teradataml 20.0.0.1__py3-none-any.whl → 20.0.0.3__py3-none-any.whl

teradataml/data/jsons/sqle/17.20/TD_Pivoting.json

@@ -0,0 +1,280 @@
+{
+    "json_schema_major_version": "1",
+    "json_schema_minor_version": "1",
+    "json_content_version": "1",
+    "function_name": "TD_Pivoting",
+    "function_version": "1.0",
+    "function_alias_name": "TD_Pivoting",
+    "function_type": "fastpath",
+    "function_category": "Feature Engineering Transform",
+    "function_r_name": "aa.td.pivoting",
+    "short_description": "This function is used to pivot the data i.e. change the data from sparse format to dense format.",
+    "long_description": "This function is used to pivot the data i.e. change the data from sparse format to dense format.",
+    "input_tables": [
+      {
+        "requiredInputKind": [
+          "PartitionByKey"
+        ],
+        "isOrdered": false,
+        "partitionByOne": false,
+        "name": "InputTable",
+        "alternateNames": [],
+        "isRequired": true,
+        "rDescription": "Specifies the table containing the input data to be pivoted.",
+        "description": "Specifies the table containing the input data to be pivoted.",
+        "datatype": "TABLE_ALIAS",
+        "allowsLists": false,
+        "rName": "data",
+        "useInR": true,
+        "rOrderNum": 1
+      }
+    ],
+    "argument_clauses": [
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "ALL"
+        ],
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "PartitionColumns",
+        "alternateNames": [],
+        "isRequired": true,
+        "rDescription": "Specify the name of the input table columns on which to partition the input.",
+        "description": "Specify the name of the input table columns on which to partition the input.",
+        "datatype": "COLUMNS",
+        "allowsLists": true,
+        "rName": "partition.columns",
+        "useInR": true,
+        "rOrderNum": 2
+      },
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "ALL"
+        ],
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "TargetColumns",
+        "alternateNames": [],
+        "isRequired": true,
+        "rDescription": "Specify the columns from the input table which contains the data for pivoting.",
+        "description": "Specify the columns from the input table which contains the data for pivoting.",
+        "datatype": "COLUMNS",
+        "allowsLists": true,
+        "rName": "target.columns",
+        "useInR": true,
+        "rOrderNum": 3
+      },
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "ALL"
+        ],
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "Accumulate",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specifies the input table columns to copy to the output table. By default, the function copies no input table columns to the output table.",
+        "description": "Specifies the input table columns to copy to the output table. By default, the function copies no input table columns to the output table.",
+        "datatype": "COLUMNS",
+        "allowsLists": true,
+        "rName": "accumulate",
+        "useInR": true,
+        "rOrderNum": 4
+      },
+      {
+        "lowerBound": 1,
+        "upperBound": 2147483647,
+        "lowerBoundType": "INCLUSIVE",
+        "upperBoundType": "INCLUSIVE",
+        "allowNaN": false,
+        "name": "RowsPerPartition",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify the integer value which will specify the maximum number of rows in the partition.",
+        "description": "Specify the integer value which will specify the maximum number of rows in the partition.",
+        "datatype": "INTEGER",
+        "allowsLists": false,
+        "rName": "rows.per.partition",
+        "useInR": true,
+        "rOrderNum": 5
+      },
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "STRING"
+        ],
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "PivotColumn",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify the name of the input table column that contains the pivot keys.",
+        "description": "Specify the name of the input table column that contains the pivot keys.",
+        "datatype": "COLUMNS",
+        "allowsLists": false,
+        "rName": "pivot.column",
+        "useInR": true,
+        "rOrderNum": 6
+      },
+      {
+        "permittedValues": [],
+        "isOutputColumn": false,
+        "checkDuplicate": true,
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "PivotKeys",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "If you specify the PivotColumn argument, then this argument specifies the names of the pivot keys.",
