Add morph-kgc materialize

README.md

@@ -134,6 +134,9 @@ See:
  width="231"
  />
 
+ ## Test
+ It is possible to test against IPython Notebooks with: `pytest --nbmake examples/*ipynb`
+
 
 ## License and Copyright
 

dat/morph-default-config.ini

@@ -0,0 +1,36 @@
+[DEFAULT]
+main_dir: .
+mappings_dir: .
+
+
+[CONFIGURATION]
+
+# INPUT
+na_filter=yes
+na_values=,#N/A,N/A,#N/A N/A,n/a,NA,<NA>,#NA,NULL,null,NaN,nan,None
+
+# OUTPUT
+output_dir=${main_dir}/morph-output
+output_file=result
+output_format=N-QUADS
+clean_output_dir=no
+only_printable_characters=no
+safe_percent_encoding=
+
+# MAPPINGS
+mapping_partition=PARTIAL-AGGREGATIONS
+infer_sql_datatypes=no
+
+# MATERIALIZATION
+chunksize=100000
+
+# MULTIPROCESSING
+number_of_processes=2
+
+# LOGS
+logging_level=INFO
+logs_file=
+
+
+[DataSource1]
+mappings=${main_dir}/recipes.ttl

examples/ex6_2.ipynb

@@ -0,0 +1,117 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# for use in tutorial and development; do not include this `sys.path` change in production:\n",
+    "import sys ; sys.path.insert(0, \"../\")\n",
+    "\n",
+    "from icecream import ic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Load data via Morph-KGC\n",
+    "\n",
+    "> [`morph-kgc`](https://github.com/oeg-upm/morph-kgc) is an engine that constructs RDF knowledge graphs from heterogeneous data sources with R2RML and RML mapping languages. Morph-KGC is built on top of pandas and it leverages mapping partitions to significantly reduce execution times and memory consumption for large data sources.\n",
+    "\n",
+    "Data can be loaded from multiple text format but also via different ORMs (i.e. SQLAlchemy), via a config file with extension `.ini`.\n",
+    "\n",
+    "For documentation see [USAGE](https://github.com/oeg-upm/Morph-KGC/wiki/Usage)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First, let's load our recipe KG:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from os.path import dirname\n",
+    "import kglab\n",
+    "import os\n",
+    "\n",
+    "namespaces = {\n",
+    "    \"nom\":  \"http://example.org/#\",\n",
+    "    \"wtm\":  \"http://purl.org/heals/food/\",\n",
+    "    \"ind\":  \"http://purl.org/heals/ingredient/\",\n",
+    "    \"skos\": \"http://www.w3.org/2004/02/skos/core#\",\n",
+    "    }\n",
+    "\n",
+    "kg = kglab.KnowledgeGraph(\n",
+    "    name = \"A recipe KG example based on Food.com\",\n",
+    "    base_uri = \"https://www.food.com/recipe/\",\n",
+    "    namespaces = namespaces,\n",
+    "    )\n",
+    "\n",
+    "datapath = dirname(os.getcwd()) + \"/dat/recipes.ttl\"\n",
+    "configpath = dirname(os.getcwd()) + \"/dat/morph-default-config.ini\"\n",
+    "\n",
+    "# config = f\"\"\"[DataSource1]\n",
+    "# mappings={datapath}\"\"\"\n",
+    "\n",
+    "print(configpath)\n",
+    "kg.materialize(configpath)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's try to query."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "sparql = \"\"\"\n",
+    "    SELECT ?subject ?object\n",
+    "    WHERE {\n",
+    "        ?subject rdf:type wtm:Recipe .\n",
+    "        ?subject wtm:hasIngredient ?object .\n",
+    "    }\n",
+    "    \"\"\"\n",
+    "\n",
+    "for row in kg._g.query(sparql):\n",
+    "    ic(row.asdict())"
+   ]
+  }
+ ],
+ "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": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

kglab/kglab.py

@@ -1,7 +1,7 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-# see license https://github.com/DerwenAI/kglab#license-and-copyright
+""" KG Lab main class
 
+see license https://github.com/DerwenAI/kglab#license-and-copyright
+"""
 ######################################################################
 ## kglab - core classes
 
@@ -35,6 +35,9 @@
 import typing
 import urlpath  # type: ignore  # pylint: disable=E0401
 
+### third-parties bindings
+import morph_kgc
+
 if get_gpu_count() > 0:
     import cudf  # type: ignore  # pylint: disable=E0401
 
@@ -1449,3 +1452,15 @@ def infer_skos_hierarchical_mappings (
                 self.add(s, _skos.narrower, o)
             else:
                 self.remove(s, _skos.narrowMatch, o)
+
+    def materialize(self, config: str) -> rdflib.Graph:
+        """ Binding to morph-kgc `materialize()` """
+
+        if len(self._g) == 0:
+            # generate the triples and load them to an RDFlib graph      
+            self._g = morph_kgc.materialize(config)
+        else:
+            # merge
+            # for caveats about merging this way:
+            # <https://rdflib.readthedocs.io/en/stable/merging.html>
+            self._g.parse(morph_kgc.materialize(config))

requirements.txt

@@ -6,6 +6,7 @@ gcsfs >= 0.7.1
 gensim >= 3.8.3
 icecream >= 2.1
 matplotlib >= 3.3.4
+morph-kgc >= 1.5
 networkx >= 2.6
 numpy >= 1.19.2
 owlrl >= 6.0.2