chore: regens API reference docs (#889)
diff --git a/docs/dyn/bigquery_v2.models.html b/docs/dyn/bigquery_v2.models.html
index 029d8fd..2f813fe 100644
--- a/docs/dyn/bigquery_v2.models.html
+++ b/docs/dyn/bigquery_v2.models.html
@@ -87,7 +87,7 @@
<code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>
<p class="firstline">Retrieves the next page of results.</p>
<p class="toc_element">
- <code><a href="#patch">patch(projectId, datasetId, modelId, body)</a></code></p>
+ <code><a href="#patch">patch(projectId, datasetId, modelId, body=None)</a></code></p>
<p class="firstline">Patch specific fields in the specified model.</p>
<h3>Method Details</h3>
<div class="method">
@@ -95,9 +95,9 @@
<pre>Deletes the model specified by modelId from the dataset.
Args:
- projectId: string, Project ID of the model to delete. (required)
- datasetId: string, Dataset ID of the model to delete. (required)
- modelId: string, Model ID of the model to delete. (required)
+ projectId: string, Required. Project ID of the model to delete. (required)
+ datasetId: string, Required. Dataset ID of the model to delete. (required)
+ modelId: string, Required. Model ID of the model to delete. (required)
</pre>
</div>
@@ -106,60 +106,82 @@
<pre>Gets the specified model resource by model ID.
Args:
- projectId: string, Project ID of the requested model. (required)
- datasetId: string, Dataset ID of the requested model. (required)
- modelId: string, Model ID of the requested model. (required)
+ projectId: string, Required. Project ID of the requested model. (required)
+ datasetId: string, Required. Dataset ID of the requested model. (required)
+ modelId: string, Required. Model ID of the requested model. (required)
Returns:
An object of the form:
{
- "labelColumns": [ # Output only. Label columns that were used to train this model.
- # The output of the model will have a "predicted_" prefix to these columns.
- { # A field or a column.
- "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
- # specified (e.g., CREATE FUNCTION statement can omit the return type;
- # in this case the output parameter does not have this "type" field).
- # Examples:
- # INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
- # {type_kind="STRUCT",
- # struct_type={fields=[
- # {name="x", type={type_kind="STRING"}},
- # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
- # ]}}
- "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
- "fields": [
- # Object with schema name: StandardSqlField
- ],
- },
- "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
- "typeKind": "A String", # Required. The top level type of this field.
- # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
- },
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
- },
- ],
- "description": "A String", # [Optional] A user-friendly description of this model.
- "trainingRuns": [ # Output only. Information for all training runs in increasing order of
- # start_time.
+ "labels": { # The labels associated with this model. You can use these to organize
+ # and group your models. Label keys and values can be no longer
+ # than 63 characters, can only contain lowercase letters, numeric
+ # characters, underscores and dashes. International characters are allowed.
+ # Label values are optional. Label keys must start with a letter and each
+ # label in the list must have a different key.
+ "a_key": "A String",
+ },
+ "description": "A String", # Optional. A user-friendly description of this model.
+ "trainingRuns": [ # Output only. Information for all training runs in increasing order of start_time.
{ # Information about a single training query run for the model.
"evaluationMetrics": { # Evaluation metrics of a model. These are either computed on all training # The evaluation metrics over training/eval data that were computed at the
# end of training.
# data or just the eval data based on whether eval data was used during
# training. These are not present for imported models.
- "clusteringMetrics": { # Evaluation metrics for clustering models. # [Beta] Populated for clustering models.
+ "clusteringMetrics": { # Evaluation metrics for clustering models. # Populated for clustering models.
"meanSquaredDistance": 3.14, # Mean of squared distances between each sample to its cluster centroid.
"daviesBouldinIndex": 3.14, # Davies-Bouldin index.
+ "clusters": [ # [Beta] Information for all clusters.
+ { # Message containing the information about one cluster.
+ "count": "A String", # Count of training data rows that were assigned to this cluster.
+ "featureValues": [ # Values of highly variant features for this cluster.
+ { # Representative value of a single feature within the cluster.
+ "featureColumn": "A String", # The feature column name.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
+ "categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
+ "categoryCounts": [ # Counts of all categories for the categorical feature. If there are
+ # more than ten categories, we return top ten (by count) and return
+ # one more CategoryCount with category "_OTHER_" and count as
+ # aggregate counts of remaining categories.
+ { # Represents the count of a single category within the cluster.
+ "category": "A String", # The name of category.
+ "count": "A String", # The count of training samples matching the category within the
+ # cluster.
+ },
+ ],
+ },
+ },
+ ],
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
- "regressionMetrics": { # Evaluation metrics for regression models. # Populated for regression models.
+ "regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
+ # factorization models.
+ # factorization models.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
"meanSquaredError": 3.14, # Mean squared error.
"medianAbsoluteError": 3.14, # Median absolute error.
"rSquared": 3.14, # R^2 score.
},
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "meanSquaredError": 3.14, # Similar to the mean squared error computed in regression and explicit
+ # recommendation models except instead of computing the rating directly,
+ # the output from evaluate is computed against a preference which is 1 or 0
+ # depending on if the rating exists or not.
+ "meanAveragePrecision": 3.14, # Calculates a precision per user for all the items by ranking them and
+ # then averages all the precisions across all the users.
+ "averageRank": 3.14, # Determines the goodness of a ranking by computing the percentile rank
+ # from the predicted confidence and dividing it by the original rank.
+ "normalizedDiscountedCumulativeGain": 3.14, # A metric to determine the goodness of a ranking calculated from the
+ # predicted confidence by comparing it to an ideal rank measured by the
+ # original ratings.
+ },
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
"negativeLabel": "A String", # Label representing the negative class.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -189,12 +211,16 @@
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
"truePositives": "A String", # Number of true samples predicted as true.
- "recall": 3.14, # Aggregate recall.
- "precision": 3.14, # Aggregate precision.
+ "recall": 3.14, # The fraction of actual positive labels that were given a positive
+ # prediction.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
"falseNegatives": "A String", # Number of false samples predicted as false.
"trueNegatives": "A String", # Number of true samples predicted as false.
"falsePositives": "A String", # Number of false samples predicted as true.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
"positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
},
],
},
@@ -228,29 +254,81 @@
# confusion matrix.
"rows": [ # One row per actual label.
{ # A single row in the confusion matrix.
