added self-contained word count in PySpark

YANG007SUN · Jan 29, 2018 · 9df039f · 9df039f
1 parent d413439
commit 9df039f
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 0 deletions.
diff --git a/tutorial/wordcount/run_word_count.sh b/tutorial/wordcount/run_word_count.sh
@@ -0,0 +1,11 @@
+# define Spark's installed directory
+export SPARK_HOME="/Users/mparsian/spark-2.2.1"
+#
+# define your input path
+#INPUT_PATH="$SPARK_HOME/licenses/LICENSE-heapq.txt"
+#
+# define your PySpark program
+PROG="/Users/mparsian/zmp/pyspark_book_project/programs/word_count.py"
+#
+# submit your spark application
+$SPARK_HOME/bin/spark-submit $PROG 
diff --git a/tutorial/wordcount/run_word_count_ver2.sh b/tutorial/wordcount/run_word_count_ver2.sh
@@ -0,0 +1,11 @@
+# define Spark's installed directory
+export SPARK_HOME="/Users/mparsian/spark-2.2.1"
+#
+# define your input path
+INPUT_PATH="file:///Users/mparsian/spark-2.2.1/zbin/sample.txt"
+#
+# define your PySpark program
+PROG="/Users/mparsian/zmp/github/pyspark-tutorial/tutorial/wordcount/word_count_ver2.py"
+#
+# submit your spark application
+$SPARK_HOME/bin/spark-submit $PROG $INPUT_PATH