MySQL :: HeatWave User Guide :: 3.18 HeatWave AutoML Error Messages

Error number: ML001016; SQLSTATE: HY000

Message: Only classification, regression, and forecasting tasks are supported.

Example: ERROR HY000: ML001016: Only classification, regression, and forecasting tasks are supported.

Check the task option in the ML_TRAIN call to ensure that it is specified correctly.

Error number: ML001031; SQLSTATE: HY000

Message: Running as a classification task. % classes have less than % samples per class, and cannot be trained on. Maybe it should be trained as a regression task instead of a classification task. Or the task ran on the default setting - classification, due to an incorrect JSON task argument.

Example: ERROR HY000: ML001031: Running as a classification task. 189 classes have less than 5 samples per class, and cannot be trained on. Maybe it should be trained as a regression task instead of a classification task. Or the task ran on the default setting - classification, due to an incorrect JSON task argument.

If a classification model is intended, add more samples to the data to increase the minority class count; that is, add more rows with the under-represented target column value. If a classification model was not intended, run ML_TRAIN with the regression task option.

Error number: ML001051; SQLSTATE: HY000

Message: One or more rows contain all NaN values. Imputation is not possible on such rows.

Example: ERROR HY000: ML001051: One or more rows contain all NaN values. Imputation is not possible on such rows.

MySQL does not support NaN values. Replace with NULL.

Error number: ML001052; SQLSTATE: HY000

Message: All columns are dropped. They are constant, mostly unique, or have a lot of missing values!

Example: ERROR HY000: ML001052: All columns are dropped. They are constant, mostly unique, or have a lot of missing values!

ML_TRAIN ignores columns with certain characteristics such as columns missing more than 20% of values and columns containing the same single value. See Section 3.4, “Preparing Data”.

Error number: ML001053; SQLSTATE: HY000

Message: Unlabeled samples detected in the training data. (Values in target column can not be NULL).

Example: ERROR HY000: ML001053: Unlabeled samples detected in the training data. (Values in target column can not be NULL).

Training data must be labeled. See Section 3.4, “Preparing Data”.

Error number: ML003000; SQLSTATE: HY000

Message: Number of offloaded datasets has reached the limit!

Example: ERROR HY000: ML003000: Number of offloaded datasets has reached the limit!

Error number: ML003011; SQLSTATE: HY000

Message: Columns of provided data need to match those used for training. Provided - ['%', '%', '%'] vs Trained - ['%', '%'].

Example: ERROR HY000: ML003011: Columns of provided data need to match those used for training. Provided - ['petal length', 'petal width', 'sepal length', 'sepal width'] vs Trained - ['petal length', 'sepal length', 'sepal width'].

The input data columns do not match the columns of training dataset used to train the model. Compare the input data to the training data to identify the discrepancy.

Error number: ML003012; SQLSTATE: HY000

Message: The table (%) is NULL or has not been loaded.

Example: ERROR HY000: ML003012: The table (mlcorpus.iris_train) is NULL or has not been loaded.

There is no data in the specified table.

Error number: ML003014; SQLSTATE: HY000

Message: The size of model generated is larger than the maximum allowed.

Example: ERROR HY000: ML003014: The size of model generated is larger than the maximum allowed.

Models greater than 900 MB in size are not supported.

Error number: ML003015; SQLSTATE: HY000

Message: The input column types do not match the column types of dataset which the model was trained on. ['%', '%'] vs ['%', '%'].

Example: ERROR HY000: ML003015: The input column types do not match the column types of dataset which the model was trained on. ['numerical', 'numerical', 'categorical', 'numerical'] vs ['numerical', 'numerical', 'numerical', 'numerical'].

Error number: ML003016; SQLSTATE: HY000

Message: Missing argument \"row_json\" in input JSON -> dict_keys(['%', '%']).

Example: ERROR HY000: ML003016: Missing argument \"row_json\" in input JSON -> dict_keys(['operation', 'user_name', 'table_name', 'schema_name', 'model_handle']).

Error number: ML003017; SQLSTATE: HY000

Message: The corresponding value of row_json should be a string!

Example: ERROR HY000: ML003017: The corresponding value of row_json should be a string!

Error number: ML003018; SQLSTATE: HY000

Message: The corresponding value of row_json is NOT a valid JSON!

Example: ERROR HY000: ML003018: The corresponding value of row_json is NOT a valid JSON!

Error number: ML003019; SQLSTATE: HY000

Message: Invalid data for the metric (%). Score could not be computed.

Example: ERROR HY000: ML003019: Invalid data for the metric (roc_auc). Score could not be computed.

The scoring metric is legal and supported, but the data provided is not suitable to calculate such a score. For example: ROC_AUC for multi-class classification. Try a different scoring metric.

Error number: ML003020; SQLSTATE: HY000

Message: Unsupported scoring function (%) for current task (%).

Example: ERROR HY000: ML003020: Unsupported scoring function (accuracy) for current task (regression).

The scoring metric is legal and supported, but the task provided is not suitable to calculate such a score; for example: Using the accuracy metric for a regression model.

Error number: ML003021; SQLSTATE: HY000

Message: Cannot train a regression task with a non-numeric target column.