+        "description": "If you specify the PivotColumn argument, then this argument specifies the names of the pivot keys.",
+        "datatype": "STRING",
+        "allowsLists": true,
+        "rName": "pivot.keys",
+        "useInR": true,
+        "rOrderNum": 7
+      },
+      {
+        "permittedValues": [],
+        "isOutputColumn": false,
+        "checkDuplicate": true,
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "PivotKeysAlias",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "If you specify the PivotKeys argument, then this argument specifies the alias names of the pivot keys.",
+        "description": "If you specify the PivotKeys argument, then this argument specifies the alias names of the pivot keys.",
+        "datatype": "STRING",
+        "allowsLists": true,
+        "rName": "pivot.keys.alias",
+        "useInR": true,
+        "rOrderNum": 8
+      },
+      {
+        "permittedValues": [],
+        "isOutputColumn": false,
+        "checkDuplicate": false,
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "DefaultPivotValues",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify exactly one default value for each pivot_key . The nth default_pivot_value applies to the nth pivot_key.",
+        "description": "Specify exactly one default value for each pivot_key . The nth default_pivot_value applies to the nth pivot_key.",
+        "datatype": "STRING",
+        "allowsLists": true,
+        "rName": "default.pivot.values",
+        "useInR": true,
+        "rOrderNum": 9
+      },
+      {
+        "permittedValues": [],
+        "isOutputColumn": false,
+        "checkDuplicate": false,
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "Aggregation",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify the aggregation for the target columns. Aggregation can be provided as one of the single value {CONCAT | UNIQUE_CONCAT | SUM | MIN | MAX | AVG}  which will be applicable to all target columns or you can specify multiple values for multiple target columns in following format: ColumnName:{CONCAT|UNIQUE_CONCAT|SUM|MIN|MAX|AVG} [,...].",
+        "description": "Specify the aggregation for the target columns. Aggregation can be provided as one of the single value {CONCAT | UNIQUE_CONCAT | SUM | MIN | MAX | AVG}  which will be applicable to all target columns or you can specify multiple values for multiple target columns in following format: ColumnName:{CONCAT|UNIQUE_CONCAT|SUM|MIN|MAX|AVG} [,...].",
+        "datatype": "STRING",
+        "allowsLists": true,
+        "rName": "aggregation",
+        "useInR": true,
+        "rOrderNum": 10
+      },
+      {
+        "permittedValues": [],
+        "isOutputColumn": false,
+        "checkDuplicate": false,
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "Delimiters",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify the delimiter to be used for concatenating the values of a target column. A delimiter is a single character string. You can specify a single delimiter values which will be applicable to all target columns or you can specify multiple delimiter values for multiple target columns in following format: ColumnName:single_char [,...].",
+        "description": "Specify the delimiter to be used for concatenating the values of a target column. A delimiter is a single character string. You can specify a single delimiter values which will be applicable to all target columns or you can specify multiple delimiter values for multiple target columns in following format: ColumnName:single_char [,...].",
+        "datatype": "STRING",
+        "allowsLists": true,
+        "rName": "delimiters",
+        "useInR": true,
+        "rOrderNum": 11
+      },
+      {
+        "permittedValues": [],
+        "isOutputColumn": false,
+        "checkDuplicate": false,
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "CombinedColumnSizes",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify maximum size of the concatenated string. You can specify a single values which will be applicable to all target columns or you can specify multiple size value for multiple target columns in following format: ColumnName:size_value [,...].",
+        "description": "Specify maximum size of the concatenated string. You can specify a single values which will be applicable to all target columns or you can specify multiple size value for multiple target columns in following format: ColumnName:size_value [,...].",
+        "datatype": ["STRING", "INTEGER"],
+        "allowsLists": true,
+        "rName": "combined.column.sizes",
+        "useInR": true,
+        "rOrderNum": 12
+      },
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "ALL"
