Naive Bayesian classification prediction
Instructions for Use
This method predicts data based on models trained in naive Bayesian classification or existing models. The result returns the feature dataset (FeatureRDD).
Parameter Description
| Parameter Name | Default Value | Parameter Definition | Parameter Type |
|---|---|---|---|
| Model save directory |
The specified save directory for the model | String | |
| Mapping field of predicted data (Optional) |
Mapping field of predicted data. The corresponding relationship between the explanation field names of the model and the prediction dataset field names, and each explanation field should have a corresponding field in the prediction dataset. If no corresponding relationship is set, all fields in the explanatory variable array must exist in the predicted dataset | JavaExplanatoryFieldMatching | |
| The distance explanatory variable mapping of predicted data (Optional) |
represents the corresponding relationship between the distance explanatory variable name created by the model based on the distance explanatory variable dataset and the predicted distance explanatory variable dataset. If the training distance explanatory variable dataset is input when training the model, the prediction distance explanatory variable dataset must be input, and each distance explanatory variable field should correspond to a prediction distance explanatory variable dataset. And the search distance used in predicting the distance explanatory variable dataset is the search distance of the distance explanatory variable. The name of the explanatory variable is the input distanceFieldName, which can also be obtained from the interpretoryIndex in the JSON string of the model training results | ExplanatoryDistanceRDDMatching | |
| Prediction dataset |
Prediction dataset. The connection information for accessing data needs to include information such as data type, connection parameters, and dataset name. Set using the '-- key=value' method, with multiple values separated by '' spaces. If the HBase data is connected as -- providerType=hbase -- hbase. zookeepers=192.168.12.34:2181-- hbase. catalog=demo -- dataset=dltb; Connect dsf data as -- providerType=dsf -- path= hdfs://ip:9000/dsfdata ; The local data is -- providerType=dsf -- path=/home/dsfdata | String | |
| Result Dataset |
Result Dataset. The connection information for accessing data needs to include information such as data type, connection parameters, and dataset name. Set using the '-- key=value' method, with multiple values separated by '' spaces. If the HBase data is connected as -- providerType=hbase -- hbase. zookeepers=192.168.12.34:2181-- hbase. catalog=demo -- dataset=dltb; Connect dsf data as -- providerType=dsf -- path= hdfs://ip:9000/dsfdata ; The local data is -- providerType=dsf -- path=/home/dsfdata | String | |
| Data query conditions (Optional) |
Data query conditions, which support attribute conditions and Spatial query, such as SmID<100 and BBOX (the_geom, 120,30121,31) | String |