Example: ERROR HY000: ML003021: Cannot train a regression task with a non-numeric target column.

ML_TRAIN was run with the regression task type on a training dataset with a non-numeric target column. Regression models require a numeric target column.

Error number: ML003022; SQLSTATE: HY000

Message: At least 2 target classes are needed for classification task

Example: ERROR HY000: ML003022: At least 2 target classes are needed for classification task.

ML_TRAIN was run with the classification task type on a training dataset where the target column did not have at least two possible values.

Error number: ML003023; SQLSTATE: 3877 (HY000)

Message: Unknown option given. Allowed options for training are: ['task', 'model_list', 'exclude_model_list', 'optimization_metric', 'exclude_column_list', 'datetime_index', 'endogenous_variables', 'exogenous_variables', 'positive_class', 'users', 'items', 'user_columns', 'item_columns'].

Example: ERROR 3877 (HY000): ML003023: Unknown option given. Allowed options for training are: ['task', 'model_list', 'exclude_model_list', 'optimization_metric', 'exclude_column_list', 'datetime_index', 'endogenous_variables', 'exogenous_variables', 'positive_class', 'users', 'items', 'user_columns', 'item_columns'].

The ML_TRAIN call specified an unknown option.

Error number: ML003024; SQLSTATE: HY000

Message: Not enough available memory, unloading any RAPID tables will help to free up memory.

Example: ERROR HY000: ML003024: Not enough available memory, unloading any RAPID tables will help to free up memory.

There is not enough memory on the HeatWave Cluster to perform the operation. Try unloading data that was loaded for analytics to free up space.

The recommended node shape for HeatWave AutoML functionality is HeatWave.256GB. The HeatWave.16GB node shape might not have enough memory to train the model with large data sets. If this error message appears with the smaller node shape and HeatWave AutoML, use the larger shape instead.

Error number: ML003027; SQLSTATE: 3877 (HY000)

Message: JSON attribute (item_columns) must be in JSON_ARRAY type.

Example: ERROR 3877 (HY000): ML003027: JSON attribute (item_columns) must be in JSON_ARRAY type.

Specify the item_columns JSON attribute as a JSON array.

Error number: ML003027; SQLSTATE: 3877 (HY000)

Message: JSON attribute (user_columns) must be in JSON_ARRAY type.

Example: ERROR 3877 (HY000): ML003027: JSON attribute (user_columns) must be in JSON_ARRAY type.

Specify the user_columns JSON attribute as a JSON array.

Error number: ML003039; SQLSTATE: HY000

Message: Not all user specified columns are present in the input table - missing columns are {%}.

Example: ERROR HY000: ML003039: Not all user specified columns are present in the input table - missing columns are {C4}.

The syntax includes a column that is not available.

Error number: ML003047; SQLSTATE: HY000

Message: All columns cannot be excluded. User provided exclude_column_list is ['%', '%'].

Example: ERROR HY000: ML003047: All columns cannot be excluded. User provided exclude_column_list is ['C0', 'C1', 'C2', 'C3'].

The syntax includes an exclude_column_list that attempts to exclude too many columns.

Error number: ML003048; SQLSTATE: HY000

Message: exclude_column_list JSON attribute must be of JSON_ARRAY type.

Example: ERROR HY000: ML003048: exclude_column_list JSON attribute must be of JSON_ARRAY type.

The syntax includes a malformed JSON_ARRAY for the exclude_column_list.

Error number: ML003048; SQLSTATE: HY000

Message: include_column_list JSON attribute must be of JSON_ARRAY type.

Example: ERROR HY000: ML003048: include_column_list JSON attribute must be of JSON_ARRAY type.

The syntax includes a malformed JSON_ARRAY for the include_column_list.

Error number: ML003049; SQLSTATE: HY000

Message: One or more columns in include_column_list ([%]) does not exist. Existing columns are (['%', '%']).

Example: ERROR HY000: ML003049: One or more columns in include_column_list ([C15]) does not exist. Existing columns are (['C0', 'C1', 'C2', 'C3']).

The syntax includes an include_column_list that expects a column that does not exist.

Error number: ML003050; SQLSTATE: HY000

Message: include_column_list must be a subset of exogenous_variables for forecasting task.

Example: ERROR HY000: ML003050: include_column_list must be a subset of exogenous_variables for forecasting task.

The syntax for a forecasting task includes an include_column_list that expects one or more columns that are not defined by exogenous_variables.

Error number: ML003052; SQLSTATE: HY000

Message: Target column provided % is one of the independent variables used to train the model [%, %, %].

Example: ERROR HY000: ML003052: Target column provided LSTAT is one of the independent variables used to train the model [RM, RAD, LSTAT].

The syntax defines a target_column_name that is one of the independent variables used to train the model.

Error number: ML003053; SQLSTATE: HY000

Message: datetime_index must be specified by the user for forecasting task and must be a column in the training table.

Example: ERROR HY000: ML003053: datetime_index must be specified by the user for forecasting task and must be a column in the training table.

The syntax for a forecasting task must include datetime_index, and this must be a column in the training table.

