def __init__(self, dataset: str, use_correct_type: bool, use_old_semantic_typer: bool, train_sm_ids: List[str],
exec_dir: Optional[Union[str, Path]] = None, sm_type_dir: Optional[Union[str, Path]] = None):
self.dataset: str = dataset
self.train_sm_ids = train_sm_ids
self.ont = get_ontology(dataset)
self.karma_models: Dict[str, KarmaModel] = {km.id: km for km in get_karma_models(dataset)}
# can only run once time, trying re-invoke will generate an error
self.__has_run_modeling = False
if exec_dir is None:
exec_dir = get_cache_dir(dataset, train_sm_ids) / "mohsen_jws2015"
self.exec_dir: Path = Path(exec_dir)
self.sm_type_dir = sm_type_dir
# parameters for mohsen's algorithm
self.use_old_semantic_typer = use_old_semantic_typer
self.use_correct_type = use_correct_type
assert Settings.get_instance().semantic_labeling_top_n_stypes <= 4
self.num_candidate_semantic_type = 4
self.multiple_same_property_per_node = True
self.coherence = 1.0
self.confidence = 1.0
self.size_reduction = 0.5
self.num_candidate_mappings = 50
self.mapping_branching_factor = 50
self.topk_steiner_tree = 10
# take all, not cut off everything
self.cut_off = int(1e6)
self.our_and_karma_sm_alignments = {}
def get_instance(dataset: str, train_sms: List[SemanticModel]):
if PrimaryKey.instance is None:
cache_file = get_cache_dir(
dataset, train_sms) / "weak_models" / "primary_keys.json"
if not cache_file.exists():
train_sm_ids = {sm.id for sm in train_sms}
train_tbls = {
tbl.id: tbl
for tbl in get_data_tables(dataset)
if tbl.id in train_sm_ids
}
predictions: Dict[str, List[dict]] = defaultdict(lambda: [])
pesudo_primary_keys = {}
for sm in train_sms:
jsonld_objects = jsonld_generator(sm, train_tbls[sm.id])
for n in sm.graph.iter_class_nodes():
fields = [
e.label.decode("utf-8")
for e in n.iter_outgoing_links()
if e.get_target_node().is_data_node()
]
if len(fields) == 0:
continue
if 'karma:classLink' in fields:
pesudo_primary_keys[n.label] = 'karma:classLink'
continue
results = extract_node_data(n, jsonld_objects)
views = create_unique_views(results, fields)
predictions[n.label].append(
predict_pesudo_keys(fields, views))
for class_lbl, preds in predictions.items():
total = defaultdict(lambda: 0)
for pred in preds:
for link_lbl in pred:
total[link_lbl] += pred[link_lbl]
for link_lbl, count in total.items():
total[link_lbl] = count
pesudo_primary_keys[class_lbl] = max(total.items(),
key=lambda x: x[1])[0]
PrimaryKey.instance = PrimaryKey({
k: v.encode('utf-8')
for k, v in pesudo_primary_keys.items()
})
cache_file.parent.mkdir(exist_ok=True, parents=True)
serializeJSON(PrimaryKey.instance, cache_file, indent=4)
else:
PrimaryKey.instance: PrimaryKey = deserializeJSON(
cache_file, Class=PrimaryKey)
return PrimaryKey.instance
def __init__(self,
dataset: str,
train_sms: List[SemanticModel],
exec_dir: Optional[Path] = None) -> None:
self.dataset = dataset
self.train_source_ids = {sm.id for sm in train_sms}
if exec_dir is None:
exec_dir = get_cache_dir(dataset, train_sms) / "semantic-labeling"
self.exec_dir = Path(exec_dir)
self.exec_dir.mkdir(exist_ok=True, parents=True)
self.model = None
self.stype_db = SemanticTypeDB.get_stype_db(
dataset, [sm.id for sm in train_sms], self.exec_dir)
def get_data_constraint_model(
dataset: str,
train_sms: List[SemanticModel],
) -> DataConstraint:
global _instance
if _instance is None:
cache_file = get_cache_dir(
dataset, train_sms) / "weak_models" / "data_constraint.pkl"
cache_file.parent.mkdir(exist_ok=True, parents=True)
need_rebuilt = True
settings = Settings.get_instance()
valid_threshold = settings.data_constraint_valid_threshold
guess_datetime_threshold = settings.data_constraint_guess_datetime_threshold
n_comparison_samples = settings.data_constraint_n_comparison_samples
random_seed = settings.random_seed
n_sample = settings.n_samples
if cache_file.exists():
DataConstraint.logger.debug("Try to load previous run...")
