basic-average

basic-average/basic-average.txt

@@ -0,0 +1,26 @@
+# ./pyspark
+Python 2.6.9 (unknown, Sep  9 2014, 15:05:12)
+[GCC 4.2.1 Compatible Apple LLVM 6.0 (clang-600.0.39)] on darwin
+Welcome to
+      ____              __
+     / __/__  ___ _____/ /__
+    _\ \/ _ \/ _ `/ __/  '_/
+   /__ / .__/\_,_/_/ /_/\_\   version 1.2.0
+      /_/
+
+Using Python version 2.6.9 (unknown, Sep  9 2014 15:05:12)
+SparkContext available as sc.
+>>> sc
+<pyspark.context.SparkContext object at 0x10ab3e210>
+>>>
+>>> nums = sc.parallelize([1, 2, 3, 4, 5, 6, 7, 8, 20])
+>>> nums.collect()
+[1, 2, 3, 4, 5, 6, 7, 8, 20]
+>>> sumAndCount = nums.map(lambda x: (x, 1)).fold((0, 0), (lambda x, y: (x[0] + y[0], x[1] + y[1])))
+>>> sumAndCount
+(56, 9)
+>>>
+>>> avg = float(sumAndCount[0]) / float(sumAndCount[1])
+>>> avg
+6.2222222222222223
+>>>