Error number: ML003054; SQLSTATE: HY000

Message: endogenous_variables must be specified by the user for forecasting task and must be column(s) in the training table.

Example: ERROR HY000: ML003054: endogenous_variables must be specified by the user for forecasting task and must be column(s) in the training table.

The syntax for a forecasting task must include the endogenous_variables option, and these must be a column or columns in the training table.

Error number: ML003055; SQLSTATE: HY000

Message: endogenous_variables / exogenous_variables option must be of JSON_ARRAY type.

Example: ERROR HY000: ML003055: endogenous_variables / exogenous_variables option must be of JSON_ARRAY type.

The syntax for a forecasting task includes endogenous_variables or exogenous_variables that do not have valid JSON format.

Error number: ML003056; SQLSTATE: HY000

Message: exclude_column_list cannot contain any of endogenous or exogenous variables for forecasting task.

Example: ERROR HY000: ML003056: exclude_column_list cannot contain any of endogenous or exogenous variables for forecasting task.

The syntax for a forecasting task includes exclude_column_list that contains columns that are also in endogenous_variables or exogenous_variables.

Error number: ML003057; SQLSTATE: HY000

Message: endogenous and exogenous variables may not have any common columns for forecasting task.

Example: ERROR HY000: ML003057: endogenous and exogenous variables may not have any common columns for forecasting task.

The syntax for a forecasting task includes endogenous_variables and exogenous_variables, and they have one or more columns in common.

Error number: ML003058; SQLSTATE: HY000

Message: Can not train a forecasting task with non-numeric endogenous_variables column(s).

Example: ERROR HY000: ML003058: Can not train a forecasting task with non-numeric endogenous_variables column(s).

The syntax for a forecasting task includes endogenous_variables and some of the columns are not defined as numeric.

Error number: ML003059; SQLSTATE: HY000

Message: User provided list of models ['ThetaForecaster', 'ETSForecaster', 'SARIMAXForecaster', 'ExpSmoothForecaster'] does not include any supported models for the task. Supported models for the given task and table are ['DynFactorForecaster', 'VARMAXForecaster'].

Example: ERROR HY000: ML003059: User provided list of models ['ThetaForecaster', 'ETSForecaster', 'SARIMAXForecaster', 'ExpSmoothForecaster'] does not include any supported models for the task. Supported models for the given task and table are ['DynFactorForecaster', 'VARMAXForecaster'].

The syntax for a forecasting task includes multivariate endogenous_variables, but the provided models only support univariate endogenous_variables.

Error number: ML003060; SQLSTATE: HY000

Message:: endogenous_variables may not contain repeated column names ['%1', '%2', '%1'].

Example: ERROR HY000: ML003060: endogenous_variables may not contain repeated column names ['wind', 'solar', 'wind'].

The syntax for a forecasting task includes endogenous_variables with a repeated column.

Error number: ML003061; SQLSTATE: HY000

Message: exogenous_variables may not contain repeated column names ['consumption', 'wind_solar', 'consumption'].

Example: ERROR HY000: ML003061: exogenous_variables may not contain repeated column names ['consumption', 'wind_solar', 'consumption'].

The syntax for a forecasting task includes exogenous_variables with a repeated column.

Error number: ML003062; SQLSTATE: HY000

Message: endogenous_variables argument must not be NULL.

Example: ERROR HY000: ML003062: endogenous_variables argument must not be NULL.

The syntax for a forecasting task includes endogenous_variables with a NULL argument.

Error number: ML003063; SQLSTATE: HY000

Message: exogenous_variables argument must not be NULL when provided by user.

Example: ERROR HY000: ML003063: exogenous_variables argument must not be NULL when provided by user.

The syntax for a forecasting task includes user provided exogenous_variables with a NULL argument.

Error number: ML003064; SQLSTATE: HY000

Message: Cannot exclude all models.

Example: ERROR HY000: ML003064: Cannot exclude all models.

The syntax for a forecasting task must include at least one model.

Error number: ML003065; SQLSTATE: HY000

Message: Prediction table cannot have overlapping datetime_index with train table when exogenous_variables are used. It can only forecast into future.

Example: ERROR HY000: ML003065: Prediction table cannot have overlapping datetime_index with train table when exogenous_variables are used. It can only forecast into future.

The syntax for a forecasting task includes exogenous_variables and the prediction table contains values in the datetime_index column that overlap with values in the datetime_index column in the training table.

Error number: ML003066; SQLSTATE: HY000

Message: datetime_index for test table must not have missing dates after the last date in training table. Please ensure test table starts on or before 2034-01-01 00:00:00. Currently, start date in the test table is 2036-01-01 00:00:00.

Example: ERROR HY000: ML003066: datetime_index for test table must not have missing dates after the last date in training table. Please ensure test table starts on or before 2034-01-01 00:00:00. Currently, start date in the test table is 2036-01-01 00:00:00.

The syntax for a forecasting task includes a prediction table that contains values in the datetime_index column that leave a gap to the values in the datetime_index column in the training table.

Error number: ML003067; SQLSTATE: HY000

Message: datetime_index for forecasting task must be between year 1678 and 2261.

Example: ERROR HY000: ML003067: datetime_index for forecasting task must be between year 1678 and 2261.

