Constructor
new LinearRegressionModel()
Extends
- module:eclairjs/mllib/regression.RegressionModel
Methods
(static) load(path) → {module:eclairjs/mllib/regression.LinearRegressionModel}
Parameters:
| Name | Type | Description |
|---|---|---|
path |
string |
Returns:
(static) read() → {module:eclairjs/ml/util.MLReader}
Returns:
coefficients() → {module:eclairjs/mllib/linalg.Vector}
Returns:
copy(extra) → {module:eclairjs/mllib/regression.LinearRegressionModel}
Parameters:
| Name | Type | Description |
|---|---|---|
extra |
module:eclairjs/ml/param.ParamMap |
Returns:
evaluate(dataset) → {module:eclairjs/ml/regression.LinearRegressionSummary}
Evaluates the model on a test dataset.
Parameters:
| Name | Type | Description |
|---|---|---|
dataset |
module:eclairjs/sql.Dataset | Test dataset to evaluate model on. |
Returns:
hasSummary() → {boolean}
Indicates whether a training summary exists for this model instance.
Returns:
- Type
- boolean
intercept() → {Array.<flaot>}
Returns:
- Type
- Array.<flaot>
summary() → {module:eclairjs/ml/regression.LinearRegressionTrainingSummary}
Gets summary (e.g. residuals, mse, r-squared ) of model on training set. An exception is
thrown if `trainingSummary == None`.
Returns:
uid() → {string}
An immutable unique ID for the object and its derivatives.
Returns:
- Type
- string
write() → {module:eclairjs/ml/util.MLWriter}
Returns a MLWriter instance for this ML instance.
For [[LinearRegressionModel]], this does NOT currently save the training summary.
An option to save summary may be added in the future.
This also does not save the parent currently.