Sq. Map
# (F-tests)
# contrast.stderr_or_expl_mean_sq_map.wasGeneratedBy
# (contrast.estimation)
stderr_explmeansq_map = (
contrast.stderr_or_expl_mean_sq_map)
self.bundle.wasGeneratedBy(
stderr_explmeansq_map.id,
contrast.estimation.id)
self.add_object(stderr_explmeansq_map)
self.add_object(
stderr_explmeansq_map.coord_space)
if isinstance(stderr_explmeansq_map,
ContrastStdErrMap) and \
stderr_explmeansq_map.contrast_var:
self.add_object(
stderr_explmeansq_map.contrast_var)
if stderr_explmeansq_map.var_coord_space:
self.add_object(
stderr_explmeansq_map.var_coord_space)
if stderr_explmeansq_map.contrast_var.coord_space:
self.add_object(
stderr_explmeansq_map.contrast_var.coord_space)
self.add_object(
stderr_explmeansq_map.contrast_var.file,
export_file=False)
self.bundle.wasDerivedFrom(
stderr_explmeansq_map.id,
stderr_explmeansq_map.contrast_var.id)
self.add_object(stderr_explmeansq_map.file)
# Create Statistic Map
# contrast.stat_map.wasGeneratedBy(contrast.estimation)
self.bundle.wasGeneratedBy(contrast.stat_map.id,
contrast.estimation.id)
self.add_object(contrast.stat_map)
self.add_object(contrast.stat_map.coord_space)
# Copy Statistical map in export directory
self.add_object(contrast.stat_map.file)
if contrast.stat_map.derfrom is not None:
self.bundle.wasDerivedFrom(
contrast.stat_map.id,
contrast.stat_map.derfrom.id)
self.add_object(contrast.stat_map.derfrom)
self.add_object(contrast.stat_map.derfrom.file,
export_file=False)
# Create Z Statistic Map
if contrast.z_stat_map:
# contrast.z_stat_map.wasGeneratedBy(contrast.estimation)
self.bundle.wasGeneratedBy(contrast.z_stat_map.id,
contrast.estimation.id)
self.add_object(contrast.z_stat_map)
self.add_object(contrast.z_stat_map.coord_space)
# Copy Statistical map in export directory
self.add_object(contrast.z_stat_map.file)
# self.add_object(contrast)
# Add inference steps
for contrast_id, inferences in list(self.inferences.items()):
contrast = self._get_contrast(contrast_id)
for inference in inferences:
if contrast.z_stat_map:
used_id = contrast.z_stat_map.id
else:
used_id = contrast.stat_map.id
# inference.inference_act.used(used_id)
self.bundle.used(inference.inference_act.id, used_id)
# inference.inference_act.wasAssociatedWith(self.software)
self.bundle.wasAssociatedWith(inference.inference_act.id,
self.software.id)
# self.add_object(inference)
# Excursion set
# inference.excursion_set.wasGeneratedBy(inference.inference_act)
self.bundle.wasGeneratedBy(inference.excursion_set.id,
inference.inference_act.id)
self.add_object(inference.excursion_set)
self.add_object(inference.excursion_set.coord_space)
if inference.excursion_set.visu is not None:
self.add_object(inference.excursion_set.visu)
if inference.excursion_set.visu.file is not None:
self.add_object(inference.excursion_set.visu.file)
# Copy "Excursion set map" file in export directory
self.add_object(inference.excursion_set.file)
if inference.excursion_set.clust_map is not None:
self.add_object(inference.excursion_set.clust_map)
self.add_object(inference.excursion_set.clust_map.file)
self.add_object(
inference.excursion_set.clust_map.coord_space)
if inference.excursion_set.mip is not None:
self.add_object(inference.excursion_set.mip)
self.add_object(inference.excursion_set.mip.file)
# Height threshold
if inference.height_thresh.equiv_thresh is not None:
for equiv in inference.height_thresh.equiv_thresh:
self.add_object(equiv)
self.add_object(inference.height_thresh)
# Extent threshold
if inference.extent_thresh.equiv_thresh is not None:
for equiv in inference.extent_thresh.equiv_thresh:
self.add_object(equiv)
self.add_object(inference.extent_thresh)
# Display Mask (potentially more than 1)
if inference.disp_mask:
for mask in inference.disp_mask:
# inference.inference_act.used(mask)
self.bundle.used(inference.inference_act.id,
mask.id)
self.add_object(mask)
# Create coordinate space entity
self.add_object(mask.coord_space)
# Create "Display Mask Map" entity
self.add_object(mask.file)
if mask.derfrom is not None:
self.bundle.wasDerivedFrom(mask.id,
mask.derfrom.id)
self.add_object(mask.derfrom)
self.add_object(mask.derfrom.file,
export_file=False)
# Search Space
self.bundle.wasGeneratedBy(inference.search_space.id,
inference.inference_act.id)
# inference.search_space.wasGeneratedBy(inference.inference_act)
self.add_object(inference.search_space)
self.add_object(inference.search_space.coord_space)
# Copy "Mask map" in export directory
self.add_object(inference.search_space.file)
# Peak Definition
if inference.peak_criteria:
# inference.inference_act.used(inference.peak_criteria)
self.bundle.used(inference.inference_act.id,
inference.peak_criteria.id)
self.add_object(inference.peak_criteria)
# Cluster Definition
if inference.cluster_criteria:
# inference.inference_act.used(inference.cluster_criteria)
self.bundle.used(inference.inference_act.id,
inference.cluster_criteria.id)
self.add_object(inference.cluster_criteria)
if inference.clusters:
# Clusters and peaks
for cluster in inference.clusters:
# cluster.wasDerivedFrom(inference.excursion_set)
self.bundle.wasDerivedFrom(
cluster.id, inference.excursion_set.id)
self.add_object(cluster)
for peak in cluster.peaks:
self.bundle.wasDerivedFrom(peak.id, cluster.id)
self.add_object(peak)
self.add_object(peak.coordinate)
if cluster.cog is not None:
self.bundle.wasDerivedFrom(cluster.cog.id,
cluster.id)
self.add_object(cluster.cog)
self.add_object(cluster.cog.coordinate)
# Inference activity
# inference.inference_act.wasAssociatedWith(inference.software_id)
# inference.inference_act.used(inference.height_thresh)
self.bundle.used(inference.inference_act.id,
inference.height_thresh.id)
# inference.inference_act.used(inference.extent_thresh)
self.bundle.used(inference.inference_act.id,
inference.extent_thresh.id)
self.bundle.used(inference.inference_act.id,
analysis_masks[contrast.estimation.id])
self.add_object(inference.inference_act)
# Write-out prov file
self.save_prov_to_files()
return self.out_dir
except Exception:
self.cleanup()
raise
def _get_model_fitting(self, mf_id):
"""
Retreive model fitting with identifier 'mf_id' from the list of model
fitting objects stored in self.model_fitting
"""
for model_fitting in self.model_fittings:
if model_fitting.activity.id == mf_id:
return model_fitting
raise Exception("Model fitting activity with id: " + str(mf_id) +
" not found.")
def _get_contrast(self, con_id):
"""
Retreive contrast with identifier 'con_id' from the list of contrast
objects stored in self.contrasts
"""
for contrasts in list(self.contrasts.values()):
for contrast in contrasts:
if contrast.estimation.id == con_id:
return contrast
raise Exception("Contrast activity with id: " + str(con_id) +
" not found.")
def _add_namespaces(self):
"""
Add namespaces to NIDM document.
"""
self.doc.add_namespace(NIDM)
self.doc.add_namespace(NIIRI)
self.doc.add_namespace(CRYPTO)
self.doc.add_namespace(DCT)
self.doc.add_namespace(DC)
self.doc.add_namespace(NFO)
self.doc.add_namespace(OBO)
self.doc.add_namespace(SCR)
self.doc.add_namespace(NIF)
def _create_bundle(self, version):
"""
Initialise NIDM-Results bundle.
"""
# *** Bundle entity
if not hasattr(self, 'bundle_ent'):
self.bundle_ent = NIDMResultsBundle(nidm_version=version['num'])
self.bundle = ProvBundle(identifier=self.bundle_ent.id)
self.bundle_ent.export(self.version, self.export_dir)
# # provn export
# self.bundle = ProvBundle(identifier=bundle_id)
self.doc.entity(self.bundle_ent.id,
other_attributes=self.bundle_ent.attributes)
# *** NIDM-Results Export Activity
if version['num'] not in ["1.0.0", "1.1.0"]:
if not hasattr(self, 'export_act'):
self.export_act = NIDMResultsExport()
self.export_act.export(self.version, self.export_dir)
# self.doc.update(self.export_act.p)
self.doc.activity(self.export_act.id,
other_attributes=self.export_act.attributes)
# *** bundle was Generated by NIDM-Results Export Activity
if not hasattr(self, 'export_time'):
self.export_time = str(datetime.datetime.now().time())
if version['num'] in ["1.0.0", "1.1.0"]:
self.doc.wasGeneratedBy(entity=self.bundle_ent.id,
time=self.export_time)
else:
# provn
self.doc.wasGeneratedBy(
entity=self.bundle_ent.id, activity=self.export_act.id,
time=self.export_time)
# *** NIDM-Results Exporter (Software Agent)
if version['num'] not in ["1.0.0", "1.1.0"]:
if not hasattr(self, 'exporter'):
self.exporter = self._get_exporter()
self.exporter.export(self.version, self.export_dir)
# self.doc.update(self.exporter.p)
self.doc.agent(self.exporter.id,
other_attributes=self.exporter.attributes)
self.doc.wasAssociatedWith(self.export_act.id, self.exporter.id)
def _get_model_parameters_estimations(self, error_model):
"""
Infer model estimation method from the 'error_model'. Return an object
of type ModelParametersEstimation.
"""
if error_model.dependance == NIDM_INDEPEDENT_ERROR:
if error_model.variance_homo:
estimation_method = STATO_OLS
else:
estimation_method = STATO_WLS
else:
estimation_method = STATO_GLS
mpe = ModelParametersEstimation(estimation_method, self.software.id)
return mpe
def use_prefixes(self, ttl):
prefix_file = os.path.join(os.path.dirname(__file__), 'prefixes.csv')
context = dict()
with open(prefix_file, encoding="ascii") as csvfile:
reader = csv.reader(csvfile)
next(reader, None) # skip the headers
for alphanum_id, prefix, uri in reader:
if alphanum_id in ttl:
context[prefix] = uri
ttl = "@prefix " + prefix + ": <" + uri + "> .\n" + ttl
ttl = ttl.replace(alphanum_id, prefix + ":")
if uri in ttl:
ttl = ttl.replace(alphanum_id, prefix + ":")
elif uri in ttl:
context[prefix] = uri
ttl = "@prefix " + prefix + ": <" + uri + "> .\n" + ttl
ttl = ttl.replace(alphanum_id, prefix + ":")
return (ttl, context)
def save_prov_to_files(self, showattributes=False):
"""
Write-out provn serialisation to nidm.provn.
"""
self.doc.add_bundle(self.bundle)
# provn_file = os.path.join(self.export_dir, 'nidm.provn')
# provn_fid = open(provn_file, 'w')
# # FIXME None
# # provn_fid.write(self.doc.get_provn(4).replace("None", "-"))
# provn_fid.close()
ttl_file = os.path.join(self.export_dir, 'nidm.ttl')
ttl_txt = self.doc.serialize(format='rdf', rdf_format='turtle')
ttl_txt, json_context = self.use_prefixes(ttl_txt)
# Add namespaces to json-ld context
for namespace in self.doc._namespaces.get_registered_namespaces():
json_context[namespace._prefix] = namespace._uri
for namespace in \
list(self.doc._namespaces._default_namespaces.values()):
json_context[namespace._prefix] = namespace._uri
json_context["xsd"] = "http://www.w3.org/2000/01/rdf-schema#"
# Work-around to issue with INF value in rdflib (reported in
# https://github.com/RDFLib/rdflib/pull/655)
ttl_txt = ttl_txt.replace(' inf ', ' "INF"^^xsd:float ')
with open(ttl_file, 'w') as ttl_fid:
ttl_fid.write(ttl_txt)
# print(json_context)
jsonld_file = os.path.join(self.export_dir, 'nidm.json')
jsonld_txt = self.doc.serialize(format='rdf', rdf_format='json-ld',
context=json_context)
with open(jsonld_file, 'w') as jsonld_fid:
jsonld_fid.write(jsonld_txt)
# provjsonld_file = os.path.join(self.export_dir, 'nidm.provjsonld')
# provjsonld_txt = self.doc.serialize(format='jsonld')
# with open(provjsonld_file, 'w') as provjsonld_fid:
# provjsonld_fid.write(provjsonld_txt)
# provn_file = os.path.join(self.export_dir, 'nidm.provn')
# provn_txt = self.doc.serialize(format='provn')
# with open(provn_file, 'w') as provn_fid:
# provn_fid.write(provn_txt)
# Post-processing
if not self.zipped:
# Just rename temp directory to output_path
os.rename(self.export_dir, self.out_dir)
else:
# Create a zip file that contains the content of the temp directory
os.chdir(self.export_dir)
zf = zipfile.ZipFile(os.path.join("..", self.out_dir), mode='w')
try:
for root, dirnames, filenames in os.walk("."):
for filename in filenames:
zf.write(os.path.join(filename))
finally:
zf.close()
# Need to move up before deleting the folder
os.chdir("..")
