mirror of https://github.com/gsi-upm/sitc
Updated URL rdf and LOD
J. Fernando Sánchez
4 years ago
parent
21dc5ec3de
commit
2248188219
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,661 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "7276f055a8c504d3c80098c62ed41a4f",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-0bfe38f97f6ab2d2",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"<header style=\"width:100%;position:relative\">\n",
|
||||||
|
" <div style=\"width:80%;float:right;\">\n",
|
||||||
|
" <h1>Course Notes for Learning Intelligent Systems</h1>\n",
|
||||||
|
" <h3>Department of Telematic Engineering Systems</h3>\n",
|
||||||
|
" <h5>Universidad Politécnica de Madrid</h5>\n",
|
||||||
|
" </div>\n",
|
||||||
|
" <img style=\"width:15%;\" src=\"../logo.jpg\" alt=\"UPM\" />\n",
|
||||||
|
"</header>"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "bd478e6253226d24ba7f33cb9f6ba706",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-0cd673883ee592d1",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"## Advanced SPARQL\n",
|
||||||
|
"\n",
|
||||||
|
"This notebook complements [the SPARQL notebook](./01_SPARQL.ipynb) with some advanced commands.\n",
|
||||||
|
"\n",
|
||||||
|
"If you have not completed the exercises in the previous notebook, please do so before continuing.\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "9ea4fd529653214745b937d5fc4559e5",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-10264483046abcc4",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"## Objectives\n",
|
||||||
|
"\n",
|
||||||
|
"* To cover some SPARQL concepts that are less frequently used "
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "2fedf0d73fc90104d1ab72c3413dfc83",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-4f8492996e74bf20",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"## Tools\n",
|
||||||
|
"\n",
|
||||||
|
"See [the SPARQL notebook](./01_SPARQL_Introduction.ipynb#Tools)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "c5f8646518bd832a47d71f9d3218237a",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-eb13908482825e42",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"Run this line to enable the `%%sparql` magic command."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from helpers import *"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Exercises"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### Working with dates"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"To explore dates, we will focus on our Writers example.\n",
|
||||||
|
"\n",
|
||||||
|
"First, search for writers born in the XX century.\n",
|
||||||
|
"You can use a special filter, knowing that `\"2000\"^^xsd:date` is the first date of year 2000."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "69e23e6e3dc06ca9d2b5d878c2baba94",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-ab7755944d46f9ca",
|
||||||
|
"locked": false,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"%%sparql\n",
|
||||||
|
"\n",
|
||||||
|
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
|
||||||
|
"PREFIX dct:<http://purl.org/dc/terms/>\n",
|
||||||
|
"PREFIX dbc:<http://dbpedia.org/resource/Category:>\n",
|
||||||
|
"PREFIX dbo:<http://dbpedia.org/ontology/>\n",
|
||||||
|
"\n",
|
||||||
|
"SELECT ?escritor, ?nombre, year(?fechaNac) as ?nac\n",
|
||||||
|
"\n",
|
||||||
|
"WHERE {\n",
|
||||||
|
" ?escritor dct:subject dbc:Spanish_novelists .\n",
|
||||||
|
