docs: update generated docs (#981)
diff --git a/docs/dyn/bigquery_v2.models.html b/docs/dyn/bigquery_v2.models.html
index 6d1b63c..ff2df87 100644
--- a/docs/dyn/bigquery_v2.models.html
+++ b/docs/dyn/bigquery_v2.models.html
@@ -81,7 +81,7 @@
<code><a href="#get">get(projectId, datasetId, modelId)</a></code></p>
<p class="firstline">Gets the specified model resource by model ID.</p>
<p class="toc_element">
- <code><a href="#list">list(projectId, datasetId, maxResults=None, pageToken=None)</a></code></p>
+ <code><a href="#list">list(projectId, datasetId, pageToken=None, maxResults=None)</a></code></p>
<p class="firstline">Lists all models in the specified dataset. Requires the READER dataset</p>
<p class="toc_element">
<code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>
@@ -114,22 +114,10 @@
An object of the form:
{
- "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.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
- "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",
- },
+ "modelType": "A String", # Output only. Type of the model resource.
"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.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -142,7 +130,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -150,13 +137,13 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "modelType": "A String", # Output only. Type of the model resource.
"featureColumns": [ # Output only. Input feature columns that were used to train this model.
{ # A field or a column.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -169,7 +156,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -177,7 +163,9 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
"expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
@@ -190,14 +178,6 @@
"startTime": "A String", # The start time of this training run.
"results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
- "clusterInfos": [ # Information about top clusters for clustering models.
- { # Information about a single cluster for clustering model.
- "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
- # to each point assigned to the cluster.
- "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
- "centroidId": "A String", # Centroid id.
- },
- ],
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"index": 42, # Index of the iteration, 0 based.
@@ -208,6 +188,17 @@
"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.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ },
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
# for one time series.
"A String",
@@ -218,22 +209,11 @@
"q": "A String", # Order of the moving-average part.
},
"arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "aic": 3.14, # AIC.
"logLikelihood": 3.14, # Log-likelihood.
"variance": 3.14, # Variance.
- "aic": 3.14, # AIC.
},
"timeSeriesId": "A String", # The id to indicate different time series.
- "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.
- "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
- 3.14,
- ],
- "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
- "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
- 3.14,
- ],
- },
},
],
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
@@ -241,12 +221,35 @@
"A String",
],
},
+ "clusterInfos": [ # Information about top clusters for clustering models.
+ { # Information about a single cluster for clustering model.
+ "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
+ # to each point assigned to the cluster.
+ "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
],
"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.
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "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.
+ "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.
+ "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.
+ },
"multiClassClassificationMetrics": { # Evaluation metrics for multi-class classification/classifier models. # Populated for multi-class classification/classifier models.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
# models, the metrics are either macro-averaged or micro-averaged. When
@@ -254,8 +257,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -270,6 +271,8 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"confusionMatrixList": [ # Confusion matrix at different thresholds.
{ # Confusion matrix for multi-class classification models.
@@ -277,7 +280,6 @@
# 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.
"itemCount": "A String", # Number of items being predicted as this label.
@@ -286,6 +288,7 @@
# confidence threshold.
},
],
+ "actualLabel": "A String", # The original label of this row.
},
],
},
@@ -300,6 +303,8 @@
"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.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
"featureColumn": "A String", # The feature column name.
"categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
"categoryCounts": [ # Counts of all categories for the categorical feature. If there are
@@ -313,28 +318,25 @@
},
],
},
- "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
- # feature.
},
],
},
],
},
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
- "positiveLabel": "A String", # Label representing the positive class.
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
- "f1Score": 3.14, # The equally weighted average of recall and precision.
- "precision": 3.14, # The fraction of actual positive predictions that had positive actual
- # labels.
- "accuracy": 3.14, # The fraction of predictions given the correct label.
- "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
- "truePositives": "A String", # Number of true samples predicted as true.
"recall": 3.14, # The fraction of actual positive labels that were given a positive
# prediction.
"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.
+ "trueNegatives": "A String", # Number of true samples predicted as false.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
+ "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
+ "truePositives": "A String", # Number of true samples predicted as true.
