updated rdf and report .py scripts to read in proper files

scripts/generate-rdf.py

@@ -3,22 +3,22 @@
 from kgx.cli.cli_utils import transform as kgx_transform
 from loguru import logger
 
-logger.info(f"Creating rdf output: output/geneontology.org_macroMolecularMachine_associations.nt.gz ...")
 
 src_files = []
-src_nodes = f"output/geneontology.org_macroMolecularMachine_associations_nodes.tsv"
-src_edges = f"output/geneontology.org_macroMolecularMachine_associations_edges.tsv"
+outfile = "output/go_annotation_associations.nt.gz"
+src_nodes = "output/go_annotation_nodes.tsv"
+src_edges = "output/go_annotation_edges.tsv"
+
+logger.info("Creating rdf output: {}...".format(outfile))
 
 if Path(src_nodes).is_file():
     src_files.append(src_nodes)
 if Path(src_edges).is_file():
     src_files.append(src_edges)
 
-kgx_transform(
-    inputs=src_files,
-    input_format="tsv",
-    stream=True,
-    output=f"output/geneontology.org_macroMolecularMachine_associations.nt.gz",
-    output_format="nt",
-    output_compression="gz",
-)
+kgx_transform(inputs=src_files,
+              input_format="tsv",
+              stream=True,
+              output=outfile,
+              output_format="nt",
+              output_compression="gz")

scripts/generate-report.py

@@ -2,8 +2,11 @@
 
 import duckdb
 
-nodes_file = "output/geneontology.org_macroMolecularMachine_associations_nodes.tsv"
-edges_file = "output/geneontology.org_macroMolecularMachine_associations_edges.tsv"
+nodes_file = "output/go_annotation_nodes.tsv"
+nodes_report = "output/go_annotation_nodes_report.tsv"
+
+edges_file = "output/go_annotation_edges.tsv"
+edges_report = "output/go_annotation_edges_report.tsv"
 
 
 # Nodes
@@ -14,7 +17,9 @@
     GROUP BY all
     ORDER BY all
     """
-    duckdb.sql(f"copy ({query}) to 'output/geneontology.org_macroMolecularMachine_associations_nodes_report.tsv' (header, delimiter '\t')")
+
+    ncommand = "copy ({}) to '{}' (header, delimiter '\t')".format(query, nodes_report)
+    duckdb.sql(ncommand)
 
 # Edges
 if Path(edges_file).exists():
@@ -25,4 +30,5 @@
     GROUP BY all
     ORDER BY all
     """
-    duckdb.sql(f"copy ({query}) to 'output/geneontology.org_macroMolecularMachine_associations_edges_report.tsv' (header, delimiter '\t')")
+    ecommand = "copy ({}) to '{}' (header, delimiter '\t')".format(query, edges_report)
+    duckdb.sql(ecommand)