Skip to content

Commit 4d34e13

Browse files
rmfrankenrmfranken
committed
feat: add 2 more query examples
1 parent bd2b5b5 commit 4d34e13

1 file changed

Lines changed: 342 additions & 6 deletions

File tree

‎src/tentris-quickstart/quickstart.ipynb‎

Lines changed: 342 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -33,7 +33,7 @@
3333
},
3434
{
3535
"cell_type": "code",
36-
"execution_count": null,
36+
"execution_count": 2,
3737
"metadata": {},
3838
"outputs": [],
3939
"source": [
@@ -66,9 +66,34 @@
6666
},
6767
{
6868
"cell_type": "code",
69-
"execution_count": null,
69+
"execution_count": 3,
7070
"metadata": {},
71-
"outputs": [],
71+
"outputs": [
72+
{
73+
"data": {
74+
"text/markdown": [
75+
"🚀 Connecting to server at `http://128.178.219.51:7502`..."
76+
],
77+
"text/plain": [
78+
"<IPython.core.display.Markdown object>"
79+
]
80+
},
81+
"metadata": {},
82+
"output_type": "display_data"
83+
},
84+
{
85+
"data": {
86+
"text/markdown": [
87+
"✅ **Connection successful!** The database is ready to be queried."
88+
],
89+
"text/plain": [
90+
"<IPython.core.display.Markdown object>"
91+
]
92+
},
93+
"metadata": {},
94+
"output_type": "display_data"
95+
}
96+
],
7297
"source": [
7398
"display(Markdown(f\"🚀 Connecting to server at `{ENDPOINT_URL}`...\"))\n",
7499
"\n",
@@ -104,9 +129,34 @@
104129
},
105130
{
106131
"cell_type": "code",
107-
"execution_count": null,
132+
"execution_count": 4,
108133
"metadata": {},
109-
"outputs": [],
134+
"outputs": [
135+
{
136+
"data": {
137+
"text/markdown": [
138+
"**Running query:** Counting all triples..."
139+
],
140+
"text/plain": [
141+
"<IPython.core.display.Markdown object>"
142+
]
143+
},
144+
"metadata": {},
145+
"output_type": "display_data"
146+
},
147+
{
148+
"data": {
149+
"text/markdown": [
150+
"Total Triples in Database: **2000002**"
151+
],
152+
"text/plain": [
153+
"<IPython.core.display.Markdown object>"
154+
]
155+
},
156+
"metadata": {},
157+
"output_type": "display_data"
158+
}
159+
],
110160
"source": [
111161
"# Example 1: Count all triples in the database\n",
112162
"# This is a good way to see how much data you're working with.\n",
@@ -162,11 +212,297 @@
162212
"\n",
163213
"**Tip:** Don't forget to add `LIMIT 10` to your queries while you are exploring, so you don't accidentally try to print a million rows!"
164214
]
215+
},
216+
{
217+
"cell_type": "code",
218+
"execution_count": null,
219+
"metadata": {},
220+
"outputs": [
221+
{
222+
"data": {
223+
"text/markdown": [
224+
"**Running query:** Getting 10 triples..."
225+
],
226+
"text/plain": [
227+
"<IPython.core.display.Markdown object>"
228+
]
229+
},
230+
"metadata": {},
231+
"output_type": "display_data"
232+
},
233+
{
234+
"data": {
235+
"text/html": [
236+
"<div>\n",
237+
"<style scoped>\n",
238+
" .dataframe tbody tr th:only-of-type {\n",
239+
" vertical-align: middle;\n",
240+
" }\n",
241+
"\n",
242+
" .dataframe tbody tr th {\n",
243+
" vertical-align: top;\n",
244+
" }\n",
245+
"\n",
246+
" .dataframe thead th {\n",
247+
" text-align: right;\n",
248+
" }\n",
249+
"</style>\n",
250+
"<table border=\"1\" class=\"dataframe\">\n",
251+
" <thead>\n",
252+
" <tr style=\"text-align: right;\">\n",
253+
" <th></th>\n",
254+
" <th>repoName</th>\n",
255+
" <th>disciplineIRI</th>\n",
256+
" <th>disciplineDescription</th>\n",
257+
" </tr>\n",
258+
" </thead>\n",
259+
" <tbody>\n",
260+
" <tr>\n",
261+
" <th>0</th>\n",
262+
" <td>Example Software 64899</td>\n",
263+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
264+
" <td>city and county seat in Timiș County, Romania</td>\n",
265+
" </tr>\n",
266+
" <tr>\n",
267+
" <th>1</th>\n",
268+
" <td>Example Software 30239</td>\n",
269+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
270+
" <td>city and county seat in Timiș County, Romania</td>\n",
271+
" </tr>\n",
272+
" <tr>\n",
273+
" <th>2</th>\n",
274+
" <td>Example Software 54959</td>\n",
275+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
276+
