teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,267 @@
+def TargetEncodingFit(data=None, category_data=None, encoder_method=None,
+                      target_columns=None, response_column=None, alpha_prior=None,
+                      beta_prior=None, alpha_priors=None, num_distinct_responses=None,
+                      u0_prior=None, v0_prior=None, alpha0_prior=None, beta0_prior=None,
+                      default_values=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The TargetEncodingFit() function generally uses the likelihood or expected
+        value of the target variable for each category and encodes that category with
+        that value. This technique works for both binary classification and regression
+        and for multiclass classification a similar technique is applied, which encodes
+        the categorical variable with k new variables, where k is the number of classes.
+
+        The TargetEncodingFit() function takes the input data and a categorical data as
+        input and generates the required hyperparameters, which will be used by the
+        TargetEncodingTransform() function for encoding the categorical values.
+
+        Notes:
+            * This function requires the UTF8 client character set.
+            * This function does not support Pass-Through Characters (PTCs).
+            * This function does not support KanjiSJIS or Graphic data types.
+            * The maximum number of unique categories in the particular
+              column is 4000.
+            * The maximum category length is 128 characters.
+            * Columns with a large number of distinct categories can have an
+              impact on query execution time.
+
+        Usage considerations for TargetEncodingFit() function are:
+            * The input data in the TargetEncodingFit() function can have no
+              partition at all or have data_partition_column="ANY" .
+            * The TargetEncodingFit() function requires a category data to be
+              passed as a dimension. The category data should be generated by the
+              CategoricalSummary() function.
+            * Null categories will not be encoded.
+            * The "default_values" argument should be provided to TargetEncodingFit()
+              if user want to assign any target value for missing categories in the
+              TargetEncodingTransform() function.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input data containing the categorical
+            target columns.
+            Types: teradataml DataFrame
+
+        category_data:
+            Required Argument.
+            Specifies the data containing the unique categories and their counts
+            for each target columns.
+            Types: teradataml DataFrame
+
+        encoder_method:
+            Required Argument.
+            Specifies the encoder method:
+                * If the response variable is following a binary classification,
+                  for example, values are either 0 or 1, use "encoder_method" as 'CBM_BETA'.
+                * If the response variable is following a multi-class classification,
+                  for example, values are (1,...,k, where k is the number of classes),
+                  use "encoder_method" as 'CBM_DIRICHLET'.
+                * If the response variable is following a regression, for example,
+                  values are contiguous numeric values, use "encoder_method" as
+                  'CBM_GAUSSIAN_INVERSE_GAMMA'.
+            Notes:
+                * The maximum length supported is 128.
+                * "encoder_method" are not case sensitive.
+            Permitted Values: CBM_BETA, CBM_DIRICHLET, CBM_GAUSSIAN_INVERSE_GAMMA
+            Types: str
+
+        target_columns:
+            Required Argument.
+            Specifies the column from the "data" that contains the categorical values
+            to be encoded.
+            Notes:
+                * The maximum length supported is 128.
+                * The maximum list length is 2018.
+                * "target_columns" are not case sensitive.
+            Types: str OR list of Strings (str)
+
+        response_column:
+            Required Argument.
+            Specifies column from the "data" that contains the response values.
+            Notes:
+                * The maximum length supported is 128.
+                * "response_column" are not case sensitive.
+            Types: str
+
+        alpha_prior:
+            Optional Argument.
+            Specifies the prior parameter of the 'CBM_BETA' encoder method.
+            Types: int
+
+        beta_prior:
+            Optional Argument.
+            Specifies the prior parameter of the 'CBM_BETA' encoder method.
+            Types: int
+
+        alpha_priors:
+            Optional Argument.
+            Specifies the prior parameter of the 'CBM_DIRICHLET' encoder method.
+            Notes:
+                * The number of values specified in this argument must be equal to
+                  "num_distinct_responses" value.
+                * The maximum list length is 2018.
+            Types: int OR list of ints
+
+        num_distinct_responses:
+            Required when "encoder_method" is 'CBM_DIRICHLET',
+            optional otherwise.
+            Specifies the number of distinct values present in the
+            "response_column".
+            Types: int
+
+        u0_prior:
+            Optional Argument.
+            Specifies the prior parameter of the 'CBM_GAUSSIAN_INVERSE_GAMMA'
+            encoder method.
