自动机器学习开发

ruoyi-modules/management-platform/src/main/java/com/ruoyi/platform/domain/AutoMl.java

@@ -110,16 +110,19 @@ public class AutoMl {
 
     private String excludeFeaturePreprocessor;
 
+    @ApiModelProperty(value = "训练集的比率，0到1之间")
+    private Float testSize;
+
     @ApiModelProperty(value = "如何处理过拟合，如果使用基于“cv”的方法或Splitter对象，可能需要使用resampling_strategy_arguments。holdout或crossValid")
     private String resamplingStrategy;
 
-    @ApiModelProperty(value = "训练集的比率，0到1之间")
+    @ApiModelProperty(value = "重采样划分训练集和验证集，训练集的比率，0到1之间")
     private Float trainSize;
 
     @ApiModelProperty(value = "拆分数据前是否进行shuffle")
     private Boolean shuffle;
 
-    @ApiModelProperty(value = "当resamplingStrategy为crossValid时，此项必填。为整数")
+    @ApiModelProperty(value = "交叉验证的折数，当resamplingStrategy为crossValid时，此项必填，为整数")
     private Integer folds;
 
     @ApiModelProperty(value = "文件夹存放配置输出和日志文件，默认/tmp/automl")

ruoyi-modules/management-platform/src/main/resources/mapper/managementPlatform/AutoMLDaoMapper.xml

@@ -6,7 +6,7 @@
                             per_run_time_limit, ensemble_size, ensemble_class, ensemble_nbest, max_models_on_disc, seed,
                             memory_limit,
                             include_classifier, include_feature_preprocessor, include_regressor, exclude_classifier,
-                            exclude_regressor, exclude_feature_preprocessor, resampling_strategy, train_size,
+                            exclude_regressor, exclude_feature_preprocessor, test_size, resampling_strategy, train_size,
                             shuffle, folds, data_csv, target_columns, metric_name, metrics,greater_is_better,scoring_functions,tmp_folder,
                             create_by,update_by)
         values (#{autoMl.mlName}, #{autoMl.mlDescription}, #{autoMl.taskType}, #{autoMl.datasetName},
@@ -15,7 +15,7 @@
                 #{autoMl.maxModelsOnDisc}, #{autoMl.seed},
                 #{autoMl.memoryLimit}, #{autoMl.includeClassifier}, #{autoMl.includeFeaturePreprocessor},
                 #{autoMl.includeRegressor}, #{autoMl.excludeClassifier},
-                #{autoMl.excludeRegressor}, #{autoMl.excludeFeaturePreprocessor}, #{autoMl.resamplingStrategy},
+                #{autoMl.excludeRegressor}, #{autoMl.excludeFeaturePreprocessor}, #{autoMl.testSize}, #{autoMl.resamplingStrategy},
                 #{autoMl.trainSize}, #{autoMl.shuffle},
                 #{autoMl.folds}, #{autoMl.dataCsv},
                 #{autoMl.targetColumns},  #{autoMl.metricName}, #{autoMl.metrics},#{autoMl.greaterIsBetter},#{autoMl.scoringFunctions},#{autoMl.tmpFolder},
@@ -85,6 +85,9 @@
             <if test="autoMl.excludeFeaturePreprocessor != null and autoMl.excludeFeaturePreprocessor !=''">
                 exclude_feature_preprocessor = #{autoMl.excludeFeaturePreprocessor},
             </if>
+            <if test="autoMl.testSize != null and autoMl.testSize !=''">
+                test_size = #{autoMl.testSize},
+            </if>
             <if test="autoMl.resamplingStrategy != null and autoMl.resamplingStrategy !=''">
                 resampling_strategy = #{autoMl.resamplingStrategy},
             </if>