Odsluchania w miesiacu

val spark = org.apache.spark.sql.SparkSession.builder
      .master("local")
      .appName("Spark CSV Reader")
      .getOrCreate;

    val samples = spark.read.format("com.databricks.spark.csv").
      option("sep",",").
      csv("samples.txt").
      toDF("user_id", "song_id", "date_id")
    val songs = spark.read.format("com.databricks.spark.csv").
      option("sep",",").
      csv("tracks1.txt").
      toDF("track_id","song_id","artist","title","nowe_id")

    val dates = spark.read.format("com.databricks.spark.csv").
      option("sep",",").
      csv("dates.txt").
      toDF("date_id","day","month","year")

    samples.select("date_id").
      join(dates, "date_id").
      groupBy("month").
      count().
      orderBy(asc("month")).
      select("month", "count").
      show(false)