Config parameters for model config in classification

Customize the training behavior of your classification solution by passing in a dictionary of parameters in JSON format.

始める前に

Role required: ml_admin or admin

このタスクについて

You can fine-tune model performance by passing in a dictionary of parameters to adjust training behavior.

Understand the machine learning hyperparameters relevant to your model objective. This option is advanced and should be modified with care.

You can add these parameters in the solution definition form by using the following procedure.

Alternatively, you can use a script to add these parameters. For the format to use when scripting, see the What to do next section of this page.

手順

1. Navigate to All > Predictive Intelligence > Classification > Solution Definitions.
2. Open an existing classification solution or create a new one.
3. Select the Advanced Solution Settings tab in the Related Links section of the form.
4. Select New to open the Advanced Solution Setting (ml_advanced_solution_settings) form.
5. In the Solution Parameters field, search for Config parameters for model config in classification.
6. In the User Inputs field, enter the following key-value pairs, after editing the values per your requirements.
   注:

   When pasting the parameters into the solution definition form, don't include JSON's enclosing label, braces, or parentheses. Enter the key-value pairs in the format shown here, after editing the values according to your requirements.

   'max_depth': 10,'learning_rate': 0.1,'objective': 'multi:softprob','num_class': 11,'random_state': 10,'eval_metric': 'mlogloss','booster': 'gbtree','n_estimators': 150,'verbosity': 1,'use_label_encoder': false,'tree_method': 'hist','num_parallel_tree': 1,'gamma': 0.25,'subsample': 0.8,'max_delta_step': 5,'reg_alpha': 0,'reg_lambda': 1,'colsample_bytree': 0.8,'colsample_bylevel': 1,'colsample_bynode': 1,'min_child_weight': 1.25,'n_jobs': 11,'validate_parameters': true

7. Select Submit to update the solution definition.

タスクの結果

The setting appears as a row on the Advanced Solution Setting tab on your solution's form.

次のタスク

Retrain your solution.

You can also pass in this dictionary with a script. Be sure to use the enclosing label, braces, and parentheses when scripting.

Script example:

config.setModelParams({                   
                    'max_depth': 10,                   
                    'learning_rate': 0.1,
                    'objective': 'multi:softprob',
                    'num_class': 11,
                    'random_state': 10,
                    'eval_metric': 'mlogloss',
                    'booster': 'gbtree',
                    'n_estimators': 150,
                    'verbosity': 1,
                    'use_label_encoder': false,
                    'tree_method': 'hist',
                    'num_parallel_tree': 1,
                    'gamma': 0.25,
                    'subsample': 0.8,
                    'max_delta_step': 5,
                    'reg_alpha': 0,
                    'reg_lambda': 1,
                    'colsample_bytree': 0.8,
                    'colsample_bylevel': 1,
                    'colsample_bynode': 1,
                    'min_child_weight': 1.25,
                    'n_jobs': 11,
                    'validate_parameters': true
                    });

JSON example:

        
            {                    
              "classification_model_params": {
                'max_depth': 10,
                'learning_rate': 0.1,
                'objective': 'multi:softprob',
                'num_class': 11,
                'random_state': 10,
                'eval_metric': 'mlogloss',
                'booster': 'gbtree',
                'n_estimators': 150,
                'verbosity': 1,
                'use_label_encoder': false,
                'tree_method': 'hist',
                'num_parallel_tree': 1,
                'gamma': 0.25,
                'subsample': 0.8,
                'max_delta_step': 5,
                'reg_alpha': 0,
                'reg_lambda': 1,
                'colsample_bytree': 0.8,
                'colsample_bylevel': 1,
                'colsample_bynode': 1,
                'min_child_weight': 1.25,
                'n_jobs': 11,
                'validate_parameters': true
                }
              }

関連概念

• Using Machine Learning APIs

関連タスク

• Create and train a classification solution