+ "actualLabel": "A String", # The original label of this row.
"entries": [ # Info describing predicted label distribution.
{ # A single entry in the confusion matrix.
- "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
+ "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
# also add an entry indicating the number of items under the
# confidence threshold.
"itemCount": "A String", # Number of items being predicted as this label.
},
],
- "actualLabel": "A String", # The original label of this row.
},
],
},
],
},
},
- "results": [ # Output of each iteration run, results.size() <= max_iterations.
+ "dataSplitResult": { # Data split result. This contains references to the training and evaluation # Data split result of the training run. Only set when the input data is
+ # actually split.
+ # data tables that were used to train the model.
+ "trainingTable": { # Table reference of the training data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ "evaluationTable": { # Table reference of the evaluation data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ },
+ "results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
+ "arimaResult": { # (Auto-)arima fitting result. Wrap everything in ArimaResult for easier
+ # refactoring if we want to use model-specific iteration results.
+ "arimaModelInfo": [ # This message is repeated because there are multiple arima models
+ # fitted in auto-arima. For non-auto-arima model, its size is one.
+ { # Arima model information.
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
+ # for one time series.
+ "A String",
+ ],
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ },
+ "nonSeasonalOrder": { # Arima order, can be used for both non-seasonal and seasonal parts. # Non-seasonal order.
+ "q": "A String", # Order of the moving-average part.
+ "p": "A String", # Order of the autoregressive part.
+ "d": "A String", # Order of the differencing part.
+ },
+ "arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "variance": 3.14, # Variance.
+ "logLikelihood": 3.14, # Log-likelihood.
+ "aic": 3.14, # AIC.
+ },
+ "timeSeriesId": "A String", # The id to indicate different time series.
+ },
+ ],
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
+ # one time series.
+ "A String",
+ ],
+ },
"index": 42, # Index of the iteration, 0 based.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"durationMs": "A String", # Time taken to run the iteration in milliseconds.
"learnRate": 3.14, # Learn rate used for this iteration.
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
- "clusterInfos": [ # [Beta] Information about top clusters for clustering models.
+ "clusterInfos": [ # Information about top clusters for clustering models.
{ # Information about a single cluster for clustering model.
"centroidId": "A String", # Centroid id.
"clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
@@ -264,9 +342,23 @@
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
"optimizationStrategy": "A String", # Optimization strategy for training linear regression models.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
+ "feedbackType": "A String", # Feedback type that specifies which algorithm to run for matrix
+ # factorization.
+ "numFactors": "A String", # Num factors specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
+ "batchSize": "A String", # Batch size for dnn models.
+ "distanceType": "A String", # Distance type for clustering models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
+ "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
+ # less than 'min_relative_progress'. Used only for iterative training
+ # algorithms.
+ "l1Regularization": 3.14, # L1 regularization coefficient.
"maxIterations": "A String", # The maximum number of iterations in training. Used only for iterative
# training algorithms.
"earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
@@ -284,28 +376,33 @@
# 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
- "numClusters": "A String", # [Beta] Number of clusters for clustering models.
- "l1Regularization": 3.14, # L1 regularization coefficient.
- "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
- "distanceType": "A String", # [Beta] Distance type for clustering models.
+ "numClusters": "A String", # Number of clusters for clustering models.
"warmStart": True or False, # Whether to train a model from the last checkpoint.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "lossType": "A String", # Type of loss function used during training run.
+ "hiddenUnits": [ # Hidden units for dnn models.
+ "A String",
+ ],
+ "maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "userColumn": "A String", # User column specified for matrix factorization models.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
+ "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
"dataSplitEvalFraction": 3.14, # 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.
- "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
- "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
- "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
- # less than 'min_relative_progress'. Used only for iterative training
- # algorithms.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
+ # specified.
+ "minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
+ "lossType": "A String", # Type of loss function used during training run.
},
},
],
@@ -316,8 +413,8 @@
# in this case the output parameter does not have this "type" field).
# Examples:
# INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
# {type_kind="STRUCT",
# struct_type={fields=[
# {name="x", type={type_kind="STRING"}},
@@ -335,35 +432,56 @@
"name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "labels": { # [Optional] The labels associated with this model. You can use these to
- # organize and group your models. Label keys and values can be no longer
- # than 63 characters, can only contain lowercase letters, numeric
- # characters, underscores and dashes. International characters are allowed.
- # Label values are optional. Label keys must start with a letter and each
- # label in the list must have a different key.
- "a_key": "A String",
- },
- "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the
- # epoch.
+ "labelColumns": [ # Output only. Label columns that were used to train this model.
+ # The output of the model will have a "predicted_" prefix to these columns.
+ { # A field or a column.
+ "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
+ # specified (e.g., CREATE FUNCTION statement can omit the return type;
+ # in this case the output parameter does not have this "type" field).
+ # Examples:
+ # INT64: {type_kind="INT64"}
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
+ # {type_kind="STRUCT",
+ # struct_type={fields=[
+ # {name="x", type={type_kind="STRING"}},
+ # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
+ # ]}}
+ "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
+ "fields": [
+ # Object with schema name: StandardSqlField
+ ],
+ },
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
+ "typeKind": "A String", # Required. The top level type of this field.
+ # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
+ },
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
+ },
+ ],
+ "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the epoch.
"modelType": "A String", # Output only. Type of the model resource.
- "modelReference": { # Id path of a model. # Required. Unique identifier for this model.
+ "encryptionConfiguration": { # Custom encryption configuration (e.g., Cloud KMS keys). This shows the
+ # encryption configuration of the model data while stored in BigQuery
+ # storage. This field can be used with PatchModel to update encryption key
+ # for an already encrypted model.
+ "kmsKeyName": "A String", # [Optional] Describes the Cloud KMS encryption key that will be used to protect destination BigQuery table. The BigQuery Service Account associated with your project requires access to this encryption key.
+ },
+ "modelReference": { # Required. Unique identifier for this model.
"projectId": "A String", # [Required] The ID of the project containing this model.
"datasetId": "A String", # [Required] The ID of the dataset containing this model.
- "modelId": "A String", # [Required] The ID of the model. The ID must contain only
- # letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum
- # length is 1,024 characters.
+ "modelId": "A String", # [Required] The ID of the model. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
"etag": "A String", # Output only. A hash of this resource.
