Class: Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb

Defined Under Namespace

Classes: Transformation

Instance Attribute Summary collapse

Instance Attribute Details

#additional_experiments ⇒ ::Array<::String>

Returns Additional experiment flags for the Tables training pipeline.

Returns:

  • (::Array<::String>) —

    Additional experiment flags for the Tables training pipeline.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#disable_early_stopping ⇒ ::Boolean

Returns Use the entire training budget. This disables the early stopping feature. By default, the early stopping feature is enabled, which means that AutoML Tables might stop training before the entire training budget has been used.

Returns:

  • (::Boolean) —

    Use the entire training budget. This disables the early stopping feature. By default, the early stopping feature is enabled, which means that AutoML Tables might stop training before the entire training budget has been used.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#export_evaluated_data_items_config ⇒ ::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::ExportEvaluatedDataItemsConfig

Returns Configuration for exporting test set predictions to a BigQuery table. If this configuration is absent, then the export is not performed.

Returns:



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#optimization_objective ⇒ ::String

Returns Objective function the model is optimizing towards. The training process creates a model that maximizes/minimizes the value of the objective function over the validation set.

The supported optimization objectives depend on the prediction type. If the field is not set, a default objective function is used.

classification (binary): "maximize-au-roc" (default) - Maximize the area under the receiver operating characteristic (ROC) curve. "minimize-log-loss" - Minimize log loss. "maximize-au-prc" - Maximize the area under the precision-recall curve. "maximize-precision-at-recall" - Maximize precision for a specified recall value. "maximize-recall-at-precision" - Maximize recall for a specified precision value.

classification (multi-class): "minimize-log-loss" (default) - Minimize log loss.

regression: "minimize-rmse" (default) - Minimize root-mean-squared error (RMSE). "minimize-mae" - Minimize mean-absolute error (MAE). "minimize-rmsle" - Minimize root-mean-squared log error (RMSLE).

Returns:

  • (::String) —

    Objective function the model is optimizing towards. The training process creates a model that maximizes/minimizes the value of the objective function over the validation set.

    The supported optimization objectives depend on the prediction type. If the field is not set, a default objective function is used.

    classification (binary): "maximize-au-roc" (default) - Maximize the area under the receiver operating characteristic (ROC) curve. "minimize-log-loss" - Minimize log loss. "maximize-au-prc" - Maximize the area under the precision-recall curve. "maximize-precision-at-recall" - Maximize precision for a specified recall value. "maximize-recall-at-precision" - Maximize recall for a specified precision value.

    classification (multi-class): "minimize-log-loss" (default) - Minimize log loss.

    regression: "minimize-rmse" (default) - Minimize root-mean-squared error (RMSE). "minimize-mae" - Minimize mean-absolute error (MAE). "minimize-rmsle" - Minimize root-mean-squared log error (RMSLE).



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#optimization_objective_precision_value ⇒ ::Float

Returns Required when optimization_objective is "maximize-recall-at-precision". Must be between 0 and 1, inclusive.

Returns:

  • (::Float) —

    Required when optimization_objective is "maximize-recall-at-precision". Must be between 0 and 1, inclusive.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#optimization_objective_recall_value ⇒ ::Float

Returns Required when optimization_objective is "maximize-precision-at-recall". Must be between 0 and 1, inclusive.

Returns:

  • (::Float) —

    Required when optimization_objective is "maximize-precision-at-recall". Must be between 0 and 1, inclusive.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#prediction_type ⇒ ::String

Returns The type of prediction the Model is to produce. "classification" - Predict one out of multiple target values is picked for each row. "regression" - Predict a value based on its relation to other values. This type is available only to columns that contain semantically numeric values, i.e. integers or floating point number, even if stored as e.g. strings.

Returns:

  • (::String) —

    The type of prediction the Model is to produce. "classification" - Predict one out of multiple target values is picked for each row. "regression" - Predict a value based on its relation to other values. This type is available only to columns that contain semantically numeric values, i.e. integers or floating point number, even if stored as e.g. strings.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#target_column ⇒ ::String

Returns The column name of the target column that the model is to predict.

Returns:

  • (::String) —

    The column name of the target column that the model is to predict.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#train_budget_milli_node_hours ⇒ ::Integer

Returns Required. The train budget of creating this model, expressed in milli node hours i.e. 1,000 value in this field means 1 node hour.

The training cost of the model will not exceed this budget. The final cost will be attempted to be close to the budget, though may end up being (even) noticeably smaller - at the backend's discretion. This especially may happen when further model training ceases to provide any improvements.

