Prepare sc for spark_basic folder

notebooks/spark_basics/DataFrame.ipynb

@@ -17,9 +17,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -35,6 +33,8 @@
     }
    ],
    "source": [
+    "from pyspark import SparkContext\n",
+    "sc=SparkContext.getOrCreate()\n",
     "# Defines a Python list storing one JSON object.\n",
     "json_strings = ['{\"name\":\"Bob\",\"address\":{\"city\":\"Los Angeles\",\"state\":\"California\"}}']\n",
     "# Defines an RDD from the Python list.\n",
@@ -61,9 +61,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -114,14 +112,14 @@
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.12"
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
   }
  },
  "nbformat": 4,

notebooks/spark_basics/RDD.ipynb

@@ -17,9 +17,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -31,6 +29,8 @@
     }
    ],
    "source": [
+    "from pyspark import SparkContext\n",
+    "sc=SparkContext.getOrCreate()\n",
     "text_file = sc.parallelize([\"hello\",\"hello world\"])\n",
     "counts = text_file.flatMap(lambda line: line.split(\" \")) \\\n",
     "             .map(lambda word: (word, 1)) \\\n",
@@ -65,14 +65,14 @@
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.12"
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
   }
  },
  "nbformat": 4,

notebooks/spark_basics/spark_sql.ipynb

@@ -24,9 +24,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -42,6 +40,8 @@
     }
    ],
    "source": [
+    "from pyspark import SparkContext\n",
+    "sc=SparkContext.getOrCreate()\n",
     "json_strings = ['{\"name\":\"Bob\",\"address\":{\"city\":\"Los Angeles\",\"state\":\"California\"}}']\n",
     "# Defines an RDD from the Python list.\n",
     "peopleRDD = sc.parallelize(json_strings)\n",
@@ -60,9 +60,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -110,14 +108,14 @@
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.12"
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
   }
  },
  "nbformat": 4,

notebooks/spark_basics/structured_streaming.ipynb

@@ -43,7 +43,9 @@
    },
    "outputs": [],
    "source": [
-    "from pyspark.streaming import StreamingContext"
+    "from pyspark.streaming import StreamingContext\n",
+    "from pyspark import SparkContext\n",
+    "sc=SparkContext.getOrCreate()"
    ]
   },
   {
@@ -227,17 +229,16 @@
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.10"
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 2
 }
-