teradataml 20.0.0.0__py3-none-any.whl → 20.0.0.2__py3-none-any.whl

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

@@ -0,0 +1,189 @@
+def  TDNaiveBayesPredict(data = None, object = None, id_column = None,
+                         numeric_inputs = None, categorical_inputs = None,
+                         attribute_name_column = None, attribute_value_column = None,
+                         responses = None, output_prob = False, accumulate = None,
+                         **generic_arguments):
+    """
+    DESCRIPTION:
+        Function predicts classification label using model generated by NaiveBayes function
+        for a test set of data.
+    
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+        
+        object:
+            Required Argument.
+            Specifies the  teradataml DataFrame containing the model data
+            or instance of NaiveBayes.
+            Types: teradataml DataFrame or NaiveBayes
+        
+        id_column:
+            Required Argument.
+            Specifies the name of the column that uniquely identifies an 
+            observation in the "data".
+            Types: str
+        
+        numeric_inputs:
+            Optional Argument.
+            Specifies the name of the columns in "data" containing numeric attributes values.
+            Types: str OR list of Strings (str)
+        
+        categorical_inputs:
+            Optional Argument.
+            Specifies the name of the columns in "data" containing categorical attributes values.
+            Types: str OR list of Strings (str)
+        
+        attribute_name_column:
+            Optional Argument.
+            Specifies the name of the columns in "data" containing attributes names.
+            Types: str
+        
+        attribute_value_column:
+            Optional Argument.
+            Specifies the name of the columns in "data" containing attributes values.
+            Types: str
+        
+        responses:
+            Optional Argument.
+            Specifies a list of responses to output.
+            Types: str OR list of strs
+        
+        output_prob:
+            Optional Argument.
+            Specifies whether to output the probability for each response.
+            Default Value: False
+            Types: bool
+        
+        accumulate:
+            Optional Argument.
+            Specify the names of the columns in "data" that need to be copied 
+            from the input to output teradataml DataFrame.
+            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  NaiveBayesPredict.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as  NaiveBayesPredictObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            result
+    
+    
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+    
+    
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage, before importing the 
+        #        function in user space.
+        #     2. User can import the function, if it is available on 
+        #        Vantage user is connected to.
+        #     3. To check the list of analytic functions available on 
+        #        Vantage user connected to, use 
+        #        "display_analytic_functions()".
+        
+        # Load the example data.
+        load_example_data("decisionforestpredict", ["housing_train", "housing_test"])
+        
+        # Create teradataml DataFrame objects.
+        housing_train = DataFrame.from_table("housing_train")
+        housing_test = DataFrame.from_table("housing_test")
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+        
+        # Import function  NaiveBayesPredict.
+        from teradataml import  NaiveBayesPredict
+        
+        # Example 1: NaiveBayesPredict function to predict the classification label using Dense input.
+        NaiveBayes_out = NaiveBayes(data=housing_train, response_column='homestyle', 
+                                    numeric_inputs=['price','lotsize','bedrooms','bathrms','stories','garagepl'], 
+                                    categorical_inputs=['driveway','recroom','fullbase','gashw','airco','prefarea'])
+
+        NaiveBayesPredict_out = TDNaiveBayesPredict(data=housing_test, object=NaiveBayes_out.result, id_column='sn',
+                                                    numeric_inputs=['price','lotsize','bedrooms','bathrms','stories','garagepl'],
+                                                    categorical_inputs=['driveway','recroom','fullbase','gashw','airco','prefarea'],
+                                                    responses=['Classic', 'Eclectic', 'bungalow'],
+                                                    accumulate='homestyle',
+                                                    output_prob=True
+                                                    )
+        
+        # Print the result DataFrame.
+        print( NaiveBayesPredict_out.result)
+
+        # Example 2: NaiveBayesPredict function to predict the classification label using Sparse input.
+        
+        # Unpivoting the data for sparse input to naive bayes.
+        upvt_train = Unpivoting(data = housing_train, id_column = 'sn', 
+                                target_columns = ['price','lotsize','bedrooms','bathrms','stories','garagepl',
+                                                  'driveway','recroom','fullbase','gashw','airco','prefarea'],
+                                attribute_column = "AttributeName",
+                                value_column = "AttributeValue",
+                                accumulate = 'homestyle')
+
+        upvt_test = Unpivoting(data = housing_test, id_column = 'sn', 
+                               target_columns = ['price','lotsize','bedrooms','bathrms','stories','garagepl','driveway',
+                                                 'recroom','fullbase','gashw','airco','prefarea'],
+                               attribute_column = "AttributeName", value_column = "AttributeValue",
+                               accumulate = 'homestyle')
+
+        NaiveBayes_out1 = NaiveBayes(data=upvt_train.result, 
+                                     response_column='homestyle',
+                                     attribute_name_column='AttributeName', 
+                                     attribute_value_column='AttributeValue',
+                                     numeric_attributes=['price','lotsize','bedrooms','bathrms','stories','garagepl'], 
+                                     categorical_attributes=['driveway','recroom','fullbase','gashw','airco','prefarea'])
+
+        NaiveBayesPredict_out1 = TDNaiveBayesPredict(data=upvt_test.result, object=NaiveBayes_out1, id_column='sn',
+                                                     attribute_name_column='AttributeName',
+                                                     attribute_value_column='AttributeValue',
+                                                     responses=['Classic', 'Eclectic', 'bungalow'],
+                                                     accumulate='homestyle',
+                                                     output_prob=True
+                                                     )
+
+        # Print the result DataFrame.
+        print( NaiveBayesPredict_out1.result)
+    
+    """

