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

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: AutoTransformation, CategoricalArrayTransformation, CategoricalTransformation, NumericArrayTransformation, NumericTransformation, TextArrayTransformation, TextTransformation, TimestampTransformation

Instance Attribute Summary collapse

Instance Attribute Details

#auto::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::AutoTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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

#categorical::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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

#numeric::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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

#repeated_categorical::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::CategoricalArrayTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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

#repeated_numeric::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::NumericArrayTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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

#repeated_text::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextArrayTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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

#text::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TextTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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

#timestamp::Google::Cloud::AIPlatform::V1::Schema::TrainingJob::Definition::AutoMlTablesInputs::Transformation::TimestampTransformation



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
# File 'proto_docs/google/cloud/aiplatform/v1/schema/trainingjob/definition/automl_tables.rb', line 147

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