" ?escritor rdfs:label ?nombre .\n",
|
||||||
|
" ?escritor dbo:birthDate ?fechaNac .\n",
|
||||||
|
" FILTER(lang(?nombre) = \"es\") .\n",
|
||||||
|
" # YOUR ANSWER HERE\n",
|
||||||
|
"}\n",
|
||||||
|
"# YOUR ANSWER HERE\n",
|
||||||
|
"LIMIT 1000"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "211c632634327a1fd805326fa0520cdd",
|
||||||
|
"grade": true,
|
||||||
|
"grade_id": "cell-cf3821f2d33fb0f6",
|
||||||
|
"locked": true,
|
||||||
|
"points": 0,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"assert 'Camilo José Cela' in solution()['columns']['nombre']\n",
|
||||||
|
"assert 'Javier Marías' in solution()['columns']['nombre']\n",
|
||||||
|
"assert all(int(x) > 1899 and int(x) < 2001 for x in solution()['columns']['nac'])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"Now, get the list of Spanish novelists that are still alive.\n",
|
||||||
|
"\n",
|
||||||
|
"A person is alive if their death date is not defined and the were born less than 100 years ago.\n",
|
||||||
|
"\n",
|
||||||
|
"Remember, we can check whether the optional value for a key was bound in a SPARQL query using `BOUND(?key)`."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "e4579d551790c33ba4662562c6a05d99",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-474b1a72dec6827c",
|
||||||
|
"locked": false,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"%%sparql\n",
|
||||||
|
"\n",
|
||||||
|
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
|
||||||
|
"PREFIX dct:<http://purl.org/dc/terms/>\n",
|
||||||
|
"PREFIX dbc:<http://dbpedia.org/resource/Category:>\n",
|
||||||
|
"PREFIX dbo:<http://dbpedia.org/ontology/>\n",
|
||||||
|
"\n",
|
||||||
|
"SELECT ?escritor, ?nombre, year(?fechaNac) as ?nac\n",
|
||||||
|
"\n",
|
||||||
|
"WHERE {\n",
|
||||||
|
" ?escritor dct:subject dbc:Spanish_novelists .\n",
|
||||||
|
" ?escritor rdfs:label ?nombre .\n",
|
||||||
|
" ?escritor dbo:birthDate ?fechaNac .\n",
|
||||||
|
"# YOUR ANSWER HERE\n",
|
||||||
|
" FILTER(lang(?nombre) = \"es\") .\n",
|
||||||
|
"}\n",
|
||||||
|
"# YOUR ANSWER HERE\n",
|
||||||
|
"LIMIT 1000"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "770bbddef5210c28486a1929e4513ada",
|
||||||
|
"grade": true,
|
||||||
|
"grade_id": "cell-46b62dd2856bc919",
|
||||||
|
"locked": true,
|
||||||
|
"points": 0,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"assert 'Fernando Arrabal' in solution()['columns']['nombre']\n",
|
||||||
|
"assert 'Albert Espinosa' in solution()['columns']['nombre']\n",
|
||||||
|
"for year in solution()['columns']['nac']:\n",
|
||||||
|
" assert int(year) >= 1918"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Working with badly formatted dates (OPTIONAL!)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"Now, get the list of Spanish novelists that died before their fifties (i.e. younger than 50 years old), or that aren't 50 years old yet.\n",
|
||||||
|
"\n",
|
||||||
|
"For the sake of simplicity, you can use the `year(<date>)` function.\n",
|
||||||
|
"\n",
|
||||||
|
"Hint: you can use boolean logic in your filters (e.g. `&&` and `||`).\n",
|
||||||
|
"\n",
|
||||||
|
"Hint 2: Some dates are not formatted properly, which makes some queries fail when they shouldn't. As a workaround, you could convert the date to string, and back to date again: `xsd:dateTime(str(?date))`."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "2a24f623c23116fd23877facb487dd16",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-ceefd3c8fbd39d79",