},
],
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -343,8 +345,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -359,36 +359,42 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"negativeLabel": "A String", # Label representing the negative class.
+ "positiveLabel": "A String", # Label representing the positive class.
},
"regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
# factorization models.
# factorization models.
+ "meanSquaredError": 3.14, # Mean squared error.
+ "rSquared": 3.14, # R^2 score.
"medianAbsoluteError": 3.14, # Median absolute error.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
- "meanSquaredError": 3.14, # Mean squared 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.
- "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.
- "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.
- "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.
- "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.
},
},
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
+ # any more (compared to min_relative_progress). Used only for iterative
+ # training algorithms.
+ "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.
+ "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
+ # strategy.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
@@ -399,8 +405,8 @@
"hiddenUnits": [ # Hidden units for dnn models.
"A String",
],
- "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"l1Regularization": 3.14, # L1 regularization coefficient.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"distanceType": "A String", # Distance type for clustering models.
"walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
# specified.
@@ -421,49 +427,35 @@
# training algorithms.
"userColumn": "A String", # User column specified for matrix factorization models.
"maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "preserveInputStructs": True or False, # Whether to preserve the input structs in output feature names.
+ # Suppose there is a struct A with field b.
+ # When false (default), the output feature name is A_b.
+ # When true, the output feature name is A.b.
"l2Regularization": 3.14, # L2 regularization coefficient.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
"batchSize": "A String", # Batch size for dnn models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
"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.
- "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
- # when kmeans_initialization_method is CUSTOM.
"numClusters": "A String", # Number of clusters for clustering models.
"dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
"minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
- "dropout": 3.14, # Dropout probability for dnn models.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
- # overfitting for boosted tree models.
- "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
- # any more (compared to min_relative_progress). Used only for iterative
- # training algorithms.
- "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.
- "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
- # strategy.
- "itemColumn": "A String", # Item column specified for matrix factorization models.
},
"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.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
"evaluationTable": { # Table reference of the evaluation data after split.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
},
},
@@ -482,47 +474,46 @@
# 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.
},
+ "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.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
+ "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",
+ },
}</pre>
</div>
<div class="method">
- <code class="details" id="list">list(projectId, datasetId, maxResults=None, pageToken=None)</code>
+ <code class="details" id="list">list(projectId, datasetId, pageToken=None, maxResults=None)</code>
<pre>Lists all models in the specified dataset. Requires the READER dataset
role.
Args:
projectId: string, Required. Project ID of the models to list. (required)
datasetId: string, Required. Dataset ID of the models to list. (required)
- maxResults: integer, The maximum number of results to return in a single response page.
-Leverage the page tokens to iterate through the entire collection.
pageToken: string, Page token, returned by a previous call to request the next page of
results
+ 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.
{
- "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.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
- "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",
- },
+ "modelType": "A String", # Output only. Type of the model resource.
"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.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -535,7 +526,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -543,13 +533,13 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "modelType": "A String", # Output only. Type of the model resource.
"featureColumns": [ # Output only. Input feature columns that were used to train this model.
{ # A field or a column.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -562,7 +552,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -570,7 +559,9 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
"expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
@@ -583,14 +574,6 @@
"startTime": "A String", # The start time of this training run.
"results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
- "clusterInfos": [ # Information about top clusters for clustering models.
- { # Information about a single cluster for clustering model.
- "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
- # to each point assigned to the cluster.
- "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
- "centroidId": "A String", # Centroid id.
- },
- ],
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"index": 42, # Index of the iteration, 0 based.
@@ -601,6 +584,17 @@
"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.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ },
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
# for one time series.
"A String",
@@ -611,22 +605,11 @@
"q": "A String", # Order of the moving-average part.
},
"arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "aic": 3.14, # AIC.
"logLikelihood": 3.14, # Log-likelihood.
"variance": 3.14, # Variance.
- "aic": 3.14, # AIC.
},
"timeSeriesId": "A String", # The id to indicate different time series.
- "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.
- "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
- 3.14,
- ],
- "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
- "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
- 3.14,
- ],
- },
},
],
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
@@ -634,12 +617,35 @@
"A String",
],
},
+ "clusterInfos": [ # Information about top clusters for clustering models.
