Merge pull request #27 from microbiomedata/25-get-a-report-of-envo-te…

…rms-with-ids-in-the-range-of-nmdc-or-nmdc-contributors

data-vs-ontology-reports

.gitignore

@@ -1,5 +1,5 @@
 src/ontology/nmdco-redundant.ttl
-local/
+downloads/
 **/__pycache__/
 
 .DS_Store

data-vs-ontology-reports.Makefile

@@ -0,0 +1,45 @@
+RUN=poetry run
+
+.PHONY: data-vs-ontology-all data-vs-ontology-clean
+
+
+data-vs-ontology-all: data-vs-ontology-clean \
+	data-vs-ontology-reports/envo-id-ranges-report.tsv \
+	data-vs-ontology-reports/fma-usage-report.tsv
+
+data-vs-ontology-clean:
+	rm -rf data-vs-ontology-reports/*
+	mkdir -p data-vs-ontology-reports
+	touch data-vs-ontology-reports/.gitkeep
+	rm -rf downloads/*owl*
+	mkdir -p downloads
+	touch downloads/.gitkeep
+
+downloads/envo-idranges.owl.omn:
+	@echo "Downloading..."
+ifeq ($(shell command -v wget 2> /dev/null),)
+	@echo "wget is not installed, trying with curl..."
+	@curl -o $@ https://raw.githubusercontent.com/EnvironmentOntology/envo/master/src/envo/envo-idranges.owl
+else
+	@echo "Downloading with wget..."
+	@wget -O $@ https://raw.githubusercontent.com/EnvironmentOntology/envo/master/src/envo/envo-idranges.owl
+endif
+
+downloads/envo-idranges.owl.ttl: downloads/envo-idranges.owl.omn
+	@echo "Converting..."
+	@robot convert --input $< --output $@
+
+data-vs-ontology-reports/envo-id-ranges-report.tsv: downloads/envo-idranges.owl.ttl
+	@echo "Generating report..."
+	$(RUN) report-id-ranges \
+		--id-ranges-ttl $< \
+		--output $@
+
+data-vs-ontology-reports/biosample-triad-counts.tsv:
+	@echo "Generating report..."
+	$(RUN) report-instantiated-traids \
+		--output $@ \
+		--counts-output $(subst counts.tsv,report-counts.tsv,$@)
+
+data-vs-ontology-reports/fma-usage-report.tsv: data-vs-ontology-reports/biosample-triad-counts.tsv
+	grep 'FMA:' $< > $@

data-vs-ontology-reports/fma-usage-report.tsv

@@ -0,0 +1,33 @@
+nmdc:bsm-11-x80t5771	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-1zsths21	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-pqgnra85	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-aa7wmf63	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-vxy31194	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-adv25093	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-xhpt1920	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-afygsz12	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-f0y72191	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-96cg5y52	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-4fnr9v33	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-y16b7q98	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-8vae2844	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-2xw6s444	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-y4310d70	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-e5n81610	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-dcw37a90	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-spjbg416	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-4ppwq475	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-zxjp0468	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-05fh0s26	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-jxa03j76	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-nvz3sq09	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-sbrsd510	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-5aysb633	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-yvnp5859	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-7yq6an11	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-qhewdm80	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-p9t9wv58	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-dzmzp451	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-datvdm83	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-vh4jjb52	ENVO:01001002	FMA:14541	FMA:14541
+nmdc:bsm-11-0q1w4832	ENVO:01001002	FMA:14541	FMA:14541

nmdc_ontology/report_id_ranges.py

@@ -4,7 +4,7 @@
 
 
 @click.command()
-@click.option("--id-ranges-ttl", "-i", default="local/envo-idranges.owl.ttl", help="Input file path")
+@click.option("--id-ranges-ttl", "-i", default="downloads/envo-idranges.owl.ttl", help="Input file path")
 @click.option("--output", "-o", default="envo_id_ranges_report.tsv", help="Output file path")
 def generate_id_ranges(id_ranges_ttl, output):
     # Load the Turtle content into an RDF graph

nmdc_ontology/report_instantiated_traids.py

@@ -8,9 +8,9 @@
 @click.option('--api-url',
               default="https://api.microbiomedata.org/nmdcschema/biosample_set?max_page_size=9999&projection=env_broad_scale%2Cenv_local_scale%2Cenv_medium",
               help='URL of the API endpoint')
-@click.option('--output-file', default="biosample_triad_report.tsv", help='Output file name')
-@click.option('--counts-output-file', default="triad_term_counts.tsv", help='Output file name for value counts')
-def main(api_url, output_file, counts_output_file):
+@click.option('--output', default="biosample_triad_report.tsv", help='Output file name')
+@click.option('--counts-output', default="triad_term_counts.tsv", help='Output file name for value counts')
+def main(api_url, output, counts_output):
     # Send the GET request
     response = requests.get(api_url)
 
@@ -39,7 +39,7 @@ def main(api_url, output_file, counts_output_file):
         df = pd.DataFrame(rows)
 
         # Save the DataFrame to a TSV file
-        df.to_csv(output_file, sep="\t", index=False)
+        df.to_csv(output, sep="\t", index=False)
 
         # Combine all values into a single list
         combined_values = []
@@ -60,7 +60,7 @@ def main(api_url, output_file, counts_output_file):
         counts_df[['ontology', 'local_id']] = counts_df['Value'].str.split(':', n=1, expand=True)
 
         # Save counts DataFrame to a TSV file
-        counts_df.to_csv(counts_output_file, sep="\t", index=False)
+        counts_df.to_csv(counts_output, sep="\t", index=False)
     else:
         print("Failed to fetch data from the API:", response.status_code)