" <td>city and county seat in Timiș County, Romania</td>\n",
277+
" </tr>\n",
278+
" <tr>\n",
279+
" <th>3</th>\n",
280+
" <td>Example Software 27819</td>\n",
281+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
282+
" <td>city and county seat in Timiș County, Romania</td>\n",
283+
" </tr>\n",
284+
" <tr>\n",
285+
" <th>4</th>\n",
286+
" <td>Example Software 95309</td>\n",
287+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
288+
" <td>city and county seat in Timiș County, Romania</td>\n",
289+
" </tr>\n",
290+
" <tr>\n",
291+
" <th>...</th>\n",
292+
" <td>...</td>\n",
293+
" <td>...</td>\n",
294+
" <td>...</td>\n",
295+
" </tr>\n",
296+
" <tr>\n",
297+
" <th>95</th>\n",
298+
" <td>Example Software 87999</td>\n",
299+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
300+
" <td>city and county seat in Timiș County, Romania</td>\n",
301+
" </tr>\n",
302+
" <tr>\n",
303+
" <th>96</th>\n",
304+
" <td>Example Software 32009</td>\n",
305+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
306+
" <td>city and county seat in Timiș County, Romania</td>\n",
307+
" </tr>\n",
308+
" <tr>\n",
309+
" <th>97</th>\n",
310+
" <td>Example Software 42979</td>\n",
311+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
312+
" <td>city and county seat in Timiș County, Romania</td>\n",
313+
" </tr>\n",
314+
" <tr>\n",
315+
" <th>98</th>\n",
316+
" <td>Example Software 31979</td>\n",
317+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
318+
" <td>city and county seat in Timiș County, Romania</td>\n",
319+
" </tr>\n",
320+
" <tr>\n",
321+
" <th>99</th>\n",
322+
" <td>Example Software 3439</td>\n",
323+
" <td>http://www.wikidata.org/entity/Q83404</td>\n",
324+
" <td>city and county seat in Timiș County, Romania</td>\n",
325+
" </tr>\n",
326+
" </tbody>\n",
327+
"</table>\n",
328+
"<p>100 rows × 3 columns</p>\n",
329+
"</div>"
330+
],
331+
"text/plain": [
332+
" repoName disciplineIRI \\\n",
333+
"0 Example Software 64899 http://www.wikidata.org/entity/Q83404 \n",
334+
"1 Example Software 30239 http://www.wikidata.org/entity/Q83404 \n",
335+
"2 Example Software 54959 http://www.wikidata.org/entity/Q83404 \n",
336+
"3 Example Software 27819 http://www.wikidata.org/entity/Q83404 \n",
337+
"4 Example Software 95309 http://www.wikidata.org/entity/Q83404 \n",
338+
".. ... ... \n",
339+
"95 Example Software 87999 http://www.wikidata.org/entity/Q83404 \n",
340+
"96 Example Software 32009 http://www.wikidata.org/entity/Q83404 \n",
341+
"97 Example Software 42979 http://www.wikidata.org/entity/Q83404 \n",
342+
"98 Example Software 31979 http://www.wikidata.org/entity/Q83404 \n",
343+
"99 Example Software 3439 http://www.wikidata.org/entity/Q83404 \n",
344+
"\n",
345+
" disciplineDescription \n",
346+
"0 city and county seat in Timiș County, Romania \n",
347+
"1 city and county seat in Timiș County, Romania \n",
348+
"2 city and county seat in Timiș County, Romania \n",
349+
"3 city and county seat in Timiș County, Romania \n",
350+
"4 city and county seat in Timiș County, Romania \n",
351+
".. ... \n",
352+
"95 city and county seat in Timiș County, Romania \n",
353+
"96 city and county seat in Timiș County, Romania \n",
354+
"97 city and county seat in Timiș County, Romania \n",
355+
"98 city and county seat in Timiș County, Romania \n",
356+
"99 city and county seat in Timiș County, Romania \n",
357+
"\n",
358+
"[100 rows x 3 columns]"
359+
]
360+
},
361+
"metadata": {},
362+
"output_type": "display_data"
363+
}
364+
],
365+
"source": [
366+
"## Example queries:\n",
367+
"# Example 3: Get software repositories and their discipline descriptions from Wikidata (Federated Query)\n",
368+
"\n",
369+
"if graph:\n",
370+
" query_str_limit = \"\"\"\n",
371+
"PREFIX schema: <http://schema.org/> \n",
372+
"PREFIX pulse: <https://open-pulse.epfl.ch/ontology#> \n",
373+
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
374+
" \n",
375+
"SELECT ?repoName ?disciplineIRI ?disciplineDescription\n",
376+
"WHERE {\n",
377+
" # 1. Get data from our LOCAL graph\n",
