.

Author: bansalrishi

.ipynb_checkpoints/07. Classify Article-checkpoint.ipynb

@@ -66,6 +66,26 @@
     "X\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "13220"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(vectorizer.vocabulary_)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 41,
@@ -247,7 +267,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#Colelct articles in each cluster\n",
+    "#Collect articles in each cluster\n",
     "cluster={}\n",
     "for i,clus_no in enumerate(km.labels_):\n",
     "        indiv_doc = articles[i]\n",

07. Classify Article.ipynb

@@ -66,6 +66,26 @@
     "X\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "13220"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(vectorizer.vocabulary_)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 41,
@@ -247,7 +267,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#Colelct articles in each cluster\n",
+    "#Collect articles in each cluster\n",
     "cluster={}\n",
     "for i,clus_no in enumerate(km.labels_):\n",
     "        indiv_doc = articles[i]\n",