shutil.rmtree(os.path.join("..", self.export_dir))
def useGenDependency(self, aDO, usedList, genList, throughActivity):
aID = throughActivity.id
# create provlet
d1 = ProvDocument() # d1 is now an empty provenance document
d1.add_namespace("dt", "http://cs.ncl.ac.uk/dtsim/")
usedEntities = []
for aRO in usedList:
usedEntities.append(d1.entity(DTns + aRO.id))
genEntities = []
for aRO1 in genList:
genEntities.append(d1.entity(DTns + aRO1.id))
a = d1.activity(DTns + aID)
ag1 = d1.agent(DTns + str(aDO.id))
d1.wasAssociatedWith(a, ag1)
for ue in usedEntities:
d1.used(a, ue)
for gene in genEntities:
d1.wasAttributedTo(gene, ag1)
d1.wasGeneratedBy(gene, a)
# associate this provlet to each generated RO
for aRO1 in genList:
aRO1.provlet = d1
print "event {n}: DO {do}: {ro1} <- wgby <- {act} <- used {ro}".format(
n=currentReuseCount, do=aDO.id, ro1=aRO1.id, act=aID, ro=aRO.id
)
for genRO in genList:
for uRO in usedList:
# update upstream pointer
genRO.upstream.append(
(uRO, throughActivity)
) # dep on aRO through activity aID FIXME URGENTLY!!! not designed for M-M
for uRO in usedList:
for genRO in genList:
# update downstream
uRO.downstream.append((genRO, throughActivity)) # aR1 is downstream from aR1 through activity aID
# update global graph
globalUsedEntities = []
for aRO in usedList:
globalUsedEntities.append(pGlobal.entity(DTns + aRO.id))
globalGenEntities = []
for aR1 in genList:
globalGenEntities.append(pGlobal.entity(DTns + aR1.id))
a = pGlobal.activity(DTns + aID)
ag1 = pGlobal.agent(DTns + str(aDO.id))
pGlobal.wasAssociatedWith(a, ag1)
for ue in globalUsedEntities:
pGlobal.used(a, ue)
for gene in globalGenEntities:
pGlobal.wasAttributedTo(gene, ag1)
pGlobal.wasGeneratedBy(gene, a)
# trigger credit recomputation
# each used RO needs its credit updated with aRO1.credit for each generated aRO1 through activity aID
aCreditManager.addGenerationCredit(usedList, genList, throughActivity)
# self.notify(d1)
return d1
from prov.model import ProvDocument
from provdbconnector import ProvApi
from provdbconnector.db_adapters.in_memory import SimpleInMemoryAdapter
prov_api = ProvApi(adapter=SimpleInMemoryAdapter, auth_info=None)
# create the prov document
prov_document = ProvDocument()
prov_document.add_namespace("ex", "http://example.com")
prov_document.agent("ex:Bob")
prov_document.activity("ex:Alice")
prov_document.association("ex:Alice", "ex:Bob")
# create bundle
b1 = prov_document.bundle("ex:bundle1")
b1.agent("ex:Yoda")
b2 = prov_document.bundle("ex:bundle2")
b2.agent("ex:Jabba the Hutt")
document_id = prov_api.create_document(prov_document)
print(prov_api.get_document_as_provn(document_id))
# Output:
#
# document
# prefix ex <http://example.com>
#
# agent(ex:Bob)
def w3c_publication_1():
# https://github.com/lucmoreau/ProvToolbox/blob/master/asn/src/test/resources/prov/w3c-publication1.prov-asn
#===========================================================================
# bundle
#
# prefix ex <http://example.org/>
#
# prefix w3 <http://www.w3.org/>
# prefix tr <http://www.w3.org/TR/2011/>
# prefix process <http://www.w3.org/2005/10/Process-20051014/tr.html#>
# prefix email <https://lists.w3.org/Archives/Member/w3c-archive/>
# prefix chairs <https://lists.w3.org/Archives/Member/chairs/>
# prefix trans <http://www.w3.org/2005/08/01-transitions.html#>
# prefix rec54 <http://www.w3.org/2001/02pd/rec54#>
#
#
# entity(tr:WD-prov-dm-20111018, [ prov:type='rec54:WD' ])
# entity(tr:WD-prov-dm-20111215, [ prov:type='rec54:WD' ])
# entity(process:rec-advance, [ prov:type='prov:Plan' ])
#
#
# entity(chairs:2011OctDec/0004, [ prov:type='trans:transreq' ])
# entity(email:2011Oct/0141, [ prov:type='trans:pubreq' ])
# entity(email:2011Dec/0111, [ prov:type='trans:pubreq' ])
#
#
# wasDerivedFrom(tr:WD-prov-dm-20111215, tr:WD-prov-dm-20111018)
#
#
# activity(ex:act1,-,-,[prov:type="publish"])
# activity(ex:act2,-,-,[prov:type="publish"])
#
# wasGeneratedBy(tr:WD-prov-dm-20111018, ex:act1, -)
# wasGeneratedBy(tr:WD-prov-dm-20111215, ex:act2, -)
#
# used(ex:act1, chairs:2011OctDec/0004, -)
# used(ex:act1, email:2011Oct/0141, -)
# used(ex:act2, email:2011Dec/0111, -)
#
# agent(w3:Consortium, [ prov:type='prov:Organization' ])
#
# wasAssociatedWith(ex:act1, w3:Consortium, process:rec-advance)
# wasAssociatedWith(ex:act2, w3:Consortium, process:rec-advance)
#
# endBundle
#===========================================================================
g = ProvDocument()
g.add_namespace('ex', 'http://example.org/')
g.add_namespace('w3', 'http://www.w3.org/')
g.add_namespace('tr', 'http://www.w3.org/TR/2011/')
g.add_namespace('process',
'http://www.w3.org/2005/10/Process-20051014/tr.html#')
g.add_namespace('email',
'https://lists.w3.org/Archives/Member/w3c-archive/')
g.add_namespace('chairs', 'https://lists.w3.org/Archives/Member/chairs/')
g.add_namespace('trans', 'http://www.w3.org/2005/08/01-transitions.html#')
g.add_namespace('rec54', 'http://www.w3.org/2001/02pd/rec54#')
g.entity('tr:WD-prov-dm-20111018', {'prov:type': 'rec54:WD'})
g.entity('tr:WD-prov-dm-20111215', {'prov:type': 'rec54:WD'})
g.entity('process:rec-advance', {'prov:type': 'prov:Plan'})
g.entity('chairs:2011OctDec/0004', {'prov:type': 'trans:transreq'})
g.entity('email:2011Oct/0141', {'prov:type': 'trans:pubreq'})
g.entity('email:2011Dec/0111', {'prov:type': 'trans:pubreq'})
g.wasDerivedFrom('tr:WD-prov-dm-20111215', 'tr:WD-prov-dm-20111018')
g.activity('ex:act1', other_attributes={'prov:type': "publish"})
g.activity('ex:act2', other_attributes={'prov:type': "publish"})
g.wasGeneratedBy('tr:WD-prov-dm-20111018', 'ex:act1')
g.wasGeneratedBy('tr:WD-prov-dm-20111215', 'ex:act2')
g.used('ex:act1', 'chairs:2011OctDec/0004')
g.used('ex:act1', 'email:2011Oct/0141')
g.used('ex:act2', 'email:2011Dec/0111')
g.agent('w3:Consortium', other_attributes={'prov:type': "Organization"})
g.wasAssociatedWith('ex:act1', 'w3:Consortium', 'process:rec-advance')
g.wasAssociatedWith('ex:act2', 'w3:Consortium', 'process:rec-advance')
return g
def example():
g = ProvDocument()
# Local namespace
# Doesnt exist yet so we are creating it
ap = Namespace('aip', 'https://araport.org/provenance/')
# Dublin Core
g.add_namespace("dcterms", "http://purl.org/dc/terms/")
# FOAF
g.add_namespace("foaf", "http://xmlns.com/foaf/0.1/")
# Add sponsors and contributors as Agents
# ap['matthew_vaughn']
# aip:matthew_vaughn
# https://araport.org/provenance/:matthew_vaughn
# Learn this from a call to profiles service? Adds a dependency on Agave so I am open to figuring out another way
me = g.agent(ap['matthew_vaughn'], {
'prov:type': PROV["Person"], 'foaf:givenName': "Matthew Vaughn", 'foaf:mbox': "<mailto:[email protected]>"
})
# Hard coded for now
walter = g.agent(ap['walter_moreira'], {
'prov:type': PROV["Person"], 'foaf:givenName': "Walter Moreira", 'foaf:mbox': "<mailto:[email protected]>"
})
utexas = g.agent(ap['university_of_texas'], {
'prov:type': PROV["Organization"], 'foaf:givenName': "University of Texas at Austin"
})
# Set delegation to our host University
# We may have trouble doing this for other users since we don't always capture their host instituion
g.actedOnBehalfOf(walter, utexas)
g.actedOnBehalfOf(me, utexas)
# Include the ADAMA platform as an Agent and set attribution
# dcterms:title and dcterms:description are hardcoded
# dcterms:language is hard-coded
# dcterms:source is the URI of the public git source repository for ADAMA
# "dcterms:updated": "2015-04-17T09:44:56" - this would actually be the date ADAMA was updated
adama_platform = g.agent(ap['adama_platform'], {'dcterms:title': "ADAMA", 'dcterms:description': "Araport Data and Microservices API", 'dcterms:language':"en-US", 'dcterms:identifier':"https://api.araport.org/community/v0.3/", 'dcterms:updated': "2015-04-17T09:44:56" })
g.wasGeneratedBy(adama_platform, walter)
# Include the ADAMA microservice as an Agent and set attribution+delegation
# dcterms:title and dcterms:description are inherited from the service's metadata
# dcterms:language is hard-coded
# dcterms:identifier is the deployment URI for the service
# dcterms:source is the URI of the public git source repository. The URL in this example is just a dummy
#
# The name for each microservice should be unique. We've decided to
# use the combination of namespace, service name, and version
microservice_name = 'mwvaughn/bar_annotation_v1.0.0'
adama_microservice = g.agent(ap[microservice_name], {'dcterms:title': "BAR Annotation Service", 'dcterms:description': "Returns annotation from locus ID", 'dcterms:language':"en-US", 'dcterms:identifier':"https://api.araport.org/community/v0.3/mwvaughn/bar_annotation_v1.0.0", 'dcterms:source':"https://github.com/Arabidopsis-Information-Portal/prov-enabled-api-sample" })
# the microservice was generated by me on date X (don't use now, use when the service was updated)
g.wasGeneratedBy(adama_microservice, me, datetime.datetime.now())
# The microservice used the platform now
g.used(adama_microservice, adama_platform, datetime.datetime.now())
# Sources
#
# Define BAR
# Agents
nick = g.agent(ap['nicholas_provart'], {
'prov:type': PROV["Person"], 'foaf:givenName': "Nicholas Provart", 'foaf:mbox': "*****@*****.**"
})
utoronto = g.agent(ap['university_of_toronto'], {
'prov:type': PROV["Organization"], 'foaf:givenName': "University of Toronto", 'dcterms:identifier':"http://www.utoronto.ca/"
})
g.actedOnBehalfOf(nick, utoronto)
# Entity
# All fields derived from Sources.yml
# dcterms:title and dcterms:description come straight from the YAML
# dcterms:identifier - URI pointing to the source's canonical URI representation
# optional - dcterms:language: Recommended best practice is to use a controlled vocabulary such as RFC 4646
# optional - dcterms:updated: date the source was published or last updated
# optional - dcterms:license: Simple string or URI to license. Validate URI if provided?
datasource1 = g.entity(ap['datasource1'], {'dcterms:title': "BAR Arabidopsis AGI -> Annotation", 'dcterms:description': "Most recent annotation for given AGI", 'dcterms:language':"en-US", 'dcterms:identifier':"http://bar.utoronto.ca/webservices/agiToAnnot.php", 'dcterms:updated':"2015-04-17T09:44:56", 'dcterms:license':"Creative Commons 3.0" })
# Set up attribution to Nick
g.wasAttributedTo(datasource1, nick)
# Define TAIR
# Agents
# dcterms:language: Recommended best practice is to use a controlled vocabulary such as RFC 4646
eva = g.agent(ap['eva_huala'], {
'prov:type': PROV["Person"], 'foaf:givenName': "Eva Huala"
})
phoenix = g.agent(ap['phoenix_bioinformatics'], {
'prov:type': PROV["Organization"], 'foaf:givenName': "Phoenix Bioinformatics"
})
g.actedOnBehalfOf(eva, phoenix)
# Entity
# All fields derived from Sources.yml
# optional - dcterms:citation: Plain text bibliographic citation. If only provided as doi, should we try to validate it?
datasource2 = g.entity(ap['datasource2'], {'dcterms:title': "TAIR", 'dcterms:description': "The Arabidopsis Information Resource", 'dcterms:language':"en-US", 'dcterms:identifier':"https://www.arabidopsis.org/", 'dcterms:citation':"The Arabidopsis Information Resource (TAIR): improved gene annotation and new tools. Nucleic Acids Research 2011 doi: 10.1093/nar/gkr1090"})
g.wasAttributedTo(datasource2, eva)
# In Sources.yml, these two sources are nested. Define that relationship here
# There are other types of relationships but we will just use derived from for simplicity in this prototype
g.wasDerivedFrom(ap['datasource1'], ap['datasource2'])
# Depending on which ADAMA microservice type we are using, define an activity
# Eventually, break these into more atomic actions in a chain
action1 = g.activity(ap['do_query'], datetime.datetime.now())
# action1 = g.activity(ap['do_map'], datetime.datetime.now())
# action1 = g.activity(ap['do_generic'], datetime.datetime.now())
# action1 = g.activity(ap['do_passthrough'], datetime.datetime.now())
# Future... Support for ADAMA-native microservices
# action1 = g.activity(ap['generate'], datetime.datetime.now())
# Define current ADAMA response as an Entity
# This is what's being returned to the user and is thus the subject of the PROV record
# May be able to add more attributes to it but this is the minimum
response = g.entity(ap['adama_response'])
# Response is generated by the process_query action
# Time-stamp it!
g.wasGeneratedBy(response, ap['do_query'], datetime.datetime.now())
# The process_query used the microservice
g.used(ap['do_query'], adama_microservice, datetime.datetime.now())
# The microservice used datasource1
g.used(adama_microservice, datasource1, datetime.datetime.now())
# Print prov_n
print(g.get_provn())
# Print prov-json
print(g.serialize())
# Write out as a pretty picture
graph = prov.dot.prov_to_dot(g)
graph.write_png('Sources.png')
def provlist2provdoc(provlist, default_ns=DEFAULT_NS):
""" Convert a list of provenance dictionaries to a provdoc W3C PROV compatible"""
pdoc = ProvDocument()
pdoc.set_default_namespace("param:")
pdoc.add_namespace(default_ns, default_ns + ":")
pdoc.add_namespace("voprov", "voprov:")
records = {}
sess_id = ""
for provdict in provlist:
if "session_id" in provdict:
sess_id = str(provdict.pop("session_id"))
sess_qid = default_ns + ":" + sess_id
if sess_id in records:
sess = records[sess_qid]
else:
sess = pdoc.entity(sess_qid)
records[sess_qid] = sess
sess.add_attributes({
"prov:label":
"LogProvSession",
"prov:type":
"LogProvSession",
"prov:generatedAtTime":
provdict.pop("startTime"),
#'configFile': provdict.pop('configFile'),
'module':
str(provdict.pop('module')),
'class':
str(provdict.pop('class')),
'system':
str(provdict.pop('system'))[:50],
'definitions':
str(provdict.pop('definitions'))[:50],
})
# activity
if "activity_id" in provdict:
act_id = default_ns + ":" + "_".join(
[sess_id,
str(provdict.pop("activity_id")).replace("-", "")])
if act_id in records:
act = records[act_id]
else:
act = pdoc.activity(act_id)
records[act_id] = act
# activity name
if "name" in provdict:
act.add_attributes({"prov:label": provdict.pop("name")})
# activity start
if "startTime" in provdict:
act.set_time(startTime=datetime.datetime.fromisoformat(
provdict.pop("startTime")))
# activity end
if "endTime" in provdict:
act.set_time(endTime=datetime.datetime.fromisoformat(
provdict.pop("endTime")))
# in session?
# if "in_session" in provdict:
# sess_qid = default_ns + ":" + str(provdict.pop("in_session"])
# pdoc.wasInfluencedBy(
# act_id, sess_id
# ) # , other_attributes={'prov:type': "Context"})
# activity configuration
if "agent_name" in provdict:
agent_id = str(provdict.pop("agent_name"))
if ":" not in agent_id:
agent_id = default_ns + ":" + agent_id
else:
new_ns = agent_id.split(":").pop(0)
pdoc.add_namespace(new_ns, new_ns + ":")
if agent_id in records:
agent = records[agent_id]
else:
agent = pdoc.agent(agent_id)
records[agent_id] = agent
act.wasAssociatedWith(agent,
attributes={"prov:role": "Operator"})
if "parameters" in provdict:
params_record = provdict.pop("parameters")
params = {k: str(params_record[k]) for k in params_record}
# par_id = act_id + "_parameters"
# par = pdoc.entity(par_id, other_attributes=params)
# par.add_attributes({"prov:type": "Parameters"})
# par.add_attributes({"prov:label": "WasConfiguredBy"})
# act.used(par, attributes={"prov:type": "Setup"})
for name, value in params.items():
value_short = str(value)[:20]
if len(value_short) == 20:
value_short += "..."