378+
" ?repo a schema:SoftwareSourceCode ;\n",
379+
" schema:name ?repoName ;\n",
380+
" pulse:discipline ?disciplineIRI .\n",
381+
"\n",
382+
" # 2. Connect to an EXTERNAL graph (Wikidata)\n",
383+
" SERVICE <https://query.wikidata.org/sparql> {\n",
384+
" # 3. Ask Wikidata for the description of our ?disciplineIRI\n",
385+
" ?disciplineIRI schema:description ?disciplineDescription .\n",
386+
" \n",
387+
" # Ensure we get the English description\n",
388+
" FILTER(LANG(?disciplineDescription) = \"en\")\n",
389+
" }\n",
390+
"}\n",
391+
"LIMIT 100\n",
392+
"\"\"\"\n",
393+
" \n",
394+
" display(Markdown(\"**Running query:** Getting 10 triples...\"))\n",
395+
" \n",
396+
" # Run the query\n",
397+
" results = graph.query(query_str_limit)\n",
398+
" \n",
399+
" # Convert results to a list of dictionaries\n",
400+
" results_list = [row.asdict() for row in results]\n",
401+
" \n",
402+
" # Load into a pandas DataFrame and display\n",
403+
" df = pd.DataFrame(results_list)\n",
404+
" display(df)\n",
405+
" \n",
406+
"else:\n",
407+
" display(Markdown(\"⚠️ Skipping query: Database not connected.\"))\n"
408+
]
409+
},
410+
{
411+
"cell_type": "code",
412+
"execution_count": null,
413+
"metadata": {},
414+
"outputs": [
415+
{
416+
"data": {
417+
"text/markdown": [
418+
"**Running query:** Finding top 10 authors for Python repos in Chemistry..."
419+
],
420+
"text/plain": [
421+
"<IPython.core.display.Markdown object>"
422+
]
423+
},
424+
"metadata": {},
425+
"output_type": "display_data"
426+
},
427+
{
428+
"data": {
429+
"text/html": [
430+
"<div>\n",
431+
"<style scoped>\n",
432+
" .dataframe tbody tr th:only-of-type {\n",
433+
" vertical-align: middle;\n",
434+
" }\n",
435+
"\n",
436+
" .dataframe tbody tr th {\n",
437+
" vertical-align: top;\n",
438+
" }\n",
439+
"\n",
440+
" .dataframe thead th {\n",
441+
" text-align: right;\n",
442+
" }\n",
443+
"</style>\n",
444+
"<table border=\"1\" class=\"dataframe\">\n",
445+
" <thead>\n",
446+
" <tr style=\"text-align: right;\">\n",
447+
" <th></th>\n",
448+
" </tr>\n",
449+
" </thead>\n",
450+
" <tbody>\n",
451+
" </tbody>\n",
452+
"</table>\n",
453+
"</div>"
454+
],
455+
"text/plain": [
456+
"Empty DataFrame\n",
457+
"Columns: []\n",
458+
"Index: []"
459+
]
460+
},
461+
"metadata": {},
462+
"output_type": "display_data"
463+
}
464+
],
465+
"source": [
466+
"if graph: \n",
467+
" query_str = \"\"\" PREFIX schema: <http://schema.org/> \n",
468+
" PREFIX pulse: <https://open-pulse.epfl.ch/ontology#> \n",
469+
" PREFIX wd: <http://www.wikidata.org/entity/>\n",
470+
"\n",
471+
"SELECT ?personName (COUNT(DISTINCT ?repo) AS ?repoCount)\n",
472+
"WHERE {\n",
473+
" # 1. Find repositories matching the criteria\n",
474+
" ?repo a schema:SoftwareSourceCode ;\n",
475+
" schema:programmingLanguage ?language ;\n",
476+
" pulse:discipline wd:Q2329 . # wd:Q2329 is the IRI for Chemistry\n",
477+
" \n",
478+
" # 2. Filter for Python (case-insensitive)\n",
479+
"# FILTER(CONTAINS(LCASE(STR(?language)), \"python\"))\n",
480+
" \n",
481+
" # 3. Find the author of these repos\n",
482+
" ?repo schema:author ?person .\n",
483+
" \n",
484+
" # 4. Ensure the author is a Person and get their name\n",
485+
" ?person a schema:Person ;\n",
486+
" schema:name ?personName .\n",
487+
"}\n",
488+
"GROUP BY ?person ?personName\n",
489+
"ORDER BY DESC(?repoCount)\n",
490+
"LIMIT 10\n",
491+
"\"\"\"\n",
492+
"\n",
493+
"display(Markdown(\"**Running query:** Finding top 10 authors for Python repos in Chemistry...\"))\n",
494+
"\n",
495+
"# Run the query and display in pandas\n",
496+
"results = graph.query(query_str)\n",
497+
"results_list = [row.asdict() for row in results]\n",
498+
"df = pd.DataFrame(results_list)\n",
499+
"display(df)"
500+
]
165501
}
166502
],
167503
"metadata": {
168504
"kernelspec": {
169-
"display_name": ".venv",
505+
"display_name": "open-pulse-quickstart",
170506
"language": "python",
171507
"name": "python3"
172508
},

0 commit comments

Comments
 (0)