reading in de dataset

Author: ghaffaru

.ipynb_checkpoints/nltk_overview-checkpoint.ipynb

@@ -1,5 +1,71 @@
 {
  "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "showing info https://raw.githubusercontent.com/nltk/nltk_data/gh-pages/index.xml\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import nltk\n",
+    "nltk.download()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# dir(nltk)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rawData = open('data/SMSSpamCollection.csv').read()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'label,text\\n0.0,Go until jurong point, crazy.. Available only in bugis n great world la e buffet... Cine there got amore wat...\\n0.0,Ok lar... Joking wif u oni...\\n1.0,Free entry in 2 a wkly comp to win FA Cup final tkts 21st May 2005. Text FA to 87121 to receive entry questionstd txt rateTCs apply 08452810075over18s\\n0.0,U dun say so early hor... U c already then say...\\n0.0,Nah I dont think he goes to usf, he lives around here though\\n1.0,FreeMsg Hey there darling its been 3 weeks now and no word ba'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rawData[0:500]"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,