par = pdoc.entity(act_id + "_" + name)
par.add_attributes(
{"prov:label": name + " = " + value_short})
par.add_attributes({"prov:type": "voprov:Parameter"})
par.add_attributes({"voprov:name": name})
par.add_attributes({"prov:value": value_short})
act.used(par, attributes={"prov:type": "Setup"})
# usage
if "used_id" in provdict:
ent_id = str(provdict.pop("used_id"))
if ":" not in ent_id:
ent_id = default_ns + ":" + "_".join([sess_id, ent_id])
else:
new_ns = ent_id.split(":").pop(0)
pdoc.add_namespace(new_ns, new_ns + ":")
if ent_id in records:
ent = records[ent_id]
else:
ent = pdoc.entity(ent_id)
records[ent_id] = ent
rol = provdict.pop("used_role", None)
# if rol:
# ent.add_attributes({'prov:label': rol})
act.used(ent, attributes={"prov:role": rol})
# generation
if "generated_id" in provdict:
ent_id = str(provdict.pop("generated_id"))
if ":" not in ent_id:
ent_id = default_ns + ":" + "_".join([sess_id, ent_id])
else:
new_ns = ent_id.split(":").pop(0)
pdoc.add_namespace(new_ns, new_ns + ":")
if ent_id in records:
ent = records[ent_id]
else:
ent = pdoc.entity(ent_id)
records[ent_id] = ent
rol = provdict.pop("generated_role", None)
# if rol:
# ent.add_attributes({'prov:label': rol})
ent.wasGeneratedBy(act, attributes={"prov:role": rol})
for k, v in provdict.items():
act.add_attributes({k: str(v)})
# entity
if "entity_id" in provdict:
ent_id = str(provdict.pop("entity_id"))
label = ""
if ":" not in ent_id:
ent_id = default_ns + ":" + "_".join([sess_id, ent_id])
else:
new_ns = ent_id.split(":").pop(0)
pdoc.add_namespace(new_ns, new_ns + ":")
if ent_id in records:
ent = records[ent_id]
else:
ent = pdoc.entity(ent_id)
records[ent_id] = ent
if "name" in provdict:
label = provdict.pop("name")
ent.add_attributes({"voprov:name": label})
if "entity_description" in provdict:
label = provdict.pop("entity_description")
ent.add_attributes({"voprov:entity_description": label})
if "type" in provdict:
ent.add_attributes({"prov:type": provdict.pop("type")})
if "value" in provdict:
value_short = str(provdict.pop("value"))[:20]
if len(value_short) == 20:
value_short += "..."
ent.add_attributes({"prov:value": value_short})
if "location" in provdict:
location = str(provdict.pop("location"))
ent.add_attributes({"prov:location": location})
if label:
label = label + " in " + location
if label:
ent.add_attributes({"prov:label": label})
if "generated_time" in provdict:
ent.add_attributes({
"prov:generatedAtTime":
str(provdict.pop("generated_time"))
})
# member
if "member_id" in provdict:
mem_id = str(provdict.pop("member_id"))
if ":" not in mem_id:
mem_id = default_ns + ":" + "_".join([sess_id, mem_id])
else:
new_ns = mem_id.split(":").pop(0)
pdoc.add_namespace(new_ns, new_ns + ":")
if mem_id in records:
mem = records[mem_id]
else:
mem = pdoc.entity(mem_id)
records[mem_id] = mem
ent.hadMember(mem)
if "progenitor_id" in provdict:
progen_id = str(provdict.pop("progenitor_id"))
if ":" not in progen_id:
progen_id = default_ns + ":" + "_".join(
[sess_id, progen_id])
else:
new_ns = progen_id.split(":").pop(0)
pdoc.add_namespace(new_ns, new_ns + ":")
if progen_id in records:
progen = records[progen_id]
else:
progen = pdoc.entity(progen_id)
records[progen_id] = progen
ent.wasDerivedFrom(progen)
for k, v in provdict.items():
ent.add_attributes({k: str(v)})
# agent
return pdoc
class Provenance(object):
def __init__(self, output_dir):
self.output_dir = output_dir
self.doc = None
self.workflow = None
def start(self, workflow=False):
from daops import __version__ as daops_version
from housemartin import __version__ as housemartin_version
self.doc = ProvDocument()
# Declaring namespaces for various prefixes
self.doc.set_default_namespace(uri="http://purl.org/roocs/prov#")
self.doc.add_namespace("prov", uri="http://www.w3.org/ns/prov#")
self.doc.add_namespace(
"provone", uri="http://purl.dataone.org/provone/2015/01/15/ontology#"
)
self.doc.add_namespace("dcterms", uri="http://purl.org/dc/terms/")
# Define entities
project_cds = self.doc.agent(
":copernicus_CDS",
{
"prov:type": "prov:Organization",
"dcterms:title": "Copernicus Climate Data Store",
},
)
self.sw_housemartin = self.doc.agent(
":housemartin",
{
"prov:type": "prov:SoftwareAgent",
"dcterms:source": f"https://github.com/cedadev/housemartin/releases/tag/v{housemartin_version}",
},
)
self.doc.wasAttributedTo(self.sw_housemartin, project_cds)
self.sw_daops = self.doc.agent(
":daops",
{
"prov:type": "prov:SoftwareAgent",
"dcterms:source": f"https://github.com/roocs/daops/releases/tag/v{daops_version}",
},
)
# workflow
if workflow is True:
self.workflow = self.doc.entity(
":workflow", {"prov:type": "provone:Workflow"}
)
orchestrate = self.doc.activity(
":orchestrate",
other_attributes={
"prov:startedAtTime": "2020-11-26T09:15:00",
"prov:endedAtTime": "2020-11-26T09:30:00",
},
)
self.doc.wasAssociatedWith(
orchestrate, agent=self.sw_housemartin, plan=self.workflow
)
def add_operator(self, operator, parameters, collection, output):
op = self.doc.activity(
f":{operator}",
other_attributes={
":time": parameters.get("time"),
":apply_fixes": parameters.get("apply_fixes"),
},
)
# input data
ds_in = os.path.basename(collection[0])
# ds_in_attrs = {
# 'prov:type': 'provone:Data',
# 'prov:value': f'{ds_in}',
# }
op_in = self.doc.entity(f":{ds_in}")
# operator started by daops
if self.workflow:
self.doc.wasAssociatedWith(op, agent=self.sw_daops, plan=self.workflow)
else:
self.doc.start(op, starter=self.sw_daops, trigger=self.sw_housemartin)
# Generated output file
ds_out = os.path.basename(output[0])
# ds_out_attrs = {
# 'prov:type': 'provone:Data',
# 'prov:value': f'{ds_out}',
# }
op_out = self.doc.entity(f":{ds_out}")
self.doc.wasDerivedFrom(op_out, op_in, activity=op)
def write_json(self):
outfile = os.path.join(self.output_dir, "provenance.json")
self.doc.serialize(outfile, format="json")
return outfile
def write_png(self):
outfile = os.path.join(self.output_dir, "provenance.png")
figure = prov_to_dot(self.doc)
figure.write_png(outfile)
return outfile
class LogProv():
def __init__(self, log_dic):
self._prov_doc = ProvDocument()
vre_namespace = self._prov_doc.add_namespace(
'vre', 'https://www.vre4eic.eu/log#')
prov_namespace = self._prov_doc.add_namespace(
'prov', 'http://www.w3.org/ns/prov#')
if ('request_url_username' in log_dic
and log_dic['request_url_username']):
remote_host = self._prov_doc.agent(
vre_namespace['ag1'], {
prov_namespace['type']: PROV["SoftwareAgent"],
vre_namespace['hasIP']: log_dic['remote_host'],
vre_namespace['hasUsername']:
log_dic['request_url_username']
})
else:
remote_host = self._prov_doc.agent(
vre_namespace['ag1'], {
prov_namespace['type']: PROV["SoftwareAgent"],
vre_namespace['hasIP']: log_dic['remote_host']
})
if ('request_url_hostname' in log_dic
and log_dic['request_url_hostname']):
request_hostname = self._prov_doc.agent(
vre_namespace['ag2'], {
prov_namespace['type']: PROV["SoftwareAgent"],
vre_namespace['hasIP']: log_dic['remote_host']
})
request_entity = self._prov_doc.entity(
vre_namespace['en1'], {
vre_namespace['status']: log_dic['status'],
vre_namespace['responseBytes']: log_dic['response_bytes_clf']
})
received_activity = self._prov_doc.activity(
vre_namespace['ac1'],
other_attributes={
vre_namespace['requestURL']: log_dic['request_url'],
vre_namespace['requestMethod']: log_dic['request_method'],
vre_namespace['httpVersion']: log_dic['request_http_ver']
})
self._prov_doc.generation(remote_host,
activity=received_activity,
time=log_dic['time_received_tz_isoformat'])
self._prov_doc.wasAttributedTo(request_entity, received_activity)
self._prov_doc.wasAssociatedWith(received_activity, remote_host)
@property
def prov_doc(self):
return self._prov_doc
@prov_doc.setter
def prov_doc(self, value):
self._prov_doc = value
@prov_doc.deleter
def prov_doc(self):
del self._prov_doc
def w3c_publication_1():
# https://github.com/lucmoreau/ProvToolbox/blob/master/asn/src/test/resources/prov/w3c-publication1.prov-asn
# ===========================================================================
# bundle
#
# prefix ex <http://example.org/>
#
# prefix w3 <http://www.w3.org/>
# prefix tr <http://www.w3.org/TR/2011/>
# prefix process <http://www.w3.org/2005/10/Process-20051014/tr.html#>
# prefix email <https://lists.w3.org/Archives/Member/w3c-archive/>
# prefix chairs <https://lists.w3.org/Archives/Member/chairs/>
# prefix trans <http://www.w3.org/2005/08/01-transitions.html#>
# prefix rec54 <http://www.w3.org/2001/02pd/rec54#>
#
#
# entity(tr:WD-prov-dm-20111018, [ prov:type='rec54:WD' ])
# entity(tr:WD-prov-dm-20111215, [ prov:type='rec54:WD' ])
# entity(process:rec-advance, [ prov:type='prov:Plan' ])
#
#
# entity(chairs:2011OctDec/0004, [ prov:type='trans:transreq' ])
# entity(email:2011Oct/0141, [ prov:type='trans:pubreq' ])
# entity(email:2011Dec/0111, [ prov:type='trans:pubreq' ])
#
#
# wasDerivedFrom(tr:WD-prov-dm-20111215, tr:WD-prov-dm-20111018)
#
#
# activity(ex:act1,-,-,[prov:type="publish"])
# activity(ex:act2,-,-,[prov:type="publish"])
#
# wasGeneratedBy(tr:WD-prov-dm-20111018, ex:act1, -)
# wasGeneratedBy(tr:WD-prov-dm-20111215, ex:act2, -)
#
# used(ex:act1, chairs:2011OctDec/0004, -)
# used(ex:act1, email:2011Oct/0141, -)
# used(ex:act2, email:2011Dec/0111, -)
#
# agent(w3:Consortium, [ prov:type='prov:Organization' ])
#
# wasAssociatedWith(ex:act1, w3:Consortium, process:rec-advance)
# wasAssociatedWith(ex:act2, w3:Consortium, process:rec-advance)
#
# endBundle
# ===========================================================================
g = ProvDocument()
g.add_namespace("ex", "http://example.org/")
g.add_namespace("w3", "http://www.w3.org/")
g.add_namespace("tr", "http://www.w3.org/TR/2011/")
g.add_namespace("process",
"http://www.w3.org/2005/10/Process-20051014/tr.html#")
g.add_namespace("email",
"https://lists.w3.org/Archives/Member/w3c-archive/")
g.add_namespace("chairs", "https://lists.w3.org/Archives/Member/chairs/")
g.add_namespace("trans", "http://www.w3.org/2005/08/01-transitions.html#")
g.add_namespace("rec54", "http://www.w3.org/2001/02pd/rec54#")
g.entity("tr:WD-prov-dm-20111018", {"prov:type": "rec54:WD"})
g.entity("tr:WD-prov-dm-20111215", {"prov:type": "rec54:WD"})
g.entity("process:rec-advance", {"prov:type": "prov:Plan"})
g.entity("chairs:2011OctDec/0004", {"prov:type": "trans:transreq"})
g.entity("email:2011Oct/0141", {"prov:type": "trans:pubreq"})
g.entity("email:2011Dec/0111", {"prov:type": "trans:pubreq"})
g.wasDerivedFrom("tr:WD-prov-dm-20111215", "tr:WD-prov-dm-20111018")
g.activity("ex:act1", other_attributes={"prov:type": "publish"})
g.activity("ex:act2", other_attributes={"prov:type": "publish"})
g.wasGeneratedBy("tr:WD-prov-dm-20111018", "ex:act1")
g.wasGeneratedBy("tr:WD-prov-dm-20111215", "ex:act2")
g.used("ex:act1", "chairs:2011OctDec/0004")
g.used("ex:act1", "email:2011Oct/0141")
g.used("ex:act2", "email:2011Dec/0111")
g.agent("w3:Consortium", other_attributes={"prov:type": "Organization"})
g.wasAssociatedWith("ex:act1", "w3:Consortium", "process:rec-advance")
g.wasAssociatedWith("ex:act2", "w3:Consortium", "process:rec-advance")
return g
def example():
g = ProvDocument()
# Local namespace
# Doesnt exist yet so we are creating it
ap = Namespace('aip', 'https://araport.org/provenance/')
# Dublin Core
g.add_namespace("dcterms", "http://purl.org/dc/terms/")
# FOAF
g.add_namespace("foaf", "http://xmlns.com/foaf/0.1/")
# Add sponsors and contributors as Agents
# ap['matthew_vaughn']
# aip:matthew_vaughn
# https://araport.org/provenance/:matthew_vaughn
# Learn this from a call to profiles service? Adds a dependency on Agave so I am open to figuring out another way
me = g.agent(
ap['matthew_vaughn'], {
'prov:type': PROV["Person"],
'foaf:givenName': "Matthew Vaughn",
'foaf:mbox': "<mailto:[email protected]>"
})
# Hard coded for now
walter = g.agent(
ap['walter_moreira'], {
'prov:type': PROV["Person"],
'foaf:givenName': "Walter Moreira",
'foaf:mbox': "<mailto:[email protected]>"
})
utexas = g.agent(
ap['university_of_texas'], {
'prov:type': PROV["Organization"],
'foaf:givenName': "University of Texas at Austin"
})
# Set delegation to our host University
# We may have trouble doing this for other users since we don't always capture their host instituion
g.actedOnBehalfOf(walter, utexas)
