teradataml 20.0.0.3__py3-none-any.whl → 20.0.0.5__py3-none-any.whl

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

@@ -0,0 +1,267 @@
+{
+  "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",
+  "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,
+      "defaultValue":5,
+      "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/17.20/TD_Shap.json

@@ -96,7 +96,6 @@
       "name": "TrainingFunction",
       "isRequired": true,
       "datatype": "STRING",
-      "defaultValue": "TD_GLM",
       "isOutputColumn": false,
       "alternateNames": [],
       "rDescription": "Specifies the model type name.",

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

@@ -0,0 +1,134 @@
+{
+	  "json_schema_major_version": "1",
+	  "json_schema_minor_version": "1",
+	  "json_content_version": "1",
+	  "function_name": "TD_TextMorph",
+	  "function_version": "1.0",
+	  "function_type": "fastpath",
+	  "function_category": "Text Analysis",
+	  "function_alias_name": "TD_TextMorph",
+	  "function_r_name": "td.textmorph",
+	  "short_description": "This function is used to generate morph of given words in the input dataset.",
+	  "long_description": "This function is used to generate morph of given words in the input dataset.",
+	  "input_tables": [
+	    {
+	      "requiredInputKind": [
+	        "PartitionByAny"
+	      ],
+	      "isOrdered": false,
+	      "partitionByOne": false,
+	      "name": "InputTable",
+	      "alternateNames": [],
+	      "isRequired": true,
+	      "rDescription": "The table that contains the input dataset.",
+	      "description": "The table that contains the input dataset.",
+	      "datatype": "TABLE_ALIAS",
+	      "allowsLists": false,
+	      "rName": "data",
+	      "useInR": true,
+	      "rOrderNum": 1
+	    }
+	  ],
+	  "argument_clauses": [
+	    {
+	      "targetTable": [
+	        "InputTable"
+	      ],
+	      "checkDuplicate": true,
+	      "allowedTypes": [],
+	      "allowedTypeGroups": [
+	        "STRING"
+	      ],
+	      "matchLengthOfArgument": "",
+	      "allowPadding": false,
+	      "name": "WordColumn",
+	      "alternateNames": [],
+	      "isRequired": true,
+	      "rDescription": "Specify the name of the input column that contains words, for which morphs to be generated.",
+	      "description": "Specify the name of the input column that contains words, for which morphs to be generated.",
+	      "datatype": "COLUMNS",
+	      "allowsLists": false,
+	      "rName": "word.column",
+	      "useInR": true,
+	      "rOrderNum": 2
+	    },
+	    {
+	        "permittedValues": [
+            "NOUN",
+            "VERB",
+            "ADV",
+		    "ADJ"
+          ],
+          "isOutputColumn": false,
+		  "matchLengthOfArgument": "",
+          "allowPadding": false,
+          "name": "POS",
+          "alternateNames": [],
+          "isRequired": false,
+          "rDescription": "Specifies the part of speech to output.",
+          "description": "Specifies the part of speech to output.",
+          "datatype": "STRING",
+          "allowsLists": true,
+          "rName": "pos",
+          "useInR": true,
+          "rOrderNum": 3
+	    },
+	    {
+			"defaultValue": false,
+            "name": "SingleOutput",
+            "alternateNames": [],
+            "isRequired": false,
+            "rDescription": " Specify whether to output only one morph for each word. If user specifies 'false', the function outputs all morphs for each word.",
+            "description": " Specify whether to output only one morph for each word. If user specifies 'false', the function outputs all morphs for each word.",
+            "datatype": "BOOLEAN",
+            "allowsLists": false,
+            "rName": "single.output",
+            "useInR": true,
+            "rOrderNum": 4
+	    },
+		{
+			"targetTable": [
+			"InputTable"
+			],
+			"checkDuplicate": true,
+            "allowedTypes": [],
+            "allowedTypeGroups": [
+            "STRING"
+			],
+			"matchLengthOfArgument": "",
+            "allowPadding": false,
+            "name": "POSTagColumn",
+            "alternateNames": [],
+            "isRequired": false,
+            "rDescription": "Specify the name of the input table column that contains the part-of-speech (POS) tags of the words, output by the function TD_POSTagger.",
+            "description": "Specify the name of the input table column that contains the part-of-speech (POS) tags of the words, output by the function TD_POSTagger.",
+            "datatype": "COLUMNS",
+            "allowsLists": false,
+            "rName": "postag.column",
+            "useInR": true,
+            "rOrderNum": 5
+		},
+	    {
+			"targetTable": [
+            "InputTable"
+          ],
+          "checkDuplicate": true,
+          "allowedTypes": [],
+          "allowedTypeGroups": [
+            "ALL"
+          ],
+          "matchLengthOfArgument": "",
+          "allowPadding": false,
+          "name": "Accumulate",
+          "alternateNames": [],
+          "isRequired": false,
+          "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.",
+          "datatype": "COLUMNS",
+          "allowsLists": true,
+          "rName": "accumulate",
+          "useInR": true,
+          "rOrderNum": 6		
+	    }
+	  ]
+}

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

@@ -67,6 +67,23 @@
 			"useInR": true,
 			"rOrderNum": 3
 		},
+		{
+			"defaultValue": false,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "EnforceTokenLimit",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to throw an informative error when finding token larger than 64K/32K or silently discard those tokens larger.",
+			"description": "Specifies whether to throw an informative error when finding token larger than 64K/32K or silently discard those tokens larger.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "enforce.token.limit",
+			"useInR": true,
+			"rOrderNum": 4
+		},		
 		{
 			"defaultValue": true,
 			"permittedValues": [],
@@ -82,7 +99,7 @@
 			"allowsLists": false,
 			"rName": "convert.to.lowercase",
 			"useInR": true,
-			"rOrderNum": 4
+			"rOrderNum": 5
 		},
 		{
 			"defaultValue": false,
@@ -99,7 +116,7 @@
 			"allowsLists": false,
 			"rName": "stem.tokens",
 			"useInR": true,
-			"rOrderNum": 5
+			"rOrderNum": 6
 		},
 		{
 			"defaultValue": false,
@@ -116,7 +133,7 @@
 			"allowsLists": false,
 			"rName": "remove.stopwords",
 			"useInR": true,
-			"rOrderNum": 6
+			"rOrderNum": 7
 		},
 		{
 			"targetTable": [
@@ -138,7 +155,7 @@
 			"allowsLists": true,
 			"rName": "accumulate",
 			"useInR": true,
-			"rOrderNum": 7
+			"rOrderNum": 8
 		},
 		{
 			"defaultValue": " \\t\\n\\f\\r",
@@ -154,8 +171,23 @@
 			"allowsLists": false,
 			"rName": "delimiter",
 			"useInR": true,
-			"rOrderNum": 8
+			"rOrderNum": 9
 		},
+		{
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "DelimiterRegex",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies a PCRE regular expression that represents the word delimiter.",
+			"description": "Specifies a PCRE regular expression that represents the word delimiter.",
+			"datatype": "STRING",
+			"allowsLists": false,
+			"rName": "delimiter.regex",
+			"useInR": true,
+			"rOrderNum": 10
+		},		
 		{
 			"defaultValue": "!#$%&()*+,-./:;?@\\^_`{|}~",
 			"isOutputColumn": false,
@@ -170,7 +202,7 @@
 			"allowsLists": false,
 			"rName": "punctuation",
 			"useInR": true,
-			"rOrderNum": 9
+			"rOrderNum": 11
 		},
 		{
 			"defaultValue": "token",
@@ -186,7 +218,80 @@
 			"allowsLists": false,
 			"rName": "token.col.name",
 			"useInR": true,
-			"rOrderNum": 10
-		}
+			"rOrderNum": 12
+		},
+		{
+			"targetTable": [
+				"InputTable"
+			],
+			"checkDuplicate": true,
+			"allowedTypes": [],
+			"allowedTypeGroups": [
+				"INTEGER"
+			],
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "DocIdColumn",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "specifies the name of the column that uniquely identifies a row in the input table.",
+			"description": "specifies the name of the column that uniquely identifies a row in the input table.",
+			"datatype": "COLUMNS",
+			"allowsLists": false,
+			"rName": "doc.id.column",
+			"useInR": true,
+			"rOrderNum": 13
+		},	     
+		{
+			"defaultValue": false,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "ListPositions",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to output the positions of a word in list form.",
+			"description": "Specifies whether to output the positions of a word in list form.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "list.positions",
+			"useInR": true,
+			"rOrderNum": 14
+		},
+		{
+			"defaultValue": false,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "TokenFrequency",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to output the frequency for each token.",
+			"description": "Specifies whether to output the frequency for each token.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "token.frequency",
+			"useInR": true,
+			"rOrderNum": 15
+		},
+		{
+			"defaultValue": true,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "OutputByWord",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to output each token in a separate row or all tokens in one.",
+			"description": "Specifies whether to output each token in a separate row or all tokens in one.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "output.by.word",
+			"useInR": true,
+			"rOrderNum": 16
+		}	
 	]
-}
+}