"location": "A String", # Output only. The geographic location where the model resides. This value
# is inherited from the dataset.
- "friendlyName": "A String", # [Optional] A descriptive name for this model.
- "expirationTime": "A String", # [Optional] The time when this model expires, in milliseconds since the
- # epoch. If not present, the model will persist indefinitely. Expired models
+ "friendlyName": "A String", # Optional. A descriptive name for this model.
+ "expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
+ # If not present, the model will persist indefinitely. Expired models
# will be deleted and their storage reclaimed. The defaultTableExpirationMs
# property of the encapsulating dataset can be used to set a default
# expirationTime on newly created models.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs
- # since the epoch.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
}</pre>
</div>
@@ -373,66 +491,90 @@
role.
Args:
- projectId: string, Project ID of the models to list. (required)
- datasetId: string, Dataset ID of the models to list. (required)
+ projectId: string, Required. Project ID of the models to list. (required)
+ datasetId: string, Required. Dataset ID of the models to list. (required)
pageToken: string, Page token, returned by a previous call to request the next page of
results
- maxResults: integer, The maximum number of results per page.
+ maxResults: integer, The maximum number of results to return in a single response page.
+Leverage the page tokens to iterate through the entire collection.
Returns:
An object of the form:
{
+ "nextPageToken": "A String", # A token to request the next page of results.
"models": [ # Models in the requested dataset. Only the following fields are populated:
# model_reference, model_type, creation_time, last_modified_time and
# labels.
{
- "labelColumns": [ # Output only. Label columns that were used to train this model.
- # The output of the model will have a "predicted_" prefix to these columns.
- { # A field or a column.
- "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
- # specified (e.g., CREATE FUNCTION statement can omit the return type;
- # in this case the output parameter does not have this "type" field).
- # Examples:
- # INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
- # {type_kind="STRUCT",
- # struct_type={fields=[
- # {name="x", type={type_kind="STRING"}},
- # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
- # ]}}
- "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
- "fields": [
- # Object with schema name: StandardSqlField
- ],
- },
- "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
- "typeKind": "A String", # Required. The top level type of this field.
- # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
- },
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
- },
- ],
- "description": "A String", # [Optional] A user-friendly description of this model.
- "trainingRuns": [ # Output only. Information for all training runs in increasing order of
- # start_time.
+ "labels": { # The labels associated with this model. You can use these to organize
+ # and group your models. Label keys and values can be no longer
+ # than 63 characters, can only contain lowercase letters, numeric
+ # characters, underscores and dashes. International characters are allowed.
+ # Label values are optional. Label keys must start with a letter and each
+ # label in the list must have a different key.
+ "a_key": "A String",
+ },
+ "description": "A String", # Optional. A user-friendly description of this model.
+ "trainingRuns": [ # Output only. Information for all training runs in increasing order of start_time.
{ # Information about a single training query run for the model.
"evaluationMetrics": { # Evaluation metrics of a model. These are either computed on all training # The evaluation metrics over training/eval data that were computed at the
# end of training.
# data or just the eval data based on whether eval data was used during
# training. These are not present for imported models.
- "clusteringMetrics": { # Evaluation metrics for clustering models. # [Beta] Populated for clustering models.
+ "clusteringMetrics": { # Evaluation metrics for clustering models. # Populated for clustering models.
"meanSquaredDistance": 3.14, # Mean of squared distances between each sample to its cluster centroid.
"daviesBouldinIndex": 3.14, # Davies-Bouldin index.
+ "clusters": [ # [Beta] Information for all clusters.
+ { # Message containing the information about one cluster.
+ "count": "A String", # Count of training data rows that were assigned to this cluster.
+ "featureValues": [ # Values of highly variant features for this cluster.
+ { # Representative value of a single feature within the cluster.
+ "featureColumn": "A String", # The feature column name.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
+ "categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
+ "categoryCounts": [ # Counts of all categories for the categorical feature. If there are
+ # more than ten categories, we return top ten (by count) and return
+ # one more CategoryCount with category "_OTHER_" and count as
+ # aggregate counts of remaining categories.
+ { # Represents the count of a single category within the cluster.
+ "category": "A String", # The name of category.
+ "count": "A String", # The count of training samples matching the category within the
+ # cluster.
+ },
+ ],
+ },
+ },
+ ],
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
- "regressionMetrics": { # Evaluation metrics for regression models. # Populated for regression models.
+ "regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
+ # factorization models.
+ # factorization models.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
"meanSquaredError": 3.14, # Mean squared error.
"medianAbsoluteError": 3.14, # Median absolute error.
"rSquared": 3.14, # R^2 score.
},
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "meanSquaredError": 3.14, # Similar to the mean squared error computed in regression and explicit
+ # recommendation models except instead of computing the rating directly,
+ # the output from evaluate is computed against a preference which is 1 or 0
+ # depending on if the rating exists or not.
+ "meanAveragePrecision": 3.14, # Calculates a precision per user for all the items by ranking them and
+ # then averages all the precisions across all the users.
+ "averageRank": 3.14, # Determines the goodness of a ranking by computing the percentile rank
+ # from the predicted confidence and dividing it by the original rank.
+ "normalizedDiscountedCumulativeGain": 3.14, # A metric to determine the goodness of a ranking calculated from the
+ # predicted confidence by comparing it to an ideal rank measured by the
+ # original ratings.
+ },
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
"negativeLabel": "A String", # Label representing the negative class.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -462,12 +604,16 @@
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
"truePositives": "A String", # Number of true samples predicted as true.
- "recall": 3.14, # Aggregate recall.
- "precision": 3.14, # Aggregate precision.
+ "recall": 3.14, # The fraction of actual positive labels that were given a positive
+ # prediction.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
"falseNegatives": "A String", # Number of false samples predicted as false.
"trueNegatives": "A String", # Number of true samples predicted as false.
"falsePositives": "A String", # Number of false samples predicted as true.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
"positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
},
],
},
@@ -501,29 +647,81 @@
# confusion matrix.
"rows": [ # One row per actual label.
{ # A single row in the confusion matrix.
+ "actualLabel": "A String", # The original label of this row.
"entries": [ # Info describing predicted label distribution.
{ # A single entry in the confusion matrix.
- "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
+ "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
# also add an entry indicating the number of items under the
# confidence threshold.
"itemCount": "A String", # Number of items being predicted as this label.
},
],
- "actualLabel": "A String", # The original label of this row.