+        ],
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "TruncateColumns",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify columns from the target columns for which you want to truncate the concatenated string, if it is longer than the specified size. ",
+        "description": "Specify columns from the target columns for which you want to truncate the concatenated string, if it is longer than the specified size. ",
+        "datatype": "COLUMNS",
+        "allowsLists": true,
+        "rName": "truncate.columns",
+        "useInR": true,
+        "rOrderNum": 13
+      },
+      {
+        "permittedValues": [],
+        "isOutputColumn": true,
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+
+        "name": "OutputColumnNames",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify the column name to be used for the output column. The nth column name value applies to the nth output column.",
+        "description": "Specify the column name to be used for the output column. The nth column name value applies to the nth output column.",
+        "datatype": "STRING",
+        "allowsLists": true,
+        "rName": "output.column.names",
+        "useInR": true,
+        "rOrderNum": 14
+      }
+    ]
+  }

teradataml/data/jsons/sqle/17.20/TD_Shap.json

@@ -0,0 +1,222 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "1",
+  "json_content_version": "1",
+  "function_name": "TD_Shap",
+  "function_version": "1.0",
+  "commence_db_version": "",
+  "change_db_version": "",
+  "function_type": "fastpath",
+  "function_category": "Model Interpretation",
+  "function_alias_name": "TD_Shap",
+  "function_r_name": "aa.TD_Shap",
+  "ref_function_r_name": "aa.td_glm, aa.td_decisionforest, aa.td_xgboost",
+  "short_description": "Fast path function to get explanation for individual predictions (feature contributions) in a machine learning model",
+  "long_description": "Fast path function to get explanation for individual predictions (feature contributions) in a machine learning model based on the cooperative game theory optimal Shapley values.",
+  "input_tables": [
+    {
+      "name": "InputTable",
+      "isRequired": true,
+      "datatype": "TABLE_ALIAS",
+      "partitionByOne": false,
+      "isOrdered": false,
+      "omitPossible": false,
+      "alternateNames": [],
+      "rDescription": "Specifies the name of the table that contains input dataset.",
+      "description": "Specifies the name of the table that contains input dataset.",
+      "allowsLists": false,
+      "rName": "data",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "name": "ModelTable",
+      "isRequired": true,
+      "datatype": "TABLE_ALIAS",
+      "isOrdered": false,
+      "partitionByOne": false,
+      "rDescription": "Specifies the table containing the model data.",
+      "description": "Specifies the table containing the model data.",
+      "allowsLists": false,
+      "rName": "object",
+      "useInR": true,
+      "rFormulaUsage": false,
+      "rOrderNum": 2
+    }
+  ],
+    "output_tables": [
+    {
+      "name": "GlobalExplanation",
+      "isRequired": false,
+      "datatype": "TABLE_NAME",
+      "isOutputTable": true,
+      "omitPossible": false,
+      "alternateNames": [],
+      "rDescription": "Specifies the mean absolute shapley values for each input feature.",
+      "description": "Specifies the mean absolute shapley values for each input feature.",
+      "allowsLists": false,
+      "rName": "output.table",
+      "useInR": true,
+      "rOrderNum": 3
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC"
+      ],
+      "name": "IDColumn",
+      "isRequired": true,
+      "datatype": "COLUMNS",
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "alternateNames": [],
+      "rDescription": "Specifies the name of the input table column that contains the IDColumn.",
+      "description": "Specify the name of the InputTable column that contains the unique value to identify the each sample.",
+      "allowsLists": false,
+      "rName": "id.column",
+      "useInR": true,
+      "rOrderNum": 3
+    },
+    {
+      "permittedValues": [
+        "TD_GLM",
+        "TD_DECISIONFOREST",
+        "TD_XGBOOST"
+      ],
+      "name": "TrainingFunction",
+      "isRequired": true,
+      "datatype": "STRING",
+      "defaultValue": "TD_GLM",
+      "isOutputColumn": false,
+      "alternateNames": [],
+      "rDescription": "Specifies the model type name.",
+      "description": "Specifies the model type name on which we want to get explaination for individual predictions (feature contributions).",
+      "allowsLists": false,
