var lines = sparkContext.TextFile(@"hdfs://path/to/input.txt"); var words = lines.FlatMap(s => s.Split(' ')); var wordCounts = words.Map(w => new KeyValuePair<string, int>(w.Trim(), 1)) .ReduceByKey((x, y) => x + y); var wordCountCollection = wordCounts.Collect(); wordCounts.SaveAsTextFile(@"hdfs://path/to/wordcount.txt");