Merge branch 'master' of https://github.com/biolink/kgx

kgx/cli/cli_utils.py

@@ -383,7 +383,6 @@ def _process_knowledge_source(ksf: str, spec: str) -> Union[str, bool, Tuple]:
         if spec.lower() == "true":
             return True
         elif spec.lower() == "false":
-            print("returning false")
             return False
         else:
             # If a Tuple, expect a comma-delimited string?
@@ -521,7 +520,6 @@ def transform(
         pool.join()
         graphs = [r.get() for r in results]
     else:
-        print("no transform config")
         source_dict: Dict = {
             "input": {
                 "format": input_format,
@@ -557,9 +555,7 @@ def transform(
                             + "' are all rewrite specifications!"
                         )
                 else:
-                    print("not a tuple")
                     source_dict["input"][ksf] = ksf_spec
-                    print(source_dict)
 
         name = os.path.basename(inputs[0])
         transform_source(

kgx/graph_operations/summarize_graph.py

@@ -222,7 +222,7 @@ def __init__(self, category_curie: str, summary):
             # ...so that Category related entries at that
             # higher level may be properly initialized
             # for subsequent facet metadata access
-            if not self.category_curie == "unknown":
+            if self.category_curie != "unknown":
                 self.summary.node_stats[NODE_CATEGORIES].add(self.category_curie)
             self.summary.node_stats[NODE_ID_PREFIXES_BY_CATEGORY][
                 self.category_curie

kgx/sink/rdf_sink.py

@@ -309,7 +309,6 @@ def uriref(self, identifier: str) -> URIRef:
             # identifier is an entity
             fixed_identifier = identifier
             if fixed_identifier.startswith(":"):
-                # TODO: this should be handled upstream by prefixcommons-py
                 fixed_identifier = fixed_identifier.replace(":", "", 1)
             if " " in identifier:
                 fixed_identifier = fixed_identifier.replace(" ", "_")
@@ -379,7 +378,6 @@ def _get_property_type(self, p: str) -> str:
             The type for property name
 
         """
-        # TODO: this should be properly defined in the model
         default_uri_types = {
             "biolink:type",
             "biolink:category",

kgx/source/json_source.py

@@ -1,4 +1,5 @@
 import gzip
+import typing
 from typing import Optional, Generator, Any
 import ijson
 from itertools import chain
@@ -34,7 +35,7 @@ def parse(
         format: str = "json",
         compression: Optional[str] = None,
         **kwargs: Any
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from a JSON and yields records.
 

kgx/source/jsonl_source.py

@@ -1,5 +1,7 @@
 import gzip
 import re
+import typing
+
 import jsonlines
 from typing import Optional, Any, Generator, Dict
 
@@ -25,7 +27,7 @@ def parse(
         format: str = "jsonl",
         compression: Optional[str] = None,
         **kwargs: Any,
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from JSON Lines and yields records.
 

kgx/source/neo_source.py

@@ -1,4 +1,5 @@
 import itertools
+import typing
 from typing import Any, Dict, List, Optional, Iterator, Tuple, Generator
 
 from neo4j import GraphDatabase, Neo4jDriver
@@ -48,7 +49,7 @@ def parse(
         is_directed: bool = True,
         page_size: int = 50000,
         **kwargs: Any,
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from Neo4j instance and yields records
 
@@ -338,7 +339,6 @@ def load_node(self, node_data: Dict) -> Optional[Tuple]:
 
         """
         self.node_count += 1
-        # TODO: remove the seen_nodes
         self.seen_nodes.add(node_data["id"])
 
         self.set_node_provenance(node_data)
@@ -458,7 +458,6 @@ def get_pages(
             An iterator for a list of records from Neo4j. The size of the list is ``page_size``
 
         """
-        # TODO: use async
         # itertools.count(0) starts counting from zero, and would run indefinitely without a return statement.
         # it's distinguished from applying a while loop via providing an index which is formative with the for statement
         for i in itertools.count(0):

kgx/source/obograph_source.py

@@ -1,4 +1,5 @@
 import gzip
+import typing
 from itertools import chain
 from typing import Optional, Tuple, Dict, Generator, Any
 import ijson
@@ -33,7 +34,7 @@ def parse(
         format: str = "json",
         compression: Optional[str] = None,
         **kwargs: Any,
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from JSON and yields records.
 
