teradataml 20.0.0.6__py3-none-any.whl → 20.0.0.7__py3-none-any.whl

teradataml/data/docs/byom/docs/ONNXSeq2Seq.py

@@ -0,0 +1,255 @@
+def ONNXSeq2Seq(newdata=None, modeldata=None, tokenizerdata=None, accumulate=None, model_output_tensor=None,
+                encode_max_length=512, show_model_properties=False, output_length=1000,
+                overwrite_cached_models="false", is_debug=False, skip_special_tokens=True,
+                enable_memory_check=False, const_=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The ONNXSeq2Seq() function applies a sequence-to-sequence model that has 
+        been created outside Vantage and exported to Vantage in ONNX format 
+        to input data within Teradata Vantage.
+        
+    PARAMETERS:
+        newdata:
+            Required Argument.
+            Specifies the input teradataml DataFrame that contains
+            the data to be scored.
+            Types: teradataml DataFrame
+
+        modeldata:
+            Required Argument.
+            Specifies the model teradataml DataFrame to be used for
+            scoring.
+            Note:
+                * Use `retrieve_byom()` to get the teradataml DataFrame that contains the model.
+            Types: teradataml DataFrame
+
+        tokenizerdata:
+            Required Argument.
+            Specifies the tokenizer teradataml DataFrame
+            which contains the tokenizer json file.
+            Types: teradataml DataFrame
+
+        accumulate:
+            Required Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s) to
+            copy to the output. By default, the function copies all input
+            teradataml DataFrame columns to the output.
+            Types: str OR list of Strings (str) OR Feature OR list of Features
+
+        model_output_tensor:
+            Required Argument.
+            Specifies the column of the model's possible output fields
+            that the user wants to calculate and output.
+            Types: str
+
+        encode_max_length:
+            Optional Argument.
+            Specifies the maximum length of the tokenizer output token
+            encodings(only applies for models with symbolic dimensions).
+            Default Value: 512
+            Types: int
+
+        show_model_properties:
+            Optional Argument.
+            Specifies the default or expanded "model_input_fields_map" based on
+            input model for defaults or "model_input_fields_map" for expansion.
+            Default Value: False
+            Types: bool
+
+        output_length:
+            Optional Argument.
+            Specifies the output length for the model sequence output, in number of 
+            characters for the VARCHAR output. If the value exceeds the maximum Unicode 
+            VARCHAR size of 32000, a CLOB is created automatically.
+            Default Value: 1000
+            Types: int
+
+        overwrite_cached_models:
+            Optional Argument.
+            Specifies the model name that needs to be removed from the cache.
+            When a model loaded into the memory of the node fits in the cache,
+            it stays in the cache until being evicted to make space for another
+            model that needs to be loaded. Therefore, a model can remain in the
+            cache even after the completion of function execution. Other functions
+            that use the same model can use it, saving the cost of reloading it
+            into memory. User should overwrite a cached model only when it is updated,
+            to make sure that the Predict function uses the updated model instead
+            of the cached model.
+            Note:
+                Do not use the "overwrite_cached_models" argument except when user
+                is trying to replace a previously cached model. Using the argument
+                in other cases, including in concurrent queries or multiple times
+                within a short period of time lead to an OOM error.
+            Default Value: "false"
+            Permitted Values: true, t, yes, y, 1, false, f, no, n, 0, *,
+                              current_cached_model
+            Types: str
+
+        is_debug:
+            Optional Argument.
+            Specifies whether debug statements are added to a trace table or not.
+            When set to True, debug statements are added to a trace table that must
+            be created beforehand.
+            Notes:
+                * Only available with BYOM version 3.00.00.02 and later.
+                * To save logs for debugging, user can create an error log by using
+                  the is_debug=True parameter in the predict functions.
+                  A database trace table is used to collect this information which
+                  does impact performance of the function, so using small data input
+                  sizes is recommended.
+                * To generate this log, user must do the following:
+                      1. Create a global trace table with columns vproc_ID BYTE(2),
+                         Sequence INTEGER, Trace_Output VARCHAR(31000)
+                      2. Turn on session function tracing:
+                           SET SESSION FUNCTION TRACE USING '' FOR TABLE <trace_table_name_created_in_step_1>;
+                      3. Execute function with "is_debug" set to True.
+                      4. Debug information is logged to the table created in step 1.
+                      5. To turn off the logging, either disconnect from the session or
+                         run following SQL:
+                           SET SESSION FUNCTION TRACE OFF;
+                      The trace table is temporary and the information is deleted if user
+                      logs off from the session. If long term persistence is necessary,
+                      user can copy the table to a permanent table before leaving the
+                      session.
+            Default Value: False
+            Types: bool
+
+        enable_memory_check:
+            Optional Argument.
+            Specifies whether there is enough native memory for large models.
+            Default Value: True
