[BAEL-3634] Code for Spark DataFrame article (#12039)

* [BAEL-3634] Code for Spark DataFrame article * [BAEL-3634] Improve example data sample and sort aggregations * [BAEL-3634] change column name for clarity * [BAEL-3634] Update method name with U.S english standard Co-authored-by: uzma khan <uzma.khan@nominet.uk>
2022-05-03 20:47:17 +01:00
parent 744f71356b
commit 728b3c9132
17 changed files with 686 additions and 6 deletions
@@ -0,0 +1,46 @@
+package com.baeldung.dataframes;
+
+import java.util.Arrays;
+import java.util.List;
+import java.util.stream.Collectors;
+
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+
+public class CustomerToDataFrameConverterApp {
+
+    private static final List<Customer>  CUSTOMERS = Arrays.asList(
+        aCustomerWith("01", "jo", "Female", 2000),
+        aCustomerWith("02", "jack", "Male", 1200)
+    );
+
+    public static void main(String[] args) {
+        Dataset<Row> dataFrame = convertAfterMappingRows(CUSTOMERS);
+        print(dataFrame);
+        Dataset<Row> customerDF = convertToDataFrameWithNoChange();
+        print(customerDF);
+    }
+
+    public static Dataset<Row> convertToDataFrameWithNoChange() {
+       return SparkDriver.getSparkSession().createDataFrame(CUSTOMERS, Customer.class);
+    }
+
+    public static Dataset<Row> convertAfterMappingRows(List<Customer> customer) {
+        List<Row> rows = customer.stream()
+            .map(c -> new CustomerToRowMapper().call(c))
+            .collect(Collectors.toList());
+
+        return SparkDriver.getSparkSession()
+            .createDataFrame(rows, SchemaFactory.minimumCustomerDataSchema());
+    }
+
+    private static Customer aCustomerWith(String id, String name, String gender, int amount) {
+        return new Customer(id, name, gender, amount);
+    }
+
+    private static void print(Dataset<Row> dataFrame) {
+        dataFrame.printSchema();
+        dataFrame.show();
+    }
+
+}