cast timestemp to long

Java-Cesco/Detecting_fraud_clicks#8

@@ -3,13 +3,6 @@
   <component name="JavaScriptSettings">
     <option name="languageLevel" value="ES6" />
   </component>
-  <component name="MavenProjectsManager">
-    <option name="originalFiles">
-      <list>
-        <option value="$PROJECT_DIR$/pom.xml" />
-      </list>
-    </option>
-  </component>
   <component name="ProjectRootManager" version="2" languageLevel="JDK_1_8" default="false" project-jdk-name="1.8" project-jdk-type="JavaSDK">
     <output url="file:///tmp" />
   </component>

+import org.apache.commons.net.ntp.TimeStamp;
+import org.apache.spark.Aggregator;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.MapFunction;
 import org.apache.spark.sql.*;
 import org.apache.spark.sql.Row;
+import org.apache.spark.sql.types.IntegerType;
+import org.apache.spark.sql.types.LongType;
+
+import java.io.Serializable;
+import java.sql.Time;
+import java.sql.Timestamp;
+
+import static org.apache.spark.sql.functions.unix_timestamp;
 
 
 public class AvgAdvTime {
@@ -10,22 +21,19 @@ public class AvgAdvTime {
 
         SparkSession spark = SparkSession
                 .builder()
+                .master("local")
                 .appName("Java Spark SQL basic example")
                 .getOrCreate();
-
+        
         Dataset<Row> df = spark.read().format("csv")
                 .option("inferSchema", "true")
                 .option("header", "true")
                 .load("train_sample.csv");
+        df.printSchema();
         
-        df.show();
-        df.createOrReplaceTempView("logs");
-        
-        Dataset<Row> ds = spark.sql("SELECT ip, app, click_time, is_attributed" +
-                "FROM logs " +
-                "ORDER BY click_time");
-        ds.show();
-
-        System.out.println();
+        // cast timestamp to long
+        Dataset<Row> newdf = df.withColumn("utc_click_time", df.col("click_time").cast("long"));
+        newdf = newdf.withColumn("utc_attributed_time", df.col("attributed_time").cast("long"));
+        newdf.show();
     }
 }
\ No newline at end of file