+ { # Information about a single cluster for clustering model.
+ "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
+ # to each point assigned to the cluster.
+ "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
],
"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.
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "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.
+ "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.
+ "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.
+ },
"multiClassClassificationMetrics": { # Evaluation metrics for multi-class classification/classifier models. # Populated for multi-class classification/classifier models.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
# models, the metrics are either macro-averaged or micro-averaged. When
@@ -647,8 +653,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -663,6 +667,8 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"confusionMatrixList": [ # Confusion matrix at different thresholds.
{ # Confusion matrix for multi-class classification models.
@@ -670,7 +676,6 @@
# 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.
"itemCount": "A String", # Number of items being predicted as this label.
@@ -679,6 +684,7 @@
# confidence threshold.
},
],
+ "actualLabel": "A String", # The original label of this row.
},
],
},
@@ -693,6 +699,8 @@
"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.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
"featureColumn": "A String", # The feature column name.
"categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
"categoryCounts": [ # Counts of all categories for the categorical feature. If there are
@@ -706,28 +714,25 @@
},
],
},
- "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
- # feature.
},
],
},
],
},
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
- "positiveLabel": "A String", # Label representing the positive class.
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
- "f1Score": 3.14, # The equally weighted average of recall and precision.
- "precision": 3.14, # The fraction of actual positive predictions that had positive actual
- # labels.
- "accuracy": 3.14, # The fraction of predictions given the correct label.
- "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
- "truePositives": "A String", # Number of true samples predicted as true.
"recall": 3.14, # The fraction of actual positive labels that were given a positive
# prediction.
"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.
+ "trueNegatives": "A String", # Number of true samples predicted as false.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
+ "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
+ "truePositives": "A String", # Number of true samples predicted as true.
},
],
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -736,8 +741,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -752,36 +755,42 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"negativeLabel": "A String", # Label representing the negative class.
+ "positiveLabel": "A String", # Label representing the positive class.
},
"regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
# factorization models.
# factorization models.
+ "meanSquaredError": 3.14, # Mean squared error.
+ "rSquared": 3.14, # R^2 score.
"medianAbsoluteError": 3.14, # Median absolute error.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
- "meanSquaredError": 3.14, # Mean squared 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.
- "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.
- "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.
- "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.
- "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.
},
},
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
+ # any more (compared to min_relative_progress). Used only for iterative
+ # training algorithms.
+ "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.
+ "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
+ # strategy.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
@@ -792,8 +801,8 @@
"hiddenUnits": [ # Hidden units for dnn models.
"A String",
],
- "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"l1Regularization": 3.14, # L1 regularization coefficient.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"distanceType": "A String", # Distance type for clustering models.
"walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
# specified.
@@ -814,49 +823,35 @@
# training algorithms.
"userColumn": "A String", # User column specified for matrix factorization models.
"maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "preserveInputStructs": True or False, # Whether to preserve the input structs in output feature names.
+ # Suppose there is a struct A with field b.
+ # When false (default), the output feature name is A_b.
+ # When true, the output feature name is A.b.
"l2Regularization": 3.14, # L2 regularization coefficient.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
"batchSize": "A String", # Batch size for dnn models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
"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.
- "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
- # when kmeans_initialization_method is CUSTOM.
"numClusters": "A String", # Number of clusters for clustering models.
"dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
"minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
- "dropout": 3.14, # Dropout probability for dnn models.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
- # overfitting for boosted tree models.
- "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
- # any more (compared to min_relative_progress). Used only for iterative
- # training algorithms.
- "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.
- "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
- # strategy.
- "itemColumn": "A String", # Item column specified for matrix factorization models.
},
"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.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
"evaluationTable": { # Table reference of the evaluation data after split.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
},
},
@@ -875,8 +870,21 @@
# 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.
},
+ "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.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
+ "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",
+ },
},
],
+ "nextPageToken": "A String", # A token to request the next page of results.
}</pre>
</div>
@@ -906,22 +914,10 @@
The object takes the form of:
{
- "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.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
- "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",
- },
+ "modelType": "A String", # Output only. Type of the model resource.