g.actedOnBehalfOf(me, utexas)
# Include the ADAMA platform as an Agent and set attribution
# dcterms:title and dcterms:description are hardcoded
# dcterms:language is hard-coded
# dcterms:source is the URI of the public git source repository for ADAMA
# "dcterms:updated": "2015-04-17T09:44:56" - this would actually be the date ADAMA was updated
adama_platform = g.agent(
ap['adama_platform'], {
'dcterms:title': "ADAMA",
'dcterms:description': "Araport Data and Microservices API",
'dcterms:language': "en-US",
'dcterms:identifier': "https://api.araport.org/community/v0.3/",
'dcterms:updated': "2015-04-17T09:44:56"
})
g.wasGeneratedBy(adama_platform, walter)
# Include the ADAMA microservice as an Agent and set attribution+delegation
# dcterms:title and dcterms:description are inherited from the service's metadata
# dcterms:language is hard-coded
# dcterms:identifier is the deployment URI for the service
# dcterms:source is the URI of the public git source repository. The URL in this example is just a dummy
#
# The name for each microservice should be unique. We've decided to
# use the combination of namespace, service name, and version
microservice_name = 'mwvaughn/bar_annotation_v1.0.0'
adama_microservice = g.agent(
ap[microservice_name], {
'dcterms:title':
"BAR Annotation Service",
'dcterms:description':
"Returns annotation from locus ID",
'dcterms:language':
"en-US",
'dcterms:identifier':
"https://api.araport.org/community/v0.3/mwvaughn/bar_annotation_v1.0.0",
'dcterms:source':
"https://github.com/Arabidopsis-Information-Portal/prov-enabled-api-sample"
})
# the microservice was generated by me on date X (don't use now, use when the service was updated)
g.wasGeneratedBy(adama_microservice, me, datetime.datetime.now())
# The microservice used the platform now
g.used(adama_microservice, adama_platform, datetime.datetime.now())
# Sources
#
# Define BAR
# Agents
nick = g.agent(
ap['nicholas_provart'], {
'prov:type': PROV["Person"],
'foaf:givenName': "Nicholas Provart",
'foaf:mbox': "*****@*****.**"
})
utoronto = g.agent(
ap['university_of_toronto'], {
'prov:type': PROV["Organization"],
'foaf:givenName': "University of Toronto",
'dcterms:identifier': "http://www.utoronto.ca/"
})
g.actedOnBehalfOf(nick, utoronto)
# Entity
# All fields derived from Sources.yml
# dcterms:title and dcterms:description come straight from the YAML
# dcterms:identifier - URI pointing to the source's canonical URI representation
# optional - dcterms:language: Recommended best practice is to use a controlled vocabulary such as RFC 4646
# optional - dcterms:updated: date the source was published or last updated
# optional - dcterms:license: Simple string or URI to license. Validate URI if provided?
datasource1 = g.entity(
ap['datasource1'], {
'dcterms:title': "BAR Arabidopsis AGI -> Annotation",
'dcterms:description': "Most recent annotation for given AGI",
'dcterms:language': "en-US",
'dcterms:identifier':
"http://bar.utoronto.ca/webservices/agiToAnnot.php",
'dcterms:updated': "2015-04-17T09:44:56",
'dcterms:license': "Creative Commons 3.0"
})
# Set up attribution to Nick
g.wasAttributedTo(datasource1, nick)
# Define TAIR
# Agents
# dcterms:language: Recommended best practice is to use a controlled vocabulary such as RFC 4646
eva = g.agent(ap['eva_huala'], {
'prov:type': PROV["Person"],
'foaf:givenName': "Eva Huala"
})
phoenix = g.agent(
ap['phoenix_bioinformatics'], {
'prov:type': PROV["Organization"],
'foaf:givenName': "Phoenix Bioinformatics"
})
g.actedOnBehalfOf(eva, phoenix)
# Entity
# All fields derived from Sources.yml
# optional - dcterms:citation: Plain text bibliographic citation. If only provided as doi, should we try to validate it?
datasource2 = g.entity(
ap['datasource2'], {
'dcterms:title':
"TAIR",
'dcterms:description':
"The Arabidopsis Information Resource",
'dcterms:language':
"en-US",
'dcterms:identifier':
"https://www.arabidopsis.org/",
'dcterms:citation':
"The Arabidopsis Information Resource (TAIR): improved gene annotation and new tools. Nucleic Acids Research 2011 doi: 10.1093/nar/gkr1090"
})
g.wasAttributedTo(datasource2, eva)
# In Sources.yml, these two sources are nested. Define that relationship here
# There are other types of relationships but we will just use derived from for simplicity in this prototype
g.wasDerivedFrom(ap['datasource1'], ap['datasource2'])
# Depending on which ADAMA microservice type we are using, define an activity
# Eventually, break these into more atomic actions in a chain
action1 = g.activity(ap['do_query'], datetime.datetime.now())
# action1 = g.activity(ap['do_map'], datetime.datetime.now())
# action1 = g.activity(ap['do_generic'], datetime.datetime.now())
# action1 = g.activity(ap['do_passthrough'], datetime.datetime.now())
# Future... Support for ADAMA-native microservices
# action1 = g.activity(ap['generate'], datetime.datetime.now())
# Define current ADAMA response as an Entity
# This is what's being returned to the user and is thus the subject of the PROV record
# May be able to add more attributes to it but this is the minimum
response = g.entity(ap['adama_response'])
# Response is generated by the process_query action
# Time-stamp it!
g.wasGeneratedBy(response, ap['do_query'], datetime.datetime.now())
# The process_query used the microservice
g.used(ap['do_query'], adama_microservice, datetime.datetime.now())
# The microservice used datasource1
g.used(adama_microservice, datasource1, datetime.datetime.now())
# Print prov_n
print(g.get_provn())
# Print prov-json
print(g.serialize())
# Write out as a pretty picture
graph = prov.dot.prov_to_dot(g)
graph.write_png('Sources.png')
def primer_example():
# https://github.com/lucmoreau/ProvToolbox/blob/master/prov-n/src/test/resources/prov/primer.pn
# ===========================================================================
# document
g = ProvDocument()
# prefix ex <http://example/>
# prefix dcterms <http://purl.org/dc/terms/>
# prefix foaf <http://xmlns.com/foaf/0.1/>
ex = Namespace(
"ex", "http://example/"
) # namespaces do not need to be explicitly added to a document
g.add_namespace("dcterms", "http://purl.org/dc/terms/")
g.add_namespace("foaf", "http://xmlns.com/foaf/0.1/")
# entity(ex:article, [dcterms:title="Crime rises in cities"])
# first time the ex namespace was used, it is added to the document automatically
g.entity(ex["article"], {"dcterms:title": "Crime rises in cities"})
# entity(ex:articleV1)
g.entity(ex["articleV1"])
# entity(ex:articleV2)
g.entity(ex["articleV2"])
# entity(ex:dataSet1)
g.entity(ex["dataSet1"])
# entity(ex:dataSet2)
g.entity(ex["dataSet2"])
# entity(ex:regionList)
g.entity(ex["regionList"])
# entity(ex:composition)
g.entity(ex["composition"])
# entity(ex:chart1)
g.entity(ex["chart1"])
# entity(ex:chart2)
g.entity(ex["chart2"])
# entity(ex:blogEntry)
g.entity(ex["blogEntry"])
# activity(ex:compile)
g.activity(
"ex:compile") # since ex is registered, it can be used like this
# activity(ex:compile2)
g.activity("ex:compile2")
# activity(ex:compose)
g.activity("ex:compose")
# activity(ex:correct, 2012-03-31T09:21:00, 2012-04-01T15:21:00)
g.activity("ex:correct", "2012-03-31T09:21:00",
"2012-04-01T15:21:00") # date time can be provided as strings
# activity(ex:illustrate)
g.activity("ex:illustrate")
# used(ex:compose, ex:dataSet1, -, [ prov:role = "ex:dataToCompose"])
g.used("ex:compose",
"ex:dataSet1",
other_attributes={"prov:role": "ex:dataToCompose"})
# used(ex:compose, ex:regionList, -, [ prov:role = "ex:regionsToAggregateBy"])
g.used(
"ex:compose",
"ex:regionList",
other_attributes={"prov:role": "ex:regionsToAggregateBy"},
)
# wasGeneratedBy(ex:composition, ex:compose, -)
g.wasGeneratedBy("ex:composition", "ex:compose")
# used(ex:illustrate, ex:composition, -)
g.used("ex:illustrate", "ex:composition")
# wasGeneratedBy(ex:chart1, ex:illustrate, -)
g.wasGeneratedBy("ex:chart1", "ex:illustrate")
# wasGeneratedBy(ex:chart1, ex:compile, 2012-03-02T10:30:00)
g.wasGeneratedBy("ex:chart1", "ex:compile", "2012-03-02T10:30:00")
# wasGeneratedBy(ex:chart2, ex:compile2, 2012-04-01T15:21:00)
#
#
# agent(ex:derek, [ prov:type="prov:Person", foaf:givenName = "Derek",
# foaf:mbox= "<mailto:[email protected]>"])
g.agent(
"ex:derek",
{
"prov:type": PROV["Person"],
"foaf:givenName": "Derek",
"foaf:mbox": "<mailto:[email protected]>",
},
)
# wasAssociatedWith(ex:compose, ex:derek, -)
g.wasAssociatedWith("ex:compose", "ex:derek")
# wasAssociatedWith(ex:illustrate, ex:derek, -)
g.wasAssociatedWith("ex:illustrate", "ex:derek")
#
# agent(ex:chartgen, [ prov:type="prov:Organization",
# foaf:name = "Chart Generators Inc"])
g.agent(
"ex:chartgen",
{
"prov:type": PROV["Organization"],
"foaf:name": "Chart Generators Inc"
},
)
# actedOnBehalfOf(ex:derek, ex:chartgen, ex:compose)
g.actedOnBehalfOf("ex:derek", "ex:chartgen", "ex:compose")
# wasAttributedTo(ex:chart1, ex:derek)
g.wasAttributedTo("ex:chart1", "ex:derek")
# wasGeneratedBy(ex:dataSet2, ex:correct, -)
g.wasGeneratedBy("ex:dataSet2", "ex:correct")
# used(ex:correct, ex:dataSet1, -)
g.used("ex:correct", "ex:dataSet1")
# wasDerivedFrom(ex:dataSet2, ex:dataSet1, [prov:type='prov:Revision'])
g.wasDerivedFrom("ex:dataSet2",
"ex:dataSet1",
other_attributes={"prov:type": PROV["Revision"]})
# wasDerivedFrom(ex:chart2, ex:dataSet2)
g.wasDerivedFrom("ex:chart2", "ex:dataSet2")
# wasDerivedFrom(ex:blogEntry, ex:article, [prov:type='prov:Quotation'])
g.wasDerivedFrom("ex:blogEntry",
"ex:article",
other_attributes={"prov:type": PROV["Quotation"]})
# specializationOf(ex:articleV1, ex:article)
g.specializationOf("ex:articleV1", "ex:article")
# wasDerivedFrom(ex:articleV1, ex:dataSet1)
g.wasDerivedFrom("ex:articleV1", "ex:dataSet1")
# specializationOf(ex:articleV2, ex:article)
g.specializationOf("ex:articleV2", "ex:article")
# wasDerivedFrom(ex:articleV2, ex:dataSet2)
g.wasDerivedFrom("ex:articleV2", "ex:dataSet2")
# alternateOf(ex:articleV2, ex:articleV1)
g.alternateOf("ex:articleV2", "ex:articleV1")
# endDocument
return g
def primer_example_alternate():
g = ProvDocument(
namespaces={
'ex': 'http://example/',
'dcterms': 'http://purl.org/dc/terms/',
'foaf': 'http://xmlns.com/foaf/0.1/'
})
article = g.entity('ex:article',
{'dcterms:title': "Crime rises in cities"})
articleV1 = g.entity('ex:articleV1')
articleV2 = g.entity('ex:articleV2')
dataSet1 = g.entity('ex:dataSet1')
dataSet2 = g.entity('ex:dataSet2')
regionList = g.entity('ex:regionList')
composition = g.entity('ex:composition')
chart1 = g.entity('ex:chart1')
chart2 = g.entity('ex:chart2')
blogEntry = g.entity('ex:blogEntry')
compile = g.activity('ex:compile')
compile2 = g.activity('ex:compile2')
compose = g.activity('ex:compose')
correct = g.activity('ex:correct', '2012-03-31T09:21:00',
'2012-04-01T15:21:00')
illustrate = g.activity('ex:illustrate')
compose.used(dataSet1, attributes={'prov:role': "ex:dataToCompose"})
compose.used(regionList,
attributes={'prov:role': "ex:regionsToAggregateBy"})
composition.wasGeneratedBy(compose)
illustrate.used(composition)
chart1.wasGeneratedBy(illustrate)
chart1.wasGeneratedBy(compile, '2012-03-02T10:30:00')
derek = g.agent(
'ex:derek', {
'prov:type': PROV['Person'],
'foaf:givenName': "Derek",
'foaf:mbox': "<mailto:[email protected]>"
})
compose.wasAssociatedWith(derek)
illustrate.wasAssociatedWith(derek)
chartgen = g.agent('ex:chartgen', {
'prov:type': PROV["Organization"],
'foaf:name': "Chart Generators Inc"
})
derek.actedOnBehalfOf(chartgen, compose)
chart1.wasAttributedTo(derek)
dataSet2.wasGeneratedBy(correct)
correct.used(dataSet1)
dataSet2.wasDerivedFrom(dataSet1,
attributes={'prov:type': PROV['Revision']})
chart2.wasDerivedFrom(dataSet2)
blogEntry.wasDerivedFrom(article,
attributes={'prov:type': PROV['Quotation']})
articleV1.specializationOf(article)
articleV1.wasDerivedFrom(dataSet1)
articleV2.specializationOf(article)
articleV2.wasDerivedFrom(dataSet2)
articleV2.alternateOf(articleV1)
return g
class NIDMExporter():
"""
Generic class to parse a result directory to extract the pieces of
information to be stored in NIDM-Results and to generate a NIDM-Results
export.
