Mongo to Matrix.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from pymongo import MongoClient\n",
    "import numpy as np\n",
    "from lerni.models.FeaturesMatrixCreator import FeaturesMatrixCreator\n",
    "from lerni.service.Config import Config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1500"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Config.index = 'lerni_dev'\n",
    "db = MongoClient().lerni_dev\n",
    "\n",
    "feature = 'TfIdf_7e1ffa0223223'\n",
    "dataset = [doc['_id'] for doc in db.documents.find({}, ['_id'])]\n",
    "\n",
    "len(dataset)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Old"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1500, 10000)\n",
      "CPU times: user 46.9 s, sys: 57.9 s, total: 1min 44s\n",
      "Wall time: 1min 49s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "X = FeaturesMatrixCreator()._FeaturesMatrixCreator__vectorize_nested_feature(dataset, feature)\n",
    "\n",
    "print X.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## New"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1500, 10000)\n",
      "CPU times: user 1.64 s, sys: 700 ms, total: 2.34 s\n",
      "Wall time: 3.15 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "docs = db.documents.find({'_id': {'$in': dataset}}, {feature: True}).sort('_id')\n",
    "X = np.array([doc[feature] for doc in docs])\n",
    "\n",
    "print X.shape"
   ]
  }
 ],
 "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": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}