+            Types: int
+
+        v0_prior:
+            Optional Argument.
+            Specifies the prior parameter of the 'CBM_GAUSSIAN_INVERSE_GAMMA'
+            encoder method.
+            Types: int
+
+        alpha0_prior:
+            Optional Argument.
+            Specifies the prior parameter of the 'CBM_GAUSSIAN_INVERSE_GAMMA'
+            encoder method.
+            Types: int
+
+        beta0_prior:
+            Optional Argument.
+            Specifies the prior parameter of the 'CBM_GAUSSIAN_INVERSE_GAMMA'
+            encoder method.
+            Types: int
+
+        default_values:
+            Optional Argument.
+            Specifies the values to use when the category is not found during transform.
+            When only one value is specified, it will be applied to all the target columns,
+            otherwise the number of default values must be equal to the number of target
+            columns.
+            Note:
+                * The maximum list length is 2018.
+            Types: int OR list of ints
+
+        **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 TargetEncodingFit.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as TargetEncodingFitObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            1. result
+            2. output_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("teradataml", ["titanic"])
+
+        # Create teradataml DataFrame objects.
+        data_input = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Find the distinct values and counts for column 'sex' and 'embarked'.
+        categorical_summ = CategoricalSummary(data = data_input,
+                                              target_columns = ["sex", "embarked"]
+                                              )
+
+        # Find the distinct count of 'sex' and 'embarked' in which only 2 column should be present
+        # name 'ColumnName' and 'CategoryCount'.
+        category_data=categorical_summ.result.groupby('ColumnName').count()
+        category_data = category_data.assign(drop_columns = True,
+                                             ColumnName = category_data.ColumnName,
+                                             CategoryCount = category_data.count_DistinctValue)
+
+        # Example 1 : Generates the required hyperparameters when "encoder_method" is
+        #             'CBM_BETA'.
+        TargetEncodingFit_out1 = TargetEncodingFit(data = data_input,
+                                                   category_data = category_data,
+                                                   encoder_method = 'CBM_BETA',
+                                                   target_columns = ['sex', 'embarked'],
+                                                   response_column = 'survived',
+                                                   default_values = [-1, -2]
+                                                   )
+        # Print the result DataFrame.
+        print(TargetEncodingFit_out1.result)
+        print(TargetEncodingFit_out1.output_data)
+
+        # Example 2 : Generates the required hyperparameters when "encoder_method" is
+        #             'CBM_DIRICHLET'.
+        TargetEncodingFit_out2 = TargetEncodingFit(data = data_input,
+                                                   category_data = category_data,
+                                                   encoder_method = 'CBM_DIRICHLET',
+                                                   target_columns = ['sex', 'embarked'],
+                                                   response_column = 'pclass',
+                                                   num_distinct_responses = 3
+                                                   )
+        # Print the result DataFrame.
+        print(TargetEncodingFit_out2.result)
+        print(TargetEncodingFit_out2.output_data)
+
+        # Example 3 : Generates the required hyperparameters when "encoder_method" is
+        #             'CBM_GAUSSIAN_INVERSE_GAMMA'.
+        TargetEncodingFit_out3 = TargetEncodingFit(data = data_input,
+                                                   category_data = category_data,
+                                                   encoder_method = 'CBM_GAUSSIAN_INVERSE_GAMMA',
+                                                   target_columns = ['sex', 'embarked'],
+                                                   response_column = 'age',
+                                                   default_values = [-1, -2]
+                                                   )
+
+        # Print the result DataFrame.
+        print(TargetEncodingFit_out3.result)
+        print(TargetEncodingFit_out3.output_data)
+    """

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

@@ -0,0 +1,141 @@
+def TargetEncodingTransform(data=None, object=None, accumulate=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        The TargetEncodingTransform() function takes the input data
+        and a Fit data generated by the TargetEncodingFit() function
+        for encoding the categorical values.
+
+        Notes:
+            * This function requires the UTF8 client character set.
+            * This function does not support Pass-Through Characters (PTCs).
+            * This function does not support KanjiSJIS or Graphic data types.
+
+        Usage considerations for TargetEncodingTransform are:
+            * Errors are generated in these cases:
+                * When the Fit data does not meet the criteria.
+                * When category from input data is not found in the Fit data and
+                  the "default_values" argument is also not used during
+                  TargetEncodingFit() function.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the TargetEncodingFit
+            parameters generated by TargetEncodingFit() function or the instance
+            of TargetEncodingFit.
