• Home
• com.google.api.grpc
• proto-google-cloud-automl-v1beta1
• 0.134.0
• source code
• tables.proto

×

Project download

Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $

You can buy this project and download/modify it how often you want.

google.cloud.automl.v1beta1.tables.proto Maven / Gradle / Ivy

// Copyright 2024 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

syntax = "proto3";

package google.cloud.automl.v1beta1;

import "google/cloud/automl/v1beta1/classification.proto";
import "google/cloud/automl/v1beta1/column_spec.proto";
import "google/cloud/automl/v1beta1/data_items.proto";
import "google/cloud/automl/v1beta1/data_stats.proto";
import "google/cloud/automl/v1beta1/ranges.proto";
import "google/cloud/automl/v1beta1/regression.proto";
import "google/cloud/automl/v1beta1/temporal.proto";
import "google/protobuf/struct.proto";
import "google/protobuf/timestamp.proto";

option go_package = "cloud.google.com/go/automl/apiv1beta1/automlpb;automlpb";
option java_multiple_files = true;
option java_package = "com.google.cloud.automl.v1beta1";
option php_namespace = "Google\\Cloud\\AutoMl\\V1beta1";
option ruby_package = "Google::Cloud::AutoML::V1beta1";

// Metadata for a dataset used for AutoML Tables.
message TablesDatasetMetadata {
  // Output only. The table_spec_id of the primary table of this dataset.
  string primary_table_spec_id = 1;

  // column_spec_id of the primary table's column that should be used as the
  // training & prediction target.
  // This column must be non-nullable and have one of following data types
  // (otherwise model creation will error):
  //
  // * CATEGORY
  //
  // * FLOAT64
  //
  // If the type is CATEGORY , only up to
  // 100 unique values may exist in that column across all rows.
  //
  // NOTE: Updates of this field will instantly affect any other users
  // concurrently working with the dataset.
  string target_column_spec_id = 2;

  // column_spec_id of the primary table's column that should be used as the
  // weight column, i.e. the higher the value the more important the row will be
  // during model training.
  // Required type: FLOAT64.
  // Allowed values: 0 to 10000, inclusive on both ends; 0 means the row is
  //                 ignored for training.
  // If not set all rows are assumed to have equal weight of 1.
  // NOTE: Updates of this field will instantly affect any other users
  // concurrently working with the dataset.
  string weight_column_spec_id = 3;

  // column_spec_id of the primary table column which specifies a possible ML
  // use of the row, i.e. the column will be used to split the rows into TRAIN,
  // VALIDATE and TEST sets.
  // Required type: STRING.
  // This column, if set, must either have all of `TRAIN`, `VALIDATE`, `TEST`
  // among its values, or only have `TEST`, `UNASSIGNED` values. In the latter
  // case the rows with `UNASSIGNED` value will be assigned by AutoML. Note
  // that if a given ml use distribution makes it impossible to create a "good"
  // model, that call will error describing the issue.
  // If both this column_spec_id and primary table's time_column_spec_id are not
  // set, then all rows are treated as `UNASSIGNED`.
  // NOTE: Updates of this field will instantly affect any other users
  // concurrently working with the dataset.
  string ml_use_column_spec_id = 4;

  // Output only. Correlations between
  //
  // [TablesDatasetMetadata.target_column_spec_id][google.cloud.automl.v1beta1.TablesDatasetMetadata.target_column_spec_id],
  // and other columns of the
  //
  // [TablesDatasetMetadataprimary_table][google.cloud.automl.v1beta1.TablesDatasetMetadata.primary_table_spec_id].
  // Only set if the target column is set. Mapping from other column spec id to
  // its CorrelationStats with the target column.
  // This field may be stale, see the stats_update_time field for
  // for the timestamp at which these stats were last updated.
  map target_column_correlations = 6;

  // Output only. The most recent timestamp when target_column_correlations
  // field and all descendant ColumnSpec.data_stats and
  // ColumnSpec.top_correlated_columns fields were last (re-)generated. Any
  // changes that happened to the dataset afterwards are not reflected in these
  // fields values. The regeneration happens in the background on a best effort
  // basis.
  google.protobuf.Timestamp stats_update_time = 7;
}

