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

teradataml/data/jsons/sqle/20.00/TD_SMOTE.json

@@ -0,0 +1,266 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "2",
+  "json_content_version": "1",
+  "function_name": "TD_SMOTE",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Feature Engineering Transform Functions",
+  "function_alias_name": "TD_SMOTE",
+  "function_r_name": "aa.td_smote",
+  "ref_function_r_name": "aa.td_smote",
+  "short_description": "This function generates data by oversampling a minority class.",
+  "long_description": "This function generates data by oversampling a minority class using smote, adasyn, borderline-2 or smote-nc algorithms.",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the table containing the input data.",
+      "description": "Specifies the table containing the input data.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "data",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "EncodingsTable",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the table created with TD_OrdinalEncodingFit output, using the categorical input columns as TargetColumns. Used and required only with smotenc.",
+      "description": "Specifies the table creted with TD_OrdinalEncodingFit output, using the categorical input columns as TargetColumns. Used and required only with smotenc.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "encoding.data",
+      "useInR": true,
+      "rOrderNum": 2
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "INTEGER"
+      ],
+
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "IDColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "specifies the name of the column that uniquely identifies a data sample in the input table.",
+      "description": "specifies the name of the column that uniquely identifies a data sample in the input table.",
+      "datatype": "COLUMNS",
+      "allowsLists": false,
+      "rName": "id.column",
+      "useInR": true,
+      "rOrderNum": 3
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC"
+      ],
+      
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "ResponseColumn",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "specifies the name of the input table column that contains the numeric value to be used as the response value for a sample.",
+      "description": "specifies the name of the input table column that contains the numeric value to be used as the response value for a sample.",
+      "datatype": "COLUMNS",
+      "allowsLists": false,
+      "rName": "response.column",
+      "useInR": true,
+      "rOrderNum": 4
+    },    
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "InputColumns",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "specifies the name of the input table columns that the function uses for oversampling.",
+      "description": "specifies the name of the input table columns that the function uses for oversampling.",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "input.columns",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "STRING"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "CategoricalInputColumns",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "specifies the name of the categorical columns in the input table that the function uses for oversampling with smotenc.",
+      "description": "specifies the name of the categorical columns in the input table that the function uses for oversampling with smotenc.",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "categorical.columns",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "isOutputColumn": false,
+      "name": "MedianStandardDeviation",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "specifies the median of the standard deviations computed over the numerical input columns. Required only with smotenc.",
+      "description": "specifies the median of the standard deviations computed over the numerical input columns. Required only with smotenc.",
+      "datatype": "DOUBLE",
+      "allowsLists": false,
+      "rName": "median.standard.deviation",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "isOutputColumn": false,
+      "name": "MinorityClass",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "specifies the minority class for which synthetic samples need to be generated. The label for minority class under response column must be numeric integer.",
+      "description": "specifies the minority class for which synthetic samples need to be generated. The label for minority class under response column must be numeric integer.",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "minority.class",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "isOutputColumn": false,
+      "allowNaN": false,
+      "name": "OversamplingFactor",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "specifies the factor for oversampling the minority class.",
+      "description": "specifies the factor for oversampling the minority class.",
+      "datatype": "DOUBLE",
+      "allowsLists": false,
+      "rName": "oversampling.factor",
+      "useInR": true,
+      "rOrderNum": 9
+    },       
+    {
+      "permittedValues": ["smote", "adasyn", "borderline","smotenc"],
+      "isOutputColumn": false,
+      "defaultValue": "smote",
+      "name": "SamplingStrategy",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "specifies the oversampling algorithm to be used to create synthetic samples.",
+      "description": "specifies the oversampling algorithm to be used to create synthetic samples.",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "sampling.strategy",
+      "useInR": true,
+      "rOrderNum": 10
+    },
+    {
+      "defaultValue": true,
+      "isOutputColumn": false,
+      "name": "FillSampleID",
+      "isRequired": false,
+      "rDescription": "A boolean flag which specifies whether the function should write out the id of the observation used to generate the corresponding new synthetic observations.",
+      "description": "A boolean flag which specifies whether the function should write out the id of the observation used to generate the corresponding new synthetic observations.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "fill.sampleid",
+      "useInR": true,
+      "rOrderNum": 11
+    },
+    {
+      "permittedValues": ["sample", "neighbor", "null"],
+      "isOutputColumn": false,
+      "defaultValue": "sample",
+      "name": "ValueForNonInputColumns",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the value to put in a sample column for columns not specified as input columns.",
+      "description": "Specifies the value to put in a sample column for columns not specified as input columns.",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "noninput.columns.value",
+      "useInR": true,
+      "rOrderNum": 12
+    }, 
+    {
+      "defaultValue": 5,
+      "lowerBound": 2,
+      "upperBound": 100,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "NumberOfNeighbors",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the number of nearest neighbors for choosing the sample to be used in oversampling.",
+      "description": "Specifies the number of nearest neighbors for choosing the sample to be used in oversampling.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "n.neighbors",
+      "useInR": true,
+      "rOrderNum": 13
+    },
+    {
+      "lowerBound": 0,
+      "upperBound": 186006,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "Seed",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the random seed the algorithm uses for repeatable results. The function uses the seed for random interpolation and generate the synthetic sample.",
+      "description": "Specify the random seed the algorithm uses for repeatable results. The function uses the seed for random interpolation and generate the synthetic sample.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "seed",
+      "useInR": true,
+      "rOrderNum": 14
+    } 
+  ]
+}
+

