spark-df-orders-csv.scala

val ordersDF = spark.
  read.
  schema("order_id INT, order_date STRING, order_customer_id INT, order_status STRING").
  csv("/Users/itversity/Research/data/retail_db/orders")

val ordersDF = spark.
  read.
  schema("order_id INT, order_date STRING, order_customer_id INT, order_status STRING").
  format("csv").
  load("/Users/itversity/Research/data/retail_db/orders")

// Using Data Frame Operations
ordersDF.
  groupBy("order_date").
  count.
  show

ordersDF.
  groupBy("order_date").
  agg(count("order_date").alias("order_count")).
  show

// Using Spark SQL
ordersDF.createTempView("orders")
spark.
  sql("select order_date, count(1) order_count from orders group by order_date").
  show