+            Types: bool
+
+        skip_special_tokens:
+            Optional Argument.
+            Specifies whether to skip special tokens in the output.
+            Default Value: True
+            Types: bool
+
+        const_*:
+            Optional Argument.
+            Specifies the constant value to be used as a model input by using 
+            the argument name const_<field_name>. Providing constant values as 
+            parameters reduces system overhead, since the value will not be 
+            added to every row being scored.
+            Types: str
+
+        **generic_arguments:
+            Specifies the generic keyword arguments SQLE functions accept. Below
+            are the generic keyword arguments:
+                persist:
+                    Optional Argument.
+                    Specifies whether to persist the results of the
+                    function in a table or not. When set to True,
+                    results are persisted in a table; otherwise,
+                    results are garbage collected at the end of the
+                    session.
+                    Default Value: False
+                    Types: bool
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the
+                    function in a volatile table or not. When set to
+                    True, results are stored in a volatile table,
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+
+            Function allows the user to partition, hash, order or local
+            order the input data. These generic arguments are available
+            for each argument that accepts teradataml DataFrame as
+            input and can be accessed as:
+                * "<input_data_arg_name>_partition_column" accepts str or
+                  list of str (Strings) or PartitionKind
+                * "<input_data_arg_name>_hash_column" accepts str or list
+                  of str (Strings)
+                * "<input_data_arg_name>_order_column" accepts str or list
+                  of str (Strings)
+                * "local_order_<input_data_arg_name>" accepts boolean
+            Note:
+                These generic arguments are supported by teradataml if
+                the underlying SQL Engine function supports, else an
+                exception is raised.
+
+    RETURNS:
+        Instance of ONNXSeq2Seq.
+        Output teradataml DataFrame can be accessed using attribute
+        references, such as  ONNXSeq2Seq.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            result
+
+
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+
+
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage to execute the function.
+        #     2. One must import the required functions mentioned in
+        #        the example from teradataml.
+        #     3. Function will raise error if not supported on the Vantage
+        #        user is connected to.
+        #     4. To execute BYOM functions, set 'configure.byom_install_location' to the
+        #        database name where BYOM functions are installed.
+
+        # Import required libraries / functions.
+        import os, teradataml
+        from teradataml import get_connection, DataFrame
+        from teradataml import save_byom, retrieve_byom, load_example_data
+        from teradataml import configure, display_analytic_functions, execute_sql
+
+        # Load example data.
+        load_example_data("byom", "JulesBelvezeDummyData")
+
+        # Create teradataml DataFrame objects.
+        jules_data = DataFrame.from_table("JulesBelvezeDummyData")
+
+        # Assigning txt column name to rev_txt column.
+        jules_data = jules_data[jules_data.id <= 5]
+        jules_data = jules_data.assign(txt=jules_data.content)
+
+        # Set install location of BYOM functions.
+        configure.byom_install_location = "td_mldb"
+
+        # Check the list of available analytic functions.
+        display_analytic_functions(type="BYOM")
+        
+        # Note: User must have the model and tokenizer data already loaded in the database.
+        # Retrieve model.
+        modeldata = retrieve_byom("t5-small-headline-generator_fixed", table_name="seq_models")
+        tokenizerdata = retrieve_byom("t5-small-headline-generator_fixed", table_name="seq_tokenizers")
+
+        # Assigning tokenizer_id, tokenizer to model_id, model in Seq2Seq_tokenizers.
+        tokenizerdata_a1 = tokenizerdata.assign(tokenizer_id=tokenizerdata.model_id)
+        tokenizerdata_a2 = tokenizerdata_a1.assign(tokenizer=tokenizerdata_a1.model)
+
+        # Example 1: Showcasing the model properties of t5-small-headline-generator_fixed model
+        #            that has been created outside the Vantage.
+        ONNXSeq2Seq_out = ONNXSeq2Seq(modeldata = modeldata,
+                                      tokenizerdata=tokenizerdata_a2.select(['tokenizer_id', 'tokenizer']),
+                                      newdata=jules_data.select(["id", "txt"]),
+                                      accumulate='id',
+                                      model_output_tensor= 'sequences',
+                                      show_model_properties=True)
+
+        # Print the results.
+        print(ONNXSeq2Seq_out.result)
+
+        # Example 2: Using ONNXSeq2Seq with constant values.
+        ONNXSeq2Seq_out = ONNXSeq2Seq(modeldata = modeldata,
+                                      tokenizerdata=tokenizerdata_a2.select(['tokenizer_id', 'tokenizer']),
+                                      newdata=jules_data.select(["id", "txt"]),
+                                      accumulate='id',
+                                      model_output_tensor= 'sequences',
+                                      const_min_length=10,
+                                      const_max_length=84,
+                                      const_num_beams=4,
+                                      const_repetition_penalty=1.2,
+                                      const_length_penalty=2.0,
+                                      const_num_return_sequences=1)
+
+        # Print the results.
+        print(ONNXSeq2Seq_out.result)
+    """

