Skip to content
Snippets Groups Projects
Commit 44827d42 authored by Marc Feger's avatar Marc Feger
Browse files

Add groundtruth fpr dbpedia; Document progress

parent cb11f5d3
Branches
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
Showing
with 240 additions and 55 deletions
Images/Structure_DBpedia.graphml 0 → 100644
+ 117
− 0
View file @ 44827d42
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<graphml xmlns="http://graphml.graphdrawing.org/xmlns" xmlns:java="http://www.yworks.com/xml/yfiles-common/1.0/java" xmlns:sys="http://www.yworks.com/xml/yfiles-common/markup/primitives/2.0" xmlns:x="http://www.yworks.com/xml/yfiles-common/markup/2.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:y="http://www.yworks.com/xml/graphml" xmlns:yed="http://www.yworks.com/xml/yed/3" xsi:schemaLocation="http://graphml.graphdrawing.org/xmlns http://www.yworks.com/xml/schema/graphml/1.1/ygraphml.xsd">
<!--Created by yEd 3.19-->
<key attr.name="Beschreibung" attr.type="string" for="graph" id="d0"/>
<key for="port" id="d1" yfiles.type="portgraphics"/>
<key for="port" id="d2" yfiles.type="portgeometry"/>
<key for="port" id="d3" yfiles.type="portuserdata"/>
<key attr.name="url" attr.type="string" for="node" id="d4"/>
<key attr.name="description" attr.type="string" for="node" id="d5"/>
<key for="node" id="d6" yfiles.type="nodegraphics"/>
<key for="graphml" id="d7" yfiles.type="resources"/>
<key attr.name="url" attr.type="string" for="edge" id="d8"/>
<key attr.name="description" attr.type="string" for="edge" id="d9"/>
<key for="edge" id="d10" yfiles.type="edgegraphics"/>
<graph edgedefault="directed" id="G">
<data key="d0"/>
<node id="n0">
<data key="d6">
<y:ShapeNode>
<y:Geometry height="50.0" width="50.0" x="399.0" y="257.0"/>
<y:Fill color="#00CCFF" transparent="false"/>
<y:BorderStyle color="#000000" raised="false" type="line" width="1.0"/>
<y:NodeLabel alignment="center" autoSizePolicy="content" fontFamily="Dialog" fontSize="15" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="21.666015625" horizontalTextPosition="center" iconTextGap="4" modelName="custom" textColor="#000000" verticalTextPosition="bottom" visible="true" width="13.3896484375" x="18.30517578125" xml:space="preserve" y="14.1669921875">X<y:LabelModel><y:SmartNodeLabelModel distance="4.0"/></y:LabelModel><y:ModelParameter><y:SmartNodeLabelModelParameter labelRatioX="0.0" labelRatioY="0.0" nodeRatioX="0.0" nodeRatioY="0.0" offsetX="0.0" offsetY="0.0" upX="0.0" upY="-1.0"/></y:ModelParameter></y:NodeLabel>
<y:Shape type="ellipse"/>
</y:ShapeNode>
</data>
</node>
<node id="n1">
<data key="d6">
<y:ShapeNode>
<y:Geometry height="100.0" width="100.0" x="691.0" y="232.0"/>
<y:Fill color="#00CCFF" transparent="false"/>
<y:BorderStyle color="#000000" raised="false" type="line" width="1.0"/>
<y:NodeLabel alignment="center" autoSizePolicy="content" fontFamily="Dialog" fontSize="15" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="39.33203125" horizontalTextPosition="center" iconTextGap="4" modelName="custom" textColor="#000000" verticalTextPosition="bottom" visible="true" width="67.5595703125" x="16.22021484375" xml:space="preserve" y="30.333984375">Film
dbo:Film<y:LabelModel><y:SmartNodeLabelModel distance="4.0"/></y:LabelModel><y:ModelParameter><y:SmartNodeLabelModelParameter labelRatioX="0.0" labelRatioY="0.0" nodeRatioX="0.0" nodeRatioY="0.0" offsetX="0.0" offsetY="0.0" upX="0.0" upY="-1.0"/></y:ModelParameter></y:NodeLabel>
<y:Shape type="ellipse"/>
</y:ShapeNode>
</data>
</node>
<node id="n2">
<data key="d6">
<y:ShapeNode>