"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.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -934,7 +930,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -942,13 +937,13 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "modelType": "A String", # Output only. Type of the model resource.
"featureColumns": [ # Output only. Input feature columns that were used to train this model.
{ # A field or a column.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -961,7 +956,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -969,7 +963,9 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
"expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
@@ -982,14 +978,6 @@
"startTime": "A String", # The start time of this training run.
"results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
- "clusterInfos": [ # Information about top clusters for clustering models.
- { # Information about a single cluster for clustering model.
- "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
- # to each point assigned to the cluster.
- "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
- "centroidId": "A String", # Centroid id.
- },
- ],
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"index": 42, # Index of the iteration, 0 based.
@@ -1000,6 +988,17 @@
"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.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ },
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
# for one time series.
"A String",
@@ -1010,22 +1009,11 @@
"q": "A String", # Order of the moving-average part.
},
"arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "aic": 3.14, # AIC.
"logLikelihood": 3.14, # Log-likelihood.
"variance": 3.14, # Variance.
- "aic": 3.14, # AIC.
},
"timeSeriesId": "A String", # The id to indicate different time series.
- "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.
- "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
- 3.14,
- ],
- "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
- "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
- 3.14,
- ],
- },
},
],
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
@@ -1033,12 +1021,35 @@
"A String",
],
},
+ "clusterInfos": [ # Information about top clusters for clustering models.
+ { # Information about a single cluster for clustering model.
+ "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
+ # to each point assigned to the cluster.
+ "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
],
"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.
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "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.
+ "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.
+ "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.
+ },
"multiClassClassificationMetrics": { # Evaluation metrics for multi-class classification/classifier models. # Populated for multi-class classification/classifier models.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
# models, the metrics are either macro-averaged or micro-averaged. When
@@ -1046,8 +1057,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -1062,6 +1071,8 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"confusionMatrixList": [ # Confusion matrix at different thresholds.
{ # Confusion matrix for multi-class classification models.
@@ -1069,7 +1080,6 @@
# 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.
"itemCount": "A String", # Number of items being predicted as this label.
@@ -1078,6 +1088,7 @@
# confidence threshold.
},
],
+ "actualLabel": "A String", # The original label of this row.
},
],
},
@@ -1092,6 +1103,8 @@
"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.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
"featureColumn": "A String", # The feature column name.
"categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
"categoryCounts": [ # Counts of all categories for the categorical feature. If there are
@@ -1105,28 +1118,25 @@
},
],
},
- "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
- # feature.
},
],
},
],
},
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
- "positiveLabel": "A String", # Label representing the positive class.
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
- "f1Score": 3.14, # The equally weighted average of recall and precision.
- "precision": 3.14, # The fraction of actual positive predictions that had positive actual
- # labels.
- "accuracy": 3.14, # The fraction of predictions given the correct label.
- "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
- "truePositives": "A String", # Number of true samples predicted as true.
"recall": 3.14, # The fraction of actual positive labels that were given a positive
# prediction.
"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.
+ "trueNegatives": "A String", # Number of true samples predicted as false.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
+ "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
+ "truePositives": "A String", # Number of true samples predicted as true.
},
],
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -1135,8 +1145,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -1151,36 +1159,42 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"negativeLabel": "A String", # Label representing the negative class.
+ "positiveLabel": "A String", # Label representing the positive class.
},
"regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
# factorization models.
# factorization models.
+ "meanSquaredError": 3.14, # Mean squared error.
+ "rSquared": 3.14, # R^2 score.
"medianAbsoluteError": 3.14, # Median absolute error.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
- "meanSquaredError": 3.14, # Mean squared 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.
- "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.
- "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.
- "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.
- "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.
},
},
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
+ # any more (compared to min_relative_progress). Used only for iterative
+ # training algorithms.
+ "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.
+ "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
+ # strategy.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
@@ -1191,8 +1205,8 @@
"hiddenUnits": [ # Hidden units for dnn models.
"A String",
],
- "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"l1Regularization": 3.14, # L1 regularization coefficient.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"distanceType": "A String", # Distance type for clustering models.
"walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
# specified.
@@ -1213,49 +1227,35 @@
# training algorithms.
"userColumn": "A String", # User column specified for matrix factorization models.
"maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "preserveInputStructs": True or False, # Whether to preserve the input structs in output feature names.
+ # Suppose there is a struct A with field b.
+ # When false (default), the output feature name is A_b.
+ # When true, the output feature name is A.b.
"l2Regularization": 3.14, # L2 regularization coefficient.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
"batchSize": "A String", # Batch size for dnn models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
"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.
- "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
- # when kmeans_initialization_method is CUSTOM.
"numClusters": "A String", # Number of clusters for clustering models.
"dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
"minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
- "dropout": 3.14, # Dropout probability for dnn models.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
- # overfitting for boosted tree models.
- "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
- # any more (compared to min_relative_progress). Used only for iterative
- # training algorithms.
- "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.
- "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
- # strategy.
- "itemColumn": "A String", # Item column specified for matrix factorization models.
},
"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.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
"evaluationTable": { # Table reference of the evaluation data after split.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
},
},
@@ -1274,6 +1274,18 @@
# 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.
},
+ "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.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
+ "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",
+ },
}
@@ -1281,22 +1293,10 @@
An object of the form:
{
- "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.
- "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
- "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",
- },
+ "modelType": "A String", # Output only. Type of the model resource.
"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.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -1309,7 +1309,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -1317,13 +1316,13 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
- "modelType": "A String", # Output only. Type of the model resource.
"featureColumns": [ # Output only. Input feature columns that were used to train this model.
{ # A field or a column.
- "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
"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).
@@ -1336,7 +1335,6 @@
# {name="x", type={type_kind="STRING"}},
# {name="y", type={type_kind="ARRAY", array_element_type="DATE"}}
# ]}}
- "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").
"structType": { # The fields of this struct, in order, if type_kind = "STRUCT".
@@ -1344,7 +1342,9 @@
# Object with schema name: StandardSqlField
],
},
+ "arrayElementType": # Object with schema name: StandardSqlDataType # The type of the array's elements, if type_kind = "ARRAY".
},
+ "name": "A String", # Optional. The name of this field. Can be absent for struct fields.
},
],
"expirationTime": "A String", # Optional. The time when this model expires, in milliseconds since the epoch.
@@ -1357,14 +1357,6 @@
"startTime": "A String", # The start time of this training run.
"results": [ # Output of each iteration run, results.size() <= max_iterations.
{ # Information about a single iteration of the training run.
- "clusterInfos": [ # Information about top clusters for clustering models.
- { # Information about a single cluster for clustering model.
- "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
- # to each point assigned to the cluster.
- "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
- "centroidId": "A String", # Centroid id.
- },
- ],
"trainingLoss": 3.14, # Loss computed on the training data at the end of iteration.
"evalLoss": 3.14, # Loss computed on the eval data at the end of iteration.
"index": 42, # Index of the iteration, 0 based.
@@ -1375,6 +1367,17 @@
"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.
+ "arimaCoefficients": { # Arima coefficients. # Arima coefficients.
+ "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
+ 3.14,
+ ],
+ "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
+ "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
+ 3.14,
+ ],
+ },
+ "hasDrift": True or False, # Whether Arima model fitted with drift or not. It is always false
+ # when d is not 1.
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported
# for one time series.
"A String",
@@ -1385,22 +1388,11 @@
"q": "A String", # Order of the moving-average part.
},
"arimaFittingMetrics": { # ARIMA model fitting metrics. # Arima fitting metrics.
+ "aic": 3.14, # AIC.
"logLikelihood": 3.14, # Log-likelihood.
"variance": 3.14, # Variance.
- "aic": 3.14, # AIC.
},
"timeSeriesId": "A String", # The id to indicate different time series.
- "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.
- "autoRegressiveCoefficients": [ # Auto-regressive coefficients, an array of double.
- 3.14,
- ],
- "interceptCoefficient": 3.14, # Intercept coefficient, just a double not an array.
- "movingAverageCoefficients": [ # Moving-average coefficients, an array of double.
