自动机器学习开发

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

@@ -22,31 +22,86 @@ public class AutoMl {
     @ApiModelProperty(value = "实验描述")
     private String mlDescription;
 
-    @ApiModelProperty(value = "任务类型")
+    @ApiModelProperty(value = "任务类型：classification或regression")
     private String taskType;
 
+    @ApiModelProperty(value = "数据集名称")
     private String datasetName;
 
+    @ApiModelProperty(value = "搜索合适模型的时间限制（以秒为单位）。通过增加这个值，auto-sklearn有更高的机会找到更好的模型。默认3600，非必传。")
     private Integer timeLeftForThisTask;
 
+    @ApiModelProperty(value = "单次调用机器学习模型的时间限制（以秒为单位）。如果机器学习算法运行超过时间限制，将终止模型拟合。将这个值设置得足够高，这样典型的机器学习算法就可以适用于训练数据。默认600，非必传。")
     private Integer perRunTimeLimit;
 
+    @ApiModelProperty(value = "集成模型数量，如果设置为0，则没有集成。默认50，非必传。")
     private Integer ensembleSize;
 
+    @ApiModelProperty(value = "设置为None将禁用集成构建，设置为SingleBest仅使用单个最佳模型而不是集成，设置为default，它将对单目标问题使用EnsembleSelection，对多目标问题使用MultiObjectiveDummyEnsemble。默认default，非必传。")
     private String ensembleClass;
 
+    @ApiModelProperty(value = "在构建集成时只考虑ensemble_nbest模型。这是受到了“最大限度地利用集成选择”中引入的库修剪概念的启发。这是独立于ensemble_class参数的，并且这个修剪步骤是在构造集成之前完成的。默认50，非必传。")
     private Integer ensembleNbest;
 
+    @ApiModelProperty(value = "定义在磁盘中保存的模型的最大数量。额外的模型数量将被永久删除。由于这个变量的性质，它设置了一个集成可以使用多少个模型的上限。必须是大于等于1的整数。如果设置为None，则所有模型都保留在磁盘上。默认50，非必传。")
     private Integer maxModelsOnDisc;
 
+    @ApiModelProperty(value = "随机种子，将决定输出文件名。默认1，非必传。")
     private Integer seed;
 
+    @ApiModelProperty(value = "机器学习算法的内存限制（MB）。如果auto-sklearn试图分配超过memory_limit MB，它将停止拟合机器学习算法。默认3072，非必传。")
     private Integer memoryLimit;
 
+    @ApiModelProperty(value = "如果为None，则使用所有可能的分类算法。否则，指定搜索中包含的步骤和组件。有关可用组件，请参见/pipeline/components/<step>/*。与参数exclude不兼容。多选，逗号分隔。包含：adaboost\n" +
+            "bernoulli_nb\n" +
+            "decision_tree\n" +
+            "extra_trees\n" +
+            "gaussian_nb\n" +
+            "gradient_boosting\n" +
+            "k_nearest_neighbors\n" +
+            "lda\n" +
+            "liblinear_svc\n" +
+            "libsvm_svc\n" +
+            "mlp\n" +
+            "multinomial_nb\n" +
+            "passive_aggressive\n" +
+            "qda\n" +
+            "random_forest\n" +
+            "sgd")
     private String includeClassifier;
 
+    @ApiModelProperty(value = "如果为None，则使用所有可能的特征预处理算法。否则，指定搜索中包含的步骤和组件。有关可用组件，请参见/pipeline/components/<step>/*。与参数exclude不兼容。多选，逗号分隔。包含：densifier\n" +
+            "extra_trees_preproc_for_classification\n" +
+            "extra_trees_preproc_for_regression\n" +
+            "fast_ica\n" +
+            "feature_agglomeration\n" +
+            "kernel_pca\n" +
+            "kitchen_sinks\n" +
+            "liblinear_svc_preprocessor\n" +
+            "no_preprocessing\n" +
+            "nystroem_sampler\n" +
+            "pca\n" +
+            "polynomial\n" +
+            "random_trees_embedding\n" +
+            "select_percentile_classification\n" +
+            "select_percentile_regression\n" +
+            "select_rates_classification\n" +
+            "select_rates_regression\n" +
+            "truncatedSVD")
     private String includeFeaturePreprocessor;
 
