**DON'T MERGE -- ARCHIVE ** Build overhaul v4.0.0

.github/workflows/kg-build-part2.yml

@@ -1,7 +1,7 @@
 name: KG Build - Part 2 (Construct Knowledge Graphs)
 on:
  schedule:
-   - cron: '0 0 25 * *'  # runs at 00:00:00 UTC on the second day of each month
+   - cron: '0 0 29 * *'  # runs at 00:00:00 UTC on the second day of each month
 env:
  PROJECT_ID: ${{ secrets.GCE_PROJECT }}
  GCS_SERVICE_ACCOUNT: ${{ secrets.GCE_SA_KEY }}

.gitignore

@@ -35,6 +35,7 @@ builds/temp/*
 #### External Libraries
 pkt_kg/libs/deepwalk_c_master/*
 pkt_kg/libs/walking-rdf-and-owl-master/*
+pkt_kg/libs/pylucene*
 
 #### Scripts
 pkt_kg/kg_embedding_visualizer.py
@@ -48,7 +49,8 @@ scratch*.py
 /resources/embeddings/*
 /resources/knowledge_graphs/
 /resources/kr_model/
-/resources/node_data/*
+/resources/metadata/*
+!/resources/metadata/pheknowlator_source_metadata.xlsx
 /resources/ontologies/*
 /resources/owl_decoding/*
 /resources/processed_data/*
@@ -60,7 +62,7 @@ scratch*.py
 !/resources/edge_data/README.md
 !/resources/embeddings/README.md
 !/resources/knowledge_graphs/README.md
-!/resources/node_data/README.md
+!/resources/metadata/README.md
 !/resources/ontologies/ontology_source_metadata.txt
 !/resources/ontologies/README.md
 !/resources/owl_decoding/README.md

Main.py

@@ -26,7 +26,7 @@ def main():
     parser.add_argument('-b', '--kg', help='build type: "partial", "full", or "post-closure"', required=True)
     parser.add_argument('-r', '--rel', help='yes/no - adding inverse relations to knowledge graph', required=True)
     parser.add_argument('-s', '--owl', help='yes/no - removing OWL Semantics from knowledge graph', required=True)
-    parser.add_argument('-m', '--nde', help='yes/no - adding node metadata to knowledge graph', required=True)
+    parser.add_argument('-m', '--mta', help='yes/no - adding entity metadata to knowledge graph', required=True)
     parser.add_argument('-o', '--out', help='name/path to directory where to write knowledge graph', required=True)
     args = parser.parse_args()
 
@@ -85,21 +85,21 @@ def main():
 
     if args.kg == 'partial':
         kg = PartialBuild(construction=args.app,
-                          node_data=args.nde,
+                          node_data=args.mta,
                           inverse_relations=args.rel,
                           decode_owl=args.owl,
                           cpus=cpus,
                           write_location=args.out)
     elif args.kg == 'post-closure':
         kg = PostClosureBuild(construction=args.app,
-                              node_data=args.nde,
+                              node_data=args.mta,
                               inverse_relations=args.rel,
                               decode_owl=args.owl,
                               cpus=cpus,
                               write_location=args.out)
     else:
         kg = FullBuild(construction=args.app,
-                       node_data=args.nde,
+                       node_data=args.mta,
                        inverse_relations=args.rel,
                        decode_owl=args.owl,
                        cpus=cpus,

README.rst

@@ -129,7 +129,7 @@ The ``pkt_kg`` library requires a specific project directory structure.
         |         |
         |     knowledge_graphs/
         |         |
-        |     node_data/
+        |     metadata/
         |         |
         |     ontologies/
         |         |
@@ -165,7 +165,9 @@ The `KG Construction`_ Wiki page provides a detailed description of the knowledg
 
 * `resources/construction_approach/subclass_construction_map.pkl`_
 * `resources/Master_Edge_List_Dict.json`_ ➞ *automatically created after edge list construction*
-* `resources/node_data/node_metadata_dict.pkl <https://github.com/callahantiff/PheKnowLator/blob/master/resources/node_data/README.md>`__ ➞ *if adding metadata for new edges to the knowledge graph*
+* `resources/metadata/entity_metadata_dict.pkl <https://github
+.com/callahantiff/PheKnowLator/blob/master/resources/metadata/README.md>`__ ➞ *if adding metadata for new edges to the
+knowledge graph*
 * `resources/knowledge_graphs/PheKnowLator_MergedOntologies*.owl`_ ➞ *see* `ontology README`_ *for information*
 * `resources/relations_data/RELATIONS_LABELS.txt`_
 * `resources/relations_data/INVERSE_RELATIONS.txt`_ ➞ *if including inverse relations*
@@ -221,7 +223,7 @@ The program can be run locally using the `main.py`_ script or using the `main.ip
  kg = PartialBuild(kg_version='v2.0.0',
                    write_location='./resources/knowledge_graphs',
                    construction='subclass,
-                   node_data='yes,
+                   metadata='yes,
                    inverse_relations='yes',
                    cpus=available_cpus,
                    decode_owl='yes')
@@ -437,7 +439,8 @@ Callahan TJ, Tripodi IJ, Hunter LE, Baumgartner WA. `A Framework for Automated C
 
 .. _`resources/Master_Edge_List_Dict.json`: https://www.dropbox.com/s/t8sgzd847t1rof4/Master_Edge_List_Dict.json?dl=1
 
-.. _`resources/node_data/node_metadata_dict.pkl`: https://github.com/callahantiff/PheKnowLator/blob/master/resources/node_data/README.md
+.. _`resources/metadata/entity_metadata_dict.pkl`: https://github
+.com/callahantiff/PheKnowLator/blob/master/resources/metadata/README.md
 
 .. _`resources/knowledge_graphs/PheKnowLator_MergedOntologies*.owl`: https://www.dropbox.com/s/75lkod7vzpgjdaq/PheKnowLator_MergedOntologiesGeneID_Normalized_Cleaned.owl?dl=1
 

builds/build_requirements.txt

@@ -4,14 +4,15 @@ google==1.9.3
 google-api-core==1.24.1
 google-api-python-client~=1.7.9
 google-cloud-storage==1.28.0
-lxml==4.6.5
+lxml>=4.6.5
 networkx==2.4
-numpy==1.21.0
+numpy==1.19.5
 openpyxl==3.0.3
 oauth2client~=4.1.3
 Owlready2==0.25
 pandas==1.0.5
 python-json-logger==2.0.1
+pyyaml
 ray~=1.1.0
 rdflib==4.2.2
 reactome2py==0.0.8