{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Pipeline to create a small test dataset\n",
"Goal: Check if changes to transformations scripts or to the ontologies apply correctly in the data."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from rdflib import Graph\n",
"\n",
"def merge_graphs(input_path_1, input_path_2, output_path):\n",
" g = Graph()\n",
" g.parse(input_path_1)\n",
" g.parse(input_path_2)\n",
" g.serialize(destination=output_path, format='ttl')"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"src/rdf-mappings/map-tblBranch.py:502: DtypeWarning: Columns (2,9,11,16,17,18,19,20,21,31,38,39,49,56,58,60,62,67,71,72,73,74,75,77,79,82,85,86,88,94,97,98,99,100,102,104,106,109,110,112,114,117,118,119,122,124,125,126,127,128,129,130,131,132,133,134,135,136,138,139,140,141,142,143,144,145,149,150,151,152,153,154,157,165,166,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,188,189,190,194,196) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" df_tblBranch = pd.read_csv(csv_input_path, sep='\\t')\n",
" Column Column2 BranchID ... GpSel TinctChanged Column 201\n",
"0 0 NaN 1 ... NaN 1.0 NaN\n",
"1 1 NaN 2 ... NaN 1.0 NaN\n",
"2 2 NaN 3 ... NaN 1.0 NaN\n",
"3 3 NaN 4 ... NaN 1.0 NaN\n",
"4 4 NaN 5 ... NaN 1.0 NaN\n",
"... ... ... ... ... ... ... ...\n",
"40859 40859 NaN 8318_A_1 ... NaN NaN NaN\n",
"40860 40860 NaN 8425_1 ... 0.0 NaN 0.0\n",
"40861 40861 NaN 8425_A_1 ... NaN NaN NaN\n",
"40862 40862 NaN 8425_B_1 ... NaN NaN NaN\n",
"40863 40863 NaN 13770_1 ... 0.0 NaN 1.0\n",
"\n",
"[40864 rows x 205 columns]\n",
"Created data/rdf-output/test-dataset/knowledge-graph-blazon-test-dataset.ttl\n",
"Created data/rdf-output/test-dataset/knowledge-graph-blazon-test-dataset.jsonld\n",
"Export TBox to file...\n",
"Create data/rdf-output/digital-heraldry-ontology.ttl\n"
]
}
],
"source": [
"!python src/rdf-mappings/map-tblBranch.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"merge_graphs('data/rdf-output/test-dataset/knowledge-graph-blazon-test-dataset.ttl', 'data/ontologies/digital-heraldry-ontology.ttl', 'data/rdf-output/test-dataset/knowledge-graph-blazon-test-dataset.ttl')"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"src/rdf-mappings/map-tblArmItems.py:149: FutureWarning: Inferring datetime64[ns] from data containing strings is deprecated and will be removed in a future version. To retain the old behavior explicitly pass Series(data, dtype=datetime64[ns])\n",
" df_metadata = pd.read_excel(metadata_file)\n",
" Column ArmItemID ArmCode ItemNr ... CreMulti CreTint CreOrnIDR TGmember\n",
"0 3931.0 4052.0 BEL 1.0 ... NaN NaN 2.0 False\n",
"1 3931-1 4052.0 BEL 1.0 ... NaN NaN 2.0 False\n",
"2 3932.0 4053.0 BEL 2.0 ... NaN NaN NaN False\n",
"3 3933.0 4054.0 BEL 3.0 ... NaN NaN NaN False\n",
"4 3933-1 4054.0 BEL 3.0 ... NaN NaN NaN False\n",
".. ... ... ... ... ... ... ... ... ...\n",
"809 35234.0 40702.0 NLU 76.0 ... NaN O 2.0 False\n",
"810 43898.0 52699.0 NLU 77.0 ... NaN O 4.0 False\n",
"811 43899.0 52700.0 NLU 78.0 ... NaN O 4.0 False\n",
"812 43900.0 52701.0 NLU 79.0 ... NaN O 4.0 False\n",
"813 43901.0 52702.0 NLU 80.0 ... NaN O 4.0 False\n",
"\n",
"[814 rows x 46 columns]\n",
"src/rdf-mappings/map-tblArmItems.py:166: DtypeWarning: Columns (2,9,11,16,17,18,19,20,21,31,38,39,49,56,58,62,67,71,72,73,74,75,77,79,82,85,86,88,94,97,98,99,100,102,104,106,109,110,112,114,117,118,119,122,124,125,126,127,128,129,130,131,132,133,134,135,136,138,139,140,141,142,143,144,145,149,150,151,152,153,154,157,165,166,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,188,189,190,194,196) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" df_tblBranch = pd.read_csv('data/input/tblBranch_research-dataset.tsv', sep='\\t')\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"BEL\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"MAN\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"NLU\n",
"Created data/rdf-output/test-dataset/knowledge-graph-representation-test-dataset.ttl\n",
"Created data/rdf-output/test-dataset/knowledge-graph-representation-test-dataset.jsonld\n"
]
}
],
"source": [
"!python src/rdf-mappings/map-tblArmItems.py -t"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"src/rdf-mappings/integrate_manuscript_metadata_into_kg.py:72: FutureWarning: Inferring datetime64[ns] from data containing strings is deprecated and will be removed in a future version. To retain the old behavior explicitly pass Series(data, dtype=datetime64[ns])\n",
" df_metadata = pd.read_excel(metadata_file)\n",
" dho-kg-id Bestellen ... Zugriff_Internet.1 Herkunft\n",