The syntax for a forecasting task includes values in a datetime_index column that are outside the date range from 1678 to 2261.

Error number: ML003068; SQLSTATE: HY000

Message: Last date of datetime_index in the training table 2151-01-01 00:00:00 plus the length of the table 135 must be between year 1678 and 2261.

Example: ERROR HY000: ML003068: Last date of datetime_index in the training table 2151-01-01 00:00:00 plus the length of the table 135 must be between year 1678 and 2261.

The syntax for a forecasting task includes a prediction table that has too many rows, and the values in the datetime_index column would be outside the date range from 1678 to 2261.

Error number: ML003070; SQLSTATE: 3877 (HY000)

Message: For recommendation tasks both user and item column names should be provided.

Example: ERROR 3877 (HY000): ML003070: For recommendation tasks both user and item column names should be provided.

Error number: ML003071; SQLSTATE: HY000

Message: contamination must be numeric value greater than 0 and less than 0.5.

Example: ERROR HY000: ML003071: contamination must be numeric value greater than 0 and less than 0.5.

Error number: ML003071; SQLSTATE: 3877 (HY000)

Message: item_columns can not contain repeated column names ['C4', 'C4'].

Example: ERROR 3877 (HY000): ML003071: item_columns can not contain repeated column names ['C4', 'C4'].

Error number: ML003071; SQLSTATE: 3877 (HY000)

Message: user_columns can not contain repeated column names ['C4', 'C4'].

Example: ERROR 3877 (HY000): ML003071: user_columns can not contain repeated column names ['C4', 'C4'].

Error number: ML003072; SQLSTATE: HY000

Message: Can not use more than one threshold method.

Example: ERROR HY000: ML003072: Can not use more than one threshold method.

Error number: ML003072; SQLSTATE: 3877 (HY000)

Message: Target column C3 can not be specified as a user or item column.

Example: ERROR 3877 (HY000): ML003072: Target column C3 can not be specified as a user or item column.

Error number: ML003073; SQLSTATE: HY000

Message: topk must be an integer value between 1 and length of the table, inclusively (1 <= topk <= 20).

Example: ERROR HY000: ML003073: topk must be an integer value between 1 and length of the table, inclusively (1 <= topk <= 20).

Error number: ML003073; SQLSTATE: 3877 (HY000)

Message: The users and items columns should be different.

Example: ERROR 3877 (HY000): ML003073: The users and items columns should be different.

Error number: ML003074; SQLSTATE: HY000

Message: threshold must be a numeric value between 0 and 1, inclusively (0 <= threshold <= 1).

Example: ERROR HY000: ML003074: threshold must be a numeric value between 0 and 1, inclusively (0 <= threshold <= 1).

Error number: ML003074; SQLSTATE: 3877 (HY000)

Message: Unsupported ML Operation for recommendation task.

Example: ERROR 3877 (HY000): ML003074: Unsupported ML Operation for recommendation task.

Error number: ML003075; SQLSTATE: HY000

Message: Unknown option given. This scoring metric only allows for these options: ['topk'].

Example: ERROR HY000: ML003075: Unknown option given. This scoring metric only allows for these options: ['topk'].

Error number: ML003075; SQLSTATE: 3877 (HY000)

Message: Unknown option given. Allowed options for recommendations are ['recommend', 'top'].

Example: ERROR 3877 (HY000): ML003075: Unknown option given. Allowed options for recommendations are ['recommend', 'top'].

Error number: ML003076; SQLSTATE: HY000

Message: ML_EXPLAIN, ML_EXPLAIN_ROW and ML_EXPLAIN_TABLE are not supported for anomaly_detection task.

Example: ERROR HY000: ML003076: ML_EXPLAIN, ML_EXPLAIN_ROW and ML_EXPLAIN_TABLE are not supported for anomaly_detection task.

Error number: ML003076; SQLSTATE: 3877 (HY000)

Message: The recommend option should be provided when a value for topk is assigned.

Example: ERROR 3877 (HY000): ML003076: The recommend option should be provided when a value for topk is assigned.

Error number: ML003077; SQLSTATE: HY000

Message: topk must be provided as an option when metric is set as precision_at_k.

Example: ERROR HY000: ML003077: topk must be provided as an option when metric is set as precision_at_k.

Error number: ML003077; SQLSTATE: 3877 (HY000)

Message: Unknown recommend value given. Allowed values for recommend are ['ratings', 'items', 'users'].

Example: ERROR 3877 (HY000): ML003077: Unknown recommend value given. Allowed values for recommend are ['ratings', 'items', 'users'].

Error number: ML003078; SQLSTATE: HY000

Message: anomaly_detection only allows 0 (normal) and 1 (anomaly) for labels in target column with any metric used, and they have to be integer values.

Example: ERROR HY000: ML003078: anomaly_detection only allows 0 (normal) and 1 (anomaly) for labels in target column with any metric used, and they have to be integer values.

Error number: ML003078; SQLSTATE: 3877 (HY000)

Message: Should not provide a value for topk when the recommend option is set to ratings.

Example: ERROR 3877 (HY000): ML003078: Should not provide a value for topk when the recommend option is set to ratings.

