Added rdd/collect/CollectExample.py

Pedro Bernardo · Pedro Bernardo · commit 7b40998c2217 · 2017-09-27T18:16:33.000+02:00
diff --git a/rdd/collect/CollectExample.py b/rdd/collect/CollectExample.py
@@ -0,0 +1,9 @@
+from pyspark import SparkContext
+
+if __name__ == "__main__":
+    sc = SparkContext("local", "collect")
+    inputWords = ["spark", "hadoop", "spark", "hive", "pig", "cassandra", "hadoop"]
+    wordRdd = sc.parallelize(inputWords)
+    words = wordRdd.collect()
+    for word in words:
+        print(word)
