Baseline code

Author: PuneetKohli

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,90 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Imports \n",
+    "import string\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# load the data, keep only selected columns\n",
+    "# Read the file using super fast Pandas.read_csv\n",
+    "def load_required_data(path, required_columns):\n",
+    "    dataframe = pd.read_json(path, lines=True)\n",
+    "    dataframe = dataframe[required_columns]\n",
+    "    return dataframe, dataframe.values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataframe, values = load_required_data('../reviews_Apps_for_Android_5.json', [\"asin\", \"overall\", \"reviewText\", \"reviewerID\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.14"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}