teradataml/data/docs/sqle/docs_17_10/NGramSplitter.py

@@ -37,7 +37,7 @@ def NGramSplitter(data=None, text_column=None, delimiter=" ", grams=None, overla
             default value is the set of all whitespace characters which includes
             the characters for space, tab, newline, carriage return and some
             others.
-            Default Value: "[\s]+"
+            Default Value: "[\\s]+"
             Types: str
 
         grams:

teradataml/data/docs/sqle/docs_17_20/NGramSplitter.py

@@ -37,7 +37,7 @@ def NGramSplitter(data=None, text_column=None, delimiter=" ", grams=None, overla
             default value is the set of all whitespace characters which includes
             the characters for space, tab, newline, carriage return and some
             others.
-            Default Value: "[\s]+"
+            Default Value: "[\\s]+"
             Types: str
 
         grams:

teradataml/data/docs/sqle/docs_17_20/TextParser.py

@@ -1,7 +1,7 @@
 def TextParser(data=None, object=None, text_column=None, enforce_token_limit=False,
                convert_to_lowercase=True, stem_tokens=False, remove_stopwords=False,
                accumulate=None, delimiter=" \t\n\f\r", delimiter_regex=None,
-               punctuation="!#$%&()*+,-./:;?@\^_`{|}~", token_col_name=None,
+               punctuation=r"!#$%&()*+,-./:;?@\^_`{|}~", token_col_name=None,
                doc_id_column=None, list_positions=False, token_frequency=False,
                output_by_word=True, **generic_arguments):
     """

