teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,202 @@
+def ScaleTransform(data=None, object=None, accumulate=None, attribute_name_column=None,
+                   attribute_value_column=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        ScaleTransform() function scales specified columns in input data, using ScaleFit() function output.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the output of generated by
+            ScaleFit() function or the instance of ScaleFit.
+            Types: teradataml DataFrame or ScaleFit
+
+        accumulate:
+            Optional Argument.
+            Specifies the names of input teradataml DataFrame columns to copy to the output.
+            Types: str OR list of Strings (str)
+
+        attribute_name_column:
+            Optional Argument.
+            Specifies the column name in the "attribute_data" which contains attribute names.
+            Note:
+                * This is required for sparse input.
+            Types: str
+        
+        attribute_value_column:
+            Optional Argument.
+            Specifies the column name in the "attribute_data" which contains attribute values.
+            Note:
+                * This is required for sparse input.
+            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: boolean
+
+                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: boolean
+
+            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)
+                * "<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 ScaleTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as ScaleTransformObj.<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.
+
+        # Load the example data.
+        load_example_data("teradataml", ["scale_housing"])
+        load_example_data('scale', ["scale_attributes", "scale_parameters",
+        "scale_input_partitioned", "scale_input_sparse","scale_input_part_sparse"])
+
+        # Create teradataml DataFrame.
+        scaling_house = DataFrame.from_table("scale_housing")
+        scale_attribute = DataFrame.from_table("scale_attributes")
+        scale_parameter = DataFrame.from_table("scale_parameters")
+        scale_inp_part = DataFrame.from_table("scale_input_partitioned")
+        scale_inp_sparse = DataFrame.from_table("scale_input_sparse")
+        scale_inp_part_sparse = DataFrame.from_table("scale_input_part_sparse")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Scale "lotsize" with respect to mean value of the column.
+        fit_obj = ScaleFit(data=scaling_house,
+                           target_columns="lotsize",
+                           scale_method="MEAN",
+                           miss_value="KEEP",
+                           global_scale=False,
+                           multiplier="1",
+                           intercept="0")
+
+        # Print the result DataFrame.
+        print(fit_obj.output)
+
+        # Scale "lotsize" column.
+        # Note that teradataml DataFrame representing the model is passed as
+        # input to "object".
+        obj = ScaleTransform(data=scaling_house,
+                             object=fit_obj.output,
+                             accumulate="price")
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # Example 2: Scale "lotsize" column. Note that model is passed as instance of
+        #            ScaleFit to "object".
+        obj1 = ScaleTransform(data=scaling_house,
+                              object=fit_obj,
+                              accumulate="price")
+
+        # Print the result DataFrame.
+        print(obj1.result)
+
+        # Example 3: Create statistics to scale "fare" and "age" columns with respect to
+        #            maximum absolute value for partitioned input.
+        fit_obj = ScaleFit(data=scale_inp_part,
+                           attribute_data=scale_attribute,
+                           parameter_data=scale_parameter,
+                           target_columns=['fare', 'age'],
+                           scale_method="maxabs",
+                           miss_value="zero",
+                           global_scale=False,
+                           data_partition_column='pid',
+                           attribute_data_partition_column='pid',
+                           parameter_data_partition_column='pid')
+
+        obj = ScaleTransform(data=scale_inp_part,
+                             object=fit_obj.output,
+                             accumulate=['pid','passenger'],
+                             data_partition_column='pid',
+                             object_partition_column='pid')
+        
+        # Print the result DataFrame.
+        print(obj.result)
+
+
+        # Example 4: Create statistics to scale "fare" column with respect to
+        #            range for sparse input.
+        fit_obj = ScaleFit(data=scale_inp_sparse,
+                           target_attribute=['fare'],
+                           scale_method="range",
+                           miss_value="keep",
+                           global_scale=False,
+                           attribute_name_column='attribute_column',
+                           attribute_value_column='attribute_value')
+
+        obj = ScaleTransform(data=scale_inp_sparse,
+                             object=fit_obj.output,
+                             accumulate=['passenger'],
+                             attribute_name_column='attribute_column',
+                             attribute_value_column='attribute_value'
+                     )
+        
+        # Print the result DataFrame.
