teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,176 @@
+def NaiveBayesTextClassifierPredict(object=None, newdata=None,
+                                    input_token_column=None,
+                                    doc_id_columns=None,
+                                    model_type='MULTINOMIAL',
+                                    top_k=None,
+                                    model_token_column=None,
+                                    model_category_column=None,
+                                    model_prob_column=None,
+                                    output_prob=False,
+                                    responses=None,
+                                    accumulate=None,
+                                    **generic_arguments):
+    """
+    DESCRIPTION:
+        The NaiveBayesTextClassifierPredict() function uses the model generated by the
+        NaiveBayesTextClassifier() function to predict the outcomes for a test set
+        of data.
+
+    PARAMETERS:
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame which contains the model
+            data generated by the NaiveBayesTextClassifier() function or
+            instance of NaiveBayesTextClassifier.
+            Types: teradataml DataFrame or NaiveBayesTextClassifier
+
+        newdata:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the input test
+            data.
+            Types: teradataml DataFrame
+
+        input_token_column:
+            Required Argument.
+            Specifies the name of the newdata column that contains the tokens.
+            Types: str
+
+        doc_id_columns:
+            Required Argument.
+            Specifies the names of the newdata columns that contain the
+            document identifier.
+            Types: str OR list of Strings (str)
+
+        model_type:
+            Optional Argument.
+            Specifies the model type of the text classifier.
+            Permitted Values: 'MULTINOMIAL', 'BERNOULLI'
+            Default Value: 'MULTINOMIAL'
+            Types: str
+
+        top_k:
+            Optional Argument.
+            Specifies the number of most likely prediction categories to output
+            with their log-likelihood values (for example, the top 10 most likely
+            prediction categories). The default is all prediction categories.
+            Types: int
+
+        model_token_column:
+            Optional Argument.
+            Specifies the name of the object column that contains the
+            tokens. The default value is the first column of object.
+            Types: str
+
+        model_category_column:
+            Optional Argument.
+            Specifies the name of the object column that contains the
+            prediction categories. The default value is the second column of
+            object.
+            Types: str
+
+        model_prob_column:
+            Optional Argument.
+            Specifies the name of the object column that contains the token
+            counts. The default value is the third column of object.
+            Types: str
+
+        output_prob:
+            Optional Argument.
+            Specifies whether to output probabilities.
+            Default Value: False
+            Types: bool
+
+        responses:
+            Optional Argument.
+            Specifies a list of Responses to output.
+            Types: str OR list of strs
+
+        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)
+
+        **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 NaiveBayesTextClassifierPredict.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as
+        NaiveBayesTextClassifierPredictObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+        result
+
+    RAISES:
+        TeradataMlException
+
+    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("NaiveBayesTextClassifierPredict",["complaints_tokens_test","token_table"])
+
+        # Create teradataml DataFrame objects.
+        token_table = DataFrame("token_table")
+        complaints_tokens_test = DataFrame("complaints_tokens_test")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Create a model which is output of NaiveBayesTextClassifier.
+        nbt_out = NaiveBayesTextClassifier(data = token_table,
+                                           token_column = 'token',
+                                           doc_id_columns = 'doc_id',
+                                           doc_category_column = 'category',
+                                           model_type = "Bernoulli",
+                                           data_partition_column = 'category')
+
+        # Example: Run NaiveBayesTextClassifierPredict() on model generated by
+        #          NaiveBayesTextClassifier() where model_type is "Bernoulli".
+        nbt_predict_out = NaiveBayesTextClassifierPredict(object = nbt_out,
+                                                          newdata = complaints_tokens_test,
+                                                          input_token_column = 'token',
+                                                          doc_id_columns = 'doc_id',
+                                                          model_type = "Bernoulli",
+                                                          model_token_column = 'token',
+                                                          model_category_column = 'category',
+                                                          model_prob_column = 'prob',
+                                                          newdata_partition_column = 'doc_id')
+
+        # Print the result DataFrame.
+        print(nbt_predict_out.result)
+
+    """