- 3.14,
- ],
- },
},
],
"seasonalPeriods": [ # Seasonal periods. Repeated because multiple periods are supported for
@@ -1408,12 +1400,35 @@
"A String",
],
},
+ "clusterInfos": [ # Information about top clusters for clustering models.
+ { # Information about a single cluster for clustering model.
+ "clusterRadius": 3.14, # Cluster radius, the average distance from centroid
+ # to each point assigned to the cluster.
+ "clusterSize": "A String", # Cluster size, the total number of points assigned to the cluster.
+ "centroidId": "A String", # Centroid id.
+ },
+ ],
},
],
"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.
+ "rankingMetrics": { # Evaluation metrics used by weighted-ALS models specified by # [Alpha] Populated for implicit feedback type matrix factorization
+ # models.
+ # feedback_type=implicit.
+ "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.
+ "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.
+ "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.
+ },
"multiClassClassificationMetrics": { # Evaluation metrics for multi-class classification/classifier models. # Populated for multi-class classification/classifier models.
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
# models, the metrics are either macro-averaged or micro-averaged. When
@@ -1421,8 +1436,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -1437,6 +1450,8 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"confusionMatrixList": [ # Confusion matrix at different thresholds.
{ # Confusion matrix for multi-class classification models.
@@ -1444,7 +1459,6 @@
# 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.
"itemCount": "A String", # Number of items being predicted as this label.
@@ -1453,6 +1467,7 @@
# confidence threshold.
},
],
+ "actualLabel": "A String", # The original label of this row.
},
],
},
@@ -1467,6 +1482,8 @@
"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.
+ "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
+ # feature.
"featureColumn": "A String", # The feature column name.
"categoricalValue": { # Representative value of a categorical feature. # The categorical feature value.
"categoryCounts": [ # Counts of all categories for the categorical feature. If there are
@@ -1480,28 +1497,25 @@
},
],
},
- "numericalValue": 3.14, # The numerical feature value. This is the centroid value for this
- # feature.
},
],
},
],
},
"binaryClassificationMetrics": { # Evaluation metrics for binary classification/classifier models. # Populated for binary classification/classifier models.
- "positiveLabel": "A String", # Label representing the positive class.
"binaryConfusionMatrixList": [ # Binary confusion matrix at multiple thresholds.
{ # Confusion matrix for binary classification models.
- "f1Score": 3.14, # The equally weighted average of recall and precision.
- "precision": 3.14, # The fraction of actual positive predictions that had positive actual
- # labels.
- "accuracy": 3.14, # The fraction of predictions given the correct label.
- "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
- "truePositives": "A String", # Number of true samples predicted as true.
"recall": 3.14, # The fraction of actual positive labels that were given a positive
# prediction.
"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.
+ "trueNegatives": "A String", # Number of true samples predicted as false.
+ "f1Score": 3.14, # The equally weighted average of recall and precision.
+ "precision": 3.14, # The fraction of actual positive predictions that had positive actual
+ # labels.
+ "positiveClassThreshold": 3.14, # Threshold value used when computing each of the following metric.
+ "accuracy": 3.14, # The fraction of predictions given the correct label.
+ "truePositives": "A String", # Number of true samples predicted as true.
},
],
"aggregateClassificationMetrics": { # Aggregate metrics for classification/classifier models. For multi-class # Aggregate classification metrics.
@@ -1510,8 +1524,6 @@
# unweighted average is taken of those values. When micro-averaged, the
# metric is calculated globally by counting the total number of correctly
# predicted rows.
- "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
- # positive prediction. For multiclass this is a macro-averaged metric.
"threshold": 3.14, # Threshold at which the metrics are computed. For binary
# classification models this is the positive class threshold.
# For multi-class classfication models this is the confidence
@@ -1526,36 +1538,42 @@
# metric treating each class as a binary classifier.
"accuracy": 3.14, # Accuracy is the fraction of predictions given the correct label. For
# multiclass this is a micro-averaged metric.
+ "recall": 3.14, # Recall is the fraction of actual positive labels that were given a
+ # positive prediction. For multiclass this is a macro-averaged metric.
},
"negativeLabel": "A String", # Label representing the negative class.
+ "positiveLabel": "A String", # Label representing the positive class.
