def predict_target_with_query(
sparql, query, source, timeout=TIMEOUT, limit=LIMIT):
"""Predicts target with given query.
For example for pagerank_bidi:
SELECT distinct(?target) ?score {
{ dbr:Circle ?p ?target .}
UNION
{ ?target ?q dbr:Circle . }
?target dbo:wikiPageRank ?score
}
ORDER BY DESC(?score)
LIMIT 100
"""
q = query % {'source': source.n3()}
q += '\nLIMIT %d' % limit
t, q_res = gp_query._query(sparql, timeout, q)
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
target_scores = [
(get_path(row, [TARGET_VAR]), float(get_path(row, [Variable('score')])))
for row in bindings]
# print(target_scores)
return target_scores
def predict_target_with_query(
sparql, query, source, timeout=TIMEOUT, limit=LIMIT):
"""Predicts target with given query.
For example for pagerank_bidi:
SELECT distinct(?target) ?score {
{ dbr:Circle ?p ?target .}
UNION
{ ?target ?q dbr:Circle . }
?target dbo:wikiPageRank ?score
}
ORDER BY DESC(?score)
LIMIT 100
"""
q = query % {'source': source.n3()}
q += '\nLIMIT %d' % limit
t, q_res = gp_query._query(sparql, timeout, q)
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
target_scores = [
(get_path(row, [TARGET_VAR]), get_path(row, [Variable('score')]))
for row in bindings]
# print(target_scores)
return target_scores
def _q(sparql, timeout, query, selectors):
t, q_res = gp_query._query(sparql, timeout, query)
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[]))
target_scores = [[get_path(row, [sel]) for sel in selectors]
for row in bindings]
return target_scores
def _ask_chunk_result_extractor(q_res, _vars, _ret_val_mapping):
chunk_res = {}
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[]))
for row in bindings:
row_res = tuple([get_path(row, [v]) for v in _vars])
stps = _ret_val_mapping[row_res]
chunk_res.update({stp: True for stp in stps})
return chunk_res
def _predict_chunk_res(q_res, *_):
chunk_res = defaultdict(list)
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[]))
for row in bindings:
s = get_path(row, [SOURCE_VAR])
t = get_path(row, [TARGET_VAR])
chunk_res[s].append(t)
return chunk_res
def _q(sparql, timeout, query, selectors):
t, q_res = gp_query._query(sparql, timeout, query)
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
target_scores = [
[get_path(row, [sel]) for sel in selectors]
for row in bindings]
return target_scores
def _predict_chunk_res(q_res, *_):
chunk_res = defaultdict(list)
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
for row in bindings:
s = get_path(row, [SOURCE_VAR])
t = get_path(row, [TARGET_VAR])
chunk_res[s].append(t)
return chunk_res
def _ask_chunk_result_extractor(q_res, _vars, _ret_val_mapping):
chunk_res = {}
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
for row in bindings:
row_res = tuple([get_path(row, [v]) for v in _vars])
stps = _ret_val_mapping[row_res]
chunk_res.update({stp: True for stp in stps})
return chunk_res
def _var_subst_chunk_result_ext(q_res, _sel_var_and_vars, _, **kwds):
var, _vars = _sel_var_and_vars
chunk_res = Counter()
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[]))
for row in bindings:
row_res = get_path(row, [var])
count_res = int(get_path(row, [COUNT_VAR], '0'))
chunk_res[row_res] += count_res
return chunk_res
def _combined_chunk_res(q_res, _vars, _ret_val_mapping):
chunk_res = {}
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[]))
for row in bindings:
row_res = tuple([get_path(row, [v]) for v in _vars])
stps = _ret_val_mapping[row_res]
ask_res = int(get_path(row, [ASK_VAR], '0'))
count_res = int(get_path(row, [COUNT_VAR], '0'))
chunk_res.update({stp: (ask_res, count_res) for stp in stps})
return chunk_res
def _var_subst_chunk_result_ext(q_res, _sel_var_and_vars, _, **kwds):
var, _vars = _sel_var_and_vars
chunk_res = Counter()
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
for row in bindings:
row_res = get_path(row, [var])
count_res = int(get_path(row, [COUNT_VAR], '0'))
chunk_res[row_res] += count_res
return chunk_res
def _combined_chunk_res(q_res, _vars, _ret_val_mapping):
chunk_res = {}
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
for row in bindings:
row_res = tuple([get_path(row, [v]) for v in _vars])
stps = _ret_val_mapping[row_res]
ask_res = int(get_path(row, [ASK_VAR], '0'))
count_res = int(get_path(row, [COUNT_VAR], '0'))
chunk_res.update({stp: (ask_res, count_res) for stp in stps})
return chunk_res
def predict_query(sparql, timeout, graph_pattern, source,
limit=config.PREDICTION_RESULT_LIMIT):
"""Performs a single query starting at ?SOURCE returning all ?TARGETs."""
assert isinstance(graph_pattern, GraphPattern)
assert isinstance(source, Identifier)
_query_stats.predict_query_count += 1
vars_in_graph = graph_pattern.vars_in_graph
if TARGET_VAR not in vars_in_graph:
logger.warning(
'graph pattern without %s used for prediction:\n%r',
TARGET_VAR.n3(), graph_pattern
)
return timeout, set()
q = graph_pattern.to_sparql_select_query(
projection=[TARGET_VAR],
distinct=True,
bind={SOURCE_VAR: source},
limit=limit,
)
try:
t, q_res = _query(sparql, timeout, q)
except (SPARQLWrapperException, SAXParseException, URLError):
logger.warning(
'Exception occurred during prediction, assuming empty result...\n'
'Query:\n%s\nException:', q,
exc_info=1, # appends exception to message
)
t, q_res = timeout, {}
else:
if query_time_soft_exceeded(t, timeout):
kind = 'hard' if query_time_hard_exceeded(t, timeout) else 'soft'
logger.info(
'prediction query exceeded %s timeout %s:\n%s',
kind, t, q
)
res = []
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[])
)
for row in bindings:
res.append(get_path(row, [TARGET_VAR]))
return timeout, set(res)
def predict_query(sparql,
timeout,
graph_pattern,
source,
limit=config.PREDICTION_RESULT_LIMIT):
"""Performs a single query starting at ?SOURCE returning all ?TARGETs."""
assert isinstance(graph_pattern, GraphPattern)
assert isinstance(source, Identifier)
_query_stats.predict_query_count += 1
vars_in_graph = graph_pattern.vars_in_graph
if TARGET_VAR not in vars_in_graph:
logger.warning('graph pattern without %s used for prediction:\n%r',
TARGET_VAR.n3(), graph_pattern)
return timeout, []
q = graph_pattern.to_sparql_select_query(
projection=[TARGET_VAR],
distinct=True,
bind={SOURCE_VAR: source},
limit=limit,
)
try:
t, q_res = _query(sparql, timeout, q)
except (SPARQLWrapperException, SAXParseException, URLError):
logger.warning(
'Exception occurred during prediction, assuming empty result...\n'
'Query:\n%s\nException:',
q,
exc_info=1, # appends exception to message
)
t, q_res = timeout, {}
else:
if query_time_soft_exceeded(t, timeout):
kind = 'hard' if query_time_hard_exceeded(t, timeout) else 'soft'
logger.info('prediction query exceeded %s timeout %s:\n%s', kind,
t, q)
res = []
res_rows_path = ['results', 'bindings']
bindings = sparql_json_result_bindings_to_rdflib(
get_path(q_res, res_rows_path, default=[]))
for row in bindings:
res.append(get_path(row, [TARGET_VAR]))
return timeout, set(res)