model, cached_dataset, cached_train_sm_ids, extra_args = deserialize(
cache_file)
if cached_dataset == dataset \
and cached_train_sm_ids == {sm.id for sm in train_sms} \
and extra_args == (
valid_threshold, guess_datetime_threshold, n_comparison_samples,
random_seed, n_sample):
need_rebuilt = False
if need_rebuilt:
DataConstraint.logger.debug("Re-build data-constraint model...")
data_tables = [
ColumnBasedTable.from_table(tbl)
for tbl in get_sampled_data_tables(dataset)
]
model = DataConstraint(train_sms, data_tables, valid_threshold,
guess_datetime_threshold,
n_comparison_samples)
serialize((model, dataset, {sm.id
for sm in train_sms},
(valid_threshold, guess_datetime_threshold,
n_comparison_samples, random_seed, n_sample)),
cache_file)
_instance = model
return _instance
def get_stype_assistant_model(dataset: str, train_sms: List[SemanticModel]):
global _instance
if _instance is None:
cache_file = get_cache_dir(dataset, train_sms) / "weak_models" / "stype_assistant.pkl"
cache_file.parent.mkdir(exist_ok=True, parents=True)
need_rebuilt = True
if cache_file.exists():
SemanticTypeAssistant.logger.debug("Try to load previous run...")
model, cache_dataset, cache_train_sm_ids = deserialize(cache_file)
if cache_dataset == dataset and cache_train_sm_ids == {sm.id for sm in train_sms}:
need_rebuilt = False
ont_graph = get_ont_graph(dataset)
ont = get_ontology(dataset)
stat = Statistic.get_instance(train_sms)
ota = EmpiricalTripleAdviser(ont_graph, ont, stat.p_triple, 15)
model.triple_adviser = ota
if need_rebuilt:
ont_graph = get_ont_graph(dataset)
ont = get_ontology(dataset)
stat = Statistic.get_instance(train_sms)
ota = EmpiricalTripleAdviser(ont_graph, ont, stat.p_triple, 15)
typer = SemanticTyper.get_instance(dataset, train_sms)
try:
typer.load_model()
except:
sms = get_semantic_models(dataset)
train_ids = {sm.id for sm in train_sms}
typer.semantic_labeling(train_sms, [sm for sm in sms if sm.id not in train_ids], 4)
model = SemanticTypeAssistant(train_sms, typer, ota)
model.triple_adviser = None
serialize((model, dataset, {sm.id for sm in train_sms}), cache_file)
model.triple_adviser = ota
_instance = model
return _instance
def create_rust_input(dataset: str, scenario: Scenario, train_sms, test_sms):
train_sm_ids = [sm.id for sm in train_sms]
exec_dir = get_cache_dir(dataset, train_sms) / "mohsen_jws2015"
modeler = MohsenSemanticModeling(
dataset,
False,
False,
train_sm_ids,
exec_dir=exec_dir,
sm_type_dir=Path(config.fsys.debug.as_path()) / "tmp" /
"models-json-temp")
candidate_smss = modeler.sm_candidate_generation(train_sms, test_sms)
if scenario == Scenario.SCENARIO_1:
data_node_mode = DataNodeMode.IGNORE_DATA_NODE
else:
data_node_mode = DataNodeMode.NO_TOUCH
train_sm_ids = {sm.id for sm in train_sms}
real_test_sm_ids = {sm.id for sm in test_sms if sm.id not in train_sm_ids}
train_eval_hist = get_eval_hist(train_sm_ids, test_sms, candidate_smss,
data_node_mode)
test_eval_hist = get_eval_hist(real_test_sm_ids, test_sms, candidate_smss,
data_node_mode)
serializeCSV(
train_eval_hist,
exec_dir / f"evaluation_result_{scenario.value}.train.oracle.csv")
serializeCSV(
test_eval_hist,