<y:Geometry height="100.0" width="100.0" x="691.0" y="379.0"/>
<y:Fill color="#00CCFF" transparent="false"/>
<y:BorderStyle color="#000000" raised="false" type="line" width="1.0"/>
<y:NodeLabel alignment="center" autoSizePolicy="content" fontFamily="Dialog" fontSize="15" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="39.33203125" horizontalTextPosition="center" iconTextGap="4" modelName="custom" textColor="#000000" verticalTextPosition="bottom" visible="true" width="94.5419921875" x="2.72900390625" xml:space="preserve" y="30.333984375">Comedy
dbc:Comedy<y:LabelModel><y:SmartNodeLabelModel distance="4.0"/></y:LabelModel><y:ModelParameter><y:SmartNodeLabelModelParameter labelRatioX="0.0" labelRatioY="0.0" nodeRatioX="0.0" nodeRatioY="0.0" offsetX="0.0" offsetY="0.0" upX="0.0" upY="-1.0"/></y:ModelParameter></y:NodeLabel>
<y:Shape type="ellipse"/>
</y:ShapeNode>
</data>
</node>
<node id="n3">
<data key="d6">
<y:ShapeNode>
<y:Geometry height="50.0" width="50.0" x="399.0" y="404.0"/>
<y:Fill color="#00CCFF" transparent="false"/>
<y:BorderStyle color="#000000" raised="false" type="line" width="1.0"/>
<y:NodeLabel alignment="center" autoSizePolicy="content" fontFamily="Dialog" fontSize="15" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="21.666015625" horizontalTextPosition="center" iconTextGap="4" modelName="custom" textColor="#000000" verticalTextPosition="bottom" visible="true" width="13.345703125" x="18.3271484375" xml:space="preserve" y="14.1669921875">Y<y:LabelModel><y:SmartNodeLabelModel distance="4.0"/></y:LabelModel><y:ModelParameter><y:SmartNodeLabelModelParameter labelRatioX="0.0" labelRatioY="0.0" nodeRatioX="0.0" nodeRatioY="0.0" offsetX="0.0" offsetY="0.0" upX="0.0" upY="-1.0"/></y:ModelParameter></y:NodeLabel>
<y:Shape type="ellipse"/>
</y:ShapeNode>
</data>
</node>
<edge id="e0" source="n0" target="n1">
<data key="d9"/>
<data key="d10">
<y:PolyLineEdge>
<y:Path sx="0.0" sy="0.0" tx="0.0" ty="0.0"/>
<y:LineStyle color="#00FF00" type="line" width="1.0"/>
<y:Arrows source="none" target="standard"/>
<y:EdgeLabel alignment="center" configuration="AutoFlippingLabel" distance="2.0" fontFamily="Dialog" fontSize="12" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="18.1328125" horizontalTextPosition="center" iconTextGap="4" modelName="custom" preferredPlacement="anywhere" ratio="0.5" textColor="#000000" verticalTextPosition="bottom" visible="true" width="49.66796875" x="96.166015625" xml:space="preserve" y="-39.06640625">rdf:type<y:LabelModel><y:SmartEdgeLabelModel autoRotationEnabled="false" defaultAngle="0.0" defaultDistance="10.0"/></y:LabelModel><y:ModelParameter><y:SmartEdgeLabelModelParameter angle="0.0" distance="30.0" distanceToCenter="true" position="left" ratio="0.5" segment="0"/></y:ModelParameter><y:PreferredPlacementDescriptor angle="0.0" angleOffsetOnRightSide="0" angleReference="absolute" angleRotationOnRightSide="co" distance="-1.0" frozen="true" placement="anywhere" side="anywhere" sideReference="relative_to_edge_flow"/></y:EdgeLabel>
<y:BendStyle smoothed="false"/>
</y:PolyLineEdge>
</data>
</edge>
<edge id="e1" source="n0" target="n2">
<data key="d9"/>
<data key="d10">
<y:PolyLineEdge>
<y:Path sx="0.0" sy="0.0" tx="0.0" ty="0.0"/>
<y:LineStyle color="#FF0000" type="line" width="1.0"/>
<y:Arrows source="none" target="standard"/>
