Documentation ¶
Index ¶
- func DistTrain(trainStmt *ir.TrainStmt, session *pb.Session, nworkers int, ...) (string, error)
- func DocGenInMarkdown() string
- func Evaluate(evalStmt *ir.EvaluateStmt, session *pb.Session) (string, error)
- func Explain(explainStmt *ir.ExplainStmt, session *pb.Session) (string, error)
- func InitializeAttributes(trainStmt *ir.TrainStmt) error
- func Pred(predStmt *ir.PredictStmt, session *pb.Session) (string, error)
- func Train(trainStmt *ir.TrainStmt, session *pb.Session) (string, error)
- type FieldMeta
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func DistTrain ¶
func DistTrain(trainStmt *ir.TrainStmt, session *pb.Session, nworkers int, ossURIToSave, ossURIToLoad string) (string, error)
DistTrain generates a Python program for distributed train a XGBoost model. TODO(weiguoz): make DistTrain to be an implementation of the interface.
func DocGenInMarkdown ¶
func DocGenInMarkdown() string
DocGenInMarkdown generates the doc of the XGBoost in Markdown format.
func InitializeAttributes ¶
InitializeAttributes initializes the attributes of XGBoost and does type checking for them
Types ¶
type FieldMeta ¶
type FieldMeta struct { FeatureName string `json:"feature_name"` DType string `json:"dtype"` Delimiter string `json:"delimiter"` Format string `json:"format"` Shap []int `json:"shape"` IsSparse bool `json:"is_sparse"` }
FieldMeta delicates Field Meta with Json format which used in code generator
Click to show internal directories.
Click to hide internal directories.