whylabs/whylogs-python

syntax = "proto3";

import "v0_messages.proto";
import "google/protobuf/struct.proto";
import "v0_summaries.proto";

option java_package = "com.whylogs.v0.core.constraint";
option java_outer_classname = "Constraints";
option java_multiple_files = true;

/* constraints specify one of the following binary boolean relationships. */
enum Op {
    unused = 0;
    LT = 1;
    LE = 2;
    EQ = 3;
    NE = 4;
    GE = 5;
    GT = 6;
    MATCH = 7;
    NOMATCH = 8;
    BTWN = 9;
    IN_SET = 10;
    CONTAIN_SET = 11;
    EQ_SET = 12;
    APPLY_FUNC = 13;
    IN = 14;
    CONTAIN = 15;
    NOT_IN = 16;
    SUM = 17;
  }

/* Summary constraints specify a relationship between a summary field and a literal value,
   or between two summary fields.
   e.g.     'min' < 6
            'std_dev' < 2.17
            'min' > 'avg'
   */
message SummaryConstraintMsg {
  string name = 1;
  string first_field = 2;
  oneof second {
     string second_field = 3;
     double value = 4;
     SummaryBetweenConstraintMsg between = 7;
     google.protobuf.ListValue reference_set = 8;
     string value_str = 12;
  }
  Op op = 5;
  bool verbose = 6;
  double quantile_value = 9;
  oneof reference_distribution{
    ReferenceDistributionContinuousMessage continuous_distribution = 10;
    ReferenceDistributionDiscreteMessage discrete_distribution = 11;
  }
}

message ReferenceDistributionContinuousMessage {
  KllFloatsSketchMessage sketch = 1;
}

message ReferenceDistributionDiscreteMessage {
  FrequentItemsSummary frequent_items = 1;
  UniqueCountSummary unique_count = 2;
  float total_count = 3;
}

message SummaryBetweenConstraintMsg {
  oneof lower {
     string second_field = 1;
     double lower_value = 2;
  }
  oneof upper {
     string third_field = 3;
     double upper_value = 4;
  }

}

/* ValueConstraints express a binary boolean relationship between an implied numeric value and a literal, or between a string value and a regex pattern.
   These are applied to every incoming value that is processed by whylogs.  */
message ApplyFunctionMsg {
  string function = 1;
  string reference_value = 2;
}

message ValueConstraintMsg {
  string name = 1;
  oneof second_field {
    double value = 2;
    string regex_pattern = 5;
    google.protobuf.ListValue value_set = 6;
    ApplyFunctionMsg function = 7;

  }
  Op op = 3;
  bool verbose = 4;
  uint32 total = 8;
  uint32 failures = 9;
}

message MultiColumnValueConstraintMsg {
  string name = 1;
  oneof dependent {
    google.protobuf.ListValue dependent_columns = 2;
    string dependent_column = 3;
  }

  oneof reference {
    double value = 6;
    google.protobuf.ListValue value_set = 7;
    google.protobuf.ListValue reference_columns = 8;
  }
  Op op = 4;
  bool verbose = 5;
  Op internal_dependent_columns_op = 9;
  uint32 total = 10;
  uint32 failures = 11;
}

message ValueConstraintMsgs {
  repeated ValueConstraintMsg constraints = 1;
  repeated MultiColumnValueConstraintMsg multi_column_constraints = 2;
}

message SummaryConstraintMsgs {
  repeated SummaryConstraintMsg constraints = 1;
}

message DatasetConstraintMsg {
  DatasetPropertiesV0 properties = 1;
  map<string, ValueConstraintMsgs> value_constraints = 2;
  map<string, SummaryConstraintMsgs> summary_constraints = 3;
  SummaryConstraintMsgs table_shape_constraints = 4;
  ValueConstraintMsgs multi_column_value_constraints = 5;
}