reformat

Author: James Lee

src/main/java/com/sparkTutorial/sparkSql/StackOverFlowSurvey.java

@@ -49,15 +49,16 @@ public static void main(String[] args) throws Exception {
         System.out.println("=== Print records with average mid age less than 20 ===");
         castedResponse.filter(col(AGE_MIDPOINT).$less(20)).show();
 
-        System.out.println("=== Print the result with salary middle point in descending order ===");
+        System.out.println("=== Print the result by salary middle point in descending order ===");
         castedResponse.orderBy(col(SALARY_MIDPOINT ).desc()).show();
 
         System.out.println("=== Group by country and aggregate by average salary middle point and max age middle point ===");
         RelationalGroupedDataset datasetGroupByCountry = castedResponse.groupBy("country");
         datasetGroupByCountry.agg(avg(SALARY_MIDPOINT), max(AGE_MIDPOINT)).show();
 
 
-        Dataset<Row> responseWithSalaryBucket = castedResponse.withColumn(SALARY_MIDPOINT_BUCKET, col(SALARY_MIDPOINT).divide(20000).cast("integer").multiply(20000));
+        Dataset<Row> responseWithSalaryBucket = castedResponse.withColumn(
+                SALARY_MIDPOINT_BUCKET, col(SALARY_MIDPOINT).divide(20000).cast("integer").multiply(20000));
 
         System.out.println("=== With salary bucket column ===");
         responseWithSalaryBucket.select(col(SALARY_MIDPOINT), col(SALARY_MIDPOINT_BUCKET)).show();

src/main/java/com/sparkTutorial/sparkSql/TypedDataset.java

@@ -46,7 +46,7 @@ public static void main(String[] args) throws Exception {
         System.out.println("=== Print responses with average mid age less than 20 ===");
         typedDataset.filter(response -> response.getAgeMidPoint() !=null && response.getAgeMidPoint() < 20).show();
 
-        System.out.println("=== Print the result with salary middle point in descending order ===");
+        System.out.println("=== Print the result by salary middle point in descending order ===");
         typedDataset.orderBy(typedDataset.col(SALARY_MIDPOINT ).desc()).show();
 
         System.out.println("=== Group by country and aggregate by average salary middle point and max age middle point ===");
@@ -56,8 +56,8 @@ public static void main(String[] args) throws Exception {
                     .show();
 
         System.out.println("=== Group by salary bucket ===");
-        typedDataset.filter(response -> response.getSalaryMidPoint() != null)
-                    .map(response -> Math.round(response.getSalaryMidPoint()/20000) * 20000, Encoders.INT())
+        typedDataset.map(response -> response.getSalaryMidPoint() == null ?
+                                     null : Math.round(response.getSalaryMidPoint()/20000) * 20000, Encoders.INT())
                     .withColumnRenamed("value", SALARY_MIDPOINT_BUCKET)
                     .groupBy(SALARY_MIDPOINT_BUCKET)
                     .count()