gridsearchtvsplit

功能介绍

gridsearch是通过参数数组组成的网格，对其中的每一组输入参数的组很分别进行训练，预测，评估。取得评估参数最优的模型，作为最终的返回模型

tv为训练验证，将数据按照比例切分为两份，对其中一份数据做训练，对剩余一份数据做预测和评估，得到一个评估结果。

此函数用tv方法得到每一个grid对应参数的评估结果，得到最优模型

参数说明

名称 中文名称 描述 类型 是否必须？ 默认值
trainRatio 训练集比例 训练集与验证集的划分比例，取值范围为(0, 1]。 Double 0.8
ParamGrid 参数网格 指定参数的网格 ParamGrid ✓ —-
Estimator Estimator 用于调优的Estimator Estimator ✓ —-
TuningEvaluator 评估指标 用于选择最优模型的评估指标 TuningEvaluator ✓ —-

脚本示例

脚本代码

  1. def adult(url):
  2.     data = (
  3.         CsvSourceBatchOp()
  4.         .setFilePath('http://alink-dataset.cn-hangzhou.oss.aliyun-inc.com/csv/adult_train.csv')
  5.         .setSchemaStr(
  6.             'age bigint, workclass string, fnlwgt bigint,'
  7.             'education string, education_num bigint,'
  8.             'marital_status string, occupation string,'
  9.             'relationship string, race string, sex string,'
  10.             'capital_gain bigint, capital_loss bigint,'
  11.             'hours_per_week bigint, native_country string,'
  12.             'label string'
  13.         )
  14.     )
  15.     return data
  18. def adult_train():
  19.     return adult('http://alink-dataset.cn-hangzhou.oss.aliyun-inc.com/csv/adult_train.csv')
  22. def adult_test():
  23.     return adult('http://alink-dataset.cn-hangzhou.oss.aliyun-inc.com/csv/adult_test.csv')
  26. def adult_numerical_feature_strs():
  27.     return [
  28.         "age", "fnlwgt", "education_num",
  29.         "capital_gain", "capital_loss", "hours_per_week"
  30.     ]
  33. def adult_categorical_feature_strs():
  34.     return [
  35.         "workclass", "education", "marital_status",
  36.         "occupation", "relationship", "race", "sex",
  37.         "native_country"
  38.     ]
  41. def adult_features_strs():
  42.     feature = adult_numerical_feature_strs()
  43.     feature.extend(adult_categorical_feature_strs())
  45.     return feature
  48. def rf_grid_search_cv(featureCols, categoryFeatureCols, label, metric):
  49.     rf = (
  50.         RandomForestClassifier()
  51.         .setFeatureCols(featureCols)
  52.         .setCategoricalCols(categoryFeatureCols)
  53.         .setLabelCol(label)
  54.         .setPredictionCol('prediction')
  55.         .setPredictionDetailCol('prediction_detail')
  56.     )
  57.     paramGrid = (
  58.         ParamGrid()
  59.         .addGrid(rf, 'SUBSAMPLING_RATIO', [1.0, 0.99, 0.98])
  60.         .addGrid(rf, 'NUM_TREES', [3, 6, 9])
  61.     )
  62.     tuningEvaluator = (
  63.         BinaryClassificationTuningEvaluator()
  64.         .setLabelCol(label)
  65.         .setPredictionDetailCol("prediction_detail")
  66.         .setMetricName(metric)
  67.     )
  68.     cv = (
  69.         GridSearchCV()
  70.         .setEstimator(rf)
  71.         .setParamGrid(paramGrid)
  72.         .setTuningEvaluator(tuningEvaluator)
  73.         .setNumFolds(2)
  74.     )
  76.     return cv
  79. def rf_grid_search_tv(featureCols, categoryFeatureCols, label, metric):
  80.     rf = (
  81.         RandomForestClassifier()
  82.         .setFeatureCols(featureCols)
  83.         .setCategoricalCols(categoryFeatureCols)
  84.         .setLabelCol(label)
  85.         .setPredictionCol('prediction')
  86.         .setPredictionDetailCol('prediction_detail')
  87.     )
  88.     paramGrid = (
  89.         ParamGrid()
  90.         .addGrid(rf, 'SUBSAMPLING_RATIO', [1.0, 0.99, 0.98])
  91.         .addGrid(rf, 'NUM_TREES', [3, 6, 9])
  92.     )
  93.     tuningEvaluator = (
  94.         BinaryClassificationTuningEvaluator()
  95.         .setLabelCol(label)
  96.         .setPredictionDetailCol("prediction_detail")
  97.         .setMetricName(metric)
  98.     )
  99.     cv = (
  100.         GridSearchTVSplit()
  101.         .setEstimator(rf)
  102.         .setParamGrid(paramGrid)
  103.         .setTuningEvaluator(tuningEvaluator)
  104.     )
  106.     return cv
  109. def tuningcv(cv_estimator, input):
  110.     return cv_estimator.fit(input)
  113. def tuningtv(tv_estimator, input):
  114.     return tv_estimator.fit(input)
  117. def main():
  118.     print('rf cv tuning')
  119.     model = tuningcv(
  120.         rf_grid_search_cv(adult_features_strs(),
  121.                           adult_categorical_feature_strs(), 'label', 'AUC'),
  122.         adult_train()
  123.     )
  125.     print(model.getReport())
  127.     print('rf tv tuning')
  128.     model = tuningtv(
  129.         rf_grid_search_tv(adult_features_strs(),
  130.                           adult_categorical_feature_strs(), 'label', 'AUC'),
  131.         adult_train()
  132.     )
  134.     print(model.getReport())
  135. main()

