Struct google_bigquery2::TrainingOptions

pub struct TrainingOptions {
    pub optimization_strategy: Option<String>,
    pub item_column: Option<String>,
    pub user_column: Option<String>,
    pub num_factors: Option<String>,
    pub input_label_columns: Option<Vec<String>>,
    pub batch_size: Option<String>,
    pub distance_type: Option<String>,
    pub kmeans_initialization_column: Option<String>,
    pub l2_regularization: Option<f64>,
    pub num_clusters: Option<String>,
    pub min_relative_progress: Option<f64>,
    pub l1_regularization: Option<f64>,
    pub max_iterations: Option<String>,
    pub early_stop: Option<bool>,
    pub initial_learn_rate: Option<f64>,
    pub data_split_column: Option<String>,
    pub dropout: Option<f64>,
    pub warm_start: Option<bool>,
    pub hidden_units: Option<Vec<String>>,
    pub max_tree_depth: Option<String>,
    pub feedback_type: Option<String>,
    pub kmeans_initialization_method: Option<String>,
    pub preserve_input_structs: Option<bool>,
    pub learn_rate_strategy: Option<String>,
    pub data_split_eval_fraction: Option<f64>,
    pub data_split_method: Option<String>,
    pub subsample: Option<f64>,
    pub label_class_weights: Option<HashMap<String, f64>>,
    pub learn_rate: Option<f64>,
    pub model_uri: Option<String>,
    pub wals_alpha: Option<f64>,
    pub min_split_loss: Option<f64>,
    pub loss_type: Option<String>,
}

There is no detailed description.

This type is not used in any activity, and only used as part of another schema.

Fields

optimization_strategy: Option<String>

Optimization strategy for training linear regression models.

item_column: Option<String>

Item column specified for matrix factorization models.

user_column: Option<String>

User column specified for matrix factorization models.

num_factors: Option<String>

Num factors specified for matrix factorization models.

input_label_columns: Option<Vec<String>>

Name of input label columns in training data.

batch_size: Option<String>

Batch size for dnn models.

distance_type: Option<String>

Distance type for clustering models.

kmeans_initialization_column: Option<String>

The column used to provide the initial centroids for kmeans algorithm when kmeans_initialization_method is CUSTOM.

l2_regularization: Option<f64>

L2 regularization coefficient.

num_clusters: Option<String>

Number of clusters for clustering models.

min_relative_progress: Option<f64>

When early_stop is true, stops training when accuracy improvement is less than 'min_relative_progress'. Used only for iterative training algorithms.

l1_regularization: Option<f64>

L1 regularization coefficient.

max_iterations: Option<String>

The maximum number of iterations in training. Used only for iterative training algorithms.

early_stop: Option<bool>

Whether to stop early when the loss doesn't improve significantly any more (compared to min_relative_progress). Used only for iterative training algorithms.

initial_learn_rate: Option<f64>

Specifies the initial learning rate for the line search learn rate strategy.

data_split_column: Option<String>

The column to split data with. This column won't be used as a feature.

1. When data_split_method is CUSTOM, the corresponding column should be boolean. The rows with true value tag are eval data, and the false are training data.
2. When data_split_method is SEQ, the first DATA_SPLIT_EVAL_FRACTION rows (from smallest to largest) in the corresponding column are used as training data, and the rest are eval data. It respects the order in Orderable data types: https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#data-type-properties

dropout: Option<f64>

Dropout probability for dnn models.

warm_start: Option<bool>

Whether to train a model from the last checkpoint.

hidden_units: Option<Vec<String>>

Hidden units for dnn models.

max_tree_depth: Option<String>

Maximum depth of a tree for boosted tree models.

feedback_type: Option<String>

Feedback type that specifies which algorithm to run for matrix factorization.

kmeans_initialization_method: Option<String>

The method used to initialize the centroids for kmeans algorithm.

preserve_input_structs: Option<bool>

Whether to preserve the input structs in output feature names. Suppose there is a struct A with field b. When false (default), the output feature name is A_b. When true, the output feature name is A.b.

learn_rate_strategy: Option<String>

The strategy to determine learn rate for the current iteration.

data_split_eval_fraction: Option<f64>

The fraction of evaluation data over the whole input data. The rest of data will be used as training data. The format should be double. Accurate to two decimal places. Default value is 0.2.

data_split_method: Option<String>

The data split type for training and evaluation, e.g. RANDOM.

subsample: Option<f64>

Subsample fraction of the training data to grow tree to prevent overfitting for boosted tree models.

label_class_weights: Option<HashMap<String, f64>>

Weights associated with each label class, for rebalancing the training data. Only applicable for classification models.

learn_rate: Option<f64>

Learning rate in training. Used only for iterative training algorithms.

model_uri: Option<String>

[Beta] Google Cloud Storage URI from which the model was imported. Only applicable for imported models.

wals_alpha: Option<f64>

Hyperparameter for matrix factoration when implicit feedback type is specified.

min_split_loss: Option<f64>

Minimum split loss for boosted tree models.

loss_type: Option<String>

Type of loss function used during training run.

Trait Implementations

impl Clone for TrainingOptions

fn clone(&self) -> TrainingOptions

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TrainingOptions

fn fmt(&self, f: &mut Formatter) -> Result

Formats the value using the given formatter.

impl Default for TrainingOptions

fn default() -> TrainingOptions

Returns the "default value" for a type.

impl<'de> Deserialize<'de> for TrainingOptions

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error> where
    __D: Deserializer<'de>, 

Deserialize this value from the given Serde deserializer.

impl Part for TrainingOptions

impl Serialize for TrainingOptions

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error> where
    __S: Serializer, 

Serialize this value into the given Serde serializer.