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

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

@@ -0,0 +1,296 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "1",
+  "json_content_version": "1",
+  "function_name": "TD_HNSW",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Model Training",
+  "function_alias_name": "TD_HNSW",
+  "function_r_name": "td.hnsw",
+  "short_description": "The TD_HNSW function generates the HNSW model using the input data points which is then used by TD_HNSWPredict function for determining the approximate nearest neighbors for any given input data point.",
+  "long_description": "The TD_HNSW function generates the HNSW model using the input data points which is then used by TD_HNSWPredict function for determining the approximate nearest neighbors for any given input data point.",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny",
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The table that contains the input dataset for HNSW model training/update/delete operation.",
+      "description": "The table that contains the input dataset for HNSW model training/update/delete operation.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "data",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "PartitionByAny"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputModelTable",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "The table that contains the HNSW model for update/delete operation.",
+      "description": "The table that contains the HNSW model for update/delete operation.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "object",
+      "useInR": true,
+      "rOrderNum": 2
+    }
+  ],
+  "output_tables": [
+    {
+      "isOutputTable": true,
+      "omitPossible": false,
+      "name": "ModelTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the name of the table in which the generated HNSW model can be stored.",
+      "description": "Specifies the name of the table in which the generated HNSW model can be stored.",
+      "datatype": "TABLE_NAME",
+      "allowsLists": false,
+      "rName": "model.table",
+      "useInR": true,
+      "rOrderNum": 3
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "INTEGER"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "IdColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specify the column name containing unique identifier of input rows.",
+      "description": "Specify the column name containing unique identifier of input rows.",
+      "datatype": "COLUMN_NAMES",
+      "allowsLists": false,
+      "rName": "id.column",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "VECTOR","BYTE","VARBYTE"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "VectorColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the column from the input table to be used for training the HNSW model.",
+      "description": "Specifies the column from the input table to be used for training the HNSW model.",
+      "datatype": "COLUMN_NAMES",
+      "allowsLists": false,
+      "rName": "vector.column",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "NumLayer",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the maximum number of layers for the HNSW model.",
+      "description": "Specify the maximum number of layers for the HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "num.layer",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "lowerBound": 0,
+      "upperBound": 2147483647,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "Seed",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the random seed value for repeatable results.",
+      "description": "Specify the random seed value for repeatable results.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "seed",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "defaultValue": 32,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "EfConstruction",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the number of neighbors to search during training of HNSW model.",
+      "description": "Specify the number of neighbors to search during training of HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "ef.construction",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "defaultValue": 32,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "NumConnPerNode",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify number of connections for a node during training of HNSW model.",
+      "description": "Specify number of connections for a node during training of HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "numconn.pernode",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "defaultValue": 32,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "MaxNumConnPerNode",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify maximum number of connections allowed for a node during training of HNSW model.",
+      "description": "Specify maximum number of connections allowed for a node during training of HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "maxnumconn.pernode",
+      "useInR": true,
+      "rOrderNum": 10
+    },
+    {
+      "permittedValues": [
+        "EUCLIDEAN",
+        "COSINE",
+	"DOTPRODUCT"
+      ],
+      "defaultValue": "EUCLIDEAN",
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "DistanceMeasure",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the distance measure to be used for distance computation.",
+      "description": "Specify the distance measure to be used for distance computation.",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "distance.measure",
+      "useInR": true,
+      "rOrderNum": 11
+    },
+    {
+      "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": 12
+    },
+    {
+      "permittedValues": [],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "defaultValue": false,
+      "name": "ApplyHeuristics",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify whether to apply heuristics optimizations during training of HNSW model.",
+      "description": "Specify whether to apply heuristics optimizations during training of HNSW model.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "apply.heuristics",
+      "useInR": true,
+      "rOrderNum": 13
+    },
+    {
+      "permittedValues": [
+        "UPDATE",
+        "DELETE"
+      ],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "AlterOperation",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the alter operation for HNSW model. This argument is required when InputModelTable is provided.",
+      "description": "Specify the alter operation for HNSW model. This argument is required when InputModelTable is provided.",
+      "datatype": "STRING",
+      "allowsLists": true,
+      "rName": "alter.operation",
+      "useInR": true,
+      "rOrderNum": 14
+    },
+    {
+      "permittedValues": [
+        "RECONSTRUCTION",
+        "DELETENODE"
+      ],
+      "defaultValue": "RECONSTRUCTION",
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "DeleteMethod",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the method for delete operation.",
+      "description": "Specify the method for delete operation.",
+      "datatype": "STRING",
+      "allowsLists": true,
+      "rName": "delete.method",
+      "useInR": true,
+      "rOrderNum": 15
+    }
+  ]
+}

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

@@ -0,0 +1,206 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "1",
+  "json_content_version": "1",
+  "function_name": "TD_HNSWPredict",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Model Scoring",
+  "function_alias_name": "TD_HNSWPredict",
+  "function_r_name": "td.hnswpredict",
+  "short_description": "The TD_HNSWPredict function takes the InputTable and finds the approximate nearest neighbors for the input data points using the HNSW model generated from TD_HNSW function.",
+  "long_description": "The TD_HNSWPredict function takes the InputTable and finds the approximate nearest neighbors for the input data points using the HNSW model generated from TD_HNSW function.",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The table that contains the input dataset for HNSW model scoring.",
+      "description": "The table that contains the input dataset for HNSW model scoring.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "data",
+      "useInR": true,
+      "rOrderNum": 2
+    },
+    {
+      "requiredInputKind": [
+        "PartitionByAny"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "ModelTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The table that contains the HNSW model for scoring.",
+      "description": "The table that contains the HNSW model for scoring.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "object",
+      "useInR": true,
+      "rOrderNum": 1
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "INTEGER"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "IdColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specify the column name containing unique identifier of input rows.",
+      "description": "Specify the column name containing unique identifier of input rows.",
+      "datatype": "COLUMN_NAMES",
+      "allowsLists": false,
+      "rName": "id.column",
+      "useInR": true,
+      "rOrderNum": 3
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "VECTOR","BYTE","VARBYTE"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "VectorColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the column from the input table to be used for training the HNSW model.",
+      "description": "Specifies the column from the input table to be used for training the HNSW model.",
+      "datatype": "COLUMN_NAMES",
+      "allowsLists": false,
+      "rName": "vector.column",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "defaultValue": 10,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "TopK",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify number of top nearest neighbors to generate in the output.",
+      "description": "Specify number of top nearest neighbors to generate in the output.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "top_k",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "defaultValue": 32,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "EfSearch",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the number of neighbors to search during search in HNSW model.",
+      "description": "Specify the number of neighbors to search during search in HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "ef.search",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "permittedValues": [],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "defaultValue": false,
+      "name": "OutputNearestVector",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify whether to output the vector for the nearest neighbor.",
+      "description": "Specify whether to output the vector for the nearest neighbor.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "output.nearestvector",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "permittedValues": [],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "defaultValue": false,
+      "name": "OutputSimilarity",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify whether to output similarity of input datapoint to the nearest vector. If it is set to false, then the function outputs distance instead of similarity.",
+      "description": "Specify whether to output similarity of input datapoint to the nearest vector. If it is set to false, then the function outputs distance instead of similarity.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "output.similarity",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "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.",
+      "description": "Specifies the input table columns to copy to the output table.",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "accumulate",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "permittedValues": [],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "defaultValue": false,
+      "name": "SingleInputRow",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify whether input data contains only a single row.",
+      "description": "Specify whether input data contains only a single row.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "single.inputrow",
+      "useInR": true,
+      "rOrderNum": 10
+    }
+  ]
+}

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

@@ -0,0 +1,32 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "1",
+  "json_content_version": "1",
+  "function_name": "TD_HNSWSummary",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Model Exploration",
+  "function_alias_name": "TD_HNSWSummary",
+  "function_r_name": "td.hnswsummary",
+  "short_description": "The TD_HNSWSummary function takes the ModelTable generated from TD_HNSW function as input and converts the ModelTable data into readable format.",
+  "long_description": "The TD_HNSWSummary function takes the ModelTable generated from TD_HNSW function as input and converts the ModelTable data into readable format.",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "ModelTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The table that contains the HNSW model for exploration.",
+      "description": "The table that contains the HNSW model for exploration.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "object",
+      "useInR": true,
+      "rOrderNum": 1
+    }
+  ]
+}

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

@@ -92,7 +92,7 @@
       "checkDuplicate": true,
       "allowedTypes": [],
       "allowedTypeGroups": [
-        "NUMERIC","AIVECTOR","BYTE","VARBYTE"
+        "NUMERIC","VECTOR","BYTE","VARBYTE"
       ],
       "matchLengthOfArgument": "",
       "allowPadding": false,
@@ -247,4 +247,4 @@
       "rOrderNum": 13
     }
   ]
-}
+}

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

@@ -5,7 +5,7 @@
   "function_name": "TD_SMOTE",
   "function_version": "1.0",
   "function_type": "fastpath",
-  "function_category": "Feature Engineering Transform Functions",
+  "function_category": "Feature Engineering Transform",
   "function_alias_name": "TD_SMOTE",
   "function_r_name": "aa.td_smote",
   "ref_function_r_name": "aa.td_smote",
@@ -168,10 +168,10 @@
     },
     {
       "isOutputColumn": false,
-      "allowNaN": false,
+      "defaultValue": 5,
       "name": "OversamplingFactor",
       "alternateNames": [],
-      "isRequired": true,
+      "isRequired": false,
       "rDescription": "specifies the factor for oversampling the minority class.",
       "description": "specifies the factor for oversampling the minority class.",
       "datatype": "DOUBLE",

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

@@ -77,7 +77,7 @@
       "checkDuplicate": true,
       "allowedTypes": [],
       "allowedTypeGroups": [
-        "NUMERIC","AIVECTOR","BYTE","VARBYTE"
+        "NUMERIC","VECTOR","BYTE","VARBYTE"
       ],
       "matchLengthOfArgument": "",
       "allowPadding": false,
@@ -122,7 +122,7 @@
       "checkDuplicate": true,
       "allowedTypes": [],
       "allowedTypeGroups": [
-        "NUMERIC","AIVECTOR","BYTE","VARBYTE"
+        "NUMERIC","VECTOR","BYTE","VARBYTE"
       ],
       "matchLengthOfArgument": "",
       "allowPadding": false,
@@ -143,7 +143,7 @@
         "EUCLIDEAN",
         "MANHATTAN",
 	"DOTPRODUCT",
-        "MINKOWSKI"	
+        "MINKOWSKI"
       ],
       "defaultValue": "COSINE",
       "isOutputColumn": false,
@@ -163,7 +163,7 @@
     {
       "defaultValue": 10,
       "lowerBound": 1,
-      "upperBound": 100,
+      "upperBound": 1024,
       "lowerBoundType": "INCLUSIVE",
       "upperBoundType": "INCLUSIVE",
       "allowNaN": false,
@@ -203,7 +203,7 @@
       "rOrderNum": 9
     },
     {
-      "lowerBound": 2.225074e-308,
+      "lowerBound": -1.797693e+308,
       "upperBound": 1.797693e+308,
       "lowerBoundType": "INCLUSIVE",
       "upperBoundType": "INCLUSIVE",
@@ -275,4 +275,4 @@
       "rOrderNum": 13
     }
   ]
-}
+}

teradataml/data/ner_dict.csv

@@ -0,0 +1,8 @@
+"type_ner","dict"
+"location","Arkansas"
+"location","Dublin"
+"MISC","average maturity"
+"location","Ohio"
+"month","June"
+"Last Name","Gross"
+"digit regex","[0-9]+"

teradataml/data/ner_input_eng.csv

@@ -0,0 +1,7 @@
+"id","txt"
+1,"At end of August, the Janus Unconstrained fund held only 45 debt issues with 70 percent of its assets in U.S. government debt."
+2,"One Treasury issue due June 2016 alone was worth 43 percent of the fund's total assets."
+3,"Most of the bonds have short durations, with the average maturity of just over three years, indicating a generally defensive posture."
+4,"For Bill Gross, quitting Pimco's $222 billion Total Return Fund to take over a $13 million fund at Janus Capital is like resigning the U.S. presidency to become city manager of Ashtabula, Ohio, population 18,800."
+5,"Gross stunned the investing world on Friday with his abrupt departure from Pimco, the $2 trillion asset manager he co-founded in 1971 and where he had run the Total Return Fund, the world's biggest bond fund, for more than 27 years."
+6,"[0-9]+"

teradataml/data/ner_rule.csv

@@ -0,0 +1,5 @@
+"type_ner","regex"
+"email","[\w\-]([\.\w])+[\w]+@([\w\-]+\.)+[a-zA-Z]{2,4}"
+"Money","\s\$[0-9]+\s"
+"Digits","\s[0-9]+\s"
+"Name","[A-Z][a-z]+\s+[A-Z][a-z]+"