Error number: ML003079; SQLSTATE: 3877 (HY000)

Message: Provided value for option topk is not a strictly positive integer.

Example: ERROR 3877 (HY000): ML003079: Provided value for option topk is not a strictly positive integer.

Error number: ML003080; SQLSTATE: 3877 (HY000)

Message: One or more rows contains NULL or empty values. Please provide inputs without NULL or empty values for recommendation.

Example: ERROR 3877 (HY000): ML003080: One or more rows contains NULL or empty values. Please provide inputs without NULL or empty values for recommendation.

Error number: ML003081; SQLSTATE: 3877 (HY000)

Message: Options should be NULL. Options are currently not supported for this task classification.

Example: ERROR 3877 (HY000): ML003081: options should be NULL. Options are currently not supported for this task classification.

Error number: ML003082; SQLSTATE: 3877 (HY000)

Message: All supported models are excluded, but at least one model should be included.

Example: ERROR 3877 (HY000): ML003082: All supported models are excluded, but at least one model should be included.

Error number: ML003083; SQLSTATE: HY000

Message: Both user column name ['C3'] and item column name C0 must be provided as string.

Example: ERROR HY000: ML003083: Both user column name ['C3'] and item column name C0 must be provided as string.

Error number: ML003105; SQLSTATE: 3877 (HY000)

Message: Cannot recommend users to a user not present in the training table.

Example: ERROR: 3877 (HY000): ML003105: Cannot recommend users to a user not present in the training table.

Error number: ML003106; SQLSTATE: 3877 (HY000)

Message: Cannot recommend items to an item not present in the training table.

Example: ERROR 3877 (HY000): ML003106: Cannot recommend items to an item not present in the training table.

Error number: ML003107; SQLSTATE: 3877 (HY000)

Message: Users to users recommendation is not supported, please retrain your model.

Example: ERROR 3877 (HY000): ML003107: Users to users recommendation is not supported, please retrain your model.

Error number: ML003108; SQLSTATE: 3877 (HY000)

Message: Items to items recommendation is not supported, please retrain your model.

Example: ERROR 3877 (HY000): ML003108: Items to items recommendation is not supported, please retrain your model.

Error number: ML003109; SQLSTATE: HY000

Message: Invalid Model format.

Example: HY000: ML003109: Invalid Model format.

Error number: ML003111; SQLSTATE: HY000

Message: Unknown option given. Allowed options are ['batch_size'].

Example: ERROR HY000: ML003111: Unknown option given. Allowed options are ['batch_size'].

Error number: ML003112; SQLSTATE: HY000

Message: Unknown option given. Allowed options for anomaly detection are [X, Y, ...].

Example: ERROR HY000: ML003112: Unknown option given. Allowed options for anomaly detection are [X, Y, ...].

Error number: ML003114; SQLSTATE: HY000

Message: Threshold must be a numeric value.

Example: ERROR HY000: ML003114: Threshold must be a numeric value.

Error number: ML003115; SQLSTATE: HY000

Message: Empty input table after applying threshold.

Example: ERROR HY000: ML003115: Empty input table after applying threshold.

Error number: ML003116; SQLSTATE: HY000

Message: The feedback_threshold option can only be set for implicit feedback.

Example: ERROR HY000: ML003116: The feedback_threshold option can only be set for implicit feedback.

Error number: ML003117; SQLSTATE: HY000

Message: The remove_seen option can only be used with the following recommendation ['items', 'users', 'users_to_items', 'items_to_users'].

Example: ERROR HY000: ML003117: The remove_seen option can only be used with the following recommendation ['items', 'users', 'users_to_items', 'items_to_users'].

Error number: ML003118; SQLSTATE: HY000

Message: The remove_seen option must be set to either True or False. Provided input.

Example: ERROR HY000: ML003118: The remove_seen option must be set to either True or False. Provided input.

Error number: ML003119; SQLSTATE: HY000

Message: The feedback option must either be set to explicit or implicit. Provided input.

Example: ERROR HY000: ML003119: The feedback option must either be set to explicit or implicit. Provided input.

Error number: ML003120; SQLSTATE: HY000

Message: The input table needs to contain strictly more than one unique item.

Example: ERROR HY000: ML003120: The input table needs to contain strictly more than one unique item.

Error number: ML003121; SQLSTATE: HY000

Message: The input table needs to contain at least one unknown or negative rating.

Example: ERROR HY000: ML003121: The input table needs to contain at least one unknown or negative rating.

Error number: ML003122; SQLSTATE: HY000

Message: The feedback_threshold option must be numeric.

Example: ERROR HY000: ML003122: The feedback_threshold option must be numeric.

Error number: ML003123; SQLSTATE: HY000

Message: User and item columns should contain strings.

Example: ERROR HY000: ML003123: User and item columns should contain strings.

Error number: ML003124; SQLSTATE: HY000

Message: Calculation for precision_at_k metric could not complete because there are no recommended items.

Example: ERROR HY000: ML003124: Calculation for precision_at_k metric could not complete because there are no recommended items.

Error number: ML004002; SQLSTATE: HY000

Message: Output format of onnx model is not supported (output_name={%},output_shape={%},output_type={%}).

