From b15edb75859ece2938550dd74b0a9a0d7aaadb10 Mon Sep 17 00:00:00 2001
From: Alessandro <hello@alessandromarrella.com>
Date: Sat, 20 Feb 2016 19:49:32 +0100
Subject: [PATCH] Added DataFrames section and cleared outputs

---
 .DS_Store         | Bin 0 -> 6148 bytes
 spark/spark.ipynb |  45 +++++++--------------------------------------
 2 files changed, 7 insertions(+), 38 deletions(-)
 create mode 100644 .DS_Store

diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..df3e054fbb5df58a533420c860cfc13a5096e329
GIT binary patch
literal 6148
zcmeHK%}T>S5Z<j-Q#}|#QEz+m(nGbj;>l3;<fTy2gGx<k(8Z9HB(+E><Q@Ef4t*G3
z!1r)wcPlN`n~0Q|F#FBU&Scqd!%mhl#%rC{24gm3%mPKs6`=V>a2$0^a>j$m)jO`e
zZqoLG$Qz3#$Nyvi_imactj$~&v*G>w@Y;b)(o*T2=ce-0GqYA<4xfd>dE+YTHc~h3
zBsDiaRXy4AJ!9A1^lD%qMN#l&yWX+%yG?s(FA7svhJHMhdUhhiR@ALUov@WO?d5vx
z-#~QT4gF)8NKXbby|oJXH0_mMuUaXJ&B{){D0<u5rJ~p>SNna-T3avg9-f4~yZeX7
zr{|Yf%{qtAQ^}&i0la}RwEUY!90pN%3En}*Ad-+6AO?tm31Yw;an}3<t%;UG3=jjq
z!vLNS0u<3Pm}yi;2Q>Kmh~s%g6tM9wfhY_*1~ZK?0>X7FpibrHiota{_=Smc3}za2
zI^$|)c#oNxn;QyOvx8r#aK;^t)Di>4z$gP#x@%+oKlu6nKbk~6Vt^Q!C<b_bzp-C~
zC7Iefwm7V{0`vkD1>-V}UnyXyQVg+JidR9EfM1{i=orj2f(L|t1QZR_5Ceb8z$ZkP
BTtol>

literal 0
HcmV?d00001

diff --git a/spark/spark.ipynb b/spark/spark.ipynb
index 4bfac0a..40cdd7e 100644
--- a/spark/spark.ipynb
+++ b/spark/spark.ipynb
@@ -64,19 +64,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "/bin/sh: pyspark: command not found\r\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "!pyspark"
    ]
@@ -90,22 +82,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<pyspark.context.SparkContext at 0x103923610>"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "sc"
    ]
@@ -132,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },
@@ -555,23 +536,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },
-   "outputs": [
-    {
-     "ename": "NameError",
-     "evalue": "name 'df' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-5-af17cfa6d2c8>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgroupBy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"column_name\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcount\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m: name 'df' is not defined"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "df.groupBy(\"column_name\").count()"
    ]