teradataml/data/jsons/sqle/20.00/TD_VectorDistance.json

@@ -0,0 +1,278 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "1",
+  "json_content_version": "1",
+  "function_name": "TD_VectorDistance",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Model Training",
+  "function_alias_name": "TD_VectorDistance",
+  "function_r_name": "aa.td_vectordistance",
+  "short_description": "fastpath function which takes a table of target vectors and a table of reference vectors(optional) and returns a table that contains the distance between the target-reference pair.",
+  "long_description": "fastpath function which takes a table of target vectors and a table of reference vectors(optional) and returns a table that contains the distance between the target-reference pair.",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "TargetTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The relation that contains target table vectors.",
+      "description": "The relation that contains target table vectors.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "target.table",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "ReferenceTable",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "The relation that contains reference table vectors.",
+      "description": "The relation that contains reference table vectors.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "reference.table",
+      "useInR": true,
+      "rOrderNum": 2
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "TargetTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "INTEGER"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "TargetIDColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the name of the target table column that contains identifiers of the target table vectors.",
+      "description": "Specifies the name of the target table column that contains identifiers of the target table vectors.",
+      "datatype": "COLUMNS",
+      "allowsLists": false,
+      "rName": "target.id.column",
+      "useInR": true,
+      "rOrderNum": 3
+    },
+    {
+      "targetTable": [
+        "TargetTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC","AIVECTOR","BYTE","VARBYTE"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "TargetFeatureColumns",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the names of the target table columns that contain features of the target table vectors.",
+      "description": "Specifies the names of the target table columns that contain features of the target table vectors.",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "target.feature.columns",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "targetTable": [
+        "ReferenceTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "INTEGER"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "RefIDColumn",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the name of the reference table column that contains identifiers of the reference table vectors.",
+      "description": "Specifies the name of the reference table column that contains identifiers of the reference table vectors.",
+      "datatype": "COLUMNS",
+      "allowsLists": false,
+      "rName": "ref.id.column",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "targetTable": [
+        "ReferenceTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC","AIVECTOR","BYTE","VARBYTE"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "RefFeatureColumns",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the names of the reference table columns that contain features of the reference table vectors.",
+      "description": "Specifies the names of the reference table columns that contain features of the reference table vectors.",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "ref.feature.columns",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "permittedValues": [
+        "COSINE",
+        "EUCLIDEAN",
+        "MANHATTAN",
+	"DOTPRODUCT",
+        "MINKOWSKI"	
+      ],
+      "defaultValue": "COSINE",
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "DistanceMeasure",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the distance measures that the function uses.The default value is 'cosine'.",
+      "description": "Specifies the distance measures that the function uses.The default value is 'cosine'.",
+      "datatype": "STRING",
+      "allowsLists": true,
+      "rName": "distance.measure",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "defaultValue": 10,
+      "lowerBound": 1,
+      "upperBound": 100,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "TopK",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies, for each target vector and for each measure, the maximum number of closest reference vectors to include in the output table.",
+      "description": "Specifies, for each target vector and for each measure, the maximum number of closest reference vectors to include in the output table.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "topk",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "defaultValue": 2,
+      "lowerBound": 1,
+      "upperBound": 2147483647,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "PValue",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the p value for MinKowski distance.",
+      "description": "Specify the p value for MinKowski distance.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "pvalue",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "lowerBound": 2.225074e-308,
+      "upperBound": 1.797693e+308,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "SearchThresholds",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the thresholds between a pair of target and reference vectors.",
+      "description": "Specifies the thresholds between a pair of target and reference vectors.",
+      "datatype": "NUMERIC",
+      "allowsLists": true,
+      "rName": "search.thresholds",
+      "useInR": true,
+      "rOrderNum": 10
+    },
+    {
+      "permittedValues": [],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "defaultValue": false,
+      "name": "LargeReferenceInput",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "If the reference table is huge compared to the target table, then passing true in this syntax element will make the reference table as 'Partition By any' instead of 'Dimension'.",
+      "description": "If the reference table is huge compared to the target table, then passing true in this syntax element will make the reference table as 'Partition By any' instead of 'Dimension'.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "largereference.input",
+      "useInR": true,
+      "rOrderNum": 11
+    },
+    {
+      "permittedValues": [],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "defaultValue": false,
+      "name": "OutputSimilarity",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify true if the user wants similarity instead of distance.",
+      "description": "Specify true if the user wants similarity instead of distance.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "output.similarity",
+      "useInR": true,
+      "rOrderNum": 12
+    },
+    {
+      "defaultValue": 1,
+      "lowerBound": 1,
+      "upperBound": 4096,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "EmbeddingSize",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the embedding size of the vectors.",
+      "description": "Specify the embedding size of the vectors.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "embedding.size",
+      "useInR": true,
+      "rOrderNum": 13
+    }
+  ]
+}

