Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformation
- Inherits:
-
Object
- Object
- Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformation
- Includes:
- Core::Hashable, Core::JsonObjectSupport
- Defined in:
- lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb more...
Instance Attribute Summary collapse
-
#auto ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationAutoTransformation
Training pipeline will infer the proper transformation based on the statistic of dataset.
-
#categorical ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationCategoricalTransformation
Training pipeline will perform following transformation functions.
-
#numeric ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationNumericTransformation
Training pipeline will perform following transformation functions.
-
#text ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationTextTransformation
Training pipeline will perform following transformation functions.
-
#timestamp ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationTimestampTransformation
Training pipeline will perform following transformation functions.
Instance Method Summary collapse
-
#initialize(**args) ⇒ GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformation
constructor
A new instance of GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformation.
-
#update!(**args) ⇒ Object
Update properties of this object.
Constructor Details
#initialize(**args) ⇒ GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformation
Returns a new instance of GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformation.
27380 27381 27382 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 27380 def initialize(**args) update!(**args) end |
Instance Attribute Details
#auto ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationAutoTransformation
Training pipeline will infer the proper transformation based on the statistic
of dataset.
Corresponds to the JSON property auto
27340 27341 27342 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 27340 def auto @auto end |
#categorical ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationCategoricalTransformation
Training pipeline will perform following transformation functions. * The
categorical string as is--no change to case, punctuation, spelling, tense, and
so on. * Convert the category name to a dictionary lookup index and generate
an embedding for each index. * Categories that appear less than 5 times in the
training dataset are treated as the "unknown" category. The "unknown" category
gets its own special lookup index and resulting embedding.
Corresponds to the JSON property categorical
27350 27351 27352 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 27350 def categorical @categorical end |
#numeric ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationNumericTransformation
Training pipeline will perform following transformation functions. * The value
converted to float32. * The z_score of the value. * log(value+1) when the
value is greater than or equal to 0. Otherwise, this transformation is not
applied and the value is considered a missing value. * z_score of log(value+1)
when the value is greater than or equal to 0. Otherwise, this transformation
is not applied and the value is considered a missing value.
Corresponds to the JSON property numeric
27360 27361 27362 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 27360 def numeric @numeric end |
#text ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationTextTransformation
Training pipeline will perform following transformation functions. * The text
as is--no change to case, punctuation, spelling, tense, and so on. * Convert
the category name to a dictionary lookup index and generate an embedding for
each index.
Corresponds to the JSON property text
27368 27369 27370 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 27368 def text @text end |
#timestamp ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionSeq2SeqPlusForecastingInputsTransformationTimestampTransformation
Training pipeline will perform following transformation functions. * Apply the
transformation functions for Numerical columns. * Determine the year, month,
day,and weekday. Treat each value from the timestamp as a Categorical column. *
Invalid numerical values (for example, values that fall outside of a typical
timestamp range, or are extreme values) receive no special treatment and are
not removed.
Corresponds to the JSON property timestamp
27378 27379 27380 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 27378 def @timestamp end |
Instance Method Details
#update!(**args) ⇒ Object
Update properties of this object
27385 27386 27387 27388 27389 27390 27391 |
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 27385 def update!(**args) @auto = args[:auto] if args.key?(:auto) @categorical = args[:categorical] if args.key?(:categorical) @numeric = args[:numeric] if args.key?(:numeric) @text = args[:text] if args.key?(:text) @timestamp = args[:timestamp] if args.key?(:timestamp) end |