releasing version 2

CSO-Classifier.ipynb

@@ -0,0 +1,151 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Loading Libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import classifier.misc as misc\n",
+    "from classifier.syntacticmodule import CSOClassifierSyntactic as synt\n",
+    "from classifier.semanticmodule import CSOClassifierSemantic as sema\n",
+    "\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Loading Paper"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "paper = {\n",
+    "        \"title\": \"De-anonymizing Social Networks\",\n",
+    "        \"abstract\": \"Operators of online social networks are increasingly sharing potentially \"\n",
+    "        \"sensitive information about users and their relationships with advertisers, application \"\n",
+    "        \"developers, and data-mining researchers. Privacy is typically protected by anonymization, \"\n",
+    "        \"i.e., removing names, addresses, etc. We present a framework for analyzing privacy and \"\n",
+    "        \"anonymity in social networks and develop a new re-identification algorithm targeting \"\n",
+    "        \"anonymized social-network graphs. To demonstrate its effectiveness on real-world networks, \"\n",
+    "        \"we show that a third of the users who can be verified to have accounts on both Twitter, a \"\n",
+    "        \"popular microblogging service, and Flickr, an online photo-sharing site, can be re-identified \"\n",
+    "        \"in the anonymous Twitter graph with only a 12% error rate. Our de-anonymization algorithm is \"\n",
+    "        \"based purely on the network topology, does not require creation of a large number of dummy \"\n",
+    "        \"\\\"sybil\\\" nodes, is robust to noise and all existing defenses, and works even when the overlap \"\n",
+    "        \"between the target network and the adversary's auxiliary information is small.\",\n",
+    "        \"keywords\": \"data mining, data privacy, graph theory, social networking (online)\"\n",
+    "        }\n",
+    "\n",
+    "        \n",
+    "\n",
+    "from IPython.display import display, HTML\n",
+    "\n",
+    "display(HTML('<h1>'+paper[\"title\"]+'</h1>'))\n",
+    "display(HTML('<p><strong>Abstract:</strong> '+paper[\"abstract\"]+'</p>'))\n",
+    "display(HTML('<p><strong>Keywords:</strong> <i>'+paper[\"keywords\"]+'</i></p>'))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Load Model, CSO and initialize"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cso, model = misc.load_ontology_and_model()\n",
+    "\n",
+    "# Passing parematers to the two classes (synt and sema)\n",
+    "synt_module = synt(cso, paper)\n",
+    "sema_module = sema(model, cso, paper)\n",
+    "\n",
+    "#initializing variable that will contain output\n",
+    "class_res = {}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Running"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class_res[\"syntactic\"] = synt_module.classify_syntactic()\n",
+    "class_res[\"semantic\"]  = sema_module.classify_semantic()\n",
+    "\n",
+    "union = list(set(class_res[\"syntactic\"] + class_res[\"semantic\"]))\n",
+    "class_res[\"union\"] = union\n",
+    "\n",
+    "enhanced = misc.climb_ontology(cso,union)\n",
+    "class_res[\"enhanced\"] = [x for x in enhanced if x not in union]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Printing and Saving"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "print(class_res)\n",
+    "\n",
+    "with open('output.json', 'w') as outfile:\n",
+    "    json.dump(class_res, outfile, indent=4)"
+   ]
+  }
+ ],
+ "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": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

CSO-Classifier.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Feb 14 14:43:42 2019
+
+@author: angelosalatino
+"""
+
+
+
+# In[Loading Libraries]:
+
+
+import classifier.misc as misc
+from classifier.syntacticmodule import CSOClassifierSyntactic as synt
+from classifier.semanticmodule import CSOClassifierSemantic as sema
+
+import json
+
+
+# In[Loading Paper]:
+
+
+paper = {
+        "title": "De-anonymizing Social Networks",
+        "abstract": "Operators of online social networks are increasingly sharing potentially "
+        "sensitive information about users and their relationships with advertisers, application "
+        "developers, and data-mining researchers. Privacy is typically protected by anonymization, "
+        "i.e., removing names, addresses, etc. We present a framework for analyzing privacy and "
+        "anonymity in social networks and develop a new re-identification algorithm targeting "
+        "anonymized social-network graphs. To demonstrate its effectiveness on real-world networks, "
+        "we show that a third of the users who can be verified to have accounts on both Twitter, a "
+        "popular microblogging service, and Flickr, an online photo-sharing site, can be re-identified "
+        "in the anonymous Twitter graph with only a 12% error rate. Our de-anonymization algorithm is "
+        "based purely on the network topology, does not require creation of a large number of dummy "
+        "\"sybil\" nodes, is robust to noise and all existing defenses, and works even when the overlap "
+        "between the target network and the adversary's auxiliary information is small.",
+        "keywords": "data mining, data privacy, graph theory, social networking (online)"
+        }
+
+
+print(paper["title"])
+print(paper["abstract"])
+print(paper["keywords"])
+
+
+
+# In[Load Model, CSO and initialize]:
+
+
+cso, model = misc.load_ontology_and_model()
+
+# Passing parematers to the two classes (synt and sema)
+synt_module = synt(cso, paper)
+sema_module = sema(model, cso, paper)
+
+#initializing variable that will contain output
+class_res = {}
+
+
+
+# In[Running]:
+
+
+class_res["syntactic"] = synt_module.classify_syntactic()
+class_res["semantic"]  = sema_module.classify_semantic()
+
+union = list(set(class_res["syntactic"] + class_res["semantic"]))
+class_res["union"] = union
+
+enhanced = misc.climb_ontology(cso,union)
+class_res["enhanced"] = [x for x in enhanced if x not in union]
+
+
+
+# In[Printing and Saving]:
+
+
+print(class_res)
+
+with open('output.json', 'w') as outfile:
+    json.dump(class_res, outfile, indent=4)
+