},
],
},
],
},
},
- "results": [ # Output of each iteration run, results.size() <= max_iterations.
+ "dataSplitResult": { # Data split result. This contains references to the training and evaluation # Data split result of the training run. Only set when the input data is
+ # actually split.
+ # data tables that were used to train the model.
+ "trainingTable": { # Table reference of the training data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ "evaluationTable": { # Table reference of the evaluation data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ },
+ "results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
+ "arimaResult": { # (Auto-)arima fitting result. Wrap everything in ArimaResult for easier
+ # refactoring if we want to use model-specific iteration results.
+ "arimaModelInfo": [ # This message is repeated because there are multiple arima models
+ # fitted in auto-arima. For non-auto-arima model, its size is one.
+ { # Arima model information.
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
+ # for one time series.
+ "A String",
+ ],
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ },
+ "nonSeasonalOrder": { # Arima order, can be used for both non-seasonal and seasonal parts. # Non-seasonal order.
+ "q": "A String", # Order of the moving-average part.
+ "p": "A String", # Order of the autoregressive part.
+ "d": "A String", # Order of the differencing part.
+ },
+ "arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "variance": 3.14, # Variance.
+ "logLikelihood": 3.14, # Log-likelihood.
+ "aic": 3.14, # AIC.
+ },
+ "timeSeriesId": "A String", # The id to indicate different time series.
+ },
+ ],
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
+ # one time series.
+ "A String",
+ ],
+ },
"index": 42, # Index of the iteration, 0 based.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"durationMs": "A String", # Time taken to run the iteration in milliseconds.
"learnRate": 3.14, # Learn rate used for this iteration.
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
- "clusterInfos": [ # [Beta] Information about top clusters for clustering models.
+ "clusterInfos": [ # Information about top clusters for clustering models.
{ # Information about a single cluster for clustering model.
"centroidId": "A String", # Centroid id.
"clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
@@ -537,9 +735,23 @@
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
"optimizationStrategy": "A String", # Optimization strategy for training linear regression models.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
+ "feedbackType": "A String", # Feedback type that specifies which algorithm to run for matrix
+ # factorization.
+ "numFactors": "A String", # Num factors specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
+ "batchSize": "A String", # Batch size for dnn models.
+ "distanceType": "A String", # Distance type for clustering models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
+ "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
+ # less than 'min_relative_progress'. Used only for iterative training
+ # algorithms.
+ "l1Regularization": 3.14, # L1 regularization coefficient.
"maxIterations": "A String", # The maximum number of iterations in training. Used only for iterative
# training algorithms.
"earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
@@ -557,28 +769,33 @@
# 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
- "numClusters": "A String", # [Beta] Number of clusters for clustering models.
- "l1Regularization": 3.14, # L1 regularization coefficient.
- "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
- "distanceType": "A String", # [Beta] Distance type for clustering models.
+ "numClusters": "A String", # Number of clusters for clustering models.
"warmStart": True or False, # Whether to train a model from the last checkpoint.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "lossType": "A String", # Type of loss function used during training run.
+ "hiddenUnits": [ # Hidden units for dnn models.
+ "A String",
+ ],
+ "maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "userColumn": "A String", # User column specified for matrix factorization models.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
+ "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
"dataSplitEvalFraction": 3.14, # 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.
- "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
- "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
- "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
- # less than 'min_relative_progress'. Used only for iterative training
- # algorithms.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
+ # specified.
+ "minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
+ "lossType": "A String", # Type of loss function used during training run.
},
},
],
@@ -589,8 +806,8 @@
# in this case the output parameter does not have this "type" field).
# Examples:
# INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
# {type_kind="STRUCT",
# struct_type={fields=[
# {name="x", type={type_kind="STRING"}},
@@ -608,38 +825,58 @@
"name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "labels": { # [Optional] The labels associated with this model. You can use these to
- # organize and group your models. Label keys and values can be no longer
- # than 63 characters, can only contain lowercase letters, numeric
- # characters, underscores and dashes. International characters are allowed.
- # Label values are optional. Label keys must start with a letter and each
- # label in the list must have a different key.
- "a_key": "A String",
- },
- "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the
- # epoch.
+ "labelColumns": [ # Output only. Label columns that were used to train this model.
+ # The output of the model will have a "predicted_" prefix to these columns.
+ { # A field or a column.
+ "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
+ # specified (e.g., CREATE FUNCTION statement can omit the return type;
+ # in this case the output parameter does not have this "type" field).
+ # Examples:
+ # INT64: {type_kind="INT64"}
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
+ # {type_kind="STRUCT",
+ # struct_type={fields=[
+ # {name="x", type={type_kind="STRING"}},
+ # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
+ # ]}}
+ "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
+ "fields": [
+ # Object with schema name: StandardSqlField
+ ],
+ },
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
+ "typeKind": "A String", # Required. The top level type of this field.
+ # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
+ },
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
+ },
+ ],
+ "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the epoch.
"modelType": "A String", # Output only. Type of the model resource.
- "modelReference": { # Id path of a model. # Required. Unique identifier for this model.
+ "encryptionConfiguration": { # Custom encryption configuration (e.g., Cloud KMS keys). This shows the
+ # encryption configuration of the model data while stored in BigQuery
+ # storage. This field can be used with PatchModel to update encryption key
+ # for an already encrypted model.
+ "kmsKeyName": "A String", # [Optional] Describes the Cloud KMS encryption key that will be used to protect destination BigQuery table. The BigQuery Service Account associated with your project requires access to this encryption key.
+ },
+ "modelReference": { # Required. Unique identifier for this model.
"projectId": "A String", # [Required] The ID of the project containing this model.
"datasetId": "A String", # [Required] The ID of the dataset containing this model.
- "modelId": "A String", # [Required] The ID of the model. The ID must contain only
- # letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum
- # length is 1,024 characters.
+ "modelId": "A String", # [Required] The ID of the model. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
"etag": "A String", # Output only. A hash of this resource.
"location": "A String", # Output only. The geographic location where the model resides. This value
# is inherited from the dataset.
- "friendlyName": "A String", # [Optional] A descriptive name for this model.
- "expirationTime": "A String", # [Optional] The time when this model expires, in milliseconds since the
- # epoch. If not present, the model will persist indefinitely. Expired models
+ "friendlyName": "A String", # Optional. A descriptive name for this model.