+            Types: teradataml DataFrame or TargetEncodingFit
+
+        accumulate:
+            Optional Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s) to
+            be copied to the output.
+            Notes:
+                 * The maximum length supported is 128.
+                 * The maximum list length is 2047.
+                 * "accumulate" are not case sensitive.
+            Types: str OR list of Strings (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 TargetEncodingTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as TargetEncodingTransformObj.<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", ["titanic"])
+
+        # Create teradataml DataFrame objects.
+        data_input = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Find the distinct values and counts for column 'sex' and 'embarked'.
+        categorical_summ = CategoricalSummary(data=data_input,
+                                              target_columns = ["sex", "embarked"]
+                                              )
+
+        # Find the distinct count of 'sex' and 'embarked' in which only 2 column should be present
+        #  name 'ColumnName' and 'CategoryCount'.
+        category_data=categorical_summ.result.groupby('ColumnName').count()
+        category_data = category_data.assign(drop_columns=True,
+                                             ColumnName=category_data.ColumnName,
+                                             CategoryCount=category_data.count_DistinctValue)
+
+        # Generates the required hyperparameters when "encoder_method" is 'CBM_BETA'.
+        TargetEncodingFit_out = TargetEncodingFit(data=data_input,
+                                                  category_data=category_data,
+                                                  encoder_method='CBM_BETA',
+                                                  target_columns=['sex', 'embarked'],
+                                                  response_column='survived',
+                                                  default_values=[-1, -2]
+                                                  )
+
+        # Example 1 : Encode the column 'sex' and 'embarked'.
+        TargetEncodingTransform_out = TargetEncodingTransform(data=data_input,
+                                                              object=TargetEncodingFit_out,
+                                                              accumulate="passenger"
+                                                              )
+
+        # Print the result DataFrame.
+        print(TargetEncodingTransform_out.result)
+
+    """

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

@@ -0,0 +1,119 @@
+def TextMorph(data=None, word_column=None, pos=None,
+              single_output=False, postag_column=None,
+              accumulate=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        TextMorph() function generate morphs of given words in the input dataset.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        word_column:
+            Required Argument.
+            Specifies the name of the input column that contains words for which morphs are to be generated.
+            Types: str
+
+        pos:
+            Optional Argument.
+            Specifies the part of speech (POS) to output.
+            Permitted Values: "NOUN", "VERB", "ADV", "ADJ"
+            Types: str or list of str
+
+        single_output:
+            Optional Argument.
+            Specifies whether to output only one morph for each word. If set to `False`, 
+            the function outputs all morphs for each word.
+            Default Value: False
+            Types: bool
+
+        postag_column:
+            Optional Argument.
+            Specifies the name of the  column in data that contains the part-of-speech (POS) 
+            tags of the words, output by the function TD_POSTagger.
+            Types: str
+
+        accumulate:
+            Optional Argument.
+            Specifies the names of the input columns to copy to the output table.
+            Types: str or list of str
+
+        **generic_arguments:
+            Optional Argument.
+            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 SQLE Engine
+                function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of TextMorph.
+        Output teradataml DataFrames can be accessed using attribute references, such as TDTextMorphObj.<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 an error if not supported on the Vantage user is connected to.
+
+        # Load the example data.
+        load_example_data("textmorph", ["words_input","pos_input"])
+
+        # Create teradataml DataFrame objects.
+        data1 = DataFrame.from_table("words_input")
+        data2 = DataFrame.from_table("pos_input")
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+        
+        # Import function TextMorph.
+        from teradataml import TextMorph
+
+        # Example 1: Generate morphs for words in the input dataset.
+        TextMorph_out = TextMorph(data=data1,
+                                  word_column="data2",
+                                  pos=["noun", "verb"],
+                                  single_output=True,
+                                  accumulate=["id"])
+
+        # Print the result DataFrame.
+        print(TextMorph_out.result)
+
+        Example 2 : Generate morphs for words in the input dataset with POS tags.
+        TextMorph_pos = TextMorph(data=data2,
+                                  word_column="word",
+                                  postag_column="pos_tag",
+                                  accumulate=["id","pos_tag"])
+
+        # Print the result DataFrame.
+        print(TextMorph_pos.result)
+    """