Class: Google::Cloud::Dataplex::V1::DataProfileResult::Profile

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/dataplex/v1/data_profile.rb

Overview

Contains name, type, mode and field type specific profile information.

Defined Under Namespace

Classes: Field

Instance Attribute Summary collapse

Instance Attribute Details

#fields ⇒ ::Array<::Google::Cloud::Dataplex::V1::DataProfileResult::Profile::Field>

Returns List of fields with structural and profile information for each field.

Returns:



118
119
120
121
122
123
124
125
126
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
 
# File 'proto_docs/google/cloud/dataplex/v1/data_profile.rb', line 118

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

  # A field within a table.
  # @!attribute [rw] name
  #   @return [::String]
  #     The name of the field.
  # @!attribute [rw] type
  #   @return [::String]
  #     The data type retrieved from the schema of the data source. For
  #     instance, for a BigQuery native table, it is the [BigQuery Table
  #     Schema](https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#tablefieldschema).
  #     For a Dataplex Entity, it is the [Entity
  #     Schema](https://cloud.google.com/dataplex/docs/reference/rpc/google.cloud.dataplex.v1#type_3).
  # @!attribute [rw] mode
  #   @return [::String]
  #     The mode of the field. Possible values include:
  #
  #     * REQUIRED, if it is a required field.
  #     * NULLABLE, if it is an optional field.
  #     * REPEATED, if it is a repeated field.
  # @!attribute [rw] profile
  #   @return [::Google::Cloud::Dataplex::V1::DataProfileResult::Profile::Field::ProfileInfo]
  #     Profile information for the corresponding field.
  class Field
    include ::Google::Protobuf::MessageExts
    extend ::Google::Protobuf::MessageExts::ClassMethods

    # The profile information for each field type.
    # @!attribute [rw] null_ratio
    #   @return [::Float]
    #     Ratio of rows with null value against total scanned rows.
    # @!attribute [rw] distinct_ratio
    #   @return [::Float]
    #     Ratio of rows with distinct values against total scanned rows.
    #     Not available for complex non-groupable field type RECORD and fields
    #     with REPEATABLE mode.
    # @!attribute [rw] top_n_values
    #   @return [::Array<::Google::Cloud::Dataplex::V1::DataProfileResult::Profile::Field::ProfileInfo::TopNValue>]
    #     The list of top N non-null values, frequency and ratio with which
    #     they occur in the scanned data. N is 10 or equal to the number of
    #     distinct values in the field, whichever is smaller. Not available for
    #     complex non-groupable field type RECORD and fields with REPEATABLE
    #     mode.
    # @!attribute [rw] string_profile
    #   @return [::Google::Cloud::Dataplex::V1::DataProfileResult::Profile::Field::ProfileInfo::StringFieldInfo]
    #     String type field information.
    # @!attribute [rw] integer_profile
    #   @return [::Google::Cloud::Dataplex::V1::DataProfileResult::Profile::Field::ProfileInfo::IntegerFieldInfo]
    #     Integer type field information.
    # @!attribute [rw] double_profile
    #   @return [::Google::Cloud::Dataplex::V1::DataProfileResult::Profile::Field::ProfileInfo::DoubleFieldInfo]
    #     Double type field information.
    class ProfileInfo
      include ::Google::Protobuf::MessageExts
      extend ::Google::Protobuf::MessageExts::ClassMethods

      # The profile information for a string type field.
      # @!attribute [rw] min_length
      #   @return [::Integer]
      #     Minimum length of non-null values in the scanned data.
      # @!attribute [rw] max_length
      #   @return [::Integer]
      #     Maximum length of non-null values in the scanned data.
      # @!attribute [rw] average_length
      #   @return [::Float]
      #     Average length of non-null values in the scanned data.
      class StringFieldInfo
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end

      # The profile information for an integer type field.
      # @!attribute [rw] average
      #   @return [::Float]
      #     Average of non-null values in the scanned data. NaN, if the field
      #     has a NaN.
      # @!attribute [rw] standard_deviation
      #   @return [::Float]
      #     Standard deviation of non-null values in the scanned data. NaN, if
      #     the field has a NaN.
      # @!attribute [rw] min
      #   @return [::Integer]
      #     Minimum of non-null values in the scanned data. NaN, if the field
      #     has a NaN.
      # @!attribute [rw] quartiles
      #   @return [::Array<::Integer>]
      #     A quartile divides the number of data points into four parts, or
      #     quarters, of more-or-less equal size. Three main quartiles used
      #     are: The first quartile (Q1) splits off the lowest 25% of data from
      #     the highest 75%. It is also known as the lower or 25th empirical
      #     quartile, as 25% of the data is below this point. The second
      #     quartile (Q2) is the median of a data set. So, 50% of the data lies
      #     below this point. The third quartile (Q3) splits off the highest
      #     25% of data from the lowest 75%. It is known as the upper or 75th
      #     empirical quartile, as 75% of the data lies below this point.
      #     Here, the quartiles is provided as an ordered list of approximate
      #     quartile values for the scanned data, occurring in order Q1,
      #     median, Q3.
      # @!attribute [rw] max
      #   @return [::Integer]
      #     Maximum of non-null values in the scanned data. NaN, if the field
      #     has a NaN.
      class IntegerFieldInfo
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end

      # The profile information for a double type field.
      # @!attribute [rw] average
      #   @return [::Float]
      #     Average of non-null values in the scanned data. NaN, if the field
      #     has a NaN.
      # @!attribute [rw] standard_deviation
      #   @return [::Float]
      #     Standard deviation of non-null values in the scanned data. NaN, if
      #     the field has a NaN.
      # @!attribute [rw] min
      #   @return [::Float]
      #     Minimum of non-null values in the scanned data. NaN, if the field
      #     has a NaN.
      # @!attribute [rw] quartiles
      #   @return [::Array<::Float>]
      #     A quartile divides the number of data points into four parts, or
      #     quarters, of more-or-less equal size. Three main quartiles used
      #     are: The first quartile (Q1) splits off the lowest 25% of data from
      #     the highest 75%. It is also known as the lower or 25th empirical
      #     quartile, as 25% of the data is below this point. The second
      #     quartile (Q2) is the median of a data set. So, 50% of the data lies
      #     below this point. The third quartile (Q3) splits off the highest
      #     25% of data from the lowest 75%. It is known as the upper or 75th
      #     empirical quartile, as 75% of the data lies below this point.
      #     Here, the quartiles is provided as an ordered list of quartile
      #     values for the scanned data, occurring in order Q1, median, Q3.
      # @!attribute [rw] max
      #   @return [::Float]
      #     Maximum of non-null values in the scanned data. NaN, if the field
      #     has a NaN.
      class DoubleFieldInfo
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end

      # Top N non-null values in the scanned data.
      # @!attribute [rw] value
      #   @return [::String]
      #     String value of a top N non-null value.
      # @!attribute [rw] count
      #   @return [::Integer]
      #     Count of the corresponding value in the scanned data.
      # @!attribute [rw] ratio
      #   @return [::Float]
      #     Ratio of the corresponding value in the field against the total
      #     number of rows in the scanned data.
      class TopNValue
        include ::Google::Protobuf::MessageExts
        extend ::Google::Protobuf::MessageExts::ClassMethods
      end
    end
  end
end