|
||||||
|
"locked": false,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"%%sparql\n",
|
||||||
|
"\n",
|
||||||
|
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
|
||||||
|
"PREFIX dct:<http://purl.org/dc/terms/>\n",
|
||||||
|
"PREFIX dbc:<http://dbpedia.org/resource/Category:>\n",
|
||||||
|
"PREFIX dbo:<http://dbpedia.org/ontology/>\n",
|
||||||
|
"\n",
|
||||||
|
"SELECT ?escritor, ?nombre, year(?fechaNac) as ?nac, ?fechaDef\n",
|
||||||
|
"\n",
|
||||||
|
"WHERE {\n",
|
||||||
|
" ?escritor dct:subject dbc:Spanish_novelists .\n",
|
||||||
|
" ?escritor rdfs:label ?nombre .\n",
|
||||||
|
" ?escritor dbo:birthDate ?fechaNac .\n",
|
||||||
|
" # YOUR ANSWER HERE\n",
|
||||||
|
"}\n",
|
||||||
|
"# YOUR ANSWER HERE\n",
|
||||||
|
"LIMIT 100"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "18bb2d8d586bf4a5231973e69958ab75",
|
||||||
|
"grade": true,
|
||||||
|
"grade_id": "cell-461cd6ccc6c2dc79",
|
||||||
|
"locked": true,
|
||||||
|
"points": 0,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"assert 'Javier Sierra' in solution()['columns']['nombre']\n",
|
||||||
|
"assert 'http://dbpedia.org/resource/Sanmao_(author)' in solution()['columns']['escritor']"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### Regular expressions"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"[Regular expressions](https://www.w3.org/TR/rdf-sparql-query/#funcex-regex) are a very powerful tool, but we will only cover the basics in this exercise.\n",
|
||||||
|
"\n",
|
||||||
|
"In essence, regular expressions match strings against patterns.\n",
|
||||||
|
"In their simplest form, they can be used to find substrings within a variable.\n",
|
||||||
|
"For instance, using `regex(?label, \"substring\")` would only match if and only if the `?label` variable contains `substring`.\n",
|
||||||
|
"But regular expressions can be more complex than that.\n",
|
||||||
|
"For instance, we can find patterns such as: a 10 digit number, a 5 character long string, or variables without whitespaces.\n",
|
||||||
|
"\n",
|
||||||
|
"The syntax of the regex function is the following:\n",
|
||||||
|
"\n",
|
||||||
|
"```\n",
|
||||||
|
"regex(?variable, \"pattern\", \"flags\")\n",
|
||||||
|
"```\n",
|
||||||
|
"\n",
|
||||||
|
"Flags are optional configuration options for the regular expression, such as *do not care about case* (`i` flag).\n",
|
||||||
|
"\n",
|
||||||
|
"As an example, let us find the cities in Madrid that contain \"de\" in their name."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"%%sparql\n",
|
||||||
|
"\n",
|
||||||
|
"SELECT ?localidad\n",
|
||||||
|
"WHERE {\n",
|
||||||
|
" ?localidad <http://dbpedia.org/ontology/isPartOf> <http://dbpedia.org/resource/Community_of_Madrid> .\n",
|
||||||
|
" ?localidad rdfs:label ?nombre .\n",
|
||||||
|
" FILTER (lang(?nombre) = \"es\" ).\n",
|
||||||
|
" FILTER regex(?nombre, \"de\", \"i\")\n",
|
||||||
|
"}\n",
|
||||||
|
"LIMIT 10"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"Now, use regular expressions to find Spanish novelists whose **first name** is Juan.\n",
|
||||||
|
"In other words, their name **starts with** \"Juan\"."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "6e444c20b411033a6c45fd5a566018fa",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-a57d3546a812f689",
|
||||||
|
"locked": false,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"%%sparql\n",
|
||||||
|
"\n",
|
||||||
|
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