"""
def __init__(self, version, out_dir, zipped=True):
out_dirname = os.path.basename(out_dir)
out_path = os.path.dirname(out_dir)
# Create output path from output name
self.zipped = zipped
if not self.zipped:
out_dirname = out_dirname + ".nidm"
else:
out_dirname = out_dirname + ".nidm.zip"
out_dir = os.path.join(out_path, out_dirname)
# Quit if output path already exists and user doesn't want to overwrite
# it
if os.path.exists(out_dir):
msg = out_dir + " already exists, overwrite?"
if not input("%s (y/N) " % msg).lower() == 'y':
quit("Bye.")
if os.path.isdir(out_dir):
shutil.rmtree(out_dir)
else:
os.remove(out_dir)
self.out_dir = out_dir
if version == "dev":
self.version = {
'major': 10000,
'minor': 0,
'revision': 0,
'num': version
}
else:
major, minor, revision = version.split(".")
if "-rc" in revision:
revision, rc = revision.split("-rc")
else:
rc = -1
self.version = {
'major': int(major),
'minor': int(minor),
'revision': int(revision),
'rc': int(rc),
'num': version
}
# Initialise prov document
self.doc = ProvDocument()
self._add_namespaces()
# A temp directory that will contain the exported data
self.export_dir = tempfile.mkdtemp(prefix="nidm-", dir=out_path)
self.prepend_path = ''
def parse(self):
"""
Parse a result directory to extract the pieces information to be
stored in NIDM-Results.
"""
try:
# Methods: find_software, find_model_fitting, find_contrasts and
# find_inferences should be defined in the children classes and
# return a list of NIDM Objects as specified in the objects module
# Object of type Software describing the neuroimaging software
# package used for the analysis
self.software = self._find_software()
# List of objects of type ModelFitting describing the
# model fitting step in NIDM-Results (main activity: Model
# Parameters Estimation)
self.model_fittings = self._find_model_fitting()
# Dictionary of (key, value) pairs where where key is a tuple
# containing the identifier of a ModelParametersEstimation object
# and a tuple of identifiers of ParameterEstimateMap objects and
# value is an object of type Contrast describing the contrast
# estimation step in NIDM-Results (main activity: Contrast
# Estimation)
self.contrasts = self._find_contrasts()
# Inference activity and entities
# Dictionary of (key, value) pairs where key is the identifier of a
# ContrastEstimation object and value is an object of type
# Inference describing the inference step in NIDM-Results (main
# activity: Inference)
self.inferences = self._find_inferences()
except Exception:
self.cleanup()
raise
def cleanup(self):
if os.path.isdir(self.export_dir):
shutil.rmtree(self.export_dir)
def add_object(self, nidm_object, export_file=True):
"""
Add a NIDMObject to a NIDM-Results export.
"""
if not export_file:
export_dir = None
else:
export_dir = self.export_dir
if not isinstance(nidm_object, NIDMFile):
nidm_object.export(self.version, export_dir)
else:
nidm_object.export(self.version, export_dir, self.prepend_path)
# ProvDocument: add object to the bundle
if nidm_object.prov_type == PROV['Activity']:
self.bundle.activity(nidm_object.id,
other_attributes=nidm_object.attributes)
elif nidm_object.prov_type == PROV['Entity']:
self.bundle.entity(nidm_object.id,
other_attributes=nidm_object.attributes)
elif nidm_object.prov_type == PROV['Agent']:
self.bundle.agent(nidm_object.id,
other_attributes=nidm_object.attributes)
# self.bundle.update(nidm_object.p)
def export(self):
"""
Generate a NIDM-Results export.
"""
try:
if not os.path.isdir(self.export_dir):
os.mkdir(self.export_dir)
# Initialise main bundle
self._create_bundle(self.version)
self.add_object(self.software)
# Add model fitting steps
if not isinstance(self.model_fittings, list):
self.model_fittings = list(self.model_fittings.values())
for model_fitting in self.model_fittings:
# Design Matrix
# model_fitting.activity.used(model_fitting.design_matrix)
self.bundle.used(model_fitting.activity.id,
model_fitting.design_matrix.id)
self.add_object(model_fitting.design_matrix)
# *** Export visualisation of the design matrix
self.add_object(model_fitting.design_matrix.image)
if model_fitting.design_matrix.image.file is not None:
self.add_object(model_fitting.design_matrix.image.file)
if model_fitting.design_matrix.hrf_models is not None:
# drift model
self.add_object(model_fitting.design_matrix.drift_model)
if self.version['major'] > 1 or \
(self.version['major'] == 1 and
self.version['minor'] >= 3):
# Machine
# model_fitting.data.wasAttributedTo(model_fitting.machine)
self.bundle.wasAttributedTo(model_fitting.data.id,
model_fitting.machine.id)
self.add_object(model_fitting.machine)
# Imaged subject or group(s)
for sub in model_fitting.subjects:
self.add_object(sub)
# model_fitting.data.wasAttributedTo(sub)
self.bundle.wasAttributedTo(model_fitting.data.id,
sub.id)
# Data
# model_fitting.activity.used(model_fitting.data)
self.bundle.used(model_fitting.activity.id,
model_fitting.data.id)
self.add_object(model_fitting.data)
# Error Model
# model_fitting.activity.used(model_fitting.error_model)
self.bundle.used(model_fitting.activity.id,
model_fitting.error_model.id)
self.add_object(model_fitting.error_model)
# Parameter Estimate Maps
for param_estimate in model_fitting.param_estimates:
# param_estimate.wasGeneratedBy(model_fitting.activity)
self.bundle.wasGeneratedBy(param_estimate.id,
model_fitting.activity.id)
self.add_object(param_estimate)
self.add_object(param_estimate.coord_space)
self.add_object(param_estimate.file)
if param_estimate.derfrom is not None:
self.bundle.wasDerivedFrom(param_estimate.id,
param_estimate.derfrom.id)
self.add_object(param_estimate.derfrom)
self.add_object(param_estimate.derfrom.file,
export_file=False)
# Residual Mean Squares Map
# model_fitting.rms_map.wasGeneratedBy(model_fitting.activity)
self.add_object(model_fitting.rms_map)
self.bundle.wasGeneratedBy(model_fitting.rms_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.rms_map.coord_space)
self.add_object(model_fitting.rms_map.file)
if model_fitting.rms_map.derfrom is not None:
self.bundle.wasDerivedFrom(
model_fitting.rms_map.id,
model_fitting.rms_map.derfrom.id)
self.add_object(model_fitting.rms_map.derfrom)
self.add_object(model_fitting.rms_map.derfrom.file,
export_file=False)
# Resels per Voxel Map
if model_fitting.rpv_map is not None:
self.add_object(model_fitting.rpv_map)
self.bundle.wasGeneratedBy(model_fitting.rpv_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.rpv_map.coord_space)
self.add_object(model_fitting.rpv_map.file)
if model_fitting.rpv_map.inf_id is not None:
self.bundle.used(model_fitting.rpv_map.inf_id,
model_fitting.rpv_map.id)
if model_fitting.rpv_map.derfrom is not None:
self.bundle.wasDerivedFrom(
model_fitting.rpv_map.id,
model_fitting.rpv_map.derfrom.id)
self.add_object(model_fitting.rpv_map.derfrom)
self.add_object(model_fitting.rpv_map.derfrom.file,
export_file=False)
# Mask
# model_fitting.mask_map.wasGeneratedBy(model_fitting.activity)
self.bundle.wasGeneratedBy(model_fitting.mask_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.mask_map)
if model_fitting.mask_map.derfrom is not None:
self.bundle.wasDerivedFrom(
model_fitting.mask_map.id,
model_fitting.mask_map.derfrom.id)
self.add_object(model_fitting.mask_map.derfrom)
self.add_object(model_fitting.mask_map.derfrom.file,
export_file=False)
# Create coordinate space export
self.add_object(model_fitting.mask_map.coord_space)
# Create "Mask map" entity
self.add_object(model_fitting.mask_map.file)
# Grand Mean map
# model_fitting.grand_mean_map.wasGeneratedBy(model_fitting.activity)
self.bundle.wasGeneratedBy(model_fitting.grand_mean_map.id,
model_fitting.activity.id)
self.add_object(model_fitting.grand_mean_map)
# Coordinate space entity
self.add_object(model_fitting.grand_mean_map.coord_space)
# Grand Mean Map entity
self.add_object(model_fitting.grand_mean_map.file)
# Model Parameters Estimation activity
self.add_object(model_fitting.activity)
self.bundle.wasAssociatedWith(model_fitting.activity.id,
self.software.id)
# model_fitting.activity.wasAssociatedWith(self.software)
# self.add_object(model_fitting)
# Add contrast estimation steps
analysis_masks = dict()
for (model_fitting_id,
pe_ids), contrasts in list(self.contrasts.items()):
for contrast in contrasts:
model_fitting = self._get_model_fitting(model_fitting_id)
# for contrast in contrasts:
# contrast.estimation.used(model_fitting.rms_map)
self.bundle.used(contrast.estimation.id,
model_fitting.rms_map.id)
# contrast.estimation.used(model_fitting.mask_map)
self.bundle.used(contrast.estimation.id,
model_fitting.mask_map.id)
analysis_masks[contrast.estimation.id] = \
model_fitting.mask_map.id
self.bundle.used(contrast.estimation.id,
contrast.weights.id)
self.bundle.used(contrast.estimation.id,
model_fitting.design_matrix.id)
# contrast.estimation.wasAssociatedWith(self.software)
self.bundle.wasAssociatedWith(contrast.estimation.id,
self.software.id)
for pe_id in pe_ids:
# contrast.estimation.used(pe_id)
self.bundle.used(contrast.estimation.id, pe_id)
# Create estimation activity
self.add_object(contrast.estimation)
# Create contrast weights
self.add_object(contrast.weights)
if contrast.contrast_map is not None:
# Create contrast Map
# contrast.contrast_map.wasGeneratedBy(contrast.estimation)
self.bundle.wasGeneratedBy(contrast.contrast_map.id,
contrast.estimation.id)
self.add_object(contrast.contrast_map)
self.add_object(contrast.contrast_map.coord_space)
# Copy contrast map in export directory
self.add_object(contrast.contrast_map.file)
if contrast.contrast_map.derfrom is not None:
self.bundle.wasDerivedFrom(
contrast.contrast_map.id,
contrast.contrast_map.derfrom.id)
self.add_object(contrast.contrast_map.derfrom)
self.add_object(contrast.contrast_map.derfrom.file,
export_file=False)
# Create Std Err. Map (T-tests) or Explained Mean Sq. Map
# (F-tests)
# contrast.stderr_or_expl_mean_sq_map.wasGeneratedBy
# (contrast.estimation)
stderr_explmeansq_map = (
contrast.stderr_or_expl_mean_sq_map)
self.bundle.wasGeneratedBy(stderr_explmeansq_map.id,
contrast.estimation.id)
self.add_object(stderr_explmeansq_map)
self.add_object(stderr_explmeansq_map.coord_space)
if isinstance(stderr_explmeansq_map,
ContrastStdErrMap) and \
stderr_explmeansq_map.contrast_var:
self.add_object(stderr_explmeansq_map.contrast_var)
if stderr_explmeansq_map.var_coord_space:
self.add_object(
stderr_explmeansq_map.var_coord_space)
if stderr_explmeansq_map.contrast_var.coord_space:
self.add_object(
stderr_explmeansq_map.contrast_var.coord_space)
self.add_object(
stderr_explmeansq_map.contrast_var.file,
export_file=False)
self.bundle.wasDerivedFrom(
stderr_explmeansq_map.id,
stderr_explmeansq_map.contrast_var.id)
self.add_object(stderr_explmeansq_map.file)
# Create Statistic Map
# contrast.stat_map.wasGeneratedBy(contrast.estimation)
self.bundle.wasGeneratedBy(contrast.stat_map.id,
contrast.estimation.id)
self.add_object(contrast.stat_map)
self.add_object(contrast.stat_map.coord_space)
# Copy Statistical map in export directory
self.add_object(contrast.stat_map.file)
if contrast.stat_map.derfrom is not None:
self.bundle.wasDerivedFrom(
contrast.stat_map.id, contrast.stat_map.derfrom.id)
self.add_object(contrast.stat_map.derfrom)
self.add_object(contrast.stat_map.derfrom.file,
export_file=False)
# Create Z Statistic Map
if contrast.z_stat_map:
# contrast.z_stat_map.wasGeneratedBy(contrast.estimation)
self.bundle.wasGeneratedBy(contrast.z_stat_map.id,
contrast.estimation.id)
self.add_object(contrast.z_stat_map)
self.add_object(contrast.z_stat_map.coord_space)
# Copy Statistical map in export directory
self.add_object(contrast.z_stat_map.file)
# self.add_object(contrast)
# Add inference steps
for contrast_id, inferences in list(self.inferences.items()):
contrast = self._get_contrast(contrast_id)
for inference in inferences:
if contrast.z_stat_map:
used_id = contrast.z_stat_map.id
else:
used_id = contrast.stat_map.id