+ "expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
+ # If not present, the model will persist indefinitely. Expired models
# will be deleted and their storage reclaimed. The defaultTableExpirationMs
# property of the encapsulating dataset can be used to set a default
# expirationTime on newly created models.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs
- # since the epoch.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
},
],
- "nextPageToken": "A String", # A token to request the next page of results.
}</pre>
</div>
@@ -658,63 +895,85 @@
</div>
<div class="method">
- <code class="details" id="patch">patch(projectId, datasetId, modelId, body)</code>
+ <code class="details" id="patch">patch(projectId, datasetId, modelId, body=None)</code>
<pre>Patch specific fields in the specified model.
Args:
- projectId: string, Project ID of the model to patch. (required)
- datasetId: string, Dataset ID of the model to patch. (required)
- modelId: string, Model ID of the model to patch. (required)
- body: object, The request body. (required)
+ projectId: string, Required. Project ID of the model to patch. (required)
+ datasetId: string, Required. Dataset ID of the model to patch. (required)
+ modelId: string, Required. Model ID of the model to patch. (required)
+ body: object, The request body.
The object takes the form of:
{
- "labelColumns": [ # Output only. Label columns that were used to train this model.
- # The output of the model will have a "predicted_" prefix to these columns.
- { # A field or a column.
- "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
- # specified (e.g., CREATE FUNCTION statement can omit the return type;
- # in this case the output parameter does not have this "type" field).
- # Examples:
- # INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
- # {type_kind="STRUCT",
- # struct_type={fields=[
- # {name="x", type={type_kind="STRING"}},
- # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
- # ]}}
- "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
- "fields": [
- # Object with schema name: StandardSqlField
- ],
- },
- "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
- "typeKind": "A String", # Required. The top level type of this field.
- # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
- },
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
- },
- ],
- "description": "A String", # [Optional] A user-friendly description of this model.
- "trainingRuns": [ # Output only. Information for all training runs in increasing order of
- # start_time.
+ "labels": { # The labels associated with this model. You can use these to organize
+ # and group your models. Label keys and values can be no longer
+ # than 63 characters, can only contain lowercase letters, numeric
+ # characters, underscores and dashes. International characters are allowed.
+ # Label values are optional. Label keys must start with a letter and each
+ # label in the list must have a different key.
+ "a_key": "A String",
+ },
+ "description": "A String", # Optional. A user-friendly description of this model.
+ "trainingRuns": [ # Output only. Information for all training runs in increasing order of start_time.
{ # Information about a single training query run for the model.
"evaluationMetrics": { # Evaluation metrics of a model. These are either computed on all training # The evaluation metrics over training/eval data that were computed at the
# end of training.
# data or just the eval data based on whether eval data was used during
# training. These are not present for imported models.
- "clusteringMetrics": { # Evaluation metrics for clustering models. # [Beta] Populated for clustering models.
+ "clusteringMetrics": { # Evaluation metrics for clustering models. # Populated for clustering models.
"meanSquaredDistance": 3.14, # Mean of squared distances between each sample to its cluster centroid.
"daviesBouldinIndex": 3.14, # Davies-Bouldin index.
+ "clusters": [ # [Beta] Information for all clusters.
+ { # Message containing the information about one cluster.
+ "count": "A String", # Count of training data rows that were assigned to this cluster.
+ "featureValues": [ # Values of highly variant features for this cluster.
+ { # Representative value of a single feature within the cluster.
+ "featureColumn": "A String", # The feature column name.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
+ "categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
+ "categoryCounts": [ # Counts of all categories for the categorical feature. If there are
+ # more than ten categories, we return top ten (by count) and return
+ # one more CategoryCount with category "_OTHER_" and count as
+ # aggregate counts of remaining categories.
+ { # Represents the count of a single category within the cluster.
+ "category": "A String", # The name of category.
+ "count": "A String", # The count of training samples matching the category within the
+ # cluster.
+ },
+ ],
+ },
+ },
+ ],
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
- "regressionMetrics": { # Evaluation metrics for regression models. # Populated for regression models.
+ "regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
+ # factorization models.
+ # factorization models.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
"meanSquaredError": 3.14, # Mean squared error.
"medianAbsoluteError": 3.14, # Median absolute error.
"rSquared": 3.14, # R^2 score.
},
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "meanSquaredError": 3.14, # Similar to the mean squared error computed in regression and explicit
+ # recommendation models except instead of computing the rating directly,
+ # the output from evaluate is computed against a preference which is 1 or 0
+ # depending on if the rating exists or not.
+ "meanAveragePrecision": 3.14, # Calculates a precision per user for all the items by ranking them and
+ # then averages all the precisions across all the users.
+ "averageRank": 3.14, # Determines the goodness of a ranking by computing the percentile rank
+ # from the predicted confidence and dividing it by the original rank.
+ "normalizedDiscountedCumulativeGain": 3.14, # A metric to determine the goodness of a ranking calculated from the
+ # predicted confidence by comparing it to an ideal rank measured by the
+ # original ratings.
+ },
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
"negativeLabel": "A String", # Label representing the negative class.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -744,12 +1003,16 @@
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
"truePositives": "A String", # Number of true samples predicted as true.
- "recall": 3.14, # Aggregate recall.
- "precision": 3.14, # Aggregate precision.
+ "recall": 3.14, # The fraction of actual positive labels that were given a positive
+ # prediction.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
"falseNegatives": "A String", # Number of false samples predicted as false.
"trueNegatives": "A String", # Number of true samples predicted as false.
"falsePositives": "A String", # Number of false samples predicted as true.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
"positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
},
],
},
@@ -783,29 +1046,81 @@
# confusion matrix.
"rows": [ # One row per actual label.
{ # A single row in the confusion matrix.
+ "actualLabel": "A String", # The original label of this row.
"entries": [ # Info describing predicted label distribution.
{ # A single entry in the confusion matrix.
- "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
+ "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
# also add an entry indicating the number of items under the
# confidence threshold.
"itemCount": "A String", # Number of items being predicted as this label.
},
],
- "actualLabel": "A String", # The original label of this row.
},
],
},
],
},
},
- "results": [ # Output of each iteration run, results.size() <= max_iterations.
+ "dataSplitResult": { # Data split result. This contains references to the training and evaluation # Data split result of the training run. Only set when the input data is
+ # actually split.
+ # data tables that were used to train the model.