Example: HY000: ML004002: Output format of onnx model is not supported (output_name={%},output_shape={%},output_type={%}).

Error number: ML004003; SQLSTATE: HY000

Message: This ONNX model only supports fixed batch size=%.

Example: HY000: ML004003: This ONNX model only supports fixed batch size=%.

Error number: ML004005; SQLSTATE: HY000

Message: The type % in data_types_map is not supported.

Example: HY000: ML004005: The type % in data_types_map is not supported.

Error number: ML004006; SQLSTATE: HY000

Message: ML_SCORE is not supported for an onnx model that does not support batch inference.

Example: HY000: ML004006: ML_SCORE is not supported for an onnx model that does not support batch inference.

Error number: ML004007; SQLSTATE: HY000

Message: ML_EXPLAIN is not supported for an onnx model that does not support batch inference.

Example: HY000: ML004007: ML_EXPLAIN is not supported for an onnx model that does not support batch inference.

Error number: ML004008; SQLSTATE: HY000

Message: onnx model input type=% is not supported! Providing the appropriate types map using 'data_types_map' in model_metadata may resolve the issue.

Example: HY000: ML004008: onnx model input type=% is not supported! Providing the appropriate types map using 'data_types_map' in model_metadata may resolve the issue.

Error number: ML004009; SQLSTATE: HY000

Message: Input format of onnx model is not supported (onnx_input_name={%}, expected_input_shape={%}, expected_input_type={%}, data_shape={%}).

Example: HY000: ML004009: Input format of onnx model is not supported (onnx_input_name={%}, expected_input_shape={%}, expected_input_type={%}, data_shape={%}).

Error number: ML004010; SQLSTATE: HY000

Message: Output being sparse tensor with batch size > 1 is not supported.

Example: HY000: ML004010: Output being sparse tensor with batch size > 1 is not supported.

Error number: ML004010; SQLSTATE: 3877 (HY000)

Message: Received data exceeds maximum allowed length 943718400.

Example: ERROR 3877 (HY000): ML004010: Received data exceeds maximum allowed length 943718400.

Error number: ML004011; SQLSTATE: HY000

Message: predictions_name=% is not valid.

Example: HY000: ML004011: predictions_name=% is not valid.

Error number: ML004012; SQLSTATE: HY000

Message: prediction_probabilities_name=% is not valid.

Example: HY000: ML004012: prediction_probabilities_name=% is not valid.

Error number: ML004013; SQLSTATE: HY000

Message: predictions_name should be provided when task=regression and onnx model generates more than one output.

Example: HY000: ML004013: predictions_name should be provided when task=regression and onnx model generates more than one output.

Error number: ML004014; SQLSTATE: HY000

Message: Missing expected JSON key (%)

Example: ERROR HY000: ML004014: Missing expected JSON key (schema_name).

Error number: ML004014; SQLSTATE: HY000

Message: Incorrect labels_map. labels_map should include the key %

Example: HY000: ML004014: Incorrect labels_map. labels_map should include the key %

Error number: ML004015; SQLSTATE: HY000

Message: Expected JSON string type value for key (%)

Example: ERROR HY000: ML004015: Expected JSON string type value for key (schema_name).

Error number: ML004015; SQLSTATE: HY000

Message: When task=classification, if the user does not provide prediction_probabilities_name for the onnx model, ML_EXPLAIN method=% will not be supported.

Example: HY000: ML004015: When task=classification, if the user does not provide prediction_probabilities_name for the onnx model, ML_EXPLAIN method=% will not be supported. % can be "shap", "fast_shap" or "partial_dependence"

Error number: ML004016; SQLSTATE: HY000

Message: Given JSON (%, %, %, %, %) is larger than maximum permitted size.

Example: ERROR HY000: ML004016: Given JSON (prediction_row prediction_row prediction_row prediction_row prediction_row prediction_row prediction_row prediction_row) is larger than maximum permitted size.

Error number: ML004016; SQLSTATE: HY000

Message: Invalid base64-encoded ONNX string.

Example: HY000: ML004016: Invalid base64-encoded ONNX string.

Error number: ML004017; SQLSTATE: HY000

Message: Invalid ONNX model.

Example: HY000: ML004017: Invalid ONNX model.

Error number: ML004017; SQLSTATE: 3877 (HY000)

Message: Input value to plugin variable is too long.

Example: ERROR 3877 (HY000): ML004017: Input value to plugin variable is too long.

Error number: ML004018; SQLSTATE: HY000

Message: Parsing JSON arg: Invalid value. failed!

Example: ERROR HY000: ML004018: Parsing JSON arg: Invalid value. failed!

Error number: ML004018; SQLSTATE: HY000

Message: There are issues in running inference session for the onnx model. This might have happened due to inference on inputs with incorrect names, shapes or types.

Example: HY000: ML004018: There are issues in running inference session for the onnx model. This might have happened due to inference on inputs with incorrect names, shapes or types.

Error number: ML004019; SQLSTATE: HY000

Message: Expected JSON object type value for key (%)

Example: ERROR HY000: ML004019: Expected JSON object type value for key (JSON root).

