init

recommend-model-produce/src/main/java/com/tzld/piaoquan/recommend/model/produce/xgboost/XGBoostTrain.java

@@ -1,11 +1,11 @@
 package com.tzld.piaoquan.recommend.model.produce.xgboost;
 
-import com.aliyun.odps.utils.StringUtils;
 import com.google.common.collect.Lists;
 import lombok.extern.slf4j.Slf4j;
 import ml.dmlc.xgboost4j.scala.spark.XGBoostClassificationModel;
 import ml.dmlc.xgboost4j.scala.spark.XGBoostClassifier;
 import org.apache.commons.lang.math.NumberUtils;
+import org.apache.commons.lang3.StringUtils;
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.ml.linalg.SparseVector;
@@ -65,7 +65,7 @@ public class XGBoostTrain {
 
             JavaSparkContext jsc = new JavaSparkContext(spark.sparkContext());
             String file = "/dw/recommend/model/33_ad_train_data_v4/20240726/part-00099.gz";
-            //file = "/Users/dingyunpeng/Desktop/part-00099.gz";
+            file = "/Users/dingyunpeng/Desktop/part-00099.gz";
             JavaRDD<String> rdd = jsc.textFile(file);
 
             // 将 RDD[LabeledPoint] 转换为 JavaRDD<Row>