|
||||||
|
"PREFIX dct:<http://purl.org/dc/terms/>\n",
|
||||||
|
"PREFIX dbc:<http://dbpedia.org/resource/Category:>\n",
|
||||||
|
"PREFIX dbr:<http://dbpedia.org/resource/>\n",
|
||||||
|
"PREFIX dbo:<http://dbpedia.org/ontology/>\n",
|
||||||
|
"\n",
|
||||||
|
"# YOUR ANSWER HERE\n",
|
||||||
|
"\n",
|
||||||
|
"WHERE {\n",
|
||||||
|
" {\n",
|
||||||
|
" ?escritor dct:subject dbc:Spanish_poets .\n",
|
||||||
|
" }\n",
|
||||||
|
" UNION {\n",
|
||||||
|
" ?escritor dct:subject dbc:Spanish_novelists .\n",
|
||||||
|
" }\n",
|
||||||
|
" ?escritor rdfs:label ?nombre\n",
|
||||||
|
" FILTER(lang(?nombre) = \"es\") .\n",
|
||||||
|
"# YOUR ANSWER HERE\n",
|
||||||
|
"}\n",
|
||||||
|
"ORDER BY ?nombre\n",
|
||||||
|
"LIMIT 1000"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "66db9abddfafa91c2dc25577457f71fb",
|
||||||
|
"grade": true,
|
||||||
|
"grade_id": "cell-c149fe65008f39a9",
|
||||||
|
"locked": true,
|
||||||
|
"points": 0,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"assert len(solution()['columns']['nombre']) > 15\n",
|
||||||
|
"for i in solution()['columns']['nombre']:\n",
|
||||||
|
" assert 'Juan' in i\n",
|
||||||
|
"assert \"Robert Juan-Cantavella\" not in solution()['columns']['nombre']"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "1be6d6e4d8e74240ef07deffcbe5e71a",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-0c2f0113d97dc9de",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"## Group concat"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "c8dbb73a781bd24080804f289a1cea0b",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "asdasdasdddddddddddasdasdsad",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"Sometimes, it is useful to aggregate results from form different rows.\n",
|
||||||
|
"For instance, we might want to get a comma-separated list of the names in each each autonomous community in Spain.\n",
|
||||||
|
"\n",
|
||||||
|
"In those cases, we can use the `GROUP_CONCAT` function."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"%%sparql\n",
|
||||||
|
"\n",
|
||||||
|
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
|
||||||
|
"PREFIX dbo: <http://dbpedia.org/ontology/>\n",
|
||||||
|
"PREFIX dbr: <http://dbpedia.org/resource/>\n",
|
||||||
|
" \n",
|
||||||
|
"SELECT ?com, GROUP_CONCAT(?name, \",\") as ?places # notice how we rename the variable\n",
|
||||||
|
"\n",
|
||||||
|
"WHERE {\n",
|
||||||
|
" ?localidad dbo:isPartOf ?com .\n",
|
||||||
|
" ?com dbo:type dbr:Autonomous_communities_of_Spain .\n",
|
||||||
|
" ?localidad rdfs:label ?name .\n",
|
||||||
|
" FILTER (lang(?name)=\"es\")\n",
|
||||||
|
"}\n",
|
||||||
|
"\n",
|
||||||
|
"ORDER BY ?com\n",
|
||||||
|
"LIMIT 100"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"editable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"checksum": "e100e2f89c832cf832add62c107e4008",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "asdiopjasdoijasdoijasd",
|
||||||
|
"locked": true,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"source": [
|
||||||
|
"Try it yourself, to get a list of works by each of these authors:"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {
|
||||||
|
"deletable": false,
|
||||||
|
"nbgrader": {
|
||||||
|
"cell_type": "code",
|
||||||
|
"checksum": "9f6e26faab2be98c72fb7a917ac5a421",
|
||||||
|
"grade": false,
|
||||||
|
"grade_id": "cell-2e3de17c75047652",
|
||||||
|
"locked": false,
|
||||||
|
"schema_version": 3,
|
||||||
|