# inference.inference_act.used(used_id)
self.bundle.used(inference.inference_act.id, used_id)
# inference.inference_act.wasAssociatedWith(self.software)
self.bundle.wasAssociatedWith(inference.inference_act.id,
self.software.id)
# self.add_object(inference)
# Excursion set
# inference.excursion_set.wasGeneratedBy(inference.inference_act)
self.bundle.wasGeneratedBy(inference.excursion_set.id,
inference.inference_act.id)
self.add_object(inference.excursion_set)
self.add_object(inference.excursion_set.coord_space)
if inference.excursion_set.visu is not None:
self.add_object(inference.excursion_set.visu)
if inference.excursion_set.visu.file is not None:
self.add_object(inference.excursion_set.visu.file)
# Copy "Excursion set map" file in export directory
self.add_object(inference.excursion_set.file)
if inference.excursion_set.clust_map is not None:
self.add_object(inference.excursion_set.clust_map)
self.add_object(inference.excursion_set.clust_map.file)
self.add_object(
inference.excursion_set.clust_map.coord_space)
if inference.excursion_set.mip is not None:
self.add_object(inference.excursion_set.mip)
self.add_object(inference.excursion_set.mip.file)
# Height threshold
if inference.height_thresh.equiv_thresh is not None:
for equiv in inference.height_thresh.equiv_thresh:
self.add_object(equiv)
self.add_object(inference.height_thresh)
# Extent threshold
if inference.extent_thresh.equiv_thresh is not None:
for equiv in inference.extent_thresh.equiv_thresh:
self.add_object(equiv)
self.add_object(inference.extent_thresh)
# Display Mask (potentially more than 1)
if inference.disp_mask:
for mask in inference.disp_mask:
# inference.inference_act.used(mask)
self.bundle.used(inference.inference_act.id,
mask.id)
self.add_object(mask)
# Create coordinate space entity
self.add_object(mask.coord_space)
# Create "Display Mask Map" entity
self.add_object(mask.file)
if mask.derfrom is not None:
self.bundle.wasDerivedFrom(
mask.id, mask.derfrom.id)
self.add_object(mask.derfrom)
self.add_object(mask.derfrom.file,
export_file=False)
# Search Space
self.bundle.wasGeneratedBy(inference.search_space.id,
inference.inference_act.id)
# inference.search_space.wasGeneratedBy(inference.inference_act)
self.add_object(inference.search_space)
self.add_object(inference.search_space.coord_space)
# Copy "Mask map" in export directory
self.add_object(inference.search_space.file)
# Peak Definition
if inference.peak_criteria:
# inference.inference_act.used(inference.peak_criteria)
self.bundle.used(inference.inference_act.id,
inference.peak_criteria.id)
self.add_object(inference.peak_criteria)
# Cluster Definition
if inference.cluster_criteria:
# inference.inference_act.used(inference.cluster_criteria)
self.bundle.used(inference.inference_act.id,
inference.cluster_criteria.id)
self.add_object(inference.cluster_criteria)
if inference.clusters:
# Clusters and peaks
for cluster in inference.clusters:
# cluster.wasDerivedFrom(inference.excursion_set)
self.bundle.wasDerivedFrom(
cluster.id, inference.excursion_set.id)
self.add_object(cluster)
for peak in cluster.peaks:
self.bundle.wasDerivedFrom(peak.id, cluster.id)
self.add_object(peak)
self.add_object(peak.coordinate)
if cluster.cog is not None:
self.bundle.wasDerivedFrom(
cluster.cog.id, cluster.id)
self.add_object(cluster.cog)
self.add_object(cluster.cog.coordinate)
# Inference activity
# inference.inference_act.wasAssociatedWith(inference.software_id)
# inference.inference_act.used(inference.height_thresh)
self.bundle.used(inference.inference_act.id,
inference.height_thresh.id)
# inference.inference_act.used(inference.extent_thresh)
self.bundle.used(inference.inference_act.id,
inference.extent_thresh.id)
self.bundle.used(inference.inference_act.id,
analysis_masks[contrast.estimation.id])
self.add_object(inference.inference_act)
# Write-out prov file
self.save_prov_to_files()
return self.out_dir
except Exception:
self.cleanup()
raise
def _get_model_fitting(self, mf_id):
"""
Retreive model fitting with identifier 'mf_id' from the list of model
fitting objects stored in self.model_fitting
"""
for model_fitting in self.model_fittings:
if model_fitting.activity.id == mf_id:
return model_fitting
raise Exception("Model fitting activity with id: " + str(mf_id) +
" not found.")
def _get_contrast(self, con_id):
"""
Retreive contrast with identifier 'con_id' from the list of contrast
objects stored in self.contrasts
"""
for contrasts in list(self.contrasts.values()):
for contrast in contrasts:
if contrast.estimation.id == con_id:
return contrast
raise Exception("Contrast activity with id: " + str(con_id) +
" not found.")
def _add_namespaces(self):
"""
Add namespaces to NIDM document.
"""
self.doc.add_namespace(NIDM)
self.doc.add_namespace(NIIRI)
self.doc.add_namespace(CRYPTO)
self.doc.add_namespace(DCT)
self.doc.add_namespace(DC)
self.doc.add_namespace(NFO)
self.doc.add_namespace(OBO)
self.doc.add_namespace(SCR)
self.doc.add_namespace(NIF)
def _create_bundle(self, version):
"""
Initialise NIDM-Results bundle.
"""
# *** Bundle entity
if not hasattr(self, 'bundle_ent'):
self.bundle_ent = NIDMResultsBundle(nidm_version=version['num'])
self.bundle = ProvBundle(identifier=self.bundle_ent.id)
self.bundle_ent.export(self.version, self.export_dir)
# # provn export
# self.bundle = ProvBundle(identifier=bundle_id)
self.doc.entity(self.bundle_ent.id,
other_attributes=self.bundle_ent.attributes)
# *** NIDM-Results Export Activity
if version['num'] not in ["1.0.0", "1.1.0"]:
if not hasattr(self, 'export_act'):
self.export_act = NIDMResultsExport()
self.export_act.export(self.version, self.export_dir)
# self.doc.update(self.export_act.p)
self.doc.activity(self.export_act.id,
other_attributes=self.export_act.attributes)
# *** bundle was Generated by NIDM-Results Export Activity
if not hasattr(self, 'export_time'):
self.export_time = str(datetime.datetime.now().time())
if version['num'] in ["1.0.0", "1.1.0"]:
self.doc.wasGeneratedBy(entity=self.bundle_ent.id,
time=self.export_time)
else:
# provn
self.doc.wasGeneratedBy(entity=self.bundle_ent.id,
activity=self.export_act.id,
time=self.export_time)
# *** NIDM-Results Exporter (Software Agent)
if version['num'] not in ["1.0.0", "1.1.0"]:
if not hasattr(self, 'exporter'):
self.exporter = self._get_exporter()
self.exporter.export(self.version, self.export_dir)
# self.doc.update(self.exporter.p)
self.doc.agent(self.exporter.id,
other_attributes=self.exporter.attributes)
self.doc.wasAssociatedWith(self.export_act.id, self.exporter.id)
def _get_model_parameters_estimations(self, error_model):
"""
Infer model estimation method from the 'error_model'. Return an object
of type ModelParametersEstimation.
"""
if error_model.dependance == NIDM_INDEPEDENT_ERROR:
if error_model.variance_homo:
estimation_method = STATO_OLS
else:
estimation_method = STATO_WLS
else:
estimation_method = STATO_GLS
mpe = ModelParametersEstimation(estimation_method, self.software.id)
return mpe
def use_prefixes(self, ttl):
prefix_file = os.path.join(os.path.dirname(__file__), 'prefixes.csv')
context = dict()
with open(prefix_file, encoding="ascii") as csvfile:
reader = csv.reader(csvfile)
next(reader, None) # skip the headers
for alphanum_id, prefix, uri in reader:
if alphanum_id in ttl:
context[prefix] = uri
ttl = "@prefix " + prefix + ": <" + uri + "> .\n" + ttl
ttl = ttl.replace(alphanum_id, prefix + ":")
if uri in ttl:
ttl = ttl.replace(alphanum_id, prefix + ":")
elif uri in ttl:
context[prefix] = uri
ttl = "@prefix " + prefix + ": <" + uri + "> .\n" + ttl
ttl = ttl.replace(alphanum_id, prefix + ":")
return (ttl, context)
def save_prov_to_files(self, showattributes=False):
"""
Write-out provn serialisation to nidm.provn.
"""
self.doc.add_bundle(self.bundle)
# provn_file = os.path.join(self.export_dir, 'nidm.provn')
# provn_fid = open(provn_file, 'w')
# # FIXME None
# # provn_fid.write(self.doc.get_provn(4).replace("None", "-"))
# provn_fid.close()
ttl_file = os.path.join(self.export_dir, 'nidm.ttl')
ttl_txt = self.doc.serialize(format='rdf', rdf_format='turtle')
ttl_txt, json_context = self.use_prefixes(ttl_txt)
# Add namespaces to json-ld context
for namespace in self.doc._namespaces.get_registered_namespaces():
json_context[namespace._prefix] = namespace._uri
for namespace in \
list(self.doc._namespaces._default_namespaces.values()):
json_context[namespace._prefix] = namespace._uri
json_context["xsd"] = "http://www.w3.org/2000/01/rdf-schema#"
# Work-around to issue with INF value in rdflib (reported in
# https://github.com/RDFLib/rdflib/pull/655)
ttl_txt = ttl_txt.replace(' inf ', ' "INF"^^xsd:float ')
with open(ttl_file, 'w') as ttl_fid:
ttl_fid.write(ttl_txt)
# print(json_context)
jsonld_file = os.path.join(self.export_dir, 'nidm.json')
jsonld_txt = self.doc.serialize(format='rdf',
rdf_format='json-ld',
context=json_context)
with open(jsonld_file, 'w') as jsonld_fid:
jsonld_fid.write(jsonld_txt)
# provjsonld_file = os.path.join(self.export_dir, 'nidm.provjsonld')
# provjsonld_txt = self.doc.serialize(format='jsonld')
# with open(provjsonld_file, 'w') as provjsonld_fid:
# provjsonld_fid.write(provjsonld_txt)
# provn_file = os.path.join(self.export_dir, 'nidm.provn')
# provn_txt = self.doc.serialize(format='provn')
# with open(provn_file, 'w') as provn_fid:
# provn_fid.write(provn_txt)
# Post-processing
if not self.zipped:
# Just rename temp directory to output_path
os.rename(self.export_dir, self.out_dir)
else:
# Create a zip file that contains the content of the temp directory
os.chdir(self.export_dir)
zf = zipfile.ZipFile(os.path.join("..", self.out_dir), mode='w')
try:
for root, dirnames, filenames in os.walk("."):
for filename in filenames:
zf.write(os.path.join(filename))
shutil.rmtree(os.path.join("..", self.export_dir))
finally:
zf.close()
os.chdir("..")
def w3c_publication_2():
# https://github.com/lucmoreau/ProvToolbox/blob/master/asn/src/test/resources/prov/w3c-publication2.prov-asn
#===========================================================================
# bundle
#
# prefix ex <http://example.org/>
# prefix rec <http://example.org/record>
#
# prefix w3 <http://www.w3.org/TR/2011/>
# prefix hg <http://dvcs.w3.org/hg/prov/raw-file/9628aaff6e20/model/releases/WD-prov-dm-20111215/>
#
#
# entity(hg:Overview.html, [ prov:type="file in hg" ])
# entity(w3:WD-prov-dm-20111215, [ prov:type="html4" ])
#
#
# activity(ex:rcp,-,-,[prov:type="copy directory"])
#
# wasGeneratedBy(rec:g; w3:WD-prov-dm-20111215, ex:rcp, -)
#
# entity(ex:req3, [ prov:type="http://www.w3.org/2005/08/01-transitions.html#pubreq" %% xsd:anyURI ])
#
# used(rec:u; ex:rcp,hg:Overview.html,-)
# used(ex:rcp, ex:req3, -)
#
#
# wasDerivedFrom(w3:WD-prov-dm-20111215, hg:Overview.html, ex:rcp, rec:g, rec:u)
#
# agent(ex:webmaster, [ prov:type='prov:Person' ])
#
# wasAssociatedWith(ex:rcp, ex:webmaster, -)
#
# endBundle
#===========================================================================
ex = Namespace('ex', 'http://example.org/')
rec = Namespace('rec', 'http://example.org/record')
w3 = Namespace('w3', 'http://www.w3.org/TR/2011/')
hg = Namespace(
'hg',
'http://dvcs.w3.org/hg/prov/raw-file/9628aaff6e20/model/releases/WD-prov-dm-20111215/'
)
g = ProvDocument()
g.entity(hg['Overview.html'], {'prov:type': "file in hg"})
g.entity(w3['WD-prov-dm-20111215'], {'prov:type': "html4"})
g.activity(ex['rcp'], None, None, {'prov:type': "copy directory"})
g.wasGeneratedBy('w3:WD-prov-dm-20111215', 'ex:rcp', identifier=rec['g'])
g.entity(
'ex:req3', {
'prov:type':
Identifier("http://www.w3.org/2005/08/01-transitions.html#pubreq")
})
g.used('ex:rcp', 'hg:Overview.html', identifier='rec:u')
g.used('ex:rcp', 'ex:req3')
g.wasDerivedFrom('w3:WD-prov-dm-20111215', 'hg:Overview.html', 'ex:rcp',
'rec:g', 'rec:u')
g.agent('ex:webmaster', {'prov:type': "Person"})
g.wasAssociatedWith('ex:rcp', 'ex:webmaster')
return g
class ProvenanceProfile:
"""
Provenance profile.
Populated as the workflow runs.