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

@@ -0,0 +1,147 @@
+def NumApply(data=None, target_columns=None, output_columns=None, accumulate=None, apply_method=None,
+             sigmoid_style=None, in_place=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        Apply predefined numeric operation on specified target columns.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        target_columns:
+            Required Argument.
+            Specifies the name(s) of the column(s) in "data" to perform numeric operations on.
+            Types: str OR list of Strings (str)
+
+        apply_method:
+            Required Argument.
+            Specifies the numeric operator/method.
+            Permitted Values:
+                * EXP - Raises e (base of natural logarithms) to power of value,
+                        where e = 2.71828182845905.
+                * LOG - Computes base 10 logarithm of value.
+                * SIGMOID - Applies sigmoid function to value. See "sigmoid_style".
+                * SININV - Computes inverse hyperbolic sine of value.
+                * TANH - Computes hyperbolic tangent of value.
+            Types: str
+
+        in_place:
+            Optional Argument.
+            Specifies whether the output columns have the same names as the target columns.
+            When set to True, function effectively replaces each value in each target column
+            with the result of applying "apply_method" to it, otherwise copies the target
+            columns to the output and adds output columns whose values are the result of
+            applying "apply_method" to each value.
+            No target columns can be part of the "accumulate" column.
+            Default Value: True
+            Types: boolean
+
+        output_columns:
+            Optional Argument.
+            Specifies the name(s) of the output column(s) to be generated.
+            An output column name cannot exceed 128 characters.
+            By default, with "in_place" set to False, 'target_column_operator'; otherwise same as
+            "target_column" names.
+            Notes:
+                1. If any 'target_column_operator' exceeds 128 characters, specify an "output_column" for each
+                   target_column.
+                2. Ignored with "in_place" set to True.
+            Types: str OR list of strs
+
+        accumulate:
+            Optional Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s) to copy to the output.
+            Types: str OR list of Strings (str)
+
+        sigmoid_style:
+            Optional Argument, required when "apply_method" is 'sigmoid'.
+            Specifies the sigmoid style.
+            Permitted Values:
+                * LOGIT
+                * MODIFIEDLOGIT
+                * TANH
+            Default Value: LOGIT
+            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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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
+                SQLE Engine function supports, else an exception is raised.
+
+
+    RETURNS:
+        Instance of NumApply.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as NumApplyObj.<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", ["numerics"])
+
+        # Create teradataml DataFrame object.
+        numerics = DataFrame.from_table("numerics")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Apply "log" method to column "num1" in numerics.
+        obj = NumApply(data=numerics,
+                       target_columns="integer_col",
+                       apply_method="log",
+                       in_place=True)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # Example 2: Apply "sigmoid" method and "tanh" as sigmoid style.
+        obj = NumApply(data=numerics,
+                       target_columns="decimal_col",
+                       output_columns="out1",
+                       apply_method="sigmoid",
+                       sigmoid_style="tanh",
+                       in_place=False)
+
+        # Print the result DataFrame.
+        print(obj.result)
+    """