+ "trainingTable": { # Table reference of the training data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ "evaluationTable": { # Table reference of the evaluation data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ },
+ "results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
+ "arimaResult": { # (Auto-)arima fitting result. Wrap everything in ArimaResult for easier
+ # refactoring if we want to use model-specific iteration results.
+ "arimaModelInfo": [ # This message is repeated because there are multiple arima models
+ # fitted in auto-arima. For non-auto-arima model, its size is one.
+ { # Arima model information.
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
+ # for one time series.
+ "A String",
+ ],
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ },
+ "nonSeasonalOrder": { # Arima order, can be used for both non-seasonal and seasonal parts. # Non-seasonal order.
+ "q": "A String", # Order of the moving-average part.
+ "p": "A String", # Order of the autoregressive part.
+ "d": "A String", # Order of the differencing part.
+ },
+ "arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "variance": 3.14, # Variance.
+ "logLikelihood": 3.14, # Log-likelihood.
+ "aic": 3.14, # AIC.
+ },
+ "timeSeriesId": "A String", # The id to indicate different time series.
+ },
+ ],
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
+ # one time series.
+ "A String",
+ ],
+ },
"index": 42, # Index of the iteration, 0 based.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"durationMs": "A String", # Time taken to run the iteration in milliseconds.
"learnRate": 3.14, # Learn rate used for this iteration.
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
- "clusterInfos": [ # [Beta] Information about top clusters for clustering models.
+ "clusterInfos": [ # Information about top clusters for clustering models.
{ # Information about a single cluster for clustering model.
"centroidId": "A String", # Centroid id.
"clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
@@ -819,9 +1134,23 @@
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
"optimizationStrategy": "A String", # Optimization strategy for training linear regression models.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
+ "feedbackType": "A String", # Feedback type that specifies which algorithm to run for matrix
+ # factorization.
+ "numFactors": "A String", # Num factors specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
+ "batchSize": "A String", # Batch size for dnn models.
+ "distanceType": "A String", # Distance type for clustering models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
+ "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
+ # less than 'min_relative_progress'. Used only for iterative training
+ # algorithms.
+ "l1Regularization": 3.14, # L1 regularization coefficient.
"maxIterations": "A String", # The maximum number of iterations in training. Used only for iterative
# training algorithms.
"earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
@@ -839,28 +1168,33 @@
# 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
- "numClusters": "A String", # [Beta] Number of clusters for clustering models.
- "l1Regularization": 3.14, # L1 regularization coefficient.
- "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
- "distanceType": "A String", # [Beta] Distance type for clustering models.
+ "numClusters": "A String", # Number of clusters for clustering models.
"warmStart": True or False, # Whether to train a model from the last checkpoint.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "lossType": "A String", # Type of loss function used during training run.
+ "hiddenUnits": [ # Hidden units for dnn models.
+ "A String",
+ ],
+ "maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "userColumn": "A String", # User column specified for matrix factorization models.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
+ "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
"dataSplitEvalFraction": 3.14, # 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.
- "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
- "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
- "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
- # less than 'min_relative_progress'. Used only for iterative training
- # algorithms.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
+ # specified.
+ "minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
+ "lossType": "A String", # Type of loss function used during training run.
},
},
],
@@ -871,8 +1205,8 @@
# in this case the output parameter does not have this "type" field).
# Examples:
# INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
# {type_kind="STRUCT",
# struct_type={fields=[
# {name="x", type={type_kind="STRING"}},
@@ -890,35 +1224,56 @@
"name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "labels": { # [Optional] The labels associated with this model. You can use these to
- # organize and group your models. Label keys and values can be no longer
- # than 63 characters, can only contain lowercase letters, numeric
- # characters, underscores and dashes. International characters are allowed.
- # Label values are optional. Label keys must start with a letter and each
- # label in the list must have a different key.
- "a_key": "A String",
- },
- "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the
- # epoch.
+ "labelColumns": [ # Output only. Label columns that were used to train this model.
+ # The output of the model will have a "predicted_" prefix to these columns.
+ { # A field or a column.
+ "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
+ # specified (e.g., CREATE FUNCTION statement can omit the return type;
+ # in this case the output parameter does not have this "type" field).
+ # Examples:
+ # INT64: {type_kind="INT64"}
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
+ # {type_kind="STRUCT",
+ # struct_type={fields=[
+ # {name="x", type={type_kind="STRING"}},
+ # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
+ # ]}}
+ "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
+ "fields": [
+ # Object with schema name: StandardSqlField
+ ],
+ },
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
+ "typeKind": "A String", # Required. The top level type of this field.
+ # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
+ },
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
+ },
+ ],
+ "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the epoch.
"modelType": "A String", # Output only. Type of the model resource.
- "modelReference": { # Id path of a model. # Required. Unique identifier for this model.
+ "encryptionConfiguration": { # Custom encryption configuration (e.g., Cloud KMS keys). This shows the
+ # encryption configuration of the model data while stored in BigQuery
+ # storage. This field can be used with PatchModel to update encryption key
+ # for an already encrypted model.
+ "kmsKeyName": "A String", # [Optional] Describes the Cloud KMS encryption key that will be used to protect destination BigQuery table. The BigQuery Service Account associated with your project requires access to this encryption key.
+ },
+ "modelReference": { # Required. Unique identifier for this model.
"projectId": "A String", # [Required] The ID of the project containing this model.
"datasetId": "A String", # [Required] The ID of the dataset containing this model.
- "modelId": "A String", # [Required] The ID of the model. The ID must contain only
- # letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum
- # length is 1,024 characters.
+ "modelId": "A String", # [Required] The ID of the model. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
"etag": "A String", # Output only. A hash of this resource.
"location": "A String", # Output only. The geographic location where the model resides. This value
# is inherited from the dataset.
- "friendlyName": "A String", # [Optional] A descriptive name for this model.
- "expirationTime": "A String", # [Optional] The time when this model expires, in milliseconds since the
- # epoch. If not present, the model will persist indefinitely. Expired models
+ "friendlyName": "A String", # Optional. A descriptive name for this model.
+ "expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
+ # If not present, the model will persist indefinitely. Expired models
# will be deleted and their storage reclaimed. The defaultTableExpirationMs
# property of the encapsulating dataset can be used to set a default
# expirationTime on newly created models.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs
- # since the epoch.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
}
@@ -926,52 +1281,74 @@
An object of the form:
{
- "labelColumns": [ # Output only. Label columns that were used to train this model.
