Runs offline inference on models from the XGBoost Train component. Supports classification and regression with Table or LibSVM input.
Limits
Supported computing engines: MaxCompute, Flink, and DLC.
Data formats
Supported formats: Table and LibSVM.
Table format example:
f0
f1
label
0.1
1
0
0.9
2
1
LibSVM format example:
Sample data
2:1 9:1 10:1 20:1 29:1 33:1 35:1 39:1 40:1 52:1 57:1 64:1 68:1 76:1 85:1 87:1 91:1 94:1 101:1 104:1 116:1 123:1
0:1 9:1 18:1 20:1 23:1 33:1 35:1 38:1 41:1 52:1 55:1 64:1 68:1 76:1 85:1 87:1 91:1 94:1 101:1 105:1 115:1 121:1
2:1 8:1 18:1 20:1 29:1 33:1 35:1 39:1 41:1 52:1 57:1 64:1 68:1 76:1 85:1 87:1 91:1 94:1 101:1 104:1 116:1 123:1
2:1 9:1 13:1 21:1 28:1 33:1 36:1 38:1 40:1 53:1 57:1 64:1 68:1 76:1 85:1 87:1 91:1 94:1 97:1 105:1 113:1 119:1
0:1 9:1 18:1 20:1 22:1 33:1 35:1 38:1 44:1 52:1 55:1 64:1 68:1 76:1 85:1 87:1 91:1 94:1 101:1 104:1 115:1 121:1
0:1 8:1 18:1 20:1 23:1 33:1 35:1 38:1 41:1 52:1 55:1 64:1 68:1 76:1 85:1 87:1 91:1 94:1 101:1 105:1 116:1 121:1
GUI configuration
Configure the XGBoost Predict component on the Designer canvas.
Parameter | Type | Description | |
Fields Setting | Reserved Column Name | String array | Columns to preserve in output. |
Feature Columns | String array | Feature columns for Table format data. Mutually exclusive with Vector Field (LibSVM format). | |
Vector Field Name | String | Column containing LibSVM format data. Mutually exclusive with Feature Columns (Table format). | |
Parameters Setting | Prediction Result Column | String | Name of output column for prediction results. |
Execution Tuning | Number of Workers | Positive integer | Number of parallel workers. Set together with Memory per Worker. Valid values: [1, 9999]. |
Memory per Worker | Positive integer | Memory allocated per worker in MB. Valid values: [1024, 64 × 1024]. | |
Usage example
This example demonstrates XGBoost classification on Higgs boson event data using a preset template. To create this pipeline from the Use XGBoost algorithm to identify the Higgs boson template, see Create a pipeline from a preset template.
Convert the output format for evaluation
The component outputs JSON strings serialized from the open-source XGBoost library. Convert this output to enable evaluation components to process predictions.
Add an SQL Script component downstream of XGboost Predict. The SQL Script converts predictions into the format required by Binary classification Evaluation V2. Use this code:
set odps.sql.udf.getjsonobj.new=true;
select *, CONCAT("{\"0\":", 1.0-prob, ",\"1\":", prob, "}") as detail
FROM (
select *, cast(get_json_object(pred, '$[0]') as double) as prob FROM ${t1})References
XGBoost Predict requires a trained model from the XGBoost Train component. For configuration details, see XGBoost Train.
Designer provides algorithm components for data processing tasks. For a complete list, see Overview of Designer components.