rdflib utility: sparql_results_to_df

refs RDFLib/rdflib#1179

nxontology_data/tests/utils_test.py

@@ -0,0 +1,62 @@
+import pytest
+import rdflib
+
+from nxontology_data.utils import sparql_results_to_df
+
+
+@pytest.fixture
+def rdflib_foaf_graph() -> rdflib.Graph:
+    """
+    FOAF (Friend of a Friend) testing graph from rdflib.
+    """
+    graph = rdflib.Graph()
+    return graph.parse(
+        source="https://github.com/RDFLib/rdflib/raw/56dc4207ce6e7b11ed7b45fb4fd4020ba548e718/examples/foaf.n3",
+        format="n3",
+    )
+
+
+_foaf_sparql = """\
+SELECT
+  ?subject
+  ?subject_is_tim
+  (COUNT(*) AS ?n_triples)
+  (MIN(?predicate) AS ?sample_predicate)
+  (SAMPLE(?missing) AS ?missing) 
+WHERE {
+  ?subject ?predicate ?object.
+  BIND(?subject = <http://www.w3.org/People/Berners-Lee/card#i> AS ?subject_is_tim)
+  OPTIONAL {?subject <this_predicate_does_not_exist> ?missing .}
+}
+GROUP BY ?subject ?subject_is_tim
+ORDER BY DESC(?n_triples) ?subject
+LIMIT 10
+"""
+
+
+@pytest.mark.slow
+def test_sparql_results_to_df(rdflib_foaf_graph: rdflib.Graph) -> None:
+    results = rdflib_foaf_graph.query(_foaf_sparql)
+    df = sparql_results_to_df(results)
+    assert len(df) == 10
+    # test column values (no ? prefix), type (as strings), and order
+    assert list(df.columns) == [
+        "subject",
+        "subject_is_tim",
+        "n_triples",
+        "sample_predicate",
+        "missing",
+    ]
+    first_row = next(df.itertuples())
+    # test value of subject, ensuring type conversion to str
+    assert first_row.subject == "http://www.w3.org/People/Berners-Lee/card#i"
+    # test value of subject_is_tim, ensuring type conversion to bool
+    assert first_row.subject_is_tim is True
+    # test value of n_triples, ensuring type conversion to int
+    assert first_row.n_triples == 61
+    # test value of sample_predicate, ensuring type conversion to str
+    assert (
+        first_row.sample_predicate == "http://www.w3.org/1999/02/22-rdf-syntax-ns#type"
+    )
+    # test value of missing, ensuring it's None
+    assert first_row.missing is None

nxontology_data/utils.py

@@ -0,0 +1,14 @@
+import pandas as pd
+from rdflib.plugins.sparql.processor import SPARQLResult
+
+
+def sparql_results_to_df(results: SPARQLResult) -> pd.DataFrame:
+    """
+    Export results from an rdflib SPARQL query into a `pandas.DataFrame`,
+    using Python types. See https://github.com/RDFLib/rdflib/issues/1179
+    and https://github.com/RDFLib/sparqlwrapper/issues/205.
+    """
+    return pd.DataFrame(
+        data=([None if x is None else x.toPython() for x in row] for row in results),
+        columns=[str(x) for x in results.vars],
+    )

pyproject.toml

@@ -28,6 +28,8 @@ openpyxl = "^3.0.9"
 pandas = "^1.4.1"
 papermill = "^2.3.3"
 requests = "^2.26.0"
+rdflib = "^6.1.1"
+fsspec = "^2022.3.0"
 
 [tool.poetry.dev-dependencies]
 pre-commit = "^2.15.0"
@@ -51,6 +53,7 @@ module = [
     "fire.*",
     "networkx.*",
     "pandas.*",
+    "rdflib.*",
     "requests.*",
 ]
 ignore_missing_imports = true