},
"regressionMetrics": { # Evaluation metrics for regression and explicit feedback type matrix # Populated for regression models and explicit feedback type matrix
# factorization models.
# factorization models.
+ "meanSquaredError": 3.14, # Mean squared error.
+ "rSquared": 3.14, # R^2 score.
"medianAbsoluteError": 3.14, # Median absolute error.
"meanSquaredLogError": 3.14, # Mean squared log error.
"meanAbsoluteError": 3.14, # Mean absolute error.
- "meanSquaredError": 3.14, # Mean squared 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.
- "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.
- "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.
- "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.
- "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.
},
},
"trainingOptions": { # Options that were used for this training run, includes
# user specified and default options that were used.
+ "dropout": 3.14, # Dropout probability for dnn models.
+ "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
+ "labelClassWeights": { # Weights associated with each label class, for rebalancing the
+ # training data. Only applicable for classification models.
+ "a_key": 3.14,
+ },
+ "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
+ # overfitting for boosted tree models.
+ "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
+ # any more (compared to min_relative_progress). Used only for iterative
+ # training algorithms.
+ "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.
+ "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
+ # strategy.
+ "itemColumn": "A String", # Item column specified for matrix factorization models.
"inputLabelColumns": [ # Name of input label columns in training data.
"A String",
],
@@ -1566,8 +1584,8 @@
"hiddenUnits": [ # Hidden units for dnn models.
"A String",
],
- "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"l1Regularization": 3.14, # L1 regularization coefficient.
+ "kmeansInitializationMethod": "A String", # The method used to initialize the centroids for kmeans algorithm.
"distanceType": "A String", # Distance type for clustering models.
"walsAlpha": 3.14, # Hyperparameter for matrix factoration when implicit feedback type is
# specified.
@@ -1588,49 +1606,35 @@
# training algorithms.
"userColumn": "A String", # User column specified for matrix factorization models.
"maxTreeDepth": "A String", # Maximum depth of a tree for boosted tree models.
+ "preserveInputStructs": True or False, # Whether to preserve the input structs in output feature names.
+ # Suppose there is a struct A with field b.
+ # When false (default), the output feature name is A_b.
+ # When true, the output feature name is A.b.
"l2Regularization": 3.14, # L2 regularization coefficient.
"modelUri": "A String", # [Beta] Google Cloud Storage URI from which the model was imported. Only
# applicable for imported models.
"batchSize": "A String", # Batch size for dnn models.
+ "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
+ # when kmeans_initialization_method is CUSTOM.
"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.
- "kmeansInitializationColumn": "A String", # The column used to provide the initial centroids for kmeans algorithm
- # when kmeans_initialization_method is CUSTOM.
"numClusters": "A String", # Number of clusters for clustering models.
"dataSplitMethod": "A String", # The data split type for training and evaluation, e.g. RANDOM.
"minSplitLoss": 3.14, # Minimum split loss for boosted tree models.
- "dropout": 3.14, # Dropout probability for dnn models.
- "learnRate": 3.14, # Learning rate in training. Used only for iterative training algorithms.
- "labelClassWeights": { # Weights associated with each label class, for rebalancing the
- # training data. Only applicable for classification models.
- "a_key": 3.14,
- },
- "subsample": 3.14, # Subsample fraction of the training data to grow tree to prevent
- # overfitting for boosted tree models.
- "earlyStop": True or False, # Whether to stop early when the loss doesn't improve significantly
- # any more (compared to min_relative_progress). Used only for iterative
- # training algorithms.
- "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.
- "initialLearnRate": 3.14, # Specifies the initial learning rate for the line search learn rate
- # strategy.
- "itemColumn": "A String", # Item column specified for matrix factorization models.
},
"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.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
"evaluationTable": { # Table reference of the evaluation data after split.
+ "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.
"projectId": "A String", # [Required] The ID of the project containing this table.
"datasetId": "A String", # [Required] The ID of the dataset 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.
},
},
},
@@ -1649,6 +1653,18 @@
# 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.
},
+ "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.
+ "lastModifiedTime": "A String", # Output only. The time when this model was last modified, in millisecs since the epoch.
+ "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",
+ },
}</pre>
</div>