- # The output of the model will have a "predicted_" prefix to these columns.
- { # A field or a column.
- "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
- # specified (e.g., CREATE FUNCTION statement can omit the return type;
- # in this case the output parameter does not have this "type" field).
- # Examples:
- # INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
- # {type_kind="STRUCT",
- # struct_type={fields=[
- # {name="x", type={type_kind="STRING"}},
- # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
- # ]}}
- "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
- "fields": [
- # Object with schema name: StandardSqlField
- ],
- },
- "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
- "typeKind": "A String", # Required. The top level type of this field.
- # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
- },
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
- },
- ],
- "description": "A String", # [Optional] A user-friendly description of this model.
- "trainingRuns": [ # Output only. Information for all training runs in increasing order of
- # start_time.
+ "labels": { # The labels associated with this model. You can use these to organize
+ # and group your models. Label keys and values can be no longer
+ # than 63 characters, can only contain lowercase letters, numeric
+ # characters, underscores and dashes. International characters are allowed.
+ # Label values are optional. Label keys must start with a letter and each
+ # label in the list must have a different key.
+ "a_key": "A String",
+ },
+ "description": "A String", # Optional. A user-friendly description of this model.
+ "trainingRuns": [ # Output only. Information for all training runs in increasing order of start_time.
{ # Information about a single training query run for the model.
"evaluationMetrics": { # Evaluation metrics of a model. These are either computed on all training # The evaluation metrics over training/eval data that were computed at the
# end of training.
# data or just the eval data based on whether eval data was used during
# training. These are not present for imported models.
- "clusteringMetrics": { # Evaluation metrics for clustering models. # [Beta] Populated for clustering models.
+ "clusteringMetrics": { # Evaluation metrics for clustering models. # Populated for clustering models.
"meanSquaredDistance": 3.14, # Mean of squared distances between each sample to its cluster centroid.
"daviesBouldinIndex": 3.14, # Davies-Bouldin index.
+ "clusters": [ # [Beta] Information for all clusters.
+ { # Message containing the information about one cluster.
+ "count": "A String", # Count of training data rows that were assigned to this cluster.
+ "featureValues": [ # Values of highly variant features for this cluster.
+ { # Representative value of a single feature within the cluster.
+ "featureColumn": "A String", # The feature column name.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
+ "categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
+ "categoryCounts": [ # Counts of all categories for the categorical feature. If there are
+ # more than ten categories, we return top ten (by count) and return
+ # one more CategoryCount with category "_OTHER_" and count as
+ # aggregate counts of remaining categories.
+ { # Represents the count of a single category within the cluster.
+ "category": "A String", # The name of category.
+ "count": "A String", # The count of training samples matching the category within the
+ # cluster.
+ },
+ ],
+ },
+ },
+ ],
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
- "regressionMetrics": { # Evaluation metrics for regression models. # Populated for regression models.
+ "regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
+ # factorization models.
+ # factorization models.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
"meanSquaredError": 3.14, # Mean squared error.
"medianAbsoluteError": 3.14, # Median absolute error.
"rSquared": 3.14, # R^2 score.
},
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "meanSquaredError": 3.14, # Similar to the mean squared error computed in regression and explicit
+ # recommendation models except instead of computing the rating directly,
+ # the output from evaluate is computed against a preference which is 1 or 0
+ # depending on if the rating exists or not.
+ "meanAveragePrecision": 3.14, # Calculates a precision per user for all the items by ranking them and
+ # then averages all the precisions across all the users.
+ "averageRank": 3.14, # Determines the goodness of a ranking by computing the percentile rank
+ # from the predicted confidence and dividing it by the original rank.
+ "normalizedDiscountedCumulativeGain": 3.14, # A metric to determine the goodness of a ranking calculated from the
+ # predicted confidence by comparing it to an ideal rank measured by the
+ # original ratings.
+ },
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
"negativeLabel": "A String", # Label representing the negative class.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -1001,12 +1378,16 @@
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
"truePositives": "A String", # Number of true samples predicted as true.
- "recall": 3.14, # Aggregate recall.
- "precision": 3.14, # Aggregate precision.
+ "recall": 3.14, # The fraction of actual positive labels that were given a positive
+ # prediction.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
"falseNegatives": "A String", # Number of false samples predicted as false.
"trueNegatives": "A String", # Number of true samples predicted as false.
"falsePositives": "A String", # Number of false samples predicted as true.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
"positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
},
],
},
@@ -1040,29 +1421,81 @@
# confusion matrix.
"rows": [ # One row per actual label.
{ # A single row in the confusion matrix.
+ "actualLabel": "A String", # The original label of this row.
"entries": [ # Info describing predicted label distribution.
{ # A single entry in the confusion matrix.
- "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
+ "predictedLabel": "A String", # The predicted label. For confidence_threshold > 0, we will
# also add an entry indicating the number of items under the
# confidence threshold.
"itemCount": "A String", # Number of items being predicted as this label.
},
],
- "actualLabel": "A String", # The original label of this row.
},
],
},
],
},
},
- "results": [ # Output of each iteration run, results.size() <= max_iterations.
+ "dataSplitResult": { # Data split result. This contains references to the training and evaluation # Data split result of the training run. Only set when the input data is
+ # actually split.
+ # data tables that were used to train the model.
+ "trainingTable": { # Table reference of the training data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ "evaluationTable": { # Table reference of the evaluation data after split.
+ "projectId": "A String", # [Required] The ID of the project containing this table.
+ "tableId": "A String", # [Required] The ID of the table. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
+ "datasetId": "A String", # [Required] The ID of the dataset containing this table.
+ },
+ },
+ "results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
+ "arimaResult": { # (Auto-)arima fitting result. Wrap everything in ArimaResult for easier
+ # refactoring if we want to use model-specific iteration results.
+ "arimaModelInfo": [ # This message is repeated because there are multiple arima models
+ # fitted in auto-arima. For non-auto-arima model, its size is one.
+ { # Arima model information.
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
+ # for one time series.
+ "A String",
+ ],
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ },
+ "nonSeasonalOrder": { # Arima order, can be used for both non-seasonal and seasonal parts. # Non-seasonal order.
+ "q": "A String", # Order of the moving-average part.
+ "p": "A String", # Order of the autoregressive part.
