You are viewing documentation about an older version (1.0.9). View latest version

snowflake.ml.modeling.linear_model.SGDRegressor

class snowflake.ml.modeling.linear_model.SGDRegressor(*, loss='squared_error', penalty='l2', alpha=0.0001, l1_ratio=0.15, fit_intercept=True, max_iter=1000, tol=0.001, shuffle=True, verbose=0, epsilon=0.1, random_state=None, learning_rate='invscaling', eta0=0.01, power_t=0.25, early_stopping=False, validation_fraction=0.1, n_iter_no_change=5, warm_start=False, average=False, input_cols: Optional[Union[str, Iterable[str]]] = None, output_cols: Optional[Union[str, Iterable[str]]] = None, label_cols: Optional[Union[str, Iterable[str]]] = None, drop_input_cols: Optional[bool] = False, sample_weight_col: Optional[str] = None)

Bases: BaseTransformer

Linear model fitted by minimizing a regularized empirical loss with SGD For more details on this class, see sklearn.linear_model.SGDRegressor

loss: str, default=’squared_error’

The loss function to be used. The possible values are ‘squared_error’, ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’

The ‘squared_error’ refers to the ordinary least squares fit. ‘huber’ modifies ‘squared_error’ to focus less on getting outliers correct by switching from squared to linear loss past a distance of epsilon. ‘epsilon_insensitive’ ignores errors less than epsilon and is linear past that; this is the loss function used in SVR. ‘squared_epsilon_insensitive’ is the same but becomes squared loss past a tolerance of epsilon.

More details about the losses formulas can be found in the User Guide.

penalty: {‘l2’, ‘l1’, ‘elasticnet’, None}, default=’l2’

The penalty (aka regularization term) to be used. Defaults to ‘l2’ which is the standard regularizer for linear SVM models. ‘l1’ and ‘elasticnet’ might bring sparsity to the model (feature selection) not achievable with ‘l2’. No penalty is added when set to None.

alpha: float, default=0.0001

Constant that multiplies the regularization term. The higher the value, the stronger the regularization. Also used to compute the learning rate when set to learning_rate is set to ‘optimal’.

l1_ratio: float, default=0.15

The Elastic Net mixing parameter, with 0 <= l1_ratio <= 1. l1_ratio=0 corresponds to L2 penalty, l1_ratio=1 to L1. Only used if penalty is ‘elasticnet’.

fit_intercept: bool, default=True

Whether the intercept should be estimated or not. If False, the data is assumed to be already centered.

max_iter: int, default=1000

The maximum number of passes over the training data (aka epochs). It only impacts the behavior in the fit method, and not the partial_fit() method.

tol: float or None, default=1e-3

The stopping criterion. If it is not None, training will stop when (loss > best_loss - tol) for n_iter_no_change consecutive epochs. Convergence is checked against the training loss or the validation loss depending on the early_stopping parameter.

shuffle: bool, default=True

Whether or not the training data should be shuffled after each epoch.

verbose: int, default=0

The verbosity level.

epsilon: float, default=0.1

Epsilon in the epsilon-insensitive loss functions; only if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. For ‘huber’, determines the threshold at which it becomes less important to get the prediction exactly right. For epsilon-insensitive, any differences between the current prediction and the correct label are ignored if they are less than this threshold.

random_state: int, RandomState instance, default=None

Used for shuffling the data, when shuffle is set to True. Pass an int for reproducible output across multiple function calls. See Glossary.

learning_rate: str, default=’invscaling’

The learning rate schedule:

  • ‘constant’: eta = eta0

  • ‘optimal’: eta = 1.0 / (alpha * (t + t0)) where t0 is chosen by a heuristic proposed by Leon Bottou.

  • ‘invscaling’: eta = eta0 / pow(t, power_t)

  • ‘adaptive’: eta = eta0, as long as the training keeps decreasing. Each time n_iter_no_change consecutive epochs fail to decrease the training loss by tol or fail to increase validation score by tol if early_stopping is True, the current learning rate is divided by 5.

eta0: float, default=0.01

The initial learning rate for the ‘constant’, ‘invscaling’ or ‘adaptive’ schedules. The default value is 0.01.

power_t: float, default=0.25

The exponent for inverse scaling learning rate.

early_stopping: bool, default=False

Whether to use early stopping to terminate training when validation score is not improving. If set to True, it will automatically set aside a fraction of training data as validation and terminate training when validation score returned by the score method is not improving by at least tol for n_iter_no_change consecutive epochs.

validation_fraction: float, default=0.1

The proportion of training data to set aside as validation set for early stopping. Must be between 0 and 1. Only used if early_stopping is True.

n_iter_no_change: int, default=5

Number of iterations with no improvement to wait before stopping fitting. Convergence is checked against the training loss or the validation loss depending on the early_stopping parameter.

warm_start: bool, default=False

When set to True, reuse the solution of the previous call to fit as initialization, otherwise, just erase the previous solution. See the Glossary.

Repeatedly calling fit or partial_fit when warm_start is True can result in a different solution than when calling fit a single time because of the way the data is shuffled. If a dynamic learning rate is used, the learning rate is adapted depending on the number of samples already seen. Calling fit resets this counter, while partial_fit will result in increasing the existing counter.

average: bool or int, default=False

When set to True, computes the averaged SGD weights across all updates and stores the result in the coef_ attribute. If set to an int greater than 1, averaging will begin once the total number of samples seen reaches average. So average=10 will begin averaging after seeing 10 samples.

input_cols: Optional[Union[str, List[str]]]

A string or list of strings representing column names that contain features. If this parameter is not specified, all columns in the input DataFrame except the columns specified by label_cols and sample-weight_col parameters are considered input columns.

label_cols: Optional[Union[str, List[str]]]

A string or list of strings representing column names that contain labels. This is a required param for estimators, as there is no way to infer these columns. If this parameter is not specified, then object is fitted without labels(Like a transformer).

output_cols: Optional[Union[str, List[str]]]

A string or list of strings representing column names that will store the output of predict and transform operations. The length of output_cols mus match the expected number of output columns from the specific estimator or transformer class used. If this parameter is not specified, output column names are derived by adding an OUTPUT_ prefix to the label column names. These inferred output column names work for estimator’s predict() method, but output_cols must be set explicitly for transformers.

sample_weight_col: Optional[str]

A string representing the column name containing the examples’ weights. This argument is only required when working with weighted datasets.

drop_input_cols: Optional[bool], default=False

If set, the response of predict(), transform() methods will not contain input columns.

Methods

fit(dataset)

Fit linear model with Stochastic Gradient Descent For more details on this function, see sklearn.linear_model.SGDRegressor.fit

predict(dataset)

Predict using the linear model For more details on this function, see sklearn.linear_model.SGDRegressor.predict

score(dataset)

Return the coefficient of determination of the prediction For more details on this function, see sklearn.linear_model.SGDRegressor.score

set_input_cols(input_cols)

Input columns setter.

to_sklearn()

Get sklearn.linear_model.SGDRegressor object.

Attributes

model_signatures

Returns model signature of current class.