LinearRegressionModel train¶
-
train
(self, frame, label_column, observation_columns, intercept=True, num_iterations=100, step_size=1.0, reg_type=None, reg_param=0.01, mini_batch_fraction=1.0)¶ [ALPHA] Build linear regression model.
Parameters: frame : Frame
A frame to train the model on.
label_column : unicode
Column name containing the label for each observation.
observation_columns : list
List of column(s) containing the observations.
intercept : bool (default=True)
Flag indicating if the algorithm adds an intercept. Default is true.
num_iterations : int32 (default=100)
Number of iterations for SGD. Default is 100.
step_size : float64 (default=1.0)
Initial step size for SGD optimizer for the first step. Default is 1.0.
reg_type : unicode (default=None)
Regularization “L1” or “L2”. Default is “L2”.
reg_param : float64 (default=0.01)
Regularization parameter. Default is 0.01.
mini_batch_fraction : float64 (default=1.0)
Set fraction of data to be used for each SGD iteration. Default is 1.0; corresponding to deterministic/classical gradient descent.
Returns: : dict
Trained linear regression model
Creating a LinearRegression Model using the observation column and target column of the train frame
Examples
See here for examples.