<y:EdgeLabel alignment="center" configuration="AutoFlippingLabel" distance="2.0" fontFamily="Dialog" fontSize="12" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="18.1328125" horizontalTextPosition="center" iconTextGap="4" modelName="custom" preferredPlacement="anywhere" ratio="0.5" textColor="#000000" verticalTextPosition="bottom" visible="true" width="68.072265625" x="100.37905180555106" xml:space="preserve" y="20.196294730302498">dct:subject<y:LabelModel><y:SmartEdgeLabelModel autoRotationEnabled="false" defaultAngle="0.0" defaultDistance="10.0"/></y:LabelModel><y:ModelParameter><y:SmartEdgeLabelModelParameter angle="0.0" distance="30.0" distanceToCenter="true" position="left" ratio="0.5" segment="0"/></y:ModelParameter><y:PreferredPlacementDescriptor angle="0.0" angleOffsetOnRightSide="0" angleReference="absolute" angleRotationOnRightSide="co" distance="-1.0" frozen="true" placement="anywhere" side="anywhere" sideReference="relative_to_edge_flow"/></y:EdgeLabel>
<y:BendStyle smoothed="false"/>
</y:PolyLineEdge>
</data>
</edge>
<edge id="e2" source="n0" target="n3">
<data key="d9"/>
<data key="d10">
<y:PolyLineEdge>
<y:Path sx="0.0" sy="0.0" tx="0.0" ty="0.0"/>
<y:LineStyle color="#FF0000" type="line" width="1.0"/>
<y:Arrows source="none" target="standard"/>
<y:EdgeLabel alignment="center" configuration="AutoFlippingLabel" distance="2.0" fontFamily="Dialog" fontSize="12" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="46.3984375" horizontalTextPosition="center" iconTextGap="4" modelName="custom" preferredPlacement="anywhere" ratio="0.5" textColor="#000000" verticalTextPosition="bottom" visible="true" width="73.43359375" x="-99.716796875" xml:space="preserve" y="25.30078125">dct:subject
----------
dbo:genre<y:LabelModel><y:SmartEdgeLabelModel autoRotationEnabled="false" defaultAngle="0.0" defaultDistance="10.0"/></y:LabelModel><y:ModelParameter><y:SmartEdgeLabelModelParameter angle="6.283185307179586" distance="63.0" distanceToCenter="true" position="right" ratio="0.5" segment="0"/></y:ModelParameter><y:PreferredPlacementDescriptor angle="0.0" angleOffsetOnRightSide="0" angleReference="absolute" angleRotationOnRightSide="co" distance="-1.0" frozen="true" placement="anywhere" side="anywhere" sideReference="relative_to_edge_flow"/></y:EdgeLabel>
<y:BendStyle smoothed="false"/>
</y:PolyLineEdge>
</data>
</edge>
<edge id="e3" source="n3" target="n2">
<data key="d9"/>
<data key="d10">
<y:PolyLineEdge>
<y:Path sx="0.0" sy="0.0" tx="0.0" ty="0.0"/>
<y:LineStyle color="#FF0000" type="dashed" width="1.0"/>
<y:Arrows source="none" target="standard"/>
<y:EdgeLabel alignment="center" configuration="AutoFlippingLabel" distance="2.0" fontFamily="Dialog" fontSize="12" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="18.1328125" horizontalTextPosition="center" iconTextGap="4" modelName="custom" preferredPlacement="anywhere" ratio="0.5" textColor="#000000" verticalTextPosition="bottom" visible="true" width="161.74609375" x="20.126953125" xml:space="preserve" y="-39.06640624999994">Contains the word Comedy<y:LabelModel><y:SmartEdgeLabelModel autoRotationEnabled="false" defaultAngle="0.0" defaultDistance="10.0"/></y:LabelModel><y:ModelParameter><y:SmartEdgeLabelModelParameter angle="0.0" distance="30.0" distanceToCenter="true" position="left" ratio="0.21531832082290797" segment="-1"/></y:ModelParameter><y:PreferredPlacementDescriptor angle="0.0" angleOffsetOnRightSide="0" angleReference="absolute" angleRotationOnRightSide="co" distance="-1.0" frozen="true" placement="anywhere" side="anywhere" sideReference="relative_to_edge_flow"/></y:EdgeLabel>
<y:BendStyle smoothed="false"/>
</y:PolyLineEdge>
</data>
</edge>
</graph>
<data key="d7">
<y:Resources/>
</data>
</graphml>
Images/Structure_DBpedia.jpg 0 → 100644
+ 0
− 0