teradataml/data/jsons/byom/ONNXSeq2Seq.json

@@ -0,0 +1,287 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "2",
+  "json_content_version": "1",
+  "function_name": "ONNXSeq2Seq",
+  "function_version": "1.0",
+  "function_type": "byom",
+  "function_r_name": "aa.onnx.seq2seq",
+  "function_alias_name": "ONNXSeq2Seq",
+  "short_description": "This Function generates sequence values using an ONNX model in Vantage",
+  "long_description": "This function is used to calculate sequence 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 sequence values ",
+      "description": "The input table that contains the text from which we generate sequence 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 sequence values ",
+      "description": "The model table to be used for calculating sequence 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 input and output tensors for the ONNX model.",
+      "description": "Show input and output tensors for the ONNX model.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "show.model.properties",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "defaultValue": 1000,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "OutputLength",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the output format for the model sequence output ",
+      "description": "Specifies the output format for the model sequence output ",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "output.length",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "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": 9
+    },
+    {
+      "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": 10
+    },
+    {
+      "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": 11
+    },
+    {
+      "defaultValue": true,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "SkipSpecialTokens",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "If true, skips special tokens on output ",
+      "description": "If true, skips special tokens on output ",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "skip.special.tokens",
+      "useInR": true,
+      "rOrderNum": 12
+    },
+    {
+      "checkDuplicate": true,
+      "allowedTypes": ["NUMERIC","STRING"],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "Const_",
+      "regexMatch": true,
+      "matchName": "const_",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Argument starts with prefix Const_ and then the name of a constant and its value.  Can be a string or a number. ",
+      "description": "Argument starts with prefix Const_ and then the name of a constant and its value.  Can be a string or a number.",
+      "datatype": ["STRING","NUMERIC"],
+      "allowsLists": false,
+      "rName": "const_*",
+      "useInR": true,
+      "rOrderNum": 13
+    }
+  ]
+}

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

@@ -268,20 +268,16 @@
       },
   
       {
-        "defaultValue": true,
-        "permittedValues": [
-          "true",
-          "false"
-        ],
+        "permittedValues": ["TRUE", "FALSE"],
         "isOutputColumn": false,
         "name": "isDebug",
         "alternateNames": [],
         "isRequired": false,
         "rDescription": "Specify whether error logging is required.",
         "description": "Specify whether error logging is required.",
-        "datatype": "BOOLEAN",
+        "datatype": "STRING",
         "allowsLists": false,
-        "rName": "isDebug",
+        "rName": "is.debug",
         "useInR": true,
         "rOrderNum": 17
       },

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

@@ -291,20 +291,16 @@
       },
   
       {
-        "defaultValue": true,
-        "permittedValues": [
-          "true",
-          "false"
-        ],
+        "permittedValues": ["TRUE", "FALSE"],
         "isOutputColumn": false,
         "name": "isDebug",
         "alternateNames": [],
         "isRequired": false,
         "rDescription": "Specify whether error logging is required.",
         "description": "Specify whether error logging is required.",
-        "datatype": "BOOLEAN",
+        "datatype": "STRING",
         "allowsLists": false,
-        "rName": "isDebug",
+        "rName": "is.debug",
         "useInR": true,
         "rOrderNum": 17
       },

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

@@ -268,20 +268,16 @@
       },
   
       {
-        "defaultValue": true,
-        "permittedValues": [
-          "true",
-          "false"
-        ],
+        "permittedValues": ["TRUE", "FALSE"],
         "isOutputColumn": false,
         "name": "isDebug",
         "alternateNames": [],
         "isRequired": false,
         "rDescription": "Specify whether error logging is required.",
         "description": "Specify whether error logging is required.",
-        "datatype": "BOOLEAN",
+        "datatype": "STRING",
         "allowsLists": false,
-        "rName": "isDebug",
+        "rName": "is.debug",
         "useInR": true,
         "rOrderNum": 17
       },

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

@@ -268,20 +268,16 @@
       },
   
       {
-        "defaultValue": true,
-        "permittedValues": [
-          "true",
-          "false"
-        ],
+        "permittedValues": ["TRUE", "FALSE"],
         "isOutputColumn": false,
         "name": "isDebug",
         "alternateNames": [],
         "isRequired": false,
         "rDescription": "Specify whether error logging is required.",
         "description": "Specify whether error logging is required.",
-        "datatype": "BOOLEAN",
+        "datatype": "STRING",
         "allowsLists": false,
-        "rName": "isDebug",
+        "rName": "is.debug",
         "useInR": true,
         "rOrderNum": 17
       },