"""
def __init__(
self,
research_object: "ResearchObject",
full_name: str,
host_provenance: bool,
user_provenance: bool,
orcid: str,
fsaccess: StdFsAccess,
run_uuid: Optional[uuid.UUID] = None,
) -> None:
"""Initialize the provenance profile."""
self.fsaccess = fsaccess
self.orcid = orcid
self.research_object = research_object
self.folder = self.research_object.folder
self.document = ProvDocument()
self.host_provenance = host_provenance
self.user_provenance = user_provenance
self.engine_uuid = research_object.engine_uuid # type: str
self.add_to_manifest = self.research_object.add_to_manifest
if self.orcid:
_logger.debug("[provenance] Creator ORCID: %s", self.orcid)
self.full_name = full_name
if self.full_name:
_logger.debug("[provenance] Creator Full name: %s", self.full_name)
self.workflow_run_uuid = run_uuid or uuid.uuid4()
self.workflow_run_uri = self.workflow_run_uuid.urn # type: str
self.generate_prov_doc()
def __str__(self) -> str:
"""Represent this Provenvance profile as a string."""
return "ProvenanceProfile <{}> in <{}>".format(
self.workflow_run_uri,
self.research_object,
)
def generate_prov_doc(self) -> Tuple[str, ProvDocument]:
"""Add basic namespaces."""
def host_provenance(document: ProvDocument) -> None:
"""Record host provenance."""
document.add_namespace(CWLPROV)
document.add_namespace(UUID)
document.add_namespace(FOAF)
hostname = getfqdn()
# won't have a foaf:accountServiceHomepage for unix hosts, but
# we can at least provide hostname
document.agent(
ACCOUNT_UUID,
{
PROV_TYPE: FOAF["OnlineAccount"],
"prov:location": hostname,
CWLPROV["hostname"]: hostname,
},
)
self.cwltool_version = "cwltool %s" % versionstring().split()[-1]
self.document.add_namespace("wfprov",
"http://purl.org/wf4ever/wfprov#")
# document.add_namespace('prov', 'http://www.w3.org/ns/prov#')
self.document.add_namespace("wfdesc",
"http://purl.org/wf4ever/wfdesc#")
# TODO: Make this ontology. For now only has cwlprov:image
self.document.add_namespace("cwlprov", "https://w3id.org/cwl/prov#")
self.document.add_namespace("foaf", "http://xmlns.com/foaf/0.1/")
self.document.add_namespace("schema", "http://schema.org/")
self.document.add_namespace("orcid", "https://orcid.org/")
self.document.add_namespace("id", "urn:uuid:")
# NOTE: Internet draft expired 2004-03-04 (!)
# https://tools.ietf.org/html/draft-thiemann-hash-urn-01
# TODO: Change to nih:sha-256; hashes
# https://tools.ietf.org/html/rfc6920#section-7
self.document.add_namespace("data", "urn:hash::sha1:")
# Also needed for docker images
self.document.add_namespace(SHA256, "nih:sha-256;")
# info only, won't really be used by prov as sub-resources use /
self.document.add_namespace("researchobject",
self.research_object.base_uri)
# annotations
self.metadata_ns = self.document.add_namespace(
"metadata", self.research_object.base_uri + METADATA + "/")
# Pre-register provenance directory so we can refer to its files
self.provenance_ns = self.document.add_namespace(
"provenance",
self.research_object.base_uri + posix_path(PROVENANCE) + "/")
ro_identifier_workflow = self.research_object.base_uri + "workflow/packed.cwl#"
self.wf_ns = self.document.add_namespace("wf", ro_identifier_workflow)
ro_identifier_input = (self.research_object.base_uri +
"workflow/primary-job.json#")
self.document.add_namespace("input", ro_identifier_input)
# More info about the account (e.g. username, fullname)
# may or may not have been previously logged by user_provenance()
# .. but we always know cwltool was launched (directly or indirectly)
# by a user account, as cwltool is a command line tool
account = self.document.agent(ACCOUNT_UUID)
if self.orcid or self.full_name:
person = {PROV_TYPE: PROV["Person"], "prov:type": SCHEMA["Person"]}
if self.full_name:
person["prov:label"] = self.full_name
person["foaf:name"] = self.full_name
person["schema:name"] = self.full_name
else:
# TODO: Look up name from ORCID API?
pass
agent = self.document.agent(self.orcid or uuid.uuid4().urn, person)
self.document.actedOnBehalfOf(account, agent)
else:
if self.host_provenance:
host_provenance(self.document)
if self.user_provenance:
self.research_object.user_provenance(self.document)
# The execution of cwltool
wfengine = self.document.agent(
self.engine_uuid,
{
PROV_TYPE: PROV["SoftwareAgent"],
"prov:type": WFPROV["WorkflowEngine"],
"prov:label": self.cwltool_version,
},
)
# FIXME: This datetime will be a bit too delayed, we should
# capture when cwltool.py earliest started?
self.document.wasStartedBy(wfengine, None, account,
datetime.datetime.now())
# define workflow run level activity
self.document.activity(
self.workflow_run_uri,
datetime.datetime.now(),
None,
{
PROV_TYPE: WFPROV["WorkflowRun"],
"prov:label": "Run of workflow/packed.cwl#main",
},
)
# association between SoftwareAgent and WorkflowRun
main_workflow = "wf:main"
self.document.wasAssociatedWith(self.workflow_run_uri,
self.engine_uuid, main_workflow)
self.document.wasStartedBy(self.workflow_run_uri, None,
self.engine_uuid, datetime.datetime.now())
return (self.workflow_run_uri, self.document)
def evaluate(
self,
process: Process,
job: JobsType,
job_order_object: CWLObjectType,
research_obj: "ResearchObject",
) -> None:
"""Evaluate the nature of job."""
if not hasattr(process, "steps"):
# record provenance of independent commandline tool executions
self.prospective_prov(job)
customised_job = copy_job_order(job, job_order_object)
self.used_artefacts(customised_job, self.workflow_run_uri)
research_obj.create_job(customised_job)
elif hasattr(job, "workflow"):
# record provenance of workflow executions
self.prospective_prov(job)
customised_job = copy_job_order(job, job_order_object)
self.used_artefacts(customised_job, self.workflow_run_uri)
def record_process_start(
self,
process: Process,
job: JobsType,
process_run_id: Optional[str] = None) -> Optional[str]:
if not hasattr(process, "steps"):
process_run_id = self.workflow_run_uri
elif not hasattr(job, "workflow"):
# commandline tool execution as part of workflow
name = ""
if isinstance(job, (CommandLineJob, JobBase, WorkflowJob)):
name = job.name
process_name = urllib.parse.quote(name, safe=":/,#")
process_run_id = self.start_process(process_name,
datetime.datetime.now())
return process_run_id
def start_process(
self,
process_name: str,
when: datetime.datetime,
process_run_id: Optional[str] = None,
) -> str:
"""Record the start of each Process."""
if process_run_id is None:
process_run_id = uuid.uuid4().urn
prov_label = "Run of workflow/packed.cwl#main/" + process_name
self.document.activity(
process_run_id,
None,
None,
{
PROV_TYPE: WFPROV["ProcessRun"],
PROV_LABEL: prov_label
},
)
self.document.wasAssociatedWith(process_run_id, self.engine_uuid,
str("wf:main/" + process_name))
self.document.wasStartedBy(process_run_id, None, self.workflow_run_uri,
when, None, None)
return process_run_id
def record_process_end(
self,
process_name: str,
process_run_id: str,
outputs: Union[CWLObjectType, MutableSequence[CWLObjectType], None],
when: datetime.datetime,
) -> None:
self.generate_output_prov(outputs, process_run_id, process_name)
self.document.wasEndedBy(process_run_id, None, self.workflow_run_uri,
when)
def declare_file(
self, value: CWLObjectType) -> Tuple[ProvEntity, ProvEntity, str]:
if value["class"] != "File":
raise ValueError("Must have class:File: %s" % value)
# Need to determine file hash aka RO filename
entity = None # type: Optional[ProvEntity]
checksum = None
if "checksum" in value:
csum = cast(str, value["checksum"])
(method, checksum) = csum.split("$", 1)
if method == SHA1 and self.research_object.has_data_file(checksum):
entity = self.document.entity("data:" + checksum)
if not entity and "location" in value:
location = str(value["location"])
# If we made it here, we'll have to add it to the RO
with self.fsaccess.open(location, "rb") as fhandle:
relative_path = self.research_object.add_data_file(fhandle)
# FIXME: This naively relies on add_data_file setting hash as filename
checksum = PurePath(relative_path).name
entity = self.document.entity("data:" + checksum,
{PROV_TYPE: WFPROV["Artifact"]})
if "checksum" not in value:
value["checksum"] = f"{SHA1}${checksum}"
if not entity and "contents" in value:
# Anonymous file, add content as string
entity, checksum = self.declare_string(cast(
str, value["contents"]))
# By here one of them should have worked!
if not entity or not checksum:
raise ValueError(
"class:File but missing checksum/location/content: %r" % value)
# Track filename and extension, this is generally useful only for
# secondaryFiles. Note that multiple uses of a file might thus record
# different names for the same entity, so we'll
# make/track a specialized entity by UUID
file_id = value.setdefault("@id", uuid.uuid4().urn)
# A specialized entity that has just these names
file_entity = self.document.entity(
file_id,
[(PROV_TYPE, WFPROV["Artifact"]), (PROV_TYPE, WF4EVER["File"])],
) # type: ProvEntity
if "basename" in value:
file_entity.add_attributes(
{CWLPROV["basename"]: value["basename"]})
if "nameroot" in value:
file_entity.add_attributes(
{CWLPROV["nameroot"]: value["nameroot"]})
if "nameext" in value:
file_entity.add_attributes({CWLPROV["nameext"]: value["nameext"]})
self.document.specializationOf(file_entity, entity)
# Check for secondaries
for sec in cast(MutableSequence[CWLObjectType],
value.get("secondaryFiles", [])):
# TODO: Record these in a specializationOf entity with UUID?
if sec["class"] == "File":
(sec_entity, _, _) = self.declare_file(sec)
elif sec["class"] == "Directory":
sec_entity = self.declare_directory(sec)
else:
raise ValueError(f"Got unexpected secondaryFiles value: {sec}")
# We don't know how/when/where the secondary file was generated,
# but CWL convention is a kind of summary/index derived
# from the original file. As its generally in a different format
# then prov:Quotation is not appropriate.
self.document.derivation(
sec_entity,
file_entity,
other_attributes={PROV["type"]: CWLPROV["SecondaryFile"]},
)
return file_entity, entity, checksum
def declare_directory(self, value: CWLObjectType) -> ProvEntity:
"""Register any nested files/directories."""
# FIXME: Calculate a hash-like identifier for directory
# so we get same value if it's the same filenames/hashes
# in a different location.
# For now, mint a new UUID to identify this directory, but
# attempt to keep it inside the value dictionary
dir_id = cast(str, value.setdefault("@id", uuid.uuid4().urn))
# New annotation file to keep the ORE Folder listing
ore_doc_fn = dir_id.replace("urn:uuid:", "directory-") + ".ttl"
dir_bundle = self.document.bundle(self.metadata_ns[ore_doc_fn])
coll = self.document.entity(
dir_id,
[
(PROV_TYPE, WFPROV["Artifact"]),
(PROV_TYPE, PROV["Collection"]),
(PROV_TYPE, PROV["Dictionary"]),
(PROV_TYPE, RO["Folder"]),
],
)
# ORE description of ro:Folder, saved separately
coll_b = dir_bundle.entity(
dir_id,
[(PROV_TYPE, RO["Folder"]), (PROV_TYPE, ORE["Aggregation"])],
)
self.document.mentionOf(dir_id + "#ore", dir_id, dir_bundle.identifier)
# dir_manifest = dir_bundle.entity(
# dir_bundle.identifier, {PROV["type"]: ORE["ResourceMap"],
# ORE["describes"]: coll_b.identifier})
coll_attribs = [(ORE["isDescribedBy"], dir_bundle.identifier)]
coll_b_attribs = [] # type: List[Tuple[Identifier, ProvEntity]]
# FIXME: .listing might not be populated yet - hopefully
# a later call to this method will sort that
is_empty = True
if "listing" not in value:
get_listing(self.fsaccess, value)
for entry in cast(MutableSequence[CWLObjectType],
value.get("listing", [])):
is_empty = False
# Declare child-artifacts
entity = self.declare_artefact(entry)
self.document.membership(coll, entity)
# Membership relation aka our ORE Proxy
m_id = uuid.uuid4().urn
m_entity = self.document.entity(m_id)
m_b = dir_bundle.entity(m_id)
# PROV-O style Dictionary
# https://www.w3.org/TR/prov-dictionary/#dictionary-ontological-definition
# ..as prov.py do not currently allow PROV-N extensions
# like hadDictionaryMember(..)
m_entity.add_asserted_type(PROV["KeyEntityPair"])
m_entity.add_attributes({
PROV["pairKey"]: entry["basename"],
PROV["pairEntity"]: entity,
})
# As well as a being a
# http://wf4ever.github.io/ro/2016-01-28/ro/#FolderEntry
m_b.add_asserted_type(RO["FolderEntry"])
m_b.add_asserted_type(ORE["Proxy"])
m_b.add_attributes({
RO["entryName"]: entry["basename"],
ORE["proxyIn"]: coll,
ORE["proxyFor"]: entity,
})
coll_attribs.append((PROV["hadDictionaryMember"], m_entity))
coll_b_attribs.append((ORE["aggregates"], m_b))
coll.add_attributes(coll_attribs)
coll_b.add_attributes(coll_b_attribs)
# Also Save ORE Folder as annotation metadata
ore_doc = ProvDocument()
ore_doc.add_namespace(ORE)
ore_doc.add_namespace(RO)
ore_doc.add_namespace(UUID)
ore_doc.add_bundle(dir_bundle)
ore_doc = ore_doc.flattened()
ore_doc_path = str(PurePosixPath(METADATA, ore_doc_fn))
with self.research_object.write_bag_file(
ore_doc_path) as provenance_file:
ore_doc.serialize(provenance_file,
format="rdf",
rdf_format="turtle")
self.research_object.add_annotation(dir_id, [ore_doc_fn],
ORE["isDescribedBy"].uri)
if is_empty:
# Empty directory
coll.add_asserted_type(PROV["EmptyCollection"])
coll.add_asserted_type(PROV["EmptyDictionary"])
self.research_object.add_uri(coll.identifier.uri)
return coll
def declare_string(self, value: str) -> Tuple[ProvEntity, str]:
"""Save as string in UTF-8."""