// Model metadata specific to AutoML Tables.
message TablesModelMetadata {
  // Additional optimization objective configuration. Required for
  // `MAXIMIZE_PRECISION_AT_RECALL` and `MAXIMIZE_RECALL_AT_PRECISION`,
  // otherwise unused.
  oneof additional_optimization_objective_config {
    // Required when optimization_objective is "MAXIMIZE_PRECISION_AT_RECALL".
    // Must be between 0 and 1, inclusive.
    float optimization_objective_recall_value = 17;

    // Required when optimization_objective is "MAXIMIZE_RECALL_AT_PRECISION".
    // Must be between 0 and 1, inclusive.
    float optimization_objective_precision_value = 18;
  }

  // Column spec of the dataset's primary table's column the model is
  // predicting. Snapshotted when model creation started.
  // Only 3 fields are used:
  // name - May be set on CreateModel, if it's not then the ColumnSpec
  //        corresponding to the current target_column_spec_id of the dataset
  //        the model is trained from is used.
  //        If neither is set, CreateModel will error.
  // display_name - Output only.
  // data_type - Output only.
  ColumnSpec target_column_spec = 2;

  // Column specs of the dataset's primary table's columns, on which
  // the model is trained and which are used as the input for predictions.
  // The
  //
  // [target_column][google.cloud.automl.v1beta1.TablesModelMetadata.target_column_spec]
  // as well as, according to dataset's state upon model creation,
  //
  // [weight_column][google.cloud.automl.v1beta1.TablesDatasetMetadata.weight_column_spec_id],
  // and
  //
  // [ml_use_column][google.cloud.automl.v1beta1.TablesDatasetMetadata.ml_use_column_spec_id]
  // must never be included here.
  //
  // Only 3 fields are used:
  //
  // * name - May be set on CreateModel, if set only the columns specified are
  //   used, otherwise all primary table's columns (except the ones listed
  //   above) are used for the training and prediction input.
  //
  // * display_name - Output only.
  //
  // * data_type - Output only.
  repeated ColumnSpec input_feature_column_specs = 3;

  // Objective function the model is optimizing towards. The training process
  // creates a model that maximizes/minimizes the value of the objective
  // function over the validation set.
  //
  // The supported optimization objectives depend on the prediction type.
  // If the field is not set, a default objective function is used.
  //
  // CLASSIFICATION_BINARY:
  //   "MAXIMIZE_AU_ROC" (default) - Maximize the area under the receiver
  //                                 operating characteristic (ROC) curve.
  //   "MINIMIZE_LOG_LOSS" - Minimize log loss.
  //   "MAXIMIZE_AU_PRC" - Maximize the area under the precision-recall curve.
  //   "MAXIMIZE_PRECISION_AT_RECALL" - Maximize precision for a specified
  //                                   recall value.
  //   "MAXIMIZE_RECALL_AT_PRECISION" - Maximize recall for a specified
  //                                    precision value.
  //
  // CLASSIFICATION_MULTI_CLASS :
  //   "MINIMIZE_LOG_LOSS" (default) - Minimize log loss.
  //
  //
  // REGRESSION:
  //   "MINIMIZE_RMSE" (default) - Minimize root-mean-squared error (RMSE).
  //   "MINIMIZE_MAE" - Minimize mean-absolute error (MAE).
  //   "MINIMIZE_RMSLE" - Minimize root-mean-squared log error (RMSLE).
  string optimization_objective = 4;

  // Output only. Auxiliary information for each of the
  // input_feature_column_specs with respect to this particular model.
  repeated TablesModelColumnInfo tables_model_column_info = 5;

  // Required. The train budget of creating this model, expressed in milli node
  // hours i.e. 1,000 value in this field means 1 node hour.
  //
  // The training cost of the model will not exceed this budget. The final cost
  // will be attempted to be close to the budget, though may end up being (even)
  // noticeably smaller - at the backend's discretion. This especially may
  // happen when further model training ceases to provide any improvements.
  //
  // If the budget is set to a value known to be insufficient to train a
  // model for the given dataset, the training won't be attempted and
  // will error.
  //
  // The train budget must be between 1,000 and 72,000 milli node hours,
  // inclusive.
  int64 train_budget_milli_node_hours = 6;

