Added rdd/count/CountExample.py

Pedro Bernardo · Pedro Bernardo · commit 4d7b7a4d04c9 · 2017-09-27T18:11:23.000+02:00
diff --git a/rdd/count/CountExample.py b/rdd/count/CountExample.py
@@ -0,0 +1,11 @@
+from pyspark import SparkContext
+
+if __name__ == "__main__":
+    sc = SparkContext("local", "count")
+    inputWords = ["spark", "hadoop", "spark", "hive", "pig", "cassandra", "hadoop"]
+    wordRdd = sc.parallelize(inputWords)
+    print("Count: {}".format(wordRdd.count()))
+    worldCountByValue = wordRdd.countByValue()
+    print("CountByValue: ")
+    for word, count in worldCountByValue.items():
+        print("{} : {}".format(word, count))