+        print(obj.result)
+
+
+        # Example 5: Create statistics to scale "fare" column with respect to
+        #            maximum absolute value for sparse input with partition column.
+        fit_obj = ScaleFit(data=scale_inp_part_sparse,
+                           parameter_data=scale_parameter,
+                           attribute_data=scale_attribute,
+                           scale_method="maxabs",
+                           miss_value="zero",
+                           global_scale=False,
+                           attribute_name_column='attribute_column',
+                           attribute_value_column='attribute_value',
+                           data_partition_column='pid',
+                           attribute_data_partition_column='pid',
+                           parameter_data_partition_column='pid')
+
+        obj = ScaleTransform(data=scale_inp_part_sparse,
+                             object=fit_obj.output,
+                             accumulate=["passenger",'pid'],
+                             attribute_name_column='attribute_column',
+                             attribute_value_column='attribute_value',
+                             object_partition_column='pid',
+                             data_partition_column='pid')
+        
+        # Print the result DataFrame.
+        print(obj.result)
+
+    """

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

@@ -0,0 +1,206 @@
+def SentimentExtractor(data=None, cust_dict=None, add_dict=None, text_column=None,
+                       accumulate=None, analysis_type="DOCUMENT", priority="NONE",
+                       output_type="ALL", **generic_arguments):
+    """
+    DESCRIPTION:
+        The SentimentExtractor() function uses a dictionary model
+        to extract the sentiment (positive, negative, or neutral)
+        of each input document or sentence.
+
+        The dictionary model consists of WordNet, a lexical database
+        of the English language, and these negation words (no, not,
+        neither, never, and similar negation words).
+
+        The function handles negated sentiments as follows:
+            * -1 if the sentiment is negated (for example, "I am not happy")
+            * -1 if the sentiment and a negation word are separated by one
+              word (for example, "I am not very happy")
+            * +1 if the sentiment and a negation word are separated by two
+              or more words (for example, "I am not saying I am happy")
+        Notes:
+            * This function requires the UTF8 client character set for UNICODE data.
+            * This function does not support Pass Through Characters (PTCs).
+            * For information about PTCs, see Teradata Vantage™ - Analytics Database
+              International Character Set Support.
+            * This function does not support KanjiSJIS or Graphic data types.
+            * Only the English language is supported.
+            * The max length supported for sentiment word in the dictionary data
+              is 128 characters.
+            * The Max length of the sentiment_words output column is 32000 characters.
+              If the sentiment_words output column value exceeds this limit, then a
+              triple dot(...) displays at the end of the string.
+            * The Max length of the content output column is 32000 characters;
+              that is, the supported maximum length of a sentence is 32000.
+            * User can have up to 10 words in a sentiment phrase.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        cust_dict:
+            Optional Argument.
+            Specifies the input teradataml DataFrame containing custom dictionary data,
+            to use non-default custom dictionary data.
+            Types: teradataml DataFrame
+
+        add_dict:
+            Optional Argument.
+            Specifies the input teradataml DataFrame containing additional entries,
+            to add additional entries to either "cust_dict"
+            or default dictionary.
+            Types: teradataml DataFrame
+
+        text_column:
+            Required Argument.
+            Specifies the "data" column that contains the text data
+            for sentiment analysis.
+            Types: str
+
+        accumulate:
+            Optional Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s)
+            to copy to the output. By default, the function copies no
+            input teradataml DataFrame columns to the output.
+            Types: str OR list of Strings (str)
+
+        analysis_type:
+            Optional Argument.
+            Specifies the level of analysis, whether to analyze each document
+            or each sentence in a document.
+            Permitted Values:
+                * DOCUMENT - Analyzes each document.
+                * SENTENCE - Analyzes each sentence in a document.
+            Default Value: "DOCUMENT"
+            Types: str
+
+        priority:
+            Optional Argument.
+            Specifies the highest priority when returning results.
+            Permitted Values: 
+                * NONE - Provide all results the same priority.
+                * NEGATIVE_RECALL - Provide the highest priority to negative
+                                    results, including those with lower-confidence
+                                    sentiment classifications (maximizes number of
+                                    negative results returned).
+                * NEGATIVE_PRECISION - Provide the highest priority to negative
+                                       results with high-confidence sentiment classifications.