If the budget is set to a value known to be insufficient to train a model for the given dataset, the training won't be attempted and will error.

The train budget must be between 1,000 and 72,000 milli node hours, inclusive.

Returns:

  • (::Integer) —

    Required. The train budget of creating this model, expressed in milli node hours i.e. 1,000 value in this field means 1 node hour.

    The training cost of the model will not exceed this budget. The final cost will be attempted to be close to the budget, though may end up being (even) noticeably smaller - at the backend's discretion. This especially may happen when further model training ceases to provide any improvements.

    If the budget is set to a value known to be insufficient to train a model for the given dataset, the training won't be attempted and will error.

    The train budget must be between 1,000 and 72,000 milli node hours, inclusive.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#transformations ⇒ ::Array<::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation>

Returns Each transformation will apply transform function to given input column. And the result will be used for training. When creating transformation for BigQuery Struct column, the column should be flattened using "." as the delimiter.

Returns:



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end

#weight_column_name ⇒ ::String

Returns Column name that should be used as the weight column. Higher values in this column give more importance to the row during model training. The column must have numeric values between 0 and 10000 inclusively; 0 means the row is ignored for training. If weight column field is not set, then all rows are assumed to have equal weight of 1.

Returns:

  • (::String) —

    Column name that should be used as the weight column. Higher values in this column give more importance to the row during model training. The column must have numeric values between 0 and 10000 inclusively; 0 means the row is ignored for training. If weight column field is not set, then all rows are assumed to have equal weight of 1.



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
 
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 127

class AutoMlTablesInputs
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods

  # @!attribute [rw] auto
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation]
  # @!attribute [rw] numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation]
  # @!attribute [rw] categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation]
  # @!attribute [rw] timestamp
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation]
  # @!attribute [rw] text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation]
  # @!attribute [rw] repeated_numeric
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation]
  # @!attribute [rw] repeated_categorical
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation]
  # @!attribute [rw] repeated_text
  #   @return [::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation]
  class Transformation
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # Training pipeline will infer the proper transformation based on the
    # statistic of dataset.
    # @!attribute [rw] column_name
    #   @return [::String]
    class AutoTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # *  A boolean value that indicates whether the value is valid.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # 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.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] time_format
    #   @return [::String]
    #     The format in which that time field is expressed. The time_format must
    #     either be one of:
    #     * `unix-seconds`
    #     * `unix-milliseconds`
    #     * `unix-microseconds`
    #     * `unix-nanoseconds`
    #     (for respectively number of seconds, milliseconds, microseconds and
    #     nanoseconds since start of the Unix epoch);
    #     or be written in `strftime` syntax. If time_format is not set, then the
    #     default format is RFC 3339 `date-time` format, where
    #     `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class TimestampTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Training pipeline will perform following transformation functions.
    # *  The text as is--no change to case, punctuation, spelling, tense, and
    # so
    #    on.
    # *  Tokenize text to words. Convert each words to a dictionary lookup
    # index
    #    and generate an embedding for each index. Combine the embedding of all
    #    elements into a single embedding using the mean.
    # *  Tokenization is based on unicode script boundaries.
    # *  Missing values get their own lookup index and resulting embedding.
    # *  Stop-words receive no special treatment and are not removed.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as numerical array and performs following
    # transformation functions.
    # *  All transformations for Numerical types applied to the average of the
    #    all elements.
    # *  The average of empty arrays is treated as zero.
    # @!attribute [rw] column_name
    #   @return [::String]
    # @!attribute [rw] invalid_values_allowed
    #   @return [::Boolean]
    #     If invalid values is allowed, the training pipeline will create a
    #     boolean feature that indicated whether the value is valid.
    #     Otherwise, the training pipeline will discard the input row from
    #     trainining data.
    class NumericArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as categorical array and performs following
    # transformation functions.
    # *  For each element in the array, convert the category name to a
    # dictionary
    #    lookup index and generate an embedding for each index.
    #    Combine the embedding of all elements into a single embedding using
    #    the mean.
    # *  Empty arrays treated as an embedding of zeroes.
    # @!attribute [rw] column_name
    #   @return [::String]
    class CategoricalArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end

    # Treats the column as text array and performs following transformation
    # functions.
    # *  Concatenate all text values in the array into a single text value
    # using
    #    a space (" ") as a delimiter, and then treat the result as a single
    #    text value. Apply the transformations for Text columns.
    # *  Empty arrays treated as an empty text.
    # @!attribute [rw] column_name
    #   @return [::String]
    class TextArrayTransformation
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods
    end
  end
end