+    @ApiModelProperty(value = "如果为None，则使用所有可能的回归算法。否则，指定搜索中包含的步骤和组件。有关可用组件，请参见/pipeline/components/<step>/*。与参数exclude不兼容。多选，逗号分隔。包含：adaboost,\n" +
+            "ard_regression,\n" +
+            "decision_tree,\n" +
+            "extra_trees,\n" +
+            "gaussian_process,\n" +
+            "gradient_boosting,\n" +
+            "k_nearest_neighbors,\n" +
+            "liblinear_svr,\n" +
+            "libsvm_svr,\n" +
+            "mlp,\n" +
+            "random_forest,\n" +
+            "sgd")
     private String includeRegressor;
 
     private String excludeClassifier;
@@ -55,20 +110,61 @@ public class AutoMl {
 
     private String excludeFeaturePreprocessor;
 
+    @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")
     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")
     private Integer folds;
 
-    private Boolean deleteTmpFolderAfterTerminate;
+    @ApiModelProperty(value = "文件夹存放配置输出和日志文件，默认/tmp/automl")
+    private String tmpFolder;
 
+    @ApiModelProperty(value = "数据集csv文件路径")
     private String dataCsv;
 
+    @ApiModelProperty(value = "数据集csv文件中哪几列是预测目标列，逗号分隔")
     private String targetColumns;
 
+    @ApiModelProperty(value = "自定义指标名称")
+    private String metricName;
+
+    @ApiModelProperty(value = "模型优化目标指标及权重，json格式。分类的指标包含：accuracy\n" +
+            "balanced_accuracy\n" +
+            "roc_auc\n" +
+            "average_precision\n" +
+            "log_loss\n" +
+            "precision_macro\n" +
+            "precision_micro\n" +
+            "precision_samples\n" +
+            "precision_weighted\n" +
+            "recall_macro\n" +
+            "recall_micro\n" +
+            "recall_samples\n" +
+            "recall_weighted\n" +
+            "f1_macro\n" +
+            "f1_micro\n" +
+            "f1_samples\n" +
+            "f1_weighted\n" +
+            "回归的指标包含：mean_absolute_error\n" +
+            "mean_squared_error\n" +
+            "root_mean_squared_error\n" +
+            "mean_squared_log_error\n" +
+            "median_absolute_error\n" +
+            "r2")
+    private String metrics;
+
+    @ApiModelProperty(value = "指标优化方向，是越大越好还是越小越好")
+    private Boolean greaterIsBetter;
+
+    @ApiModelProperty(value = "模型计算并打印指标")
+    private String scoringFunctions;
+
     private Integer state;
 
     private String  runState;

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

@@ -7,8 +7,8 @@
                             memory_limit,
                             include_classifier, include_feature_preprocessor, include_regressor, exclude_classifier,
                             exclude_regressor, exclude_feature_preprocessor, resampling_strategy, train_size,
-                            shuffle, folds, data_csv, target_columns, create_by,
-                            update_by)
+                            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},
                 #{autoMl.timeLeftForThisTask}, #{autoMl.perRunTimeLimit},
                 #{autoMl.ensembleSize}, #{autoMl.ensembleClass}, #{autoMl.ensembleNbest},
@@ -18,7 +18,8 @@
                 #{autoMl.excludeRegressor}, #{autoMl.excludeFeaturePreprocessor}, #{autoMl.resamplingStrategy},
                 #{autoMl.trainSize}, #{autoMl.shuffle},
                 #{autoMl.folds}, #{autoMl.dataCsv},
-                #{autoMl.targetColumns}, #{autoMl.createBy}, #{autoMl.updateBy})
+                #{autoMl.targetColumns},  #{autoMl.metricName}, #{autoMl.metrics},#{autoMl.greaterIsBetter},#{autoMl.scoringFunctions},#{autoMl.tmpFolder},
+                #{autoMl.createBy}, #{autoMl.updateBy})
     </insert>
 
     <update id="edit">
@@ -99,6 +100,21 @@
             <if test="autoMl.dataCsv != null and autoMl.dataCsv !=''">
                 data_csv = #{autoMl.dataCsv},
             </if>
+            <if test="autoMl.tmpFolder != null and autoMl.tmpFolder !=''">
+                tmp_folder = #{autoMl.tmpFolder},
+            </if>
+            <if test="autoMl.metricName != null and autoMl.metricName !=''">
+                metric_name = #{autoMl.metricName},
+            </if>
+            <if test="autoMl.metrics != null and autoMl.metrics !=''">
+                metrics = #{autoMl.metrics},
+            </if>
+            <if test="autoMl.greater_is_better != null">
+                greater_is_better = #{autoMl.greaterIsBetter},
+            </if>
+            <if test="autoMl.scoringFunctions != null and autoMl.scoringFunctions !=''">
+                scoring_functions = #{autoMl.scoringFunctions},
+            </if>
             <if test="autoMl.targetColumns != null and autoMl.targetColumns !=''">
                 target_columns = #{autoMl.targetColumns},
             </if>