+                * POSITIVE_RECALL - Provide the highest priority to positive results,
+                                    including those with lower-confidence sentiment
+                                    classifications (maximizes number of positive results returned).
+                * POSITIVE_PRECISION - Provide the highest priority to positive results with high
+                                       confidence sentiment classifications.
+            Default Value: "NONE"
+            Types: str
+
+        output_type:
+            Optional Argument.
+            Specifies the kind of results to return.
+            Permitted Values:
+                * ALL - Returns all results.
+                * POS - Returns only results with positive sentiments.
+                * NEG - Returns only results with negative sentiments.
+                * NEU - Returns only results with neutral sentiments.
+            Default Value: "ALL"
+            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)
+                * "<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 SentimentExtractor.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as SentimentExtractorObj.<attribute_name>.
+        Output teradataml DataFrame attribute names are:
+            1. result
+            2. output_dictionary_data
+
+
+    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.
+
+        # Load the example data.
+        load_example_data("sentimentextractor", ["sentiment_extract_input",
+                                                  "sentiment_word_input",
+                                                  "additional_table"])
+
+        # Create teradataml DataFrame objects.
+        sentiment_extract_input = DataFrame.from_table("sentiment_extract_input")
+        sentiment_word_input = DataFrame.from_table("sentiment_word_input")
+        additional_table = DataFrame.from_table("additional_table")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1 : Extracting the sentiment (positive, negative, or neutral)
+        #             of each input document or sentence.
+        sentimentextractor_out = SentimentExtractor(text_column="review",
+                                                    data=sentiment_extract_input)
+
+        # Print the result DataFrame.
+        print(sentimentextractor_out.result)
+        print(sentimentextractor_out.output_dictionary_data)
+
+        # Example 2 : Extracting the sentiment (positive, negative, or neutral)
+        #             of each input document by specifying custom dictionary data
+        #             and adding additional entries to custom dictionary data.
+        sentimentextractor_out_1 = SentimentExtractor(text_column="review",
+                                                      accumulate=['id', 'product'],
+                                                      analysis_type="DOCUMENT",
+                                                      priority="NONE",
+                                                      output_type="ALL",
+                                                      data=sentiment_extract_input,
+                                                      cust_dict=sentiment_word_input,
+                                                      add_dict=additional_table)
+
+        # Print the result DataFrame.
+        print(sentimentextractor_out_1.result)
+        print(sentimentextractor_out_1.output_dictionary_data)
+
+    """

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

@@ -0,0 +1,114 @@
+def Sessionize(data=None, time_column=None, time_out=None, click_lag=None,
+               emit_null=False, **generic_arguments):
+    """
+    DESCRIPTION:
+        Sessionize() function maps each click in a session to a unique session identifier.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        time_column:
+            Required Argument.
+            Specifies the name of the input column that contains the click
+            times.
+            Note: The "time_column" must also be an "order_column".
+            Types: str
+
+        time_out:
+            Required Argument.
+            Specifies the number of seconds at which the session times out. If
+            "time_out" seconds elapse after a click, then the next click
+            starts a new session.
+            Types: float
+
+        click_lag:
+            Optional Argument.
+            Specifies the minimum number of seconds between clicks for the
+            session user to be considered human. If clicks are more frequent,
+            indicating that the user is a bot, the function ignores the session.
+            The "click_lag" must be less than "time_out".
+            Types: float
+
+        emit_null:
+            Optional Argument.
+            Specifies whether to output rows that have NULL values in their
+            session id and rapid fire columns, even if their timestamp_column has
+            a NULL value.
+            Default Value: False
+            Types: bool
+
+        **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: boolean
+
+                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: boolean
+
+            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)
+                * "<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 Sessionize.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as SessionizeObj.<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.
+
+        # Load the example data.
+        load_example_data("sessionize", ["sessionize_table"])
+
+        # Create teradataml DataFrame object.
+        sessionize_data = DataFrame.from_table("sessionize_table")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Mapping each click in a session to a unique session identifier.
+        #            by partition column 'partition_id' and order column 'clicktime'.
+        obj = teradataml.Sessionize(data=sessionize_data,
+                                    data_partition_column='partition_id',
+                                    data_order_column='clicktime',
+                                    time_column='clicktime',
+                                    time_out=60.0,
+                                    click_lag=0.2)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+    """