practice 1

madsh01 · madsh01 · commit 8fe6ca9b95d4 · 2018-12-16T21:30:30.000+05:30
diff --git a/rdd/WordCount_p.py b/rdd/WordCount_p.py
@@ -0,0 +1,13 @@
+from pyspark import SparkConf,SparkContext
+
+
+if __name__ == "__main__":
+    print("hipy")
+    conf= SparkConf().setAppName("word count").setMaster("local[*]")
+    sc= SparkContext(conf= conf) 
+    lines = sc.textFile("in/word_count.text")
+
+    words = lines.flatMap(lambda line: line.split(" "))
+    wordCounts = words.countByValue()
+    for word,count in wordCounts.items():
+        print("{}:{}".format(word,count))