+      "rName": "training.function",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "permittedValues": [
+        "REGRESSION",
+        "CLASSIFICATION"
+      ],
+      "name": "ModelType",
+      "isRequired": true,
+      "datatype": "STRING",
+      "defaultValue": "Regression",
+      "isOutputColumn": false,
+      "alternateNames": [],
+      "rDescription": "specifies the operation to be performed on input table.",
+      "description": "specifies the operation to be performed on input table based on target column",
+      "allowsLists": false,
+      "rName": "model.type",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC"
+      ],
+      "name": "InputColumns",
+      "isRequired": true,
+      "datatype": "COLUMNS",
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "alternateNames": [],
+      "rDescription": "Specify the names of the input table columns that need to be used for training the model (predictors, features or independent variables).",
+      "description": "Specify the names of the input table columns that need to be used for training the model (predictors, features or independent variables).",
+      "allowsLists": true,
+      "rName": "input.columns",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "name": "Detailed",
+      "isRequired": false,
+      "datatype": "BOOLEAN",
+      "isOutputColumn": false,
+      "defaultValue": false,
+      "alternateNames": [],
+      "rDescription": "Specifies whether to output detailed shap information about the forest trees.",
+      "description": "Specifies whether to output detailed shap information about the forest trees i.e. the decision tree and the specific tree information.",
+      "allowsLists": false,
+      "rName": "detailed",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "name": "Accumulate",
+      "isRequired": false,
+      "datatype": "COLUMNS",
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "alternateNames": [],
+      "rDescription": "Specifies the names of the input columns to copy to the output table.",
+      "description": "Specifies the names of the input columns to copy to the output table.",
+      "allowsLists": true,
+      "rName": "accumulate",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "name": "NumParallelTrees",
+      "isRequired": false,
+      "datatype": "INTEGER",
+      "defaultValue": 1000,
+      "lowerBound": 1,
+      "upperBound": 10000,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "alternateNames": [],
+      "rDescription": "Specify the number of parallel boosted trees.Each boosted tree operates on a sample of data that fits in an AMP's memory. By default, NumBoostedTrees is chosen equal to the number of AMPs with data.",
+      "description": "Specify the number of parallel boosted trees.Each boosted tree operates on a sample of data that fits in an AMP's memory. By default, NumBoostedTrees is chosen equal to the number of AMPs with data.",
+      "allowsLists": false,
+      "rName": "num.parallel.trees",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "name": "NumBoostRounds",
+      "isRequired": false,
+      "datatype": "INTEGER",
+      "defaultValue": 10,
+      "lowerBound": 1,
+      "upperBound": 100000,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "alternateNames": [],
+      "rDescription": "Specifies the number of iterations to boost the weak classifiers. The iterations must be an INTEGER in the range [1, 100000].",
+      "description": "Specifies the number of iterations to boost the weak classifiers. The iterations must be an INTEGER in the range [1, 100000].",
+      "allowsLists": false,
+      "rName": "num.boost.rounds",
+      "useInR": true,
+      "rOrderNum": 10
+    }
+  ]
+}

teradataml/data/jsons/sqle/17.20/TD_TFIDF.json

@@ -0,0 +1,162 @@
+{
+    "json_schema_major_version": "1",
+    "json_schema_minor_version": "1",
+    "json_content_version": "1",
+    "function_name": "TD_TFIDF",
+    "function_version": "1.0",
+    "function_type": "fastpath",
+    "function_category": "Feature Engineering Transform",
+    "function_alias_name": "TD_TFIDF",
+    "function_r_name": "td.tfidf",
+    "short_description": "This function is used to take any document set and compute the Term Frequency (TF), Inverse Document Frequency (IDF), and Term Frequency * Inverse Document Frequency (TF-IDF) scores for each term.",
+    "long_description": "This function is used to take any document set and compute the Term Frequency (TF), Inverse Document Frequency (IDF), and Term Frequency * Inverse Document Frequency (TF-IDF) scores for each term.",
+    "input_tables": [
+      {
+        "requiredInputKind": [
