stbi

.ipynb_checkpoints/STBI_Project-checkpoint.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "# import sys\n",
+    "# reload(sys)\n",
+    "# sys.setdefaultencoding('utf-8')\n",
+    "import re\n",
+    "import csv\n",
+    "import string\n",
+    "import random\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn import metrics\n",
+    "from sklearn.svm import SVC"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "#\n",
+    "#\n",
+    "file=open ('fradulent_emails.txt','r')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<_io.TextIOWrapper name='fradulent_emails.txt' mode='r' encoding='cp1252'>"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

STBI_Project.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "# import sys\n",
+    "# reload(sys)\n",
+    "# sys.setdefaultencoding('utf-8')\n",
+    "import re\n",
+    "import csv\n",
+    "import nltk\n",
+    "import string\n",
+    "import random\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from nltk.corpus import stopwords\n",
+    "from sklearn import metrics\n",
+    "from sklearn.svm import SVC"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file=open ('fradulent_emails.txt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<_io.TextIOWrapper name='fradulent_emails.txt' mode='r' encoding='cp1252'>"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "file"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Tokenization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def tokenize(row):\n",
+    "    if row is None or row is '':\n",
+    "        tokens = \"\"\n",
+    "    else:\n",
+    "        tokens = str(row).split(\" \")[:maxtokens]\n",
+    "    return tokens"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Regular expressions to remove unnecessary characters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "\n",
+    "def reg_expressions(row):\n",
+    "    tokens = []\n",
+    "    try:\n",
+    "        for token in row:\n",
+    "            token = token.lower() # make all characters lower case\n",
+    "            token = re.sub(r'[\\W\\d]', \"\", token)\n",
+    "            token = token[:maxtokenlen] # truncate token\n",
+    "            tokens.append(token)\n",
+    "    except:\n",
+    "        token = \"\"\n",
+    "        tokens.append(token)\n",
+    "    return tokens"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Stop-word removal"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def stop_word_removal(row):\n",
+    "    token = [token for token in row if token not in stopwords]\n",
+    "    token = filter(None, token)\n",
+    "    return token"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}