exec_dir / f"evaluation_result_{scenario.value}.test.oracle.csv")
# now create rust bridge
obj = {}
for gold_sm, candidate_sms in zip(test_sms, candidate_smss):
obj[gold_sm.id] = [c.graph.to_dict() for c in candidate_sms]
serializeJSON(obj, exec_dir / "rust-karma-pred-input.json")
def get_classifier(self, retrain: bool, train_examples: List[Example]):
# TODO: implement this properly, currently, we have to train and save manually
cached_file = get_cache_dir(
self.example_annotator.dataset,
list(self.example_annotator.train_source_ids)
) / "weak_models" / "node_prob_classifier.pkl"
if not cached_file.exists() or retrain:
self.logger.debug("Retrain new model")
raw_X_train = make_data(self, train_examples)
classifier = LogisticRegression(fit_intercept=True)
X_train = numpy.asarray(
[list(features.values())[1:] for features in raw_X_train])
X_train, y_train = X_train[:, :-1], [
int(x) for x in X_train[:, -1]
]
scaler = StandardScaler().fit(X_train)
scaler.transform(X_train)
try:
classifier.fit(X_train, y_train)
except ValueError as e:
assert str(e).startswith(
"This solver needs samples of at least 2 classes in the data"
)
# this should be at a starter phase when we don't have any data but use ground-truth to build
X_train = numpy.vstack([X_train, [0, 0]])
y_train.append(0)
classifier.fit(X_train, y_train)
cached_file.parent.mkdir(exist_ok=True, parents=True)
serialize((scaler, classifier), cached_file)
return scaler, classifier
return deserialize(cached_file)
def clear_cache(dataset: str) -> None:
# only clear cache which are generated for different training models
cache_dir = get_cache_dir(dataset)
for item in cache_dir.iterdir():
if item.is_dir():
shutil.rmtree(item)
def run_evaluation_workflow(dataset: str, scenario: Scenario, train_sms,
test_sms):
ont: Ontology = get_ontology(dataset)
karma_models: List[KarmaModel] = get_karma_models(dataset)
semantic_models: List[SemanticModel] = get_semantic_models(dataset)
train_sm_ids = [sm.id for sm in train_sms]
sdesc_args = dict(
dataset=dataset,
train_sm_ids=train_sm_ids,
use_correct_type=
False, # we always put semantic types to learnedSemanticTypes, even for userSetSemanticTypes
use_old_semantic_typer=False,
exec_dir=get_cache_dir(dataset, train_sms) / "mohsen_jws2015",
sm_type_dir=Path(config.fsys.debug.as_path()) / "tmp" /
"models-json-temp")
# STEP 1: run semantic typing to generate semantic typing and put result to a temporal folder
if sdesc_args['sm_type_dir'].exists():
shutil.rmtree(sdesc_args['sm_type_dir'])
sdesc_args['sm_type_dir'].mkdir(exist_ok=True, parents=True)
top_k_types = Settings.get_instance().semantic_labeling_top_n_stypes
typer = create_semantic_typer(dataset, train_sms)
typer.semantic_labeling(train_sms, test_sms, top_k_types, eval_train=True)
for sm, ksm in zip(semantic_models, karma_models):
# assign semantic types to learnedSemanticTypes
sm_alignment = SemanticModelAlignment(sm, ksm)
for col in ksm.source_columns:
attr = sm.get_attr_by_label(
sm.graph.get_node_by_id(
sm_alignment.alignment[col.id]).label.decode('utf-8'))
node = ksm.karma_graph.get_node_by_id(col.id)
link = node.get_first_incoming_link()
