diff --git a/notebooks/analysis.ipynb b/notebooks/analysis.ipynb
index b377bf5..1c32d1a 100644
--- a/notebooks/analysis.ipynb
+++ b/notebooks/analysis.ipynb
@@ -184,6 +184,19 @@
    "cell_type": "code",
    "execution_count": 7,
    "outputs": [],
+   "source": [
+    "def calculate_diversity_score(tp_mean_sd, joins_mean_sd, jvd_mean_sd):\n",
+    "    diversity = 1 / 3 * (tp_mean_sd[1]/tp_mean_sd[0] + joins_mean_sd[1]/joins_mean_sd[0] + jvd_mean_sd[1]/jvd_mean_sd[0])\n",
+    "    return diversity"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "outputs": [],
    "source": [
     "# get frequencies of each modifier obtained from the sparql queries\n",
     "count_pattern = re.compile('count|COUNT')\n",
@@ -224,7 +237,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -242,7 +255,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "outputs": [
     {
      "name": "stdout",
@@ -262,7 +275,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "outputs": [
     {
      "name": "stdout",
@@ -282,7 +295,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "outputs": [
     {
      "name": "stdout",
@@ -302,7 +315,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "outputs": [
     {
      "name": "stdout",
@@ -322,7 +335,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "outputs": [
     {
      "name": "stdout",
@@ -342,7 +355,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "outputs": [
     {
      "name": "stdout",
@@ -362,10 +375,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "outputs": [],
    "source": [
-    "qald10_wd_test = json.load(open(\"./data/qald_10/qald_10.json\"))\n",
+    "qald10_wd_test = json.load(open(\"../data/qald_10/qald_10.json\"))\n",
     "qald10_wd_test_sparqls = [question[\"query\"][\"sparql\"] for question in qald10_wd_test[\"questions\"]]"
    ],
    "metadata": {
@@ -374,7 +387,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "outputs": [
     {
      "name": "stdout",
@@ -405,6 +418,27 @@
     "collapsed": false
    }
   },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Diversity Score of QALD-10 Test set:  1.275097671454253\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Calculate Diversity Score\n",
+    "diversity_qald10_wd_test = calculate_diversity_score([mean_tp_qald10_wd_test, std_tp_qald10_wd_test], [mean_joins_qald10_wd_test, std_joins_qald10_wd_test], [mean_jvd_qald10_wd_test, std_jvd_qald10_wd_test])\n",
+    "print(\"Diversity Score of QALD-10 Test set: \", diversity_qald10_wd_test)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -416,7 +450,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -434,7 +468,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 20,
    "outputs": [
     {
      "name": "stdout",
@@ -454,7 +488,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 21,
    "outputs": [
     {
      "name": "stdout",
@@ -474,7 +508,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 22,
    "outputs": [
     {
      "name": "stdout",
@@ -494,7 +528,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 23,
    "outputs": [
     {
      "name": "stdout",
@@ -514,7 +548,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 24,
    "outputs": [
     {
      "name": "stdout",
@@ -534,7 +568,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 25,
    "outputs": [
     {
      "name": "stdout",
@@ -554,7 +588,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 26,
    "outputs": [],
    "source": [
     "qald9_dbpedia_train = json.load(open(\"/Users/longquan/Documents/OSS/QALD_9_plus/data/qald_9_plus_train_dbpedia.json\"))\n",
@@ -566,7 +600,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 27,
    "outputs": [
     {
      "name": "stdout",
@@ -597,6 +631,27 @@
     "collapsed": false
    }
   },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Diversity Score of QALD-9-Plus DBpedia Train set:  1.010026202120737\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Calculate Diversity Score\n",
+    "diversity_qald9_dbpedia_train = calculate_diversity_score([mean_tp_qald9_dbpedia_train, std_tp_qald9_dbpedia_train], [mean_joins_qald9_dbpedia_train, std_joins_qald9_dbpedia_train], [mean_jvd_qald9_dbpedia_train, std_jvd_qald9_dbpedia_train])\n",
+    "print(\"Diversity Score of QALD-9-Plus DBpedia Train set: \", diversity_qald9_dbpedia_train)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -608,7 +663,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [
     {
@@ -626,7 +681,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 30,
    "outputs": [
     {
      "name": "stdout",
@@ -646,7 +701,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 31,
    "outputs": [
     {
      "name": "stdout",
@@ -666,7 +721,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 32,
    "outputs": [
     {
      "name": "stdout",
@@ -686,7 +741,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 33,
    "outputs": [
     {
      "name": "stdout",
@@ -706,7 +761,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 34,
    "outputs": [
     {
      "name": "stdout",
@@ -726,7 +781,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 35,
    "outputs": [
     {
      "name": "stdout",
@@ -746,7 +801,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 36,
    "outputs": [],
    "source": [