Error number: ML004019; SQLSTATE: HY000

Message: The computed predictions do not have the right format. This might have happened because the provided predictions_name is not correct.

Example: HY000: ML004019: The computed predictions do not have the right format. This might have happened because the provided predictions_name is not correct.

Error number: ML004020; SQLSTATE: HY000

Message: Operation was interrupted by the user.

Example: ERROR HY000: ML004020: Operation was interrupted by the user.

If a user-initiated interruption, Ctrl-C, is detected during the first phase of HeatWave AutoML model and table load where a MySQL parallel scan is used in the HeatWave plugin to read data as of MySQL database and send it to the HeatWave Cluster, error messaging is handled by the MySQL parallel scan function and directed to ERROR 1317 (70100): Query execution was interrupted.. The ERROR 1317 (70100) message is reported to the client instead of the ML004020 error message.

Error number: ML004020; SQLSTATE: HY000

Message: The computed prediction probabilities do not have the right format. This might have happened because the provided prediction_probabilities_name is not correct.

Example: HY000: ML004020: The computed prediction probabilities do not have the right format. This might have happened because the provided prediction_probabilities_name is not correct.

Error number: ML004021; SQLSTATE: HY000

Message: The onnx model and dataset do not match. The onnx model's input=% is not a column in the dataset.

Example: HY000: ML004021: The onnx model and dataset do not match. The onnx model's input=% is not a column in the dataset.

Error number: ML004022; SQLSTATE: HY000

Message: The user does not have access privileges to %.

Example: ERROR HY000: ML004022: The user does not have access privileges to ml.foo.

Error number: ML004022; SQLSTATE: HY000

Message: Labels in y_true and y_pred should be of the same type. Got y_true=% and y_pred=YYY. Make sure that the predictions provided by the classifier coincides with the true labels.

Example: HY000: ML004022: Labels in y_true and y_pred should be of the same type. Got y_true=% and y_pred=YYY. Make sure that the predictions provided by the classifier coincides with the true labels.

Error number: ML004026; SQLSTATE: HY000

Message: A column (%) with an unsupported column type (%) detected!

Example: ERROR HY000: ML004026: A column (D1) with an unsupported column type (DATETIME) detected!

Error number: ML004051; SQLSTATE: HY000

Message: Invalid operation.

Example: ERROR HY000: ML004051: Invalid operation.

Error number: ML004999; SQLSTATE: HY000

Message: Error during Machine Learning.

Example: ERROR HY000: ML004999: Error during Machine Learning.

Error number: ML006006; SQLSTATE: 45000

Message: target_column_name should be NULL or empty.

Example: ERROR 45000: ML006006: target_column_name should be NULL or empty.

Error number: ML006017; SQLSTATE: 45000

Message: model_handle already exists in the Model Catalog.

Example: 45000: ML006017: model_handle already exists in the Model Catalog.

Error number: ML006020; SQLSTATE: 45000

Message: model_metadata should be a JSON object.

Example: 45000: ML006020: model_metadata should be a JSON object.

Error number: ML006021; SQLSTATE: 45000

Message: contamination has to be passed with anomaly_detection task.

Example: ERROR 45000: ML006021: contamination has to be passed with anomaly_detection task.

Error number: ML006022; SQLSTATE: 45000

Message: Unsupported task.

Example: ERROR 45000: ML006022: Unsupported task.

Error number: ML006023; SQLSTATE: 45000

Message: "No model object found" will be raised.

Example: 45000: ML006023: "No model object found" will be raised.

Error number: ML006027; SQLSTATE: 1644 (45000)

Message: Received results exceed `max_allowed_packet`. Please increase it or lower input options value to reduce result size.

Example: ERROR 1644 (45000): ML006027: Received results exceed `max_allowed_packet`. Please increase it or lower input options value to reduce result size.

Error number: ML006029; SQLSTATE: 45000

Message: model_handle is not Ready.

Example: 45000: ML006029: model_handle is not Ready.

Error number: ML006030; SQLSTATE: 45000

Message: onnx_inputs_info must be a json object.

Example: ERROR 45000: ML006030: onnx_inputs_info must be a json object.

Error number: ML006031; SQLSTATE: 45000

Message: Unsupported format.

Example: 45000: ML006031: Unsupported format.

Error number: ML006031; SQLSTATE: 45000

Message: onnx_outputs_info must be a json object.

Example: ERROR 45000: ML006031: onnx_outputs_info must be a json object.

Error number: ML006032; SQLSTATE: 45000

Message: data_types_map must be a json object.

Example: ERROR 45000: ML006032: data_types_map must be a json object.

Error number: ML006033; SQLSTATE: 45000

Message: labels_map must be a json object.

Example: ERROR 45000: ML006033: labels_map must be a json object.

Error number: ML006034; SQLSTATE: 45000

Message: onnx_outputs_info must be provided for task=classification.

Example: ERROR 45000: ML006034: onnx_outputs_info must be provided for task=classification.

Error number: ML006035; SQLSTATE: 45000

Message: onnx_outputs_info must only be provided for classification and regression tasks.

Example: ERROR 45000: ML006035: onnx_outputs_info must only be provided for classification and regression tasks.

