def test_default_namespace_inheritance(self):
prov_doc = ProvDocument()
prov_doc.set_default_namespace('http://www.example.org/')
bundle = prov_doc.bundle('bundle')
e1 = bundle.entity('e1')
self.assertIsNotNone(e1.identifier, "e1's identifier is None!")
self.assertRoundTripEquivalence(prov_doc)
def test_default_namespace_inheritance(self):
prov_doc = ProvDocument()
prov_doc.set_default_namespace("http://www.example.org/")
bundle = prov_doc.bundle("bundle")
e1 = bundle.entity("e1")
self.assertIsNotNone(e1.identifier, "e1's identifier is None!")
self.do_tests(prov_doc)
def test_bundle_update_simple(self):
doc = ProvDocument()
doc.set_default_namespace(EX_URI)
b1 = doc.bundle('b1')
b1.entity('e')
b2 = doc.bundle('b2')
b2.entity('e')
self.assertRaises(ProvException, lambda: b1.update(1))
self.assertRaises(ProvException, lambda: b1.update(doc))
b1.update(b2)
self.assertEqual(len(b1.get_records()), 2)
def test_bundle_update_simple(self):
doc = ProvDocument()
doc.set_default_namespace(EX_URI)
b1 = doc.bundle('b1')
b1.entity('e')
b2 = doc.bundle('b2')
b2.entity('e')
self.assertRaises(ProvException, lambda: b1.update(1))
self.assertRaises(ProvException, lambda: b1.update(doc))
b1.update(b2)
self.assertEqual(len(b1.get_records()), 2)
def create_graph(packages: List[Union[CommitModelPackage, ResourceModelPackage]]) -> ProvDocument:
"""Create graph from list of packages.
Choose graph model according to package type.
Remove duplicated specializationOf relations.
"""
graph = ProvDocument()
graph.set_default_namespace("gitlab2prov")
if not packages:
return graph
model = {
CommitModelPackage: commit_package_model,
ResourceModelPackage: resource_package_model,
ReleaseTagPackage: release_tag_model
}[type(packages[0])]
graph = model(graph, packages)
graph = enforce_uniqueness_constraints(graph)
return graph
def test_document_update_simple(self):
d1 = ProvDocument()
d1.set_default_namespace(EX_URI)
d1.entity('e')
b1 = d1.bundle('b1')
b1.entity('e')
d2 = ProvDocument()
d2.set_default_namespace(EX_URI)
d2.entity('e')
b1 = d2.bundle('b1')
b1.entity('e')
b2 = d2.bundle('b2')
b2.entity('e')
self.assertRaises(ProvException, lambda: d1.update(1))
d1.update(d2)
self.assertEqual(len(d1.get_records()), 2)
self.assertEqual(len(d1.bundles), 2)
def test_document_update_simple(self):
d1 = ProvDocument()
d1.set_default_namespace(EX_URI)
d1.entity('e')
b1 = d1.bundle('b1')
b1.entity('e')
d2 = ProvDocument()
d2.set_default_namespace(EX_URI)
d2.entity('e')
b1 = d2.bundle('b1')
b1.entity('e')
b2 = d2.bundle('b2')
b2.entity('e')
self.assertRaises(ProvException, lambda: d1.update(1))
d1.update(d2)
self.assertEqual(len(d1.get_records()), 2)
self.assertEqual(len(d1.bundles), 2)
def create_prov(self):
visits = []
for visit_id in self.db_cursor.execute(
"select visit_id from site_visits where crawl_id=?",
[str(self.crawl_id)]):
visits.append(visit_id[0])
for visit_id in visits:
try:
self.db_cursor.execute(
"select command_status from crawl_history where visit_id=?",
[str(visit_id)])
if self.db_cursor.fetchone(
)[0] == 'error': # Check if visit had an error
print('Error in visit %s' % visit_id)
continue
document = ProvDocument()
document.set_default_namespace('http://prj.com')
self.documents[
visit_id] = document # Save a blank document for this visit
except:
pass
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
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 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 get_prov():
doc = ProvDocument()
doc.set_default_namespace('http://roocs.org/')
doc.get_provn()
"""PROV model fpr GitLab2PROV."""
__author__ = "Claas de Boer, Andreas Schreiber, Lynn von Kurnatowski"
__copyright__ = "Copyright 2020, German Aerospace Center (DLR) and individual contributors"
__license__ = "MIT"
__version__ = "0.5"
__status__ = "Development"
from prov.model import ProvDocument
from prov.constants import PROV_LABEL
from prov.dot import prov_to_dot
add = ProvDocument()
add.set_default_namespace("gitlab2prov:")
add.activity("Commit",
other_attributes={
"prov:type": "commit",
"title": "",
"message": "",
"id": "",
"short_id": "",
"prov:startedAt": "",
"prov:endedAt": ""
})
add.activity("Parent Commit",
other_attributes={
"prov:type": "commit",
"title": "",
"message": "",
"id": "",
"short_id": "",
def prov_default_namespace_example(ns_postfix: str):
doc = ProvDocument()
doc.set_default_namespace("https://example.com/{0}".format(ns_postfix))
doc.entity(identifier="Entity1")
return doc
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)