@@ -182,7 +183,6 @@ def read_edge(self, edge: Dict) -> Optional[Tuple]:
                         if mapping:
                             element = self.toolkit.get_element(mapping)
 
-                    #  TODO: not sure how this exception would be thrown here.. under what conditions?
                     except ValueError as e:
                         self.owner.log_error(
                             entity=str(edge["pred"]),
@@ -254,7 +254,6 @@ def get_category(self, curie: str, node: dict) -> Optional[str]:
 
         if not category or category == "biolink:OntologyClass":
             prefix = PrefixManager.get_prefix(curie)
-            # TODO: the mapping should be via biolink-model lookups
             if prefix == "HP":
                 category = "biolink:PhenotypicFeature"
             elif prefix == "CHEBI":

kgx/source/owl_source.py

@@ -1,3 +1,4 @@
+import typing
 from typing import Set, Optional, Generator, Any
 
 import rdflib
@@ -38,7 +39,7 @@ def parse(
         format: str = "owl",
         compression: Optional[str] = None,
         **kwargs: Any,
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from an OWL and yields records.
 

kgx/source/rdf_source.py

@@ -1,4 +1,5 @@
 import gzip
+import typing
 from typing import Set, Dict, Union, Optional, Any, Tuple, List, Generator
 
 import rdflib
@@ -43,9 +44,6 @@ class RdfSource(Source):
     def __init__(self, owner):
         super().__init__(owner)
         self.DEFAULT = Namespace(self.prefix_manager.prefix_map[""])
-        # TODO: use OBO IRI from biolink model context once
-        #  https://github.com/biolink/biolink-model/issues/211 is resolved
-        # self.OBO = Namespace('http://purl.obolibrary.org/obo/')
         self.OBAN = Namespace(self.prefix_manager.prefix_map["OBAN"])
         self.PMID = Namespace(self.prefix_manager.prefix_map["PMID"])
         self.BIOLINK = Namespace(self.prefix_manager.prefix_map["biolink"])
@@ -65,7 +63,6 @@ def __init__(self, owner):
             set(self.toolkit.get_all_edge_properties(formatted=True))
         )
 
-        # TODO: validate expansion of the scope of this statement to include 'knowledge_source' and its descendants?
         for ksf in knowledge_provenance_properties:
             self.node_property_predicates.add(
                 URIRef(self.prefix_manager.expand("biolink:" + ksf))
@@ -133,7 +130,7 @@ def parse(
         format: str = "nt",
         compression: Optional[str] = None,
         **kwargs: Any,
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from RDF N-Triples and yields records.
 

kgx/source/sssom_source.py

@@ -3,6 +3,7 @@
 """
 import gzip
 import re
+import typing
 
 import pandas as pd
 from typing import Optional, Generator, Any, Dict, Tuple
@@ -70,7 +71,7 @@ def parse(
         format: str,
         compression: Optional[str] = None,
         **kwargs: Any,
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         Parse a SSSOM TSV
 

kgx/source/trapi_source.py

@@ -1,14 +1,13 @@
 import gzip
+import typing
+
 import ijson
 from itertools import chain
 from typing import Dict, Tuple, Generator, Optional, Any
 
 from kgx.source.json_source import JsonSource
 
 
-# TODO: update for TRAPI 1.0 spec
-
-
 class TrapiSource(JsonSource):
     """
     TrapiSource is responsible for reading data as records
@@ -26,7 +25,7 @@ def parse(
         format: str = "json",
         compression: Optional[str] = None,
         **kwargs: Any
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from a JSON and yields records.
 

kgx/source/tsv_source.py

@@ -1,5 +1,6 @@
 import re
 import tarfile
+import typing
 from typing import Dict, Tuple, Any, Generator, Optional, List
 import pandas as pd
 
@@ -58,7 +59,7 @@ def parse(
         format: str,
         compression: Optional[str] = None,
         **kwargs: Any,
-    ) -> Generator:
+    ) -> typing.Generator:
         """
         This method reads from a TSV/CSV and yields records.
 
@@ -128,9 +129,6 @@ def parse(
                         continue
 
                     f = tar.extractfile(member)
-                    # TODO: can this somehow be streamed here?
-                    #       Question: who put the above comment here? One wonders whether the use of the chunk-based
-                    #       file_iter, with the Generator yield statement below, isn't effectively streaming the file?
                     file_iter = pd.read_csv(
                         f,
                         dtype=str,
@@ -154,7 +152,6 @@ def parse(
                         continue
 
                     f = tar.extractfile(member)
-                    # TODO: can this somehow be streamed here?
                     file_iter = pd.read_csv(
                         f,
                         dtype=str,

kgx/transformer.py

@@ -254,7 +254,6 @@ def transform(
                     if ksf in input_args:
                         ks_args[ksf] = input_args[ksf]
 