脚本结果

  1. rf cv tuning
  2. com.alibaba.alink.pipeline.tuning.GridSearchCV
  3. [ {
  4.   "param" : [ {
  5.     "stage" : "RandomForestClassifier",
  6.     "paramName" : "numTrees",
  7.     "paramValue" : 3
  8.   }, {
  9.     "stage" : "RandomForestClassifier",
  10.     "paramName" : "subsamplingRatio",
  11.     "paramValue" : 1.0
  12.   } ],
  13.   "metric" : 0.8922549257899725
  14. }, {
  15.   "param" : [ {
  16.     "stage" : "RandomForestClassifier",
  17.     "paramName" : "numTrees",
  18.     "paramValue" : 3
  19.   }, {
  20.     "stage" : "RandomForestClassifier",
  21.     "paramName" : "subsamplingRatio",
  22.     "paramValue" : 0.99
  23.   } ],
  24.   "metric" : 0.8920255970548456
  25. }, {
  26.   "param" : [ {
  27.     "stage" : "RandomForestClassifier",
  28.     "paramName" : "numTrees",
  29.     "paramValue" : 3
  30.   }, {
  31.     "stage" : "RandomForestClassifier",
  32.     "paramName" : "subsamplingRatio",
  33.     "paramValue" : 0.98
  34.   } ],
  35.   "metric" : 0.8944982480437225
  36. }, {
  37.   "param" : [ {
  38.     "stage" : "RandomForestClassifier",
  39.     "paramName" : "numTrees",
  40.     "paramValue" : 6
  41.   }, {
  42.     "stage" : "RandomForestClassifier",
  43.     "paramName" : "subsamplingRatio",
  44.     "paramValue" : 1.0
  45.   } ],
  46.   "metric" : 0.8923867598288401
  47. }, {
  48.   "param" : [ {
  49.     "stage" : "RandomForestClassifier",
  50.     "paramName" : "numTrees",
  51.     "paramValue" : 6
  52.   }, {
  53.     "stage" : "RandomForestClassifier",
  54.     "paramName" : "subsamplingRatio",
  55.     "paramValue" : 0.99
  56.   } ],
  57.   "metric" : 0.9012141767959505
  58. }, {
  59.   "param" : [ {
  60.     "stage" : "RandomForestClassifier",
  61.     "paramName" : "numTrees",
  62.     "paramValue" : 6
  63.   }, {
  64.     "stage" : "RandomForestClassifier",
  65.     "paramName" : "subsamplingRatio",
  66.     "paramValue" : 0.98
  67.   } ],
  68.   "metric" : 0.8993774036693788
  69. }, {
  70.   "param" : [ {
  71.     "stage" : "RandomForestClassifier",
  72.     "paramName" : "numTrees",
  73.     "paramValue" : 9
  74.   }, {
  75.     "stage" : "RandomForestClassifier",
  76.     "paramName" : "subsamplingRatio",
  77.     "paramValue" : 1.0
  78.   } ],
  79.   "metric" : 0.8981738808130779
  80. }, {
  81.   "param" : [ {
  82.     "stage" : "RandomForestClassifier",
  83.     "paramName" : "numTrees",
  84.     "paramValue" : 9
  85.   }, {
  86.     "stage" : "RandomForestClassifier",
  87.     "paramName" : "subsamplingRatio",
  88.     "paramValue" : 0.99
  89.   } ],
  90.   "metric" : 0.9029671873892725
  91. }, {
  92.   "param" : [ {
  93.     "stage" : "RandomForestClassifier",
  94.     "paramName" : "numTrees",
  95.     "paramValue" : 9
  96.   }, {
  97.     "stage" : "RandomForestClassifier",
  98.     "paramName" : "subsamplingRatio",
  99.     "paramValue" : 0.98
  100.   } ],
  101.   "metric" : 0.905228896323363
  102. } ]
  103. rf tv tuning
  104. com.alibaba.alink.pipeline.tuning.GridSearchTVSplit
