Merge branch 'ml' of https://github.com/Java-Cesco/Detecting_fraud_clicks into ml

@@ -14,7 +14,6 @@ sudo yum install git -y
 sudo wget http://repos.fedorapeople.org/repos/dchen/apache-maven/epel-apache-maven.repo -O /etc/yum.repos.d/epel-apache-maven.repo
 sudo wget http://repos.fedorapeople.org/repos/dchen/apache-maven/epel-apache-maven.repo -O /etc/yum.repos.d/epel-apache-maven.repo
 sudo sed -i s/\$releasever/6/g /etc/yum.repos.d/epel-apache-maven.repo
 sudo sed -i s/\$releasever/6/g /etc/yum.repos.d/epel-apache-maven.repo
 sudo yum install -y apache-maven java-1.8.0-openjdk-devel.x86_64
 sudo yum install -y apache-maven java-1.8.0-openjdk-devel.x86_64
-sudo yum remove -y java-1.7.0*
 
 
 mvn --version
 mvn --version
 
 
@@ -26,7 +25,8 @@ cd Detecting_fraud_clicks
 mvn package
 mvn package
 
 
 # run
 # run
-java -jar target/assembly/Detecting_fraud_clicks-aggregation.jar train_sample.csv agg_data
-java -jar target/assembly/Detecting_fraud_clicks-decisionTree.jar agg_data
+java8 -jar target/assembly/Detecting_fraud_clicks-aggregation.jar train_sample.csv agg_data
+java8 -jar target/assembly/Detecting_fraud_clicks-decisionTree.jar agg_data
 
 
 ```
 ```
+> NOTE. if you face Memory error using `-Xmx2g` option in `java`
\ No newline at end of file

@@ -38,7 +38,7 @@ public class Aggregation {
         dataset = agg.countClickInTenMinutes(dataset);
         dataset = agg.countClickInTenMinutes(dataset);
         
         
         // test
         // test
-        dataset.where("ip == '5348' and app == '19'").show(10);
+//        dataset.where("ip == '5348' and app == '19'").show(10);
         
         
         // Save to scv
         // Save to scv
         Utill.saveCSVDataSet(dataset, result_path);
         Utill.saveCSVDataSet(dataset, result_path);

@@ -16,8 +16,7 @@ public class Utill {
 
 
     public static void saveCSVDataSet(Dataset<Row> dataset, String path){
     public static void saveCSVDataSet(Dataset<Row> dataset, String path){
         // Read SCV to DataSet
         // Read SCV to DataSet
-        dataset.repartition(1)
-                .write().format("com.databricks.spark.csv")
+        dataset.write().format("com.databricks.spark.csv")
                 .option("inferSchema", "true")
                 .option("inferSchema", "true")
                 .option("header", "true")
                 .option("header", "true")
                 .save(path);
                 .save(path);