teradataml/data/jsons/storedprocedure/17.20/TD_COPYART.json

@@ -0,0 +1,71 @@
+{
+    "FuncName": "TD_COPYART",
+    "FuncDescriptionShort": "TD_COPYART creates a copy of existing ART table.",
+    "FuncDescriptionLong": [
+        "creates a copy of existing ART table with permanet or volatile option."
+    ],
+    "FunctionVersion": "...",
+    "FunctionCategory": "General Utility",
+    "JSONVersion": "1",
+    "FuncRName": "td_Copy_Art",
+    "MaxInputFiles": 0,
+    "Input": [],
+    "Output": [],
+    "Params": [      
+        {
+            "Name": "DST_DATABASENAME",
+            "Type": "string",
+            "Optional": false,
+            "Description": [
+                    "Name of the target database.",
+                    "Must include where TGT_TABLENAME need to be created."
+            ],
+            "LangName": "database_name"
+        },
+        {
+            "Name": "DST_TABLENAME",
+            "Type": "string",
+            "Optional": false,
+            "Description": [
+                    "Name of the target table."
+            ],
+            "LangName": "table_name"
+        },
+        {
+            "Name": "DST_MAPNAME",
+            "Type": "string",
+            "Optional": false,
+            "Description": [
+                    "[Optional] If not specified, the default map is used.",
+                    "Provided name of the map to be used for the copy."
+            ],
+            "LangName": "map_name"
+        },
+        {
+            "Name": "DST_ISPERMTABLE",
+            "Type": "string",
+            "Optional": true,
+            "PermittedValues": [
+                    "T",
+                    "TRUE",
+                    "F",
+                    "FALSE",
+                    "t",
+                    "true",
+                    "'true'",
+                    "'false'",
+                    "f",
+                    "false"
+            ],
+            "Description": [
+                    "[Optional] If not specified, the default is true.",
+                    "If true, the target table is permanent.",
+                    "If false, the target table is volatile."
+            ],
+            "LangName": "permanent_table"
+        }
+    ],
+    "IsPlottable": true,
+    "InputFmt": false,
+    "OutputFmt": false
+}