     "qald9_dbpedia_test = json.load(open(\"/Users/longquan/Documents/OSS/QALD_9_plus/data/qald_9_plus_test_dbpedia.json\"))\n",
@@ -758,7 +813,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 37,
    "outputs": [
     {
      "name": "stdout",
@@ -789,6 +844,27 @@
     "collapsed": false
    }
   },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Diversity Score of QALD-9-Plus DBpedia Test set:  0.9439482740620054\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Calculate Diversity Score\n",
+    "diversity_qald9_dbpedia_test = calculate_diversity_score([mean_tp_qald9_dbpedia_test, std_tp_qald9_dbpedia_test], [mean_joins_qald9_dbpedia_test, std_joins_qald9_dbpedia_test], [mean_jvd_qald9_dbpedia_test, std_jvd_qald9_dbpedia_test])\n",
+    "print(\"Diversity Score of QALD-9-Plus DBpedia Test set: \", diversity_qald9_dbpedia_test)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -800,7 +876,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
@@ -818,7 +894,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 40,
    "outputs": [
     {
      "name": "stdout",
@@ -838,7 +914,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 41,
    "outputs": [
     {
      "name": "stdout",
@@ -858,7 +934,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 42,
    "outputs": [
     {
      "name": "stdout",
@@ -878,7 +954,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 43,
    "outputs": [
     {
      "name": "stdout",
@@ -898,7 +974,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 44,
    "outputs": [
     {
      "name": "stdout",
@@ -918,7 +994,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 45,
    "outputs": [
     {
      "name": "stdout",
@@ -938,7 +1014,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 46,
    "outputs": [],
    "source": [
     "qald9_wd_train = json.load(open(\"/Users/longquan/Documents/OSS/QALD_9_plus/data/qald_9_plus_train_wikidata.json\"))\n",
@@ -950,7 +1026,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 47,
    "outputs": [
     {
      "name": "stdout",
@@ -981,6 +1057,27 @@
     "collapsed": false
    }
   },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Diversity Score of QALD-9-Plus Wikidata Train set:  1.178244171151099\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Calculate Diversity Score\n",
+    "diversity_qald9_wd_train = calculate_diversity_score([mean_tp_qald9_wd_train, std_tp_qald9_wd_train], [mean_joins_qald9_wd_train, std_joins_qald9_wd_train], [mean_jvd_qald9_wd_train, std_jvd_qald9_wd_train])\n",
+    "print(\"Diversity Score of QALD-9-Plus Wikidata Train set: \", diversity_qald9_wd_train)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -992,7 +1089,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 49,
    "metadata": {},
    "outputs": [
     {
@@ -1010,7 +1107,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 50,
    "outputs": [
     {
      "name": "stdout",
@@ -1030,7 +1127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 51,
    "outputs": [
     {
      "name": "stdout",
@@ -1050,7 +1147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 52,
    "outputs": [
     {
      "name": "stdout",
@@ -1070,7 +1167,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 53,
    "outputs": [
     {
      "name": "stdout",
@@ -1090,7 +1187,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 54,
    "outputs": [
     {
      "name": "stdout",
@@ -1110,7 +1207,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 55,
    "outputs": [
     {
      "name": "stdout",
@@ -1130,7 +1227,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 56,
    "outputs": [],
    "source": [
     "qald9_wd_test = json.load(open(\"/Users/longquan/Documents/OSS/QALD_9_plus/data/qald_9_plus_test_wikidata.json\"))\n",
@@ -1142,7 +1239,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 57,
    "outputs": [
     {
      "name": "stdout",
@@ -1173,6 +1270,27 @@
     "collapsed": false
    }
   },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Diversity Score of QALD-9-Plus Wikidata Test set:  1.075475906064686\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Calculate Diversity Score\n",
+    "diversity_qald9_wd_test = calculate_diversity_score([mean_tp_qald9_wd_test, std_tp_qald9_wd_test], [mean_joins_qald9_wd_test, std_joins_qald9_wd_test], [mean_jvd_qald9_wd_test, std_jvd_qald9_wd_test])\n",
+    "print(\"Diversity Score of QALD-9-Plus Wikidata Test set: \", diversity_qald9_wd_test)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "markdown",
    "source": [
@@ -1184,7 +1302,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 59,
    "outputs": [],
    "source": [
     "import matplotlib.pyplot as plt\n",
@@ -1202,7 +1320,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 60,
    "outputs": [],
    "source": [
     "xticks = [\"QALD10-wd-test\", \"QALD9-plus-dbpedia-train\", \"QALD9-plus-dbpedia-test\", \"QALD9-plus-wd-train\", \"QALD9-plus-wd-test\"]"
@@ -1213,7 +1331,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 61,
    "outputs": [
     {
      "data": {
@@ -1235,7 +1353,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 62,
    "outputs": [
     {
      "data": {
@@ -1257,7 +1375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 63,
    "outputs": [
     {
      "data": {