Error number: ML006036; SQLSTATE: 45000

Message: % is not a valid key in onnx_inputs_info.

Example: ERROR 45000: ML006036: % is not a valid key in onnx_inputs_info.

Error number: ML006037; SQLSTATE: 45000

Message: % is not a valid key in onnx_outputs_info.

Example: ERROR 45000: ML006037: % is not a valid key in onnx_outputs_info.

Error number: ML006038; SQLSTATE: 45000

Message: For task=classification, at least one of predictions_name and prediction_probabilities_name must be provided.

Example: ERROR 45000: ML006038: For task=classification, at least one of predictions_name and prediction_probabilities_name must be provided.

Error number: ML006039; SQLSTATE: 45000

Message: prediction_probabilities_name must only be provided for task=classification.

Example: ERROR 45000: ML006039: prediction_probabilities_name must only be provided for task=classification.

Error number: ML006040; SQLSTATE: 45000

Message: predictions_name must not be an empty string.

Example: ERROR 45000: ML006040: predictions_name must not be an empty string.

Error number: ML006041; SQLSTATE: 45000

Message: prediction_probabilities_name must not be an empty string.

Example: ERROR 45000: ML006041: prediction_probabilities_name must not be an empty string.

Error number: ML006042; SQLSTATE: 45000

Message: labels_map must only be provided for task=classification.

Example: ERROR 45000: ML006042: labels_map must only be provided for task=classification.

Error number: ML006043; SQLSTATE: 45000

Message: When labels_map is provided, prediction_probabilities_name must also be provided.

Example: ERROR 45000: ML006043: When labels_map is provided, prediction_probabilities_name must also be provided.

Error number: ML006044; SQLSTATE: 45000

Message: When labels_map is provided, predictions_name must not be provided.

Example: ERROR 45000: ML006044: When labels_map is provided, predictions_name must not be provided.

Error number: ML006045; SQLSTATE: 45000

Message: ML_SCORE is not supported for a % task.

Example: ERROR 45000: ML006045: ML_SCORE is not supported for a % task.

Error number: ML006046; SQLSTATE: 45000

Message: ML_EXPLAIN is not supported for a % task.

Example: ERROR 45000: ML006046: ML_EXPLAIN is not supported for a % task.

Error number: ML006047; SQLSTATE: 45000

Message: onnx_inputs_info must only be provided when format='ONNX'.

Example: ERROR 45000: ML006047: onnx_inputs_info must only be provided when format='ONNX'.

Error number: ML006048; SQLSTATE: 45000

Message: onnx_outputs_info must only be provided when format='ONNX'.

Example: ERROR 45000: ML006048: onnx_outputs_info must only be provided when format='ONNX'.

Error number: ML006049; SQLSTATE: 45000

Message: The length of a key provided in onnx_inputs_info should not be greater than 32 characters.

Example: ERROR 45000: ML006049: The length of a key provided in onnx_inputs_info should not be greater than 32 characters.

Error number: ML006050; SQLSTATE: 45000

Message: The length of a key provided in onnx_outputs_info should not be greater than 32 characters.

Example: ERROR 45000: ML006050: The length of a key provided in onnx_outputs_info should not be greater than 32 characters.

Error number: ML006051; SQLSTATE: 45000

Message: Invalid ONNX model.

Example: ERROR 45000: ML006051: Invalid ONNX model.

Error number: ML006052; SQLSTATE: 45000

Message: Input table is empty. Please provide a table with at least one row.

Example: ERROR 45000: ML006052: Input table is empty. Please provide a table with at least one row.

Error number: ML006053; SQLSTATE: 45000

Message: Insufficient access rights. Grant user with correct privileges (SELECT, DROP, CREATE, INSERT, ALTER) on input schema.

Example: ERROR 45000: ML006053: Insufficient access rights. Grant user with correct privileges (SELECT, DROP, CREATE, INSERT, ALTER) on input schema.

Error number: ML006054; SQLSTATE: 45000

Message: Input table already contains a column named '_id'. Please provide an input table without such column.

Example: ERROR 45000: ML006054: Input table already contains a column named '_id'. Please provide an input table without such column.

Error number: ML006055; SQLSTATE: 45000

Message: Options must be a JSON_OBJECT.

Example: ERROR 45000: ML006055: Options must be a JSON_OBJECT.

Error number: ML006056; SQLSTATE: 45000

Message: batch_size must be an integer between 1 and %.

Example: ERROR 45000: ML006056: batch_size must be an integer between 1 and %.

Error number: ML006070; SQLSTATE: 45000

Message: model_list is currently not supported for anomaly_detection.

Example: ERROR 45000: ML006070: model_list is currently not supported for anomaly_detection.

Error number: ML006071; SQLSTATE: 45000

Message: exclude_model_list is currently not supported for anomaly_detection.

Example: ERROR 45000: ML006071: exclude_model_list is currently not supported for anomaly_detection.

Error number: ML006072; SQLSTATE: 45000

Message: optimization_metric is currently not supported for anomaly_detection.

Example: ERROR 45000: ML006072: optimization_metric is currently not supported for anomaly_detection.