"16 NaN NaN ... NaN Summary\n",
"270 NaN NaN ... NaN Summary\n",
"281 NaN NaN ... NaN Summary\n",
"509 NaN NaN ... NaN Summary\n",
"602 NaN NaN ... NaN Summary\n",
"607 NaN NaN ... NaN Summary\n",
"926 NaN NaN ... NaN Summary\n",
"1008 NaN NaN ... NaN Summary\n",
"1199 NaN NaN ... NaN Summary\n",
"\n",
"[9 rows x 95 columns]\n",
"Creating manuscript entities...\n",
"Traceback (most recent call last):\n",
" File \"src/rdf-mappings/integrate_manuscript_metadata_into_kg.py\", line 105, in <module>\n",
" manuscript_identifier = str(int(functions.get_numerical_id_from_ms_metadata(df_metadata, row['ArmCode'])))\n",
"ValueError: cannot convert float NaN to integer\n"
]
}
],
"source": [
"!python src/rdf-mappings/integrate_manuscript_metadata_into_kg.py"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"http://172.28.34.103/!DOCTYPE html does not look like a valid URI, trying to serialize this will break.\n"
]
},
{
"ename": "BadSyntax",
"evalue": "at line 5 of <>:\nBad syntax (expected '.' or '}' or ']' at end of statement) at ^ in:\n\"b'<!DOCTYPE html>\\n<html>\\n\\n<head>\\n '^b'<meta charset=\\'utf-8\\'>\\n <link rel=\"icon\" href=\"/assets/no_a'...\"",
"output_type": "error",
"traceback": [
"Traceback \u001b[0;36m(most recent call last)\u001b[0m:\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3398\u001b[0m in \u001b[1;35mrun_code\u001b[0m\n exec(code_obj, self.user_global_ns, self.user_ns)\n",
" Input \u001b[1;32mIn [7]\u001b[0m in \u001b[1;35m<cell line: 19>\u001b[0m\n resp = g.parse(endpoint, format='text/turtle')\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/graph.py:1267\u001b[0m in \u001b[1;35mparse\u001b[0m\n raise se\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/graph.py:1258\u001b[0m in \u001b[1;35mparse\u001b[0m\n parser.parse(source, self, **args) # type: ignore[call-arg]\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/plugins/parsers/notation3.py:1913\u001b[0m in \u001b[1;35mparse\u001b[0m\n p.loadStream(stream)\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/plugins/parsers/notation3.py:434\u001b[0m in \u001b[1;35mloadStream\u001b[0m\n return self.loadBuf(stream.read()) # Not ideal\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/plugins/parsers/notation3.py:440\u001b[0m in \u001b[1;35mloadBuf\u001b[0m\n self.feed(buf)\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/plugins/parsers/notation3.py:466\u001b[0m in \u001b[1;35mfeed\u001b[0m\n i = self.directiveOrStatement(s, j)\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/plugins/parsers/notation3.py:488\u001b[0m in \u001b[1;35mdirectiveOrStatement\u001b[0m\n return self.checkDot(argstr, j)\n",
" File \u001b[1;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/plugins/parsers/notation3.py:1149\u001b[0m in \u001b[1;35mcheckDot\u001b[0m\n self.BadSyntax(argstr, j, \"expected '.' or '}' or ']' at end of statement\")\n",
"\u001b[0;36m File \u001b[0;32m~/opt/anaconda3/envs/dho_kg_integration/lib/python3.8/site-packages/rdflib/plugins/parsers/notation3.py:1646\u001b[0;36m in \u001b[0;35mBadSyntax\u001b[0;36m\u001b[0m\n\u001b[0;31m raise BadSyntax(self._thisDoc, self.lines, argstr, i, msg)\u001b[0m\n",
"\u001b[0;36m File \u001b[0;32m<string>\u001b[0;36m\u001b[0m\n\u001b[0;31mBadSyntax\u001b[0m\n"
]
}
],
"source": [
"from rdflib import Graph\n",
"from rdflib.plugins.sparql import prepareQuery\n",
"\n",
"# Define the SPARQL query\n",
"query = prepareQuery('''\n",
" SELECT ?subject ?value\n",
" WHERE {\n",
" ?subject <http://digitalheraldry.org/digital-heraldry-ontology/entity#attributesCoATo> ?value .\n",
" }\n",
" ''')\n",
"\n",
"# Define the endpoint URL\n",
"endpoint = 'http://172.28.34.103/sparql'\n",
"\n",
"# Create a new RDF graph\n",
"g = Graph()\n",
"\n",
"# Send a GET request to the SPARQL endpoint and parse the response as RDF/XML\n",
"resp = g.parse(endpoint, format='text/turtle')\n",
"\n",
"# Check whether the parse method returned a valid RDF graph object\n",
"if not resp:\n",
" raise ValueError('Unable to parse RDF data from the endpoint')\n",
"\n",
"# Bind the graph to the namespace\n",
"g.bind('dh', 'http://digitalheraldry.org/digital-heraldry-ontology/entity#')\n",
"\n",
"# Send the SPARQL query to the endpoint and print the results\n",
"for row in g.query(query):\n",
" print(row)\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "dho_kg_integration",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.12"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "86152e4984a8eeddffd673b8a40ea9a3bfe66b19f1d4e2fbcbd65936a43d9c06"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}