"solution": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"%%sparql\n",
|
||||||
|
"\n",
|
||||||
|
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>\n",
|
||||||
|
"PREFIX dct:<http://purl.org/dc/terms/>\n",
|
||||||
|
"PREFIX dbc:<http://dbpedia.org/resource/Category:>\n",
|
||||||
|
"PREFIX dbr:<http://dbpedia.org/resource/>\n",
|
||||||
|
"PREFIX dbo:<http://dbpedia.org/ontology/>\n",
|
||||||
|
"\n",
|
||||||
|
"# YOUR ANSWER HERE\n",
|
||||||
|
"\n",
|
||||||
|
"WHERE {\n",
|
||||||
|
" ?escritor dct:subject dbc:Spanish_novelists .\n",
|
||||||
|
" ?escritor rdfs:label ?nombre .\n",
|
||||||
|
" ?escritor dbo:birthDate ?fechaNac .\n",
|
||||||
|
" ?escritor dbo:birthPlace dbr:Madrid .\n",
|
||||||
|
" OPTIONAL {\n",
|
||||||
|
" ?obra dbo:author ?escritor .\n",
|
||||||
|
" ?obra rdfs:label ?titulo .\n",
|
||||||
|
" }\n",
|
||||||
|
" OPTIONAL {\n",
|
||||||
|
" ?escritor dbo:deathDate ?fechaDef .\n",
|
||||||
|
" }\n",
|
||||||
|
" FILTER (?fechaNac <= \"2000\"^^xsd:date).\n",
|
||||||
|
" FILTER (?fechaNac >= \"1918\"^^xsd:date).\n",
|
||||||
|
" FILTER (!bound(?fechaDef) || (?fechaNac >= \"1918\"^^xsd:date)) .\n",
|
||||||
|
" FILTER(lang(?nombre) = \"es\") .\n",
|
||||||
|
" FILTER(!bound(?titulo) || lang(?titulo) = \"en\") .\n",
|
||||||
|
"\n",
|
||||||
|
"}\n",
|
||||||
|
"ORDER BY ?nombre\n",
|
||||||
|
"LIMIT 10000"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## References"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": []
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Licence\n",
|
||||||
|
"The notebook is freely licensed under under the [Creative Commons Attribution Share-Alike license](https://creativecommons.org/licenses/by/2.0/). \n",
|
||||||
|
"\n",
|
||||||
|
"© 2018 Universidad Politécnica de Madrid."
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3",
|
||||||
|
"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": "3.8.1"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 2
|
||||||
|
}
|
||||||
@ -0,0 +1,53 @@
|
|||||||
|
#!/bin/sh
|
||||||
|
|
||||||
|
# This is a bit messy
|
||||||
|
if [ "$#" -lt 1 ]; then
|
||||||
|
graph="http://example.com/sitc/submission/"
|
||||||
|
endpoint="http://fuseki.gsi.upm.es/hotels/data"
|
||||||
|
else if [ "$#" -lt 2 ]; then
|
||||||
|
endpoint=$1
|
||||||
|
graph_base="http://example.com/sitc"
|
||||||
|
else
|
||||||
|
if [ "$#" -lt 3 ]; then
|
||||||
|
endpoint=$1
|
||||||
|
graph=$2
|
||||||
|
else
|
||||||
|
echo "Usage: $0 [<endpoint>] [<graph_base_uri>]"
|
||||||
|
echo
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
|
||||||
|
upload(){
|
||||||
|
name=$1
|
||||||
|
file=$2
|
||||||
|
echo '###'
|
||||||
|
echo "Uploading: $graph"
|
||||||
|
echo "Graph: $graph"
|
||||||
|
echo "Endpoint: $endpoint"
|
||||||
|
curl -X POST \
|
||||||
|
--digest -u admin:$PASSWORD \
|
||||||
|
-H Content-Type:text/turtle \
|
||||||
|
-T "$file" \
|
||||||
|
--data-urlencode graph=$graph_base/$name \
|
||||||
|
-G $endpoint
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
total=0
|
||||||
|
echo -n "Password: "
|
||||||
|
read -s PASSWORD
|
||||||
|
|
||||||
|
echo "Uploading synthethic"
|
||||||
|
upload "synthetic" synthetic/reviews.ttl || exit 1
|
||||||
|
|
||||||
|
for i in *.ttl; do
|
||||||
|
identifier=$(echo ${i%.ttl} | md5sum | awk '{print $1}')
|
||||||
|
echo "Uploading $i"
|
||||||
|
upload $identifier $i
|
||||||
|
total=$((total + 1))
|
||||||
|
done
|
||||||
|
echo Uploaded $total
|
||||||
Loading…
Reference in New Issue