View file @ 44827d42
Images/Structure_DBpedia.jpg

16.3 KiB

Images/Structure_Wikidata.jpg 0 → 100644
+ 0
− 0
View file @ 44827d42
Images/Structure_Wikidata.jpg

39.3 KiB

Images/Structure_Wikidata_modified.graphml
+ 1
− 51
View file @ 44827d42
......@@ -105,31 +105,6 @@ wd:Q40831<y:LabelModel><y:SmartNodeLabelModel distance="4.0"/></y:LabelModel><y:
</y:ShapeNode>
</data>
</node>
<node id="n8">
<data key="d6">
<y:ShapeNode>
<y:Geometry height="100.0" width="100.0" x="272.0" y="450.0"/>
<y:Fill color="#00CCFF" transparent="false"/>
<y:BorderStyle color="#000000" raised="false" type="line" width="1.0"/>
<y:NodeLabel alignment="center" autoSizePolicy="content" fontFamily="Dialog" fontSize="15" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="39.33203125" horizontalTextPosition="center" iconTextGap="4" modelName="custom" textColor="#000000" verticalTextPosition="bottom" visible="true" width="54.21484375" x="22.892578125" xml:space="preserve" y="30.333984375">human
wd:Q5<y:LabelModel><y:SmartNodeLabelModel distance="4.0"/></y:LabelModel><y:ModelParameter><y:SmartNodeLabelModelParameter labelRatioX="0.0" labelRatioY="0.0" nodeRatioX="0.0" nodeRatioY="0.0" offsetX="0.0" offsetY="0.0" upX="0.0" upY="-1.0"/></y:ModelParameter></y:NodeLabel>
<y:Shape type="ellipse"/>
</y:ShapeNode>
</data>
</node>
<node id="n9">
<data key="d6">
<y:ShapeNode>
<y:Geometry height="100.0" width="100.0" x="229.0" y="610.0"/>
<y:Fill color="#00CCFF" transparent="false"/>
<y:BorderStyle color="#000000" raised="false" type="line" width="1.0"/>
<y:NodeLabel alignment="center" autoSizePolicy="content" fontFamily="Dialog" fontSize="15" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="56.998046875" horizontalTextPosition="center" iconTextGap="4" modelName="custom" textColor="#000000" verticalTextPosition="bottom" visible="true" width="77.42529296875" x="11.287353515625" xml:space="preserve" y="21.5009765625">xsd:int
xsd:string
xsd:date<y:LabelModel><y:SmartNodeLabelModel distance="4.0"/></y:LabelModel><y:ModelParameter><y:SmartNodeLabelModelParameter labelRatioX="0.0" labelRatioY="0.0" nodeRatioX="0.0" nodeRatioY="0.0" offsetX="0.0" offsetY="0.0" upX="0.0" upY="-1.0"/></y:ModelParameter></y:NodeLabel>
<y:Shape type="ellipse"/>
</y:ShapeNode>
</data>
</node>
<edge id="e0" source="n0" target="n1">
<data key="d10">
<y:PolyLineEdge>
......@@ -265,32 +240,7 @@ wdt:P279<y:LabelModel><y:SmartEdgeLabelModel autoRotationEnabled="false" default
</y:PolyLineEdge>
</data>
</edge>
<edge id="e10" source="n0" target="n8">
<data key="d10">
<y:PolyLineEdge>
<y:Path sx="0.0" sy="0.0" tx="0.0" ty="0.0"/>
<y:LineStyle color="#000000" type="line" width="1.0"/>
<y:Arrows source="none" target="standard"/>
<y:EdgeLabel alignment="center" configuration="AutoFlippingLabel" distance="2.0" fontFamily="Dialog" fontSize="12" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="32.265625" horizontalTextPosition="center" iconTextGap="4" modelName="custom" preferredPlacement="anywhere" ratio="0.5" textColor="#000000" verticalTextPosition="bottom" visible="true" width="50.892578125" x="-60.910225754211126" xml:space="preserve" y="10.618150160960454">director
wdt:P57<y:LabelModel><y:SmartEdgeLabelModel autoRotationEnabled="false" defaultAngle="0.0" defaultDistance="10.0"/></y:LabelModel><y:ModelParameter><y:SmartEdgeLabelModelParameter angle="0.0" distance="30.0" distanceToCenter="true" position="right" ratio="0.2932278091863161" segment="-1"/></y:ModelParameter><y:PreferredPlacementDescriptor angle="0.0" angleOffsetOnRightSide="0" angleReference="absolute" angleRotationOnRightSide="co" distance="-1.0" frozen="true" placement="anywhere" side="anywhere" sideReference="relative_to_edge_flow"/></y:EdgeLabel>
