LAB 2.1 SOLVED

Author: semanurkps

ASP 2 - Spark Core/ASP 2.1L - Spark SQL Lab.py

@@ -35,7 +35,8 @@
 # COMMAND ----------
 
 # TODO
-events_df = FILL_IN
+events_df = spark.table('events')
+display(events_df)
 
 # COMMAND ----------
 
@@ -44,7 +45,7 @@
 
 # COMMAND ----------
 
-# TODO
+events_df.printSchema()
 
 # COMMAND ----------
 
@@ -56,10 +57,25 @@
 
 # COMMAND ----------
 
+result_df = spark.sql("""
+SELECT *
+FROM events
+WHERE device = 'macOS'
+ORDER BY event_timestamp;
+""")
+
+display(result_df)
+
+# COMMAND ----------
+
 # TODO
-mac_df = (events_df
- .FILL_IN
+mac_df = (events_df.select("*")
+ .where("device = 'macOS'")
+ .orderBy("event_timestamp")
  )
+mac_df.show()
+
+
 
 # COMMAND ----------
 
@@ -69,8 +85,8 @@
 # COMMAND ----------
 
 # TODO
-num_rows = mac_df.FILL_IN
-rows = mac_df.FILL_IN
+num_rows = mac_df.count()
+rows = mac_df.take(5)
 
 # COMMAND ----------
 
@@ -94,7 +110,12 @@
 # COMMAND ----------
 
 # TODO
-mac_sql_df = spark.FILL_IN
+mac_sql_df = spark.sql("""
+SELECT *
+FROM events
+WHERE device = 'macOS'
+ORDER BY event_timestamp;
+""")
 
 display(mac_sql_df)