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

@@ -0,0 +1,135 @@
+def OneHotEncodingFit(data=None, is_input_dense=None, target_column=None, categorical_values=None, other_column=None,
+                      attribute_column=None, value_column=None, target_attributes=None, other_attributes=None,
+                      **generic_arguments):
+    """
+    DESCRIPTION:
+        Function records all the parameters required for OneHotEncodingTransform() function.
+        Such as, target attributes and their categorical values to be encoded and other parameters.
+        Output of OneHotEncodingFit() function is used by OneHotEncodingTransform() function for encoding
+        the input data. It supports inputs in both sparse and dense format.
+        Note:
+            * For input to be considered as sparse input, column names must be provided for
+             'data_partition_column' argument.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        is_input_dense:
+            Required Argument.
+            Specifies whether input is in dense format or sparse format.
+            Types: boolean
+
+        target_column:
+            Required Argument when 'is_input_dense=True', disallowed otherwise.
+            Specifies the name of the column in "data" to be encoded.
+            Types: str
+
+        categorical_values:
+            Required Argument when 'is_input_dense=True', disallowed otherwise.
+            Specifies the categorical values to encode in one-hot form.
+            Types: str OR list of strs
+
+        other_column:
+            Required Argument when 'is_input_dense=True', disallowed otherwise.
+            Specifies a category name for values that "categorical_values" does not specify
+            (categorical values not to encode in one-hot form).
+            Default Value: 'other'
+            Types: str
+
+        attribute_column:
+            Required Argument when 'is_input_dense=False', disallowed otherwise.
+            Specifies the name of the column in "data" which contains attribute
+            names.
+            Types: str
+
+        value_column:
+            Required Argument when 'is_input_dense=False', disallowed otherwise.
+            Specifies the name of the column in "data" which contains attribute
+            values.
+            Types: str
+
+        target_attributes:
+            Required Argument when 'is_input_dense=False', disallowed otherwise.
+            Specifies one or more attributes to encode in one-hot form. Every target attribute must
+            be in "attribute_column".
+            Types: str OR list of strs
+
+        other_attributes:
+            Optional Argument when 'is_input_dense=False', disallowed otherwise.
+            For each target attribute, specifies a category name for attributes that "target_attributes"
+            does not specify. The nth "other_attributes" corresponds to the nth "target_attribute".
+            Types: str OR list of strs
+
+        **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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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
+                SQLE Engine function supports, else an exception is raised.
+
+
+    RETURNS:
+        Instance of OneHotEncodingFit.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as OneHotEncodingFitObj.<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 object.
+        titanic_data = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Generate fit object to encode "male" and "female" values of column "sex".
+        fit_obj = OneHotEncodingFit(data=titanic_data,
+                                    is_input_dense=True,
+                                    target_column="sex",
+                                    categorical_values=["male", "female"],
+                                    other_column="other")
+
+        # Print the result DataFrame.
+        print(fit_obj.result)
+
+    """

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

@@ -0,0 +1,109 @@
+def OneHotEncodingTransform(data=None, object=None, is_input_dense=None, **generic_arguments):
+    """
+    DESCRIPTION:
+        Function encodes specified attributes and categorical values as one-hot numeric vectors,
+        using OneHotEncodingFit() function output.
+        Notes:
+            * In case of sparse input, neither 'data_partition_column' nor
+              'object_partition_column' can be used independently.
+            * In case of dense input, if 'data_partition_column' is having value
+              PartitionKind.ANY, then 'object_partition_column' should have value
+              PartitionKind.DIMENSION.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the encoding parameters generated by
+            OneHotEncodingFit() function or the instance of OneHotEncodingFit.
+            Types: teradataml DataFrame or OneHotEncodingFit
+
+        is_input_dense:
+            Required Argument.
+            Specifies whether input is in dense format or sparse format.
+            Types: boolean
+
+        **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 table or not.
+                    When set to True, results are persisted in 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 volatile table or not.
+                    When set to True, results are stored in 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
+                SQLE Engine function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of OneHotEncodingTransform.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as OneHotEncodingTransformObj.<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 object.
+        titanic_data = DataFrame.from_table("titanic")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Transform categorical column "sex" to numerical columns "sex_male", "sex_female",
+        #            and "sex_other" using OneHotEncodingFit() and OneHotEncodingTransform().
+
+        # Generate fit object for column "sex".
+        fit_obj = OneHotEncodingFit(data=titanic_data,
+                                    is_input_dense=True,
+                                    target_column="sex",
+                                    categorical_values=["male", "female"],
+                                    other_column="other")
+
+        # Print the result DataFrame.
+        print(fit_obj.result)
+
+        # Encode "male" and "female" values of column "sex".
+        obj = OneHotEncodingTransform(data=titanic_data,
+                                      object=fit_obj.result,
+                                      is_input_dense=True)
+
+        # Print the result DataFrame.
+        print(obj.result)
+    """