<y:BendStyle smoothed="false"/>
</y:PolyLineEdge>
</data>
</edge>
<edge id="e11" source="n8" target="n9">
<data key="d10">
<y:PolyLineEdge>
<y:Path sx="0.0" sy="0.0" tx="0.0" ty="0.0"/>
<y:LineStyle color="#000000" type="line" width="1.0"/>
<y:Arrows source="none" target="standard"/>
<y:EdgeLabel alignment="center" configuration="AutoFlippingLabel" distance="2.0" fontFamily="Dialog" fontSize="12" fontStyle="plain" hasBackgroundColor="false" hasLineColor="false" height="32.265625" horizontalTextPosition="center" iconTextGap="4" modelName="custom" preferredPlacement="anywhere" ratio="0.5" textColor="#000000" verticalTextPosition="bottom" visible="true" width="76.59765625" x="-105.64017998909665" xml:space="preserve" y="0.668326611161774">date of birth
wdt:P569<y:LabelModel><y:SmartEdgeLabelModel autoRotationEnabled="false" defaultAngle="0.0" defaultDistance="10.0"/></y:LabelModel><y:ModelParameter><y:SmartEdgeLabelModelParameter angle="6.283185307179586" distance="60.6731274819218" distanceToCenter="true" position="right" ratio="0.03391911414948138" segment="-1"/></y:ModelParameter><y:PreferredPlacementDescriptor angle="0.0" angleOffsetOnRightSide="0" angleReference="absolute" angleRotationOnRightSide="co" distance="-1.0" frozen="true" placement="anywhere" side="anywhere" sideReference="relative_to_edge_flow"/></y:EdgeLabel>
<y:BendStyle smoothed="false"/>
</y:PolyLineEdge>
</data>
</edge>
<edge id="e12" source="n0" target="n7">
<data key="d9"/>
<edge id="e10" source="n0" target="n7">
<data key="d10">
<y:PolyLineEdge>
<y:Path sx="0.0" sy="0.0" tx="0.0" ty="0.0"/>
......
README.md
+ 77
− 2
View file @ 44827d42
......@@ -16,7 +16,7 @@ There are gradations of the terms film e.g. `animated feature film (wd:Q29168811
and `animated film (wd:Q202866)`. These sub-concepts in turn result in the term `film (wd:Q11424)`.
![Structure](./Images/structure_mod.jpg)
![Structure](./Images/Structure_Wikidata.jpg)
At first all entities X are searched which were marked directly as film.
......@@ -211,3 +211,78 @@ This results in a percentage of about `0.1158%` of all identified movies.
The query was structured as follows:
![formula wikidata](./Images/formula_wikidata.png)
### DBPedia
In this section all comedy movies are extracted from DBPedia. The following scheme is used.
![structure dbpedia](./Images/Structure_DBpedia.jpg)
This scheme is much smaller than that of Wikidata, as no general concept or consistency can be identified.
However, the films can be requested directly as such, as they are clearly described in
the [ontology](http://mappings.dbpedia.org/server/ontology/classes/) of DBPedia.
First, all entities of the type film are determined.
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX dbc: <http://dbpedia.org/resource/Category:>
PREFIX dbo: <http://dbpedia.org/ontology/>
PREFIX dct: <http://purl.org/dc/terms/>
SELECT DISTINCT ?movie
WHERE{
# X type Comedy
{?movie rdf:type dbo:Film.}
}GROUP BY ?movie
This determines a total of `10000` independent entities.
This is a problem because the public endpoint limits the maximum result size to 10000 results.
For details see [here](https://wiki.dbpedia.org/public-sparql-endpoint).
There are comparable works that come on `87000` film entities.
See [here](https://wiki.dbpedia.org/about/facts-figures) for more information.
Next, out of the `10000`, all those entities are extracted that were directly titled with comedy.
