Add dart to JSON schema. (#5218)

* Add dart to JSON schema.

* Use spaces instead of tab.
This commit is contained in:
Jiaming Yuan
2020-01-28 13:29:09 +08:00
committed by GitHub
parent 0c7455276d
commit ef19480eda
3 changed files with 219 additions and 186 deletions

View File

@@ -1,6 +1,140 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"definitions": {
"gbtree": {
"type": "object",
"properties": {
"name": {
"const": "gbtree"
},
"model": {
"type": "object",
"properties": {
"gbtree_model_param": {
"$ref": "#/definitions/gbtree_model_param"
},
"trees": {
"type": "array",
"items": {
"type": "object",
"properties": {
"tree_param": {
"type": "object",
"properties": {
"num_nodes": {
"type": "string"
},
"size_leaf_vector": {
"type": "string"
},
"num_feature": {
"type": "string"
}
},
"required": [
"num_nodes",
"num_feature",
"size_leaf_vector"
]
},
"id": {
"type": "integer"
},
"loss_changes": {
"type": "array",
"items": {
"type": "number"
}
},
"sum_hessian": {
"type": "array",
"items": {
"type": "number"
}
},
"base_weights": {
"type": "array",
"items": {
"type": "number"
}
},
"leaf_child_counts": {
"type": "array",
"items": {
"type": "integer"
}
},
"left_children": {
"type": "array",
"items": {
"type": "integer"
}
},
"right_children": {
"type": "array",
"items": {
"type": "integer"
}
},
"parents": {
"type": "array",
"items": {
"type": "integer"
}
},
"split_indices": {
"type": "array",
"items": {
"type": "integer"
}
},
"split_conditions": {
"type": "array",
"items": {
"type": "number"
}
},
"default_left": {
"type": "array",
"items": {
"type": "boolean"
}
}
},
"required": [
"tree_param",
"loss_changes",
"sum_hessian",
"base_weights",
"leaf_child_counts",
"left_children",
"right_children",
"parents",
"split_indices",
"split_conditions",
"default_left"
]
}
},
"tree_info": {
"type": "array",
"items": {
"type": "integer"
}
}
},
"required": [
"gbtree_model_param",
"trees",
"tree_info"
]
}
},
"required": [
"name",
"model"
]
},
"gbtree_model_param": {
"type": "object",
"properties": {
@@ -35,7 +169,6 @@
"size_leaf_vector"
]
},
"reg_loss_param": {
"type": "object",
"properties": {
@@ -47,14 +180,14 @@
"softmax_multiclass_param": {
"type": "object",
"properties": {
"num_class": { "type": "string" }
"num_class": { "type": "string" }
}
},
"lambda_rank_param": {
"type": "object",
"properties": {
"num_pairsample": { "type": "string" },
"fix_list_weight": { "type": "string" }
"num_pairsample": { "type": "string" },
"fix_list_weight": { "type": "string" }
}
}
},
@@ -74,156 +207,46 @@
"properties": {
"gradient_booster": {
"oneOf": [
{
"$ref": "#/definitions/gbtree"
},
{
"type": "object",
"properties": {
"name": {
"const": "gbtree"
},
"name": { "const": "gblinear" },
"model": {
"type": "object",
"properties": {
"gbtree_model_param": {
"$ref": "#/definitions/gbtree_model_param"
},
"trees": {
"weights": {
"type": "array",
"items": {
"type": "object",
"properties": {
"tree_param": {
"type": "object",
"properties": {
"num_nodes": {
"type": "string"
},
"size_leaf_vector": {
"type": "string"
},
"num_feature": {
"type": "string"
}
},
"required": [
"num_nodes",
"num_feature",
"size_leaf_vector"
]
},
"id": {
"type": "integer"
},
"loss_changes": {
"type": "array",
"items": {
"type": "number"
}
},
"sum_hessian": {
"type": "array",
"items": {
"type": "number"
}
},
"base_weights": {
"type": "array",
"items": {
"type": "number"
}
},
"leaf_child_counts": {
"type": "array",
"items": {
"type": "integer"
}
},
"left_children": {
"type": "array",
"items": {
"type": "integer"
}
},
"right_children": {
"type": "array",
"items": {
"type": "integer"
}
},
"parents": {
"type": "array",
"items": {
"type": "integer"
}
},
"split_indices": {
"type": "array",
"items": {
"type": "integer"
}
},
"split_conditions": {
"type": "array",
"items": {
"type": "number"
}
},
"default_left": {
"type": "array",
"items": {
"type": "boolean"
}
}
},
"required": [
"tree_param",
"loss_changes",
"sum_hessian",
"base_weights",
"leaf_child_counts",
"left_children",
"right_children",
"parents",
"split_indices",
"split_conditions",
"default_left"
]
}
},
"tree_info": {
"type": "array",
"items": {
"type": "integer"
"type": "number"
}
}
},
"required": [
"gbtree_model_param",
"trees"
]
}
}
}
},
{
"type": "object",
"properties": {
"name": { "const": "dart" },
"gbtree": {
"$ref": "#/definitions/gbtree"
},
"weight_drop": {