byte_s = BytesIO(str(value).encode(ENCODING))
data_file = self.research_object.add_data_file(byte_s,
content_type=TEXT_PLAIN)
checksum = PurePosixPath(data_file).name
# FIXME: Don't naively assume add_data_file uses hash in filename!
data_id = "data:%s" % PurePosixPath(data_file).stem
entity = self.document.entity(data_id, {
PROV_TYPE: WFPROV["Artifact"],
PROV_VALUE: str(value)
}) # type: ProvEntity
return entity, checksum
def declare_artefact(self, value: Optional[CWLOutputType]) -> ProvEntity:
"""Create data artefact entities for all file objects."""
if value is None:
# FIXME: If this can happen in CWL, we'll
# need a better way to represent this in PROV
return self.document.entity(CWLPROV["None"], {PROV_LABEL: "None"})
if isinstance(value, (bool, int, float)):
# Typically used in job documents for flags
# FIXME: Make consistent hash URIs for these
# that somehow include the type
# (so "1" != 1 != "1.0" != true)
entity = self.document.entity(uuid.uuid4().urn,
{PROV_VALUE: value})
self.research_object.add_uri(entity.identifier.uri)
return entity
if isinstance(value, (str, str)):
(entity, _) = self.declare_string(value)
return entity
if isinstance(value, bytes):
# If we got here then we must be in Python 3
byte_s = BytesIO(value)
data_file = self.research_object.add_data_file(byte_s)
# FIXME: Don't naively assume add_data_file uses hash in filename!
data_id = "data:%s" % PurePosixPath(data_file).stem
return self.document.entity(
data_id,
{
PROV_TYPE: WFPROV["Artifact"],
PROV_VALUE: str(value)
},
)
if isinstance(value, MutableMapping):
if "@id" in value:
# Already processed this value, but it might not be in this PROV
entities = self.document.get_record(value["@id"])
if entities:
return entities[0]
# else, unknown in PROV, re-add below as if it's fresh
# Base case - we found a File we need to update
if value.get("class") == "File":
(entity, _, _) = self.declare_file(value)
value["@id"] = entity.identifier.uri
return entity
if value.get("class") == "Directory":
entity = self.declare_directory(value)
value["@id"] = entity.identifier.uri
return entity
coll_id = value.setdefault("@id", uuid.uuid4().urn)
# some other kind of dictionary?
# TODO: also Save as JSON
coll = self.document.entity(
coll_id,
[
(PROV_TYPE, WFPROV["Artifact"]),
(PROV_TYPE, PROV["Collection"]),
(PROV_TYPE, PROV["Dictionary"]),
],
)
if value.get("class"):
_logger.warning("Unknown data class %s.", value["class"])
# FIXME: The class might be "http://example.com/somethingelse"
coll.add_asserted_type(CWLPROV[value["class"]])
# Let's iterate and recurse
coll_attribs = [] # type: List[Tuple[Identifier, ProvEntity]]
for (key, val) in value.items():
v_ent = self.declare_artefact(val)
self.document.membership(coll, v_ent)
m_entity = self.document.entity(uuid.uuid4().urn)
# Note: only support PROV-O style dictionary
# https://www.w3.org/TR/prov-dictionary/#dictionary-ontological-definition
# as prov.py do not easily allow PROV-N extensions
m_entity.add_asserted_type(PROV["KeyEntityPair"])
m_entity.add_attributes({
PROV["pairKey"]: str(key),
PROV["pairEntity"]: v_ent
})
coll_attribs.append((PROV["hadDictionaryMember"], m_entity))
coll.add_attributes(coll_attribs)
self.research_object.add_uri(coll.identifier.uri)
return coll
# some other kind of Collection?
# TODO: also save as JSON
try:
members = []
for each_input_obj in iter(value):
# Recurse and register any nested objects
e = self.declare_artefact(each_input_obj)
members.append(e)
# If we reached this, then we were allowed to iterate
coll = self.document.entity(
uuid.uuid4().urn,
[
(PROV_TYPE, WFPROV["Artifact"]),
(PROV_TYPE, PROV["Collection"]),
],
)
if not members:
coll.add_asserted_type(PROV["EmptyCollection"])
else:
for member in members:
# FIXME: This won't preserve order, for that
# we would need to use PROV.Dictionary
# with numeric keys
self.document.membership(coll, member)
self.research_object.add_uri(coll.identifier.uri)
# FIXME: list value does not support adding "@id"
return coll
except TypeError:
_logger.warning("Unrecognized type %s of %r", type(value), value)
# Let's just fall back to Python repr()
entity = self.document.entity(uuid.uuid4().urn,
{PROV_LABEL: repr(value)})
self.research_object.add_uri(entity.identifier.uri)
return entity
def used_artefacts(
self,
job_order: Union[CWLObjectType, List[CWLObjectType]],
process_run_id: str,
name: Optional[str] = None,
) -> None:
"""Add used() for each data artefact."""
if isinstance(job_order, list):
for entry in job_order:
self.used_artefacts(entry, process_run_id, name)
else:
# FIXME: Use workflow name in packed.cwl, "main" is wrong for nested workflows
base = "main"
if name is not None:
base += "/" + name
for key, value in job_order.items():
prov_role = self.wf_ns[f"{base}/{key}"]
try:
entity = self.declare_artefact(value)
self.document.used(
process_run_id,
entity,
datetime.datetime.now(),
None,
{"prov:role": prov_role},
)
except OSError:
pass
def generate_output_prov(
self,
final_output: Union[CWLObjectType, MutableSequence[CWLObjectType],
None],
process_run_id: Optional[str],
name: Optional[str],
) -> None:
"""Call wasGeneratedBy() for each output,copy the files into the RO."""
if isinstance(final_output, MutableSequence):
for entry in final_output:
self.generate_output_prov(entry, process_run_id, name)
elif final_output is not None:
# Timestamp should be created at the earliest
timestamp = datetime.datetime.now()
# For each output, find/register the corresponding
# entity (UUID) and document it as generated in
# a role corresponding to the output
for output, value in final_output.items():
entity = self.declare_artefact(value)
if name is not None:
name = urllib.parse.quote(str(name), safe=":/,#")
# FIXME: Probably not "main" in nested workflows
role = self.wf_ns[f"main/{name}/{output}"]
else:
role = self.wf_ns["main/%s" % output]
if not process_run_id:
process_run_id = self.workflow_run_uri
self.document.wasGeneratedBy(entity, process_run_id, timestamp,
None, {"prov:role": role})
def prospective_prov(self, job: JobsType) -> None:
"""Create prospective prov recording as wfdesc prov:Plan."""
if not isinstance(job, WorkflowJob):
# direct command line tool execution
self.document.entity(
"wf:main",
{
PROV_TYPE: WFDESC["Process"],
"prov:type": PROV["Plan"],
"prov:label": "Prospective provenance",
},
)
return
self.document.entity(
"wf:main",
{
PROV_TYPE: WFDESC["Workflow"],
"prov:type": PROV["Plan"],
"prov:label": "Prospective provenance",
},
)
for step in job.steps:
stepnametemp = "wf:main/" + str(step.name)[5:]
stepname = urllib.parse.quote(stepnametemp, safe=":/,#")
provstep = self.document.entity(
stepname,
{
PROV_TYPE: WFDESC["Process"],
"prov:type": PROV["Plan"]
},
)
self.document.entity(
"wf:main",
{
"wfdesc:hasSubProcess": provstep,
"prov:label": "Prospective provenance",
},
)
# TODO: Declare roles/parameters as well
def activity_has_provenance(self, activity, prov_ids):
# type: (str, List[Identifier]) -> None
"""Add http://www.w3.org/TR/prov-aq/ relations to nested PROV files."""
# NOTE: The below will only work if the corresponding metadata/provenance arcp URI
# is a pre-registered namespace in the PROV Document
attribs = [(PROV["has_provenance"], prov_id) for prov_id in prov_ids]
self.document.activity(activity, other_attributes=attribs)
# Tip: we can't use https://www.w3.org/TR/prov-links/#term-mention
# as prov:mentionOf() is only for entities, not activities
uris = [i.uri for i in prov_ids]
self.research_object.add_annotation(activity, uris,
PROV["has_provenance"].uri)
def finalize_prov_profile(self, name):
# type: (Optional[str]) -> List[Identifier]
"""Transfer the provenance related files to the RO."""
# NOTE: Relative posix path
if name is None:
# main workflow, fixed filenames
filename = "primary.cwlprov"
else:
# ASCII-friendly filename, avoiding % as we don't want %2520 in manifest.json
wf_name = urllib.parse.quote(str(name), safe="").replace("%", "_")
# Note that the above could cause overlaps for similarly named
# workflows, but that's OK as we'll also include run uuid
# which also covers thhe case of this step being run in
# multiple places or iterations
filename = f"{wf_name}.{self.workflow_run_uuid}.cwlprov"
basename = str(PurePosixPath(PROVENANCE) / filename)
# TODO: Also support other profiles than CWLProv, e.g. ProvOne
# list of prov identifiers of provenance files
prov_ids = []
# https://www.w3.org/TR/prov-xml/
with self.research_object.write_bag_file(basename +
".xml") as provenance_file:
self.document.serialize(provenance_file, format="xml", indent=4)
prov_ids.append(self.provenance_ns[filename + ".xml"])
# https://www.w3.org/TR/prov-n/
with self.research_object.write_bag_file(basename +
".provn") as provenance_file:
self.document.serialize(provenance_file, format="provn", indent=2)
prov_ids.append(self.provenance_ns[filename + ".provn"])
# https://www.w3.org/Submission/prov-json/
with self.research_object.write_bag_file(basename +
".json") as provenance_file:
self.document.serialize(provenance_file, format="json", indent=2)
prov_ids.append(self.provenance_ns[filename + ".json"])
# "rdf" aka https://www.w3.org/TR/prov-o/
# which can be serialized to ttl/nt/jsonld (and more!)
# https://www.w3.org/TR/turtle/
with self.research_object.write_bag_file(basename +
".ttl") as provenance_file:
self.document.serialize(provenance_file,
format="rdf",
rdf_format="turtle")
prov_ids.append(self.provenance_ns[filename + ".ttl"])
# https://www.w3.org/TR/n-triples/
with self.research_object.write_bag_file(basename +
".nt") as provenance_file:
self.document.serialize(provenance_file,
format="rdf",
rdf_format="ntriples")
prov_ids.append(self.provenance_ns[filename + ".nt"])
# https://www.w3.org/TR/json-ld/
# TODO: Use a nice JSON-LD context
# see also https://eprints.soton.ac.uk/395985/
# 404 Not Found on https://provenance.ecs.soton.ac.uk/prov.jsonld :(
with self.research_object.write_bag_file(basename +
".jsonld") as provenance_file:
self.document.serialize(provenance_file,
format="rdf",
rdf_format="json-ld")
prov_ids.append(self.provenance_ns[filename + ".jsonld"])
_logger.debug("[provenance] added provenance: %s", prov_ids)
return prov_ids
def write_targets_prov(self, tlist, C, bundle_id):
#Initialisation
# cs = b.agent('CrowdScanner')
if self.document_id == -1:
d = ProvDocument()
d.add_namespace(AO)
d.set_default_namespace(self.defaultns % self.game_id)
if uploadprov:
provstore_document = self.api.document.create(d, name="Operation%s CrowdScanner" % self.game_id, public=True)
document_uri = provstore_document.url
logging.info("prov doc URI: " + str(document_uri))
self.provfilelist.append(provstore_document.id)
self.savelocalrecord()
self.document_id = provstore_document.id
b = ProvDocument() # Create a new document for this update
b.add_namespace(AO)
b.set_default_namespace(self.defaultns % self.game_id)
# cs to be used with all targets
cs = b.agent('agent/CrowdScanner', (('prov:type', AO['IBCCAlgo']), ('prov:type', PROV['SoftwareAgent'])))
timestamp = time.time() # Record the timestamp at each update to generate unique identifiers
startTime = datetime.datetime.fromtimestamp(timestamp)
endTime = startTime
activity = b.activity('activity/cs/update_report_%s' % timestamp, startTime, endTime)
activity.wasAssociatedWith(cs)
#Add target and report entities
for i, tdata in enumerate(tlist):
if self.changedtargets[i]==0:
continue
#Target entity for target i
tid = int(tdata[0])
x = tdata[1]
y = tdata[2]
# targettype = tdata[3] #don't record here, it will be revealed and recorded by UAVs
v = int(tdata[4])
agentids = tdata[7]
targetattributes = {'ao:longitude': x, 'ao:latitude': y, }
#'ao:asset_type':str(targettype)}
target_v0 = b.entity('cs/target/'+str(tid)+'.'+str(v), targetattributes)
#Post the root report if this is the first version
if v==0:
self.targets[tid] = b.entity('cs/target/'+str(tid))
else:
try:
target_v0.wasDerivedFrom(self.targetversions[tid])
except KeyError:
logging.error("Got a key error for key " + str(tid) + ', which is supposed to be version' + str(v))
self.targetversions[tid] = target_v0
target_v0.specializationOf(self.targets[tid])
target_v0.wasAttributedTo(cs)
#Report entities for origins of target i
for j, r in enumerate(self.target_rep_ids[i]):
if r not in self.postedreports:
Crow = C[r,:]
x = Crow[1]
y = Crow[2]
reptext = tdata[5][j].decode('utf8')
# Try to replace unusual characters
reptext = reptext.encode('ascii', 'replace')
agentid = agentids[j]
reporter_name = 'agent/crowdreporter%s' % agentid
b.agent(reporter_name, (('prov:type', AO['CrowdReporter']), ('prov:type', PROV['Person'])))
reportattributes = {'ao:longitude': x, 'ao:latitude': y, 'ao:report': reptext}
self.postedreports[r] = b.entity('cs/report/'+str(r), reportattributes)
self.postedreports[r].wasAttributedTo(reporter_name)
activity.used(self.postedreports[r])
target_v0.wasDerivedFrom(self.postedreports[r])
if uploadprov:
#Invalidate old targets no longer in use
for i,tid in enumerate(self.targets_to_invalidate):
target_v = self.targetversions[tid]
b.wasInvalidatedBy(target_v, activity)
#Post the document to the server
#bundle = b.bundle('crowd_scanner')
bundle_id = 'bundle/csupdate/%s' % timestamp
self.api.add_bundle(self.document_id, b.serialize(), bundle_id)