node.learned_semantic_types = [
KarmaSemanticType(node.id, stype.domain, stype.type,
typer.__class__.__name__,
stype.confidence_score)
for stype in attr.semantic_types
]
node.user_semantic_types = [
KarmaSemanticType(node.id,
link.get_source_node().label.decode(),
link.label.decode(), "User", 1.0)
]
serializeJSON(ksm.to_normalized_json_model(ont),
sdesc_args['sm_type_dir'] / f"{ksm.id}-model.json",
indent=4)
# STEP 2: invoking semantic modeling
modeler = MohsenSemanticModeling(**sdesc_args)
pred_sms = modeler.sm_prediction(train_sms, test_sms)
# STEP 3: prediction semantic mapping result
eval_hist = [["source", "precision", "recall", "f1", "stype-acc"]]
if scenario == Scenario.SCENARIO_1:
data_node_mode = DataNodeMode.IGNORE_DATA_NODE
else:
data_node_mode = DataNodeMode.NO_TOUCH
for sm, pred_sm in zip(test_sms, pred_sms):
eval_result = smodel_eval.f1_precision_recall(sm.graph, pred_sm.graph,
data_node_mode)
eval_hist.append([
sm.id, eval_result["precision"], eval_result["recall"],
eval_result["f1"],
smodel_eval.stype_acc(sm.graph, pred_sm.graph)
])
eval_hist.append([
'average',
np.average([float(x[1]) for x in eval_hist[1:]]),
np.average([float(x[2]) for x in eval_hist[1:]]),
np.average([float(x[3]) for x in eval_hist[1:]]),
np.average([float(x[4]) for x in eval_hist[1:]])
])
serializeCSV(
eval_hist,
sdesc_args["exec_dir"] / f"evaluation_result_{scenario.value}.csv")
# STEP 4: prediction semantic labeling result
pred_stypes = modeler.semantic_labeling(train_sms, test_sms)
for pred_stype, sm in zip(pred_stypes, test_sms):
for attr in sm.attrs:
if attr.label not in pred_stype:
attr.semantic_types = []
else:
attr.semantic_types = pred_stype[attr.label]
eval_sources(
test_sms, sdesc_args["exec_dir"] /
f"evaluation_result_{scenario.value}_stype.csv")
# STEP 5: visualize the prediction
(sdesc_args['exec_dir'] / "prediction-viz").mkdir(exist_ok=True)
need_render_graphs = [
(colorize_prediction(
pred_sm.graph,
AutoLabel.auto_label_max_f1(sm.graph, pred_sm.graph, False)[0]),
sdesc_args['exec_dir'] / "prediction-viz" / f"{sm.id}.png")
for sm, pred_sm in zip(test_sms, pred_sms)
]
with ThreadPool(32) as p:
p.map(render_graph, need_render_graphs)
return eval_hist
if __name__ == '__main__':
# HYPER-ARGS
args = get_shell_args()
Settings.get_instance(
False
).semantic_labeling_top_n_stypes = args.semantic_labeling_top_n_stypes
Settings.get_instance().semantic_labeling_method = args.semantic_typer
Settings.get_instance().log_current_settings()
exp_dir = Path(args.exp_dir)
assert exp_dir.exists()
source_models = {sm.id: sm for sm in get_semantic_models(args.dataset)}
train_sms = [source_models[sid] for sid in args.kfold['train_sm_ids']]
test_sms = [source_models[sid] for sid in args.kfold['test_sm_ids']]
eval_hist = run_evaluation_workflow(args.dataset, Scenario.SCENARIO_2,
train_sms, test_sms)
serializeCSV(eval_hist,
exp_dir / f"kfold-{get_short_train_name(train_sms)}.test.csv")
serializeJSON(args,
exp_dir /
f"kfold-{get_short_train_name(train_sms)}.meta.json",
indent=4)
shutil.move(
get_cache_dir(args.dataset, train_sms) / "mohsen_jws2015",
exp_dir / f"kfold-{get_short_train_name(train_sms)}")