"type": "array",
"items": {
"type": "number"
}
}
},
"required": [
"name",
"model"
"gbtree",
"weight_drop"
]
},
{
"type": "object",
"properties": {
"name": { "const": "gblinear" },
"model": {
"type": "object",
"properties": {
"weights": {
"type": "array",
"items": {
"type": "number"
}
}
}
}
}
}
}
]
},
@@ -233,51 +256,51 @@
"type": "object",
"properties": {
"name": { "const": "reg:squarederror" },
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
},
"required": [
"name",
"reg_loss_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "reg:squaredlogerror" },
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
},
"required": [
"name",
"reg_loss_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "reg:logistic" },
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
},
"required": [
"name",
"reg_loss_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "binary:logistic" },
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
},
"required": [
"name",
"reg_loss_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "binary:logitraw" },
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
"reg_loss_param": { "$ref": "#/definitions/reg_loss_param"}
},
"required": [
"name",
@@ -285,46 +308,46 @@
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "count:poisson" },
"poisson_regression_param": {
"type": "object",
"properties": {
"max_delta_step": { "type": "string" }
}
}
"poisson_regression_param": {
"type": "object",
"properties": {
"max_delta_step": { "type": "string" }
}
}
},
"required": [
"name",
"poisson_regression_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "reg:tweedie" },
"tweedie_regression_param": {
"type": "object",
"properties": {
"tweedie_variance_power": { "type": "string" }
}
}
"tweedie_regression_param": {
"type": "object",
"properties": {
"tweedie_variance_power": { "type": "string" }
}
}
},
"required": [
"name",
"tweedie_regression_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "survival:cox" }
},
"required": [ "name" ]
},
{
{
"type": "object",
"properties": {
"name": { "const": "reg:gamma" }
@@ -332,22 +355,22 @@
"required": [ "name" ]
},
{
{
"type": "object",
"properties": {
"name": { "const": "multi:softprob" },
"softmax_multiclass_param": { "$ref": "#/definitions/softmax_multiclass_param"}
"softmax_multiclass_param": { "$ref": "#/definitions/softmax_multiclass_param"}
},
"required": [
"name",
"softmax_multiclass_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "multi:softmax" },
"softmax_multiclass_param": { "$ref": "#/definitions/softmax_multiclass_param"}
"softmax_multiclass_param": { "$ref": "#/definitions/softmax_multiclass_param"}
},
"required": [
"name",
@@ -355,33 +378,33 @@
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "rank:pairwise" },
"lambda_rank_param": { "$ref": "#/definitions/lambda_rank_param"}
"lambda_rank_param": { "$ref": "#/definitions/lambda_rank_param"}
},
"required": [
"name",
"lambda_rank_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "rank:ndcg" },
"lambda_rank_param": { "$ref": "#/definitions/lambda_rank_param"}
"lambda_rank_param": { "$ref": "#/definitions/lambda_rank_param"}
},
"required": [
"name",
"lambda_rank_param"
]
},
{
{
"type": "object",
"properties": {
"name": { "const": "rank:map" },
"lambda_rank_param": { "$ref": "#/definitions/lambda_rank_param"}
"lambda_rank_param": { "$ref": "#/definitions/lambda_rank_param"}
},
"required": [
"name",
@@ -391,14 +414,14 @@
]
},
"learner_model_param": {
"type": "object",
"properties": {
"base_score": { "type": "string" },
"num_class": { "type": "string" },
"num_feature": { "type": "string" }
}
}
"learner_model_param": {
"type": "object",
"properties": {
"base_score": { "type": "string" },
"num_class": { "type": "string" },
"num_feature": { "type": "string" }
}
}
},
"required": [
"gradient_booster",

View File

@@ -201,6 +201,8 @@ Another important feature of JSON format is a documented `Schema
XGBoost. Here is the initial draft of JSON schema for the output model (not
serialization, which will not be stable as noted above). It's subject to change due to
the beta status. For an example of parsing XGBoost tree model, see ``/demo/json-model``.
Please notice the "weight_drop" field used in "dart" booster. XGBoost does not scale tree
leaf directly, instead it saves the weights as a separated array.
.. include:: ../model.schema
:code: json