  // Output only. The actual training cost of the model, expressed in milli
  // node hours, i.e. 1,000 value in this field means 1 node hour. Guaranteed
  // to not exceed the train budget.
  int64 train_cost_milli_node_hours = 7;

  // Use the entire training budget. This disables the early stopping feature.
  // By default, the early stopping feature is enabled, which means that AutoML
  // Tables might stop training before the entire training budget has been used.
  bool disable_early_stopping = 12;
}

// Contains annotation details specific to Tables.
message TablesAnnotation {
  // Output only. A confidence estimate between 0.0 and 1.0, inclusive. A higher
  // value means greater confidence in the returned value.
  // For
  //
  // [target_column_spec][google.cloud.automl.v1beta1.TablesModelMetadata.target_column_spec]
  // of FLOAT64 data type the score is not populated.
  float score = 1;

  // Output only. Only populated when
  //
  // [target_column_spec][google.cloud.automl.v1beta1.TablesModelMetadata.target_column_spec]
  // has FLOAT64 data type. An interval in which the exactly correct target
  // value has 95% chance to be in.
  DoubleRange prediction_interval = 4;

  // The predicted value of the row's
  //
  // [target_column][google.cloud.automl.v1beta1.TablesModelMetadata.target_column_spec].
  // The value depends on the column's DataType:
  //
  // * CATEGORY - the predicted (with the above confidence `score`) CATEGORY
  //   value.
  //
  // * FLOAT64 - the predicted (with above `prediction_interval`) FLOAT64 value.
  google.protobuf.Value value = 2;

  // Output only. Auxiliary information for each of the model's
  //
  // [input_feature_column_specs][google.cloud.automl.v1beta1.TablesModelMetadata.input_feature_column_specs]
  // with respect to this particular prediction.
  // If no other fields than
  //
  // [column_spec_name][google.cloud.automl.v1beta1.TablesModelColumnInfo.column_spec_name]
  // and
  //
  // [column_display_name][google.cloud.automl.v1beta1.TablesModelColumnInfo.column_display_name]
  // would be populated, then this whole field is not.
  repeated TablesModelColumnInfo tables_model_column_info = 3;

  // Output only. Stores the prediction score for the baseline example, which
  // is defined as the example with all values set to their baseline values.
  // This is used as part of the Sampled Shapley explanation of the model's
  // prediction. This field is populated only when feature importance is
  // requested. For regression models, this holds the baseline prediction for
  // the baseline example. For classification models, this holds the baseline
  // prediction for the baseline example for the argmax class.
  float baseline_score = 5;
}

// An information specific to given column and Tables Model, in context
// of the Model and the predictions created by it.
message TablesModelColumnInfo {
  // Output only. The name of the ColumnSpec describing the column. Not
  // populated when this proto is outputted to BigQuery.
  string column_spec_name = 1;

  // Output only. The display name of the column (same as the display_name of
  // its ColumnSpec).
  string column_display_name = 2;

  // Output only. When given as part of a Model (always populated):
  // Measurement of how much model predictions correctness on the TEST data
  // depend on values in this column. A value between 0 and 1, higher means
  // higher influence. These values are normalized - for all input feature
  // columns of a given model they add to 1.
  //
  // When given back by Predict (populated iff
  // [feature_importance
  // param][google.cloud.automl.v1beta1.PredictRequest.params] is set) or Batch
  // Predict (populated iff
  // [feature_importance][google.cloud.automl.v1beta1.PredictRequest.params]
  // param is set):
  // Measurement of how impactful for the prediction returned for the given row
  // the value in this column was. Specifically, the feature importance
  // specifies the marginal contribution that the feature made to the prediction
  // score compared to the baseline score. These values are computed using the
  // Sampled Shapley method.
  float feature_importance = 3;
}