-                # TODO: does this call also need the default_provenance named argument?
                 intermediate_source_generator = intermediate_source.parse(
                     intermediate_sink.graph, **ks_args
                 )
@@ -362,7 +361,6 @@ def process(self, source: Generator, sink: Sink) -> None:
                     # last element of rec is the node properties
                     sink.write_node(rec[-1])
 
-    # TODO: review whether or not the 'save()' method need to be 'knowledge_source' aware?
     def save(self, output_args: Dict) -> None:
         """
         Save data from the in-memory store to a desired sink.

kgx/utils/infores.py

@@ -160,7 +160,6 @@ def _process_infores(source: str) -> str:
                 infores = re.sub(r"[\W]", "", infores)
                 infores = re.sub(r"_", "-", infores)
 
-                # TODO: to be fully compliant, the InfoRes needs to have the 'infores' prefix?
                 infores = "infores:" + infores
 
                 return infores
@@ -336,7 +335,6 @@ def set_provenance_map(self, kwargs: Dict):
         """
         if "default_provenance" in kwargs:
             self.default_provenance = kwargs.pop("default_provenance")
-            print(self.default_provenance)
 
         ksf_found = []
         for ksf in knowledge_provenance_properties:
@@ -353,9 +351,7 @@ def set_provenance_map(self, kwargs: Dict):
                         )
                 else:
                     ir = self.get_mapping(ksf)
-                    print(ir)
                     self.mapping[ksf] = ir.set_provenance_map_entry(ksf_value)
-                    print("mapping", self.mapping)
 
         # if none specified, add at least one generic 'knowledge_source'
         if not ksf_found:
@@ -384,7 +380,6 @@ def set_provenance(self, ksf: str, data: Dict):
         """
 
         if ksf not in data.keys():
-            print(data.keys())
             if ksf in self.mapping and not isinstance(self.mapping[ksf], dict):
                 data[ksf] = self.mapping[ksf]()
             else:
@@ -394,7 +389,6 @@ def set_provenance(self, ksf: str, data: Dict):
         else:
             # If data is s a non-string iterable then, coerce into a simple list of sources
             if isinstance(data[ksf], (list, set, tuple)):
-                print("is a tuple???")
                 sources = list(data[ksf])
             else:
                 # wraps knowledge sources that are multivalued in a list even if single valued

kgx/utils/kgx_utils.py

@@ -297,7 +297,6 @@ def expand(
 
 _default_toolkit = None
 
-# TODO: not sure how threadsafe this simple-minded Toolkit cache is
 _toolkit_versions: Dict[str, Toolkit] = dict()
 
 
@@ -418,7 +417,6 @@ def get_prefix_prioritization_map() -> Dict[str, List]:
     """
     toolkit = get_toolkit()
     prefix_prioritization_map = {}
-    # TODO: Lookup via Biolink CURIE should be supported in bmt
     descendants = toolkit.get_descendants("named thing")
     descendants.append("named thing")
     for d in descendants:
@@ -493,7 +491,6 @@ def get_biolink_property_types() -> Dict:
         property_type = get_type_for_property(p)
         types[p] = property_type
 
-    # TODO: this should be moved to biolink model
     types["biolink:predicate"] = "uriorcurie"
     types["biolink:edge_label"] = "uriorcurie"
     return types
@@ -503,8 +500,6 @@ def get_type_for_property(p: str) -> str:
     """
     Get type for a property.
 
-    TODO: Move this to biolink-model-default_toolkit
-
     Parameters
     ----------
     p: str

kgx/utils/rdf_utils.py

@@ -29,7 +29,6 @@
 property_mapping: Dict = dict()
 reverse_property_mapping: Dict = dict()
 
-# TODO: this should be populated via bmt
 is_property_multivalued = {
     "id": False,
     "subject": False,

kgx/validator.py

@@ -66,9 +66,7 @@ def get_the_validator(
         Creates and manages a default singleton Validator in the module, when called
         """
         if not cls._the_validator:
-            # TODO: This may need to be adjusted periodically,
-            #       but for now, we reset the model to a recent version
-            cls.set_biolink_model("2.2.11")
+            cls.set_biolink_model("3.0.0")
             cls._the_validator = Validator(
                 verbose=verbose,
                 progress_monitor=progress_monitor,
@@ -92,7 +90,6 @@ def __init__(
             Callable[[GraphEntityType, List], None]
         ] = progress_monitor
 
-        # TODO: fix... this attribute is not used anywhere at the moment?
         self.schema: Optional[str] = schema
 
         # internal attributes
@@ -274,7 +271,6 @@ def get_required_edge_properties(toolkit: Optional[Toolkit] = None) -> list:
     def validate(self, graph: BaseGraph):
         """
         Validate nodes and edges in a graph.
-        TODO: Support strict mode
 
         Parameters
         ----------