Human Health vocabulary

.gitignore

@@ -0,0 +1,135 @@
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask instance folder
+instance/
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# IPython Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# dotenv
+.env
+
+# virtualenv
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+
+# Rope project settings
+.ropeproject
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and Webstorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff:
+.idea/workspace.xml
+.idea/tasks.xml
+.idea/dictionaries
+.idea/vcs.xml
+.idea/jsLibraryMappings.xml
+
+# Sensitive or high-churn files:
+.idea/dataSources.ids
+.idea/dataSources.xml
+.idea/dataSources.local.xml
+.idea/sqlDataSources.xml
+.idea/dynamic.xml
+.idea/uiDesigner.xml
+
+# Gradle:
+.idea/gradle.xml
+.idea/libraries
+
+# Mongo Explorer plugin:
+.idea/mongoSettings.xml
+
+## File-based project format:
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+/out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+# Created by .ignore support plugin (hsz.mobi)

scripts/human-health-vocab/generate-human-health-skos.py

@@ -0,0 +1,62 @@
+
+import pandas
+import urllib.parse
+from rdflib import RDF, RDFS, XSD, Graph, URIRef, Literal, Namespace
+
+vocab_uri = "http://data.globalchange.gov/vocab/human-health"
+
+SKOS = Namespace("http://www.w3.org/2004/02/skos/core#")
+DCT = Namespace("http://purl.org/dc/terms/")
+GCIS = Namespace("http://data.globalchange.gov/gcis.owl#")
+MESH = Namespace("http://id.nlm.nih.gov/mesh/")
+
+g = Graph()
+g.bind("skos", SKOS)
+g.bind("dcterms", DCT)
+g.bind("mesh", MESH)
+
+vocab = g.resource(URIRef(vocab_uri))
+vocab.add(RDF.type, SKOS.ConceptScheme)
+vocab.add(DCT.title, Literal("Human Health Vocabulary"))
+
+csv_file = "TermRelationship_vector_borne_12_22.xlsx"
+df = pandas.read_excel(csv_file, sheetname='Term')
+
+for index, row in df.iterrows():
+    if row["Term"] is not pandas.np.nan:
+
+        term = row["Term"].strip()
+        uri = vocab_uri+"/concept/"+urllib.parse.quote_plus(term)
+
+        concept = g.resource(URIRef(uri))
+        concept.add(RDF.type, SKOS.Concept)
+        concept.add(SKOS.prefLabel, Literal(term))
+        concept.add(SKOS.inScheme, vocab)
+
+        if row["Definition"] is not pandas.np.nan:
+            definition = row["Definition"].strip()
+            concept.add(SKOS.definition, Literal(definition))
+
+        if row["extURI"] is not pandas.np.nan:
+            source = row["extURI"].strip()
+            concept.add(DCT.source, URIRef(source))
+
+        if row["MeSH Unique ID"] is not pandas.np.nan:
+            mesh_id = row["MeSH Unique ID"].strip()
+            mesh_uri = MESH+mesh_id
+            concept.add(SKOS.closeMatch, URIRef(mesh_uri))
+
+
+df = pandas.read_excel(csv_file, sheetname='SubPredObj')
+for index, row in df.iterrows():
+    if row["Predicate"] is not pandas.np.nan:
+
+        _subject = vocab_uri + "/concept/" + urllib.parse.quote_plus(row["Subject"].strip())
+        _object = vocab_uri + "/concept/" + urllib.parse.quote_plus(row["Object"].strip())
+
+        if row["Predicate"] == "skos:narrower":
+            g.add((URIRef(_subject), SKOS.narrower, URIRef(_object)))
+        else:
+            g.add((URIRef(_subject), SKOS.related, URIRef(_object)))
+
+g.serialize("human-health.ttl", format="turtle")