  105. [ {
  106.   "param" : [ {
  107.     "stage" : "RandomForestClassifier",
  108.     "paramName" : "numTrees",
  109.     "paramValue" : 3
  110.   }, {
  111.     "stage" : "RandomForestClassifier",
  112.     "paramName" : "subsamplingRatio",
  113.     "paramValue" : 1.0
  114.   } ],
  115.   "metric" : 0.9022694229691741
  116. }, {
  117.   "param" : [ {
  118.     "stage" : "RandomForestClassifier",
  119.     "paramName" : "numTrees",
  120.     "paramValue" : 3
  121.   }, {
  122.     "stage" : "RandomForestClassifier",
  123.     "paramName" : "subsamplingRatio",
  124.     "paramValue" : 0.99
  125.   } ],
  126.   "metric" : 0.8963559966080328
  127. }, {
  128.   "param" : [ {
  129.     "stage" : "RandomForestClassifier",
  130.     "paramName" : "numTrees",
  131.     "paramValue" : 3
  132.   }, {
  133.     "stage" : "RandomForestClassifier",
  134.     "paramName" : "subsamplingRatio",
  135.     "paramValue" : 0.98
  136.   } ],
  137.   "metric" : 0.9041948454957178
  138. }, {
  139.   "param" : [ {
  140.     "stage" : "RandomForestClassifier",
  141.     "paramName" : "numTrees",
  142.     "paramValue" : 6
  143.   }, {
  144.     "stage" : "RandomForestClassifier",
  145.     "paramName" : "subsamplingRatio",
  146.     "paramValue" : 1.0
  147.   } ],
  148.   "metric" : 0.8982021117392784
  149. }, {
  150.   "param" : [ {
  151.     "stage" : "RandomForestClassifier",
  152.     "paramName" : "numTrees",
  153.     "paramValue" : 6
  154.   }, {
  155.     "stage" : "RandomForestClassifier",
  156.     "paramName" : "subsamplingRatio",
  157.     "paramValue" : 0.99
  158.   } ],
  159.   "metric" : 0.9031851535310546
  160. }, {
  161.   "param" : [ {
  162.     "stage" : "RandomForestClassifier",
  163.     "paramName" : "numTrees",
  164.     "paramValue" : 6
  165.   }, {
  166.     "stage" : "RandomForestClassifier",
  167.     "paramName" : "subsamplingRatio",
  168.     "paramValue" : 0.98
  169.   } ],
  170.   "metric" : 0.9034443322241488
  171. }, {
  172.   "param" : [ {
  173.     "stage" : "RandomForestClassifier",
  174.     "paramName" : "numTrees",
  175.     "paramValue" : 9
  176.   }, {
  177.     "stage" : "RandomForestClassifier",
  178.     "paramName" : "subsamplingRatio",
  179.     "paramValue" : 1.0
  180.   } ],
  181.   "metric" : 0.8993474753000145
  182. }, {
  183.   "param" : [ {
  184.     "stage" : "RandomForestClassifier",
  185.     "paramName" : "numTrees",
  186.     "paramValue" : 9
  187.   }, {
  188.     "stage" : "RandomForestClassifier",
  189.     "paramName" : "subsamplingRatio",
  190.     "paramValue" : 0.99
  191.   } ],
  192.   "metric" : 0.9090250137144916
  193. }, {
  194.   "param" : [ {
  195.     "stage" : "RandomForestClassifier",
  196.     "paramName" : "numTrees",
  197.     "paramValue" : 9
  198.   }, {
  199.     "stage" : "RandomForestClassifier",
  200.     "paramName" : "subsamplingRatio",
  201.     "paramValue" : 0.98
  202.   } ],
  203.   "metric" : 0.9129786771786127
  204. } ]