{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+-----+\n",
      "|    word|count|\n",
      "+--------+-----+\n",
      "|     rat|    2|\n",
      "|     cat|    2|\n",
      "|elephant|    1|\n",
      "+--------+-----+\n",
      "\n",
      "(0, array([ 0.69630218], dtype=float32), array([ 0.00331201], dtype=float32))\n",
      "(20, array([ 0.28020507], dtype=float32), array([ 0.21137346], dtype=float32))\n",
      "(40, array([ 0.15433531], dtype=float32), array([ 0.2732774], dtype=float32))\n",
      "(60, array([ 0.11638315], dtype=float32), array([ 0.29194263], dtype=float32))\n",
      "(80, array([ 0.10493983], dtype=float32), array([ 0.29757056], dtype=float32))\n",
      "(100, array([ 0.10148945], dtype=float32), array([ 0.2992675], dtype=float32))\n",
      "(120, array([ 0.10044909], dtype=float32), array([ 0.29977915], dtype=float32))\n",
      "(140, array([ 0.10013542], dtype=float32), array([ 0.2999334], dtype=float32))\n",
      "(160, array([ 0.10004086], dtype=float32), array([ 0.29997993], dtype=float32))\n",
      "(180, array([ 0.10001232], dtype=float32), array([ 0.29999396], dtype=float32))\n",
      "(200, array([ 0.10000371], dtype=float32), array([ 0.29999819], dtype=float32))\n"
     ]
    }
   ],
   "source": [
    "import urllib2   \n",
    "import tensorflow as tf  \n",
    "import numpy as np  \n",
    "import findspark     \n",
    " \n",
    "findspark.init()  \n",
    "from pyspark import SparkContext, SparkFiles, SQLContext\n",
    " \n",
    "if not 'sc' in locals():  \n",
    "    sc = SparkContext()  \n",
    " \n",
    "if not 'sqlContext' in locals():\n",
    " sqlContext = SQLContext(sc)\n",
    " \n",
    "wordsDF = sqlContext.createDataFrame([('cat',), ('elephant',), ('rat',), ('rat',), ('cat', )], ['word'])   \n",
    "wordCountsDF = wordsDF.groupBy(\"word\").count()   \n",
    "wordCountsDF.show() \n",
    " \n",
    "x_data = np.random.rand(100).astype(np.float32)  \n",
    "y_data = x_data * 0.1 + 0.3  \n",
    " \n",
    "W = tf.Variable(tf.random_uniform([1], -1.0, 1.0))  \n",
    "b = tf.Variable(tf.zeros([1]))  \n",
    "y = W * x_data + b  \n",
    " \n",
    "loss = tf.reduce_mean(tf.square(y - y_data))  \n",
    "optimizer = tf.train.GradientDescentOptimizer(0.5)  \n",
    "train = optimizer.minimize(loss)  \n",
    " \n",
    "init = tf.initialize_all_variables()  \n",
    " \n",
    "sess = tf.Session()  \n",
    "sess.run(init)  \n",
    " \n",
    "for step in range(201):  \n",
    "    sess.run(train)  \n",
    "    if step % 20 == 0:  \n",
    "        print(step, sess.run(W), sess.run(b)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [Root]",
   "language": "python",
   "name": "Python [Root]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}