+          "PartitionByAny"
+        ],
+        "isOrdered": false,
+        "partitionByOne": false,
+        "name": "InputTable",
+        "alternateNames": [],
+        "isRequired": true,
+        "rDescription": "The table that contains the document id and the term.",
+        "description": "The table that contains the document id and the term.",
+        "datatype": "TABLE_ALIAS",
+        "allowsLists": false,
+        "rName": "data",
+        "useInR": true,
+        "rOrderNum": 1
+      }
+    ],
+    "argument_clauses": [
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "INTEGER"
+        ],
+        "requiredLength": 1,
+        "matchLengthOfArgument": "",
+        "allowPadding": true,
+        "name": "DocIdColumn",
+        "alternateNames": [],
+        "isRequired": true,
+        "rDescription": "Specifies the name of the input table column that contains the document identifier.",
+        "description": "Specifies the name of the input table column that contains the document identifier.",
+        "datatype": "COLUMN_NAMES",
+        "allowsLists": false,
+        "rName": "doc.id.column",
+        "useInR": true,
+        "rOrderNum": 2
+      },
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "STRING"
+        ],
+        "requiredLength": 1,
+        "matchLengthOfArgument": "",
+        "allowPadding": true,
+        "name": "TokenColumn",
+        "alternateNames": [],
+        "isRequired": true,
+        "rDescription": "Specifies the name of the input table column that contains the tokens.",
+        "description": "Specifies the name of the input table column that contains the tokens.",
+        "datatype": "COLUMN_NAMES",
+        "allowsLists": false,
+        "rName": "token.column",
+        "useInR": true,
+        "rOrderNum": 3
+      },
+      {
+        "permittedValues": [
+          "BOOL",
+          "COUNT",
+          "NORMAL",
+          "LOG",
+          "AUGMENT"
+        ],
+        "defaultValue": "NORMAL",
+        "isOutputColumn": false,
+        "name": "TFNormalization",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specifies the normalization method for calculating the term frequency (TF). Default: 'NORMAL'.",
+        "description": "Specifies the normalization method for calculating the term frequency (TF). Default: 'NORMAL'.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "rName": "tf.normalization",
+        "useInR": true,
+        "rOrderNum": 4
+      },
+      {
+        "permittedValues": [
+          "UNARY",
+          "LOG",
+          "LOGNORM",
+          "SMOOTH"
+        ],
+        "defaultValue": "LOG",
+        "isOutputColumn": false,
+        "name": "IDFNormalization",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specifies the normalization method for calculating the inverse document frequency (IDF). Default: 'LOG'.",
+        "description": "Specifies the normalization method for calculating the inverse document frequency (IDF). Default: 'LOG'.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "rName": "idf.normalization",
+        "useInR": true,
+        "rOrderNum": 5
+      },
+      {
+        "permittedValues": [
+          "L2",
+          "L1",
+          "NONE"
+        ],
+        "defaultValue": "NONE",
+        "isOutputColumn": false,
+        "name": "Regularization",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specifies the regularization method for calculating the TF-IDF score. Default: 'NONE'.",
+        "description": "Specifies the regularization method for calculating the TF-IDF score. Default: 'NONE'.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "rName": "regularization",
+        "useInR": true,
+        "rOrderNum": 6
+      },
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": [],
+        "allowedTypeGroups": [
+          "ALL"
+        ],
+        "matchLengthOfArgument": "",
+        "allowPadding": true,
+        "name": "Accumulate",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specifies the names of the input table columns to copy to the output table.",
+        "description": "Specifies the names of the input table columns to copy to the output table.",
+        "datatype": "COLUMNS",
+        "allowsLists": true,
+        "rName": "accumulate",
+        "useInR": true,
+        "rOrderNum": 7
+      }
+    ]
+  }

teradataml/data/jsons/sqle/17.20/TD_TextParser.json

@@ -80,7 +80,7 @@
 			"description": "Specifies whether to convert input text to lowercase.",
 			"datatype": "BOOLEAN",
 			"allowsLists": false,
-			"rName": "covert.to.lowercase",
+			"rName": "convert.to.lowercase",
 			"useInR": true,
 			"rOrderNum": 4
 		},