+ "d": "A String", # Order of the differencing part.
+ },
+ "arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "variance": 3.14, # Variance.
+ "logLikelihood": 3.14, # Log-likelihood.
+ "aic": 3.14, # AIC.
+ },
+ "timeSeriesId": "A String", # The id to indicate different time series.
+ },
+ ],
+ "seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
+ # one time series.
+ "A String",
+ ],
+ },
"index": 42, # Index of the iteration, 0 based.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"durationMs": "A String", # Time taken to run the iteration in milliseconds.
"learnRate": 3.14, # Learn rate used for this iteration.
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
- "clusterInfos": [ # [Beta] Information about top clusters for clustering models.
+ "clusterInfos": [ # Information about top clusters for clustering models.
{ # Information about a single cluster for clustering model.
"centroidId": "A String", # Centroid id.
"clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
@@ -1076,9 +1509,23 @@
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
"optimizationStrategy": "A String", # Optimization strategy for training linear regression models.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
+ "feedbackType": "A String", # Feedback type that specifies which algorithm to run for matrix
+ # factorization.
+ "numFactors": "A String", # Num factors specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
+ "batchSize": "A String", # Batch size for dnn models.
+ "distanceType": "A String", # Distance type for clustering models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
+ "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
+ # less than 'min_relative_progress'. Used only for iterative training
+ # algorithms.
+ "l1Regularization": 3.14, # L1 regularization coefficient.
"maxIterations": "A String", # The maximum number of iterations in training. Used only for iterative
# training algorithms.
"earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
@@ -1096,28 +1543,33 @@
# 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
- "numClusters": "A String", # [Beta] Number of clusters for clustering models.
- "l1Regularization": 3.14, # L1 regularization coefficient.
- "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
- "distanceType": "A String", # [Beta] Distance type for clustering models.
+ "numClusters": "A String", # Number of clusters for clustering models.
"warmStart": True or False, # Whether to train a model from the last checkpoint.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "lossType": "A String", # Type of loss function used during training run.
+ "hiddenUnits": [ # Hidden units for dnn models.
+ "A String",
+ ],
+ "maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "userColumn": "A String", # User column specified for matrix factorization models.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
+ "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
"dataSplitEvalFraction": 3.14, # 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.
- "l2Regularization": 3.14, # L2 regularization coefficient.
+ "dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
- "learnRateStrategy": "A String", # The strategy to determine learn rate for the current iteration.
- "minRelativeProgress": 3.14, # When early_stop is true, stops training when accuracy improvement is
- # less than 'min_relative_progress'. Used only for iterative training
- # algorithms.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
+ # specified.
+ "minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
+ "lossType": "A String", # Type of loss function used during training run.
},
},
],
@@ -1128,8 +1580,8 @@
# in this case the output parameter does not have this "type" field).
# Examples:
# INT64: {type_kind="INT64"}
- # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
- # STRUCT<x STRING, y ARRAY<DATE>>:
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
# {type_kind="STRUCT",
# struct_type={fields=[
# {name="x", type={type_kind="STRING"}},
@@ -1147,35 +1599,56 @@
"name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "labels": { # [Optional] The labels associated with this model. You can use these to
- # organize and group your models. Label keys and values can be no longer
- # than 63 characters, can only contain lowercase letters, numeric
- # characters, underscores and dashes. International characters are allowed.
- # Label values are optional. Label keys must start with a letter and each
- # label in the list must have a different key.
- "a_key": "A String",
- },
- "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the
- # epoch.
+ "labelColumns": [ # Output only. Label columns that were used to train this model.
+ # The output of the model will have a "predicted_" prefix to these columns.
+ { # A field or a column.
+ "type": { # The type of a variable, e.g., a function argument. # Optional. The type of this parameter. Absent if not explicitly
+ # specified (e.g., CREATE FUNCTION statement can omit the return type;
+ # in this case the output parameter does not have this "type" field).
+ # Examples:
+ # INT64: {type_kind="INT64"}
+ # ARRAY<STRING>: {type_kind="ARRAY", array_element_type="STRING"}
+ # STRUCT<x STRING, y ARRAY<DATE>>:
+ # {type_kind="STRUCT",
+ # struct_type={fields=[
+ # {name="x", type={type_kind="STRING"}},
+ # {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
+ # ]}}
+ "structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
+ "fields": [
+ # Object with schema name: StandardSqlField
+ ],
+ },
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
+ "typeKind": "A String", # Required. The top level type of this field.
+ # Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY").
+ },
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
+ },
+ ],
+ "creationTime": "A String", # Output only. The time when this model was created, in millisecs since the epoch.
"modelType": "A String", # Output only. Type of the model resource.
- "modelReference": { # Id path of a model. # Required. Unique identifier for this model.
+ "encryptionConfiguration": { # Custom encryption configuration (e.g., Cloud KMS keys). This shows the
+ # encryption configuration of the model data while stored in BigQuery
+ # storage. This field can be used with PatchModel to update encryption key
+ # for an already encrypted model.
+ "kmsKeyName": "A String", # [Optional] Describes the Cloud KMS encryption key that will be used to protect destination BigQuery table. The BigQuery Service Account associated with your project requires access to this encryption key.
+ },
+ "modelReference": { # Required. Unique identifier for this model.
"projectId": "A String", # [Required] The ID of the project containing this model.
"datasetId": "A String", # [Required] The ID of the dataset containing this model.
- "modelId": "A String", # [Required] The ID of the model. The ID must contain only
- # letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum
- # length is 1,024 characters.
+ "modelId": "A String", # [Required] The ID of the model. The ID must contain only letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum length is 1,024 characters.
},
"etag": "A String", # Output only. A hash of this resource.
"location": "A String", # Output only. The geographic location where the model resides. This value
# is inherited from the dataset.
- "friendlyName": "A String", # [Optional] A descriptive name for this model.
- "expirationTime": "A String", # [Optional] The time when this model expires, in milliseconds since the
- # epoch. If not present, the model will persist indefinitely. Expired models
+ "friendlyName": "A String", # Optional. A descriptive name for this model.
+ "expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
+ # If not present, the model will persist indefinitely. Expired models
# will be deleted and their storage reclaimed. The defaultTableExpirationMs
# property of the encapsulating dataset can be used to set a default
# expirationTime on newly created models.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs
- # since the epoch.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
}</pre>
</div>