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX dbc: <http://dbpedia.org/resource/Category:>
PREFIX dbo: <http://dbpedia.org/ontology/>
PREFIX dct: <http://purl.org/dc/terms/>
SELECT DISTINCT ?movie
WHERE{
# X type Film
{?movie rdf:type dbo:Film.}
# Imagine a inner join
# X subject Comedy
{?movie dct:subject dbc:Comedy}
}GROUP BY ?movie
It detects `4` entities that are directly marked with Comedy.
For example one result is: `dbpedia.org/resource/The_Clowns_(film)`.
Then all films whose subject is derived from comedy will be determined.
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX dbc: <http://dbpedia.org/resource/Category:>
PREFIX dbo: <http://dbpedia.org/ontology/>
PREFIX dct: <http://purl.org/dc/terms/>
SELECT DISTINCT ?movie
WHERE{
# X type Film
{?movie rdf:type dbo:Film.}
# Imagine a inner join
# X subject Comedy
{?movie dct:subject dbc:Comedy}
UNION
# X subject Y; Y like "Comedy".
{?movie dct:subject ?y FILTER CONTAINS(lcase(str(?y)), "comedy").}
# X genre Y; Y like "Comedy".
{?movie dbo:genre ?y FILTER CONTAINS (lcase(str(?y)), "comedy").}
}GROUP BY ?movie
This results in `10000` comedy movies (oh wonder !).
\ No newline at end of file
app.py
+ 6
− 1
View file @ 44827d42
from flask import Flask
from flask.json import jsonify
from src.main import assemble_wikidata_groundtruth
from src.main import assemble_wikidata_groundtruth, assemble_dbpedia_groundtruth
app = Flask(__name__)
......@@ -11,6 +11,11 @@ def wikidata_groundtruth():
return jsonify(assemble_wikidata_groundtruth())
@app.route('/dbpedia/groundtruth')
def dbpedia_groundtruth():
return jsonify(assemble_dbpedia_groundtruth())
@app.route('/')
def hello_there():
return 'Hello there!'
......
src/__init__.py
+ 1
− 0
View file @ 44827d42
WIKIDATA_ENTRYPOINT = 'https://query.wikidata.org/sparql'
DBPEDIA_ENTRYPOINT = 'http://dbpedia.org/sparql'
src/main.py
+ 15
− 1
View file @ 44827d42
from typing import Dict
from src import WIKIDATA_ENTRYPOINT
from src import WIKIDATA_ENTRYPOINT, DBPEDIA_ENTRYPOINT
from src.lib.engine import SPARQLEngine
from src.lib.writer import FileWriter
......@@ -17,3 +17,17 @@ def assemble_wikidata_groundtruth() -> Dict:
writer = FileWriter(destination='static/wikidata_groundtruth.txt', data=data)
writer.as_json()
return data
def assemble_dbpedia_groundtruth() -> Dict:
"""
This method assembles the groundtruth for the data in dbpedia.
It also writes them to /static/data/dbpedia_groundtruth.txt
:return: Groundtruth of wikidata as JSON.
"""
engine = SPARQLEngine(entrypoint=DBPEDIA_ENTRYPOINT, query='static/dbpedia_groundtruth.sparql')
data = engine.get_json()
writer = FileWriter(destination='static/dbpedia_groundtruth.txt', data=data)
writer.as_json()
return data
static/dbpedia_groundtruth.sparql 0 → 100644
+ 22
− 0
View file @ 44827d42
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX dbc: <http://dbpedia.org/resource/Category:>
PREFIX dbo: <http://dbpedia.org/ontology/>
PREFIX dct: <http://purl.org/dc/terms/>
SELECT DISTINCT ?movie
WHERE{
# X type Film
{?movie rdf:type dbo:Film.}
# Imagine a inner join
# X subject Comedy
{?movie dct:subject dbc:Comedy}
UNION
# X subject Y; Y like "Comedy".
{?movie dct:subject ?y FILTER CONTAINS(lcase(str(?y)), "comedy").}
# X genre Y; Y like "Comedy".
{?movie dbo:genre ?y FILTER CONTAINS (lcase(str(?y)), "comedy").}
}GROUP BY ?movie
static/dbpedia_groundtruth.txt 0 → 100644
+ 1
− 0
View file @ 44827d42
Source diff could not be displayed: it is too large. Options to address this: view the blob.
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment