teradataml 20.0.0.2__py3-none-any.whl → 20.0.0.4__py3-none-any.whl

teradataml/data/docs/uaf/docs_17_20/DWT2D.py

@@ -202,7 +202,10 @@ def DWT2D(data1=None, data1_filter_expr=None, data2=None,
                         data2_filter_expr=data2.id==1,
                         input_fmt_input_mode="MANY2ONE")
 
-        # Example 1: Perform discrete wavelet transform (DWT) for two-dimensional data
+        # Print the result DataFrame.
+        print(uaf_out.result)
+
+        # Example 2: Perform discrete wavelet transform (DWT) for two-dimensional data
         #            using only one matrix as input and wavelet as 'haar'.
         uaf_out = DWT2D(data1=data1_matrix_df,
                         wavelet='haar')

teradataml/data/docs/uaf/docs_17_20/DickeyFuller.py

@@ -1,5 +1,5 @@
 def DickeyFuller(data=None, data_filter_expr=None, algorithm=None, 
-                 max_lags=None, drift_trend_formula=None, 
+                 max_lags=0,
                  **generic_arguments):
     """
     DESCRIPTION:
@@ -10,18 +10,23 @@ def DickeyFuller(data=None, data_filter_expr=None, algorithm=None,
         other factors.
 
         The following procedure is an example of how to use DickeyFuller() function:
-            * Run regression tests.
-            * Determine the algorithm for Dickey Fuller statistic data.
-            * Run DickeyFuller() function using the algorithm.
-            * (Result shows series contains unit roots) Use DIFF() and
-              SeasonalNormalize() functions to remove unit roots.
+            * Run DickeyFuller() on the time series being modeled.
+            * Retrieve the results of the DickeyFuller() test to determine if the
+              time series contains any unit roots.
+            * If unit roots are present, use a technique such as differencing such as Diff()
+              or seasonal normalization, such as SeasonalNormalize(), to create a new series,
+              then rerun the DickeyFuller() test to verify that the differenced or
+              seasonally-normalized series unit root are removed.
+            * If the result shows unit roots, use Diff() and SeasonalNormalize()
+              to remove unit roots.
 
 
     PARAMETERS:
         data:
             Required Argument.
-            Speciifes a single logical-runtime series as an input.
-            Types: TDSeries
+            Specifies a single logical-runtime series as an input or TDAnalyticResult which
+            contains ARTFITRESIDUALS layer.
+            Types: TDSeries, TDAnalyticResult
 
         data_filter_expr:
             Optional Argument.
@@ -34,26 +39,18 @@ def DickeyFuller(data=None, data_filter_expr=None, algorithm=None,
             Permitted Values:
                 * NONE: Random walk
                 * DRIFT: Random walk with drift
-                * TREND: Random walk with linear trend
                 * DRIFTNTREND: Random walk with drift and trend
-                * FORMULA: Random walk with selected drift, trend and
-                           auxiliary lags
+                * SQUARED: Random walk with drift, trend, and
+                           quadratic trend.
             Types: str
 
         max_lags:
             Optional Argument.
             Specifies the maximum number of lags to use with the regression
-            equation.
+            equation. Range is [0, 100]
+            DefaultValue: 0
             Types: int
 
-        drift_trend_formula:
-            Optional Argument.
-            Specifies the formula used to represent the drift and trend portions
-            of the regression.
-            Note:
-                * Valid only when "algorithm" is set to 'formula'.
-            Types: str
-
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions.
             Below are the generic keyword arguments:
@@ -136,7 +133,7 @@ def DickeyFuller(data=None, data_filter_expr=None, algorithm=None,
         #             for the presence of the unit roots using random walk with
         #             linear trend for regression.
         uaf_out = DickeyFuller(data=data_series_df,
-                               algorithm='TREND')
+                               algorithm='DRIFT')
 
         # Print the result DataFrame.
         print(uaf_out.result)

teradataml/data/hnsw_alter_data.csv

@@ -0,0 +1,5 @@
+id,array_col
+10,"1,1"
+11,"2,2"
+12,"3,3"
+13,"4,4"

teradataml/data/hnsw_data.csv

@@ -0,0 +1,10 @@
+id,array_col
+1,"18,18"
+2,"19,19"
+3,"20,20"
+4,"55,55"
+5,"56,56"
+6,"57,57"
+7,"88,88"
+8,"89,89"
+9,"90,90"

teradataml/data/jsons/byom/h2opredict.json

@@ -142,7 +142,7 @@
       "rDescription": " Specifies the model type as 'DAI' or 'OpenSource' for  H2O model prediction. ",
       "description": " Specifies the model type as 'DAI' or 'OpenSource' for  H2O model prediction. ",
       "datatype": "STRING",
-      "allowsLists": true,
+      "allowsLists": false,
       "rName": "model.type",
       "useInR": true,
       "rOrderNum": 6

teradataml/data/jsons/byom/onnxembeddings.json

@@ -0,0 +1,266 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "2",
+  "json_content_version": "1",
+  "function_name": "ONNXEmbeddings",
+  "function_version": "1.0",
+  "function_type": "byom",
+  "function_r_name": "aa.onnx.embeddings",
+  "function_alias_name": "ONNXEmbeddings",
+  "short_description": "This Function generates embeddings values using an ONNX model in Vantage",
+  "long_description": "This function is used to calculate embeddings values in Vantage with a  HuggingFace model that has been created outside Vantage and exported to vantage using ONNX format",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny",
+        "PartitionByKey"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "partitionByOneInclusive": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The input table that contains the text from which we generate embedding values ",
+      "description": "The input table that contains the text from which we generate embedding values ",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "newdata",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "partitionByOneInclusive": false,
+      "name": "ModelTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The model table to be used for calculating embedding values ",
+      "description": "The model table to be used for calculating embedding values ",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "modeldata",
+      "useInR": true,
+      "rOrderNum": 2
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "partitionByOneInclusive": false,
+      "name": "TokenizerTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The tokenizer table which contains the tokenizer json file ",
+      "description": "The tokenizer table which contains the tokenizer json file ",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "tokenizerdata",
+      "useInR": true,
+      "rOrderNum": 3
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "Accumulate",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the names of input_table columns to copy to the output table.",
+      "description": "Specify the names of the input columns to copy to the output table. ",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "accumulate",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "ModelOutputTensor",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the column of the model's possible output fields that the user wants to calculate and output ",
+      "description": "Specifies the column of the model's possible output fields that the user wants to calculate and output ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "model.output.tensor",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "defaultValue": 512,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "EncodeMaxLength",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the maximum length of the tokenizer output token encodings(only applies for models with symbolic dimensions) ",
+      "description": "Specifies the maximum length of the tokenizer output token encodings(only applies for models with symbolic dimensions) ",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "encode.max.length",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "defaultValue": false,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "ShowModelProperties",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": " Show default or expanded ModelInputFieldsMap based on input model for defaults or ModelInputFieldsMap for expansion. ",
+      "description": " Show default or expanded ModelInputFieldsMap based on input model for defaults or ModelInputFieldsMap for expansion. ",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "show.model.properties",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "defaultValue": "emb_",
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "OutputColumnPrefix",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the column prefix for each of the output columns when using FLOAT32 OutputFormat ",
+      "description": "Specifies the column prefix for each of the output columns when using FLOAT32 OutputFormat ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "output.column.prefix",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "defaultValue": "VARBYTE(3072)",
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "OutputFormat",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the output format for the model embeddings output ",
+      "description": "Specifies the output format for the model embeddings output ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "output.format",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "permittedValues": [
+        "true",
+        "t",
+        "yes",
+        "y",
+        "1",
+        "false",
+        "f",
+        "no",
+        "n",
+        "0",
+        "*",
+        "current_cached_model"
+      ],
+      "defaultValue": "false",
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "OverwriteCachedModel",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the model name that needs to be removed from the cache. * can also be used to remove the models ",
+      "description": " Specifies the model name that needs to be removed from the cache. * can also be used to remove the models ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "overwrite.cached.models",
+      "useInR": true,
+      "rOrderNum": 10
+    },
+    {
+      "defaultValue": false,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "IsDebug",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Print additional information in trace table regarding execution of ONNXPredict ",
+      "description": " Print additional information in trace table regarding execution of ONNXPredict ",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "is.debug",
+      "useInR": true,
+      "rOrderNum": 11
+    },
+    {
+      "defaultValue": true,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "EnableMemoryCheck",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "If true, verifies if there is enough native memory for large models ",
+      "description": "If true, verifies if there is enough native memory for large models ",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "enable.memory.check",
+      "useInR": true,
+      "rOrderNum": 12
+    }
+  ]
+}

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_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
 		},