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

@@ -0,0 +1,142 @@
+def TFIDF(data = None, doc_id_column = None, token_column = None,
+          tf_normalization = "NORMAL", idf_normalization = "LOG", 
+          regularization = "NONE", accumulate = None,
+          **generic_arguments):
+    
+    """
+    DESCRIPTION:
+        Function takes any document set and computes the Term Frequency (TF), 
+        Inverse Document Frequency (IDF), and Term Frequency Inverse Document 
+        Frequency (TF-IDF) scores for each term.
+    
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame that contains
+            the document id and the term.
+            Types: teradataml DataFrame
+        
+        doc_id_column:
+            Required Argument.
+            Specifies the name of the column in "data" that contains the 
+            document identifier.
+            Types: str
+        
+        token_column:
+            Required Argument.
+            Specifies the name of the column in "data" that contains the tokens.
+            Types: str
+        
+        tf_normalization:
+            Optional Argument.
+            Specifies the normalization method for calculating the term frequency (TF).
+            Default Value: "NORMAL"
+            Permitted Values: BOOL, COUNT, NORMAL, LOG, AUGMENT
+            Types: str
+        
+        idf_normalization:
+            Optional Argument.
+            Specifies the normalization method for calculating the inverse 
+            document frequency (IDF).
+            Default Value: "LOG"
+            Permitted Values: UNARY, LOG, LOGNORM, SMOOTH
+            Types: str
+        
+        regularization:
+            Optional Argument.
+            Specifies the regularization method for calculating the TF-IDF score. 
+            Default Value: "NONE"
+            Permitted Values: L2, L1, NONE
+            Types: str
+        
+        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)
+
+        **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 TFIDF.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as  TFIDFObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            result
+    
+    
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+    
+    
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage, before importing the 
+        #        function in user space.
+        #     2. User can import the function, if it is available on 
+        #        Vantage user is connected to.
+        #     3. To check the list of analytic functions available on 
+        #        Vantage user connected to, use 
+        #        "display_analytic_functions()".
+        
+        # Load the example data.
+        load_example_data('naivebayestextclassifier',"token_table")
+        
+        # Create teradataml DataFrame objects.
+        inp = DataFrame.from_table('token_table')
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+        
+        # Import function  TFIDF.
+        from teradataml import  TFIDF
+        
+        # Example 1 : Compute the TF, IDF and TF-IDF scores
+        #             for each term in the input data.
+        TFIDF_out = TFIDF(data=inp, 
+                          doc_id_column='doc_id',
+                          token_column='token',
+                          tf_normalization = "LOG", 
+                          idf_normalization = "SMOOTH", 
+                          regularization = "L2",
+                          accumulate=['category'])
+        
+        # Print the result DataFrame.
+        print(TFIDF_out.result)
+    """

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

@@ -0,0 +1,216 @@
+def Unpivoting(data = None, id_column = None, target_columns = None,
+                alias_names = None, attribute_column = "AttributeName", value_column = "AttributeValue",
+                accumulate = None, include_nulls = False, input_types = False, output_varchar = False,
+                indexed_attribute = False, include_datatypes = False,
+                **generic_arguments):
+    
+    """
+    DESCRIPTION:
+        Function unpivots the data, that is, changes the data from
+        dense format to sparse format.
+    
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+        
+        id_column:
+            Required Argument.
+            Specifies the name of the column in "data" which contains the input data identifier.
+            Types: str
+        
+        target_columns:
+            Required Argument.
+            Specifies the name(s) of input teradataml DataFrame column(s) which contains the data for  
+            unpivoting.
+            Types: str OR list of Strings (str)
+
+            Optional Argument.
+            Specifies alternate names for the values in the 'attribute_column'.
+            Types: str OR list of strs
+
+        alias_names:
+            Optional Argument.
+            Specifies alternate names for the values in the 'attribute_column'. 
+            column.
+            Types: str OR list of strs
+        
+        attribute_column:
+            Optional Argument.
+            Specifies the name of the column in the output DataFrame, which holds the names of pivoted columns.
+            Default Value: "AttributeName"
+            Types: str
+        
+        value_column:
+            Optional Argument.
+            Specifies the name of the column in the output DataFrame, which holds the values of pivoted columns.
+            Default Value: "AttributeValue"
+            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)
+        
+        include_nulls:
+            Optional Argument.
+            Specifies whether or not to include nulls in the transformation.
+            Default Value: False
+            Types: bool
+        
+        input_types:
+            Optional Argument.
+            Specifies whether attribute values should be organized into multiple columns based on data type groups.
+            Note:
+                * 'input_types' argument cannot be used when output_varchar is set to True.
+            Default Value: False
+            Types: bool
+        
+        output_varchar:
+            Optional Argument.
+            Specifies whether to output the 'value_column' in varchar format regardless of its data type.
+            Note:
+                * 'output_varchar' argument cannot be used when input_types is set to True.
+            Default Value: False
+            Types: bool
+        
+        indexed_attribute:
+            Optional Argument.
+            Specifies whether to output the column indexes instead of column names in AttributeName column. 
+            When set to True, outputs the column indexes instead of column names.
+            Default Value: False
+            Types: bool
+        
+        include_datatypes:
+            Optional Argument.
+            Specifies whether to output the original datatype name. When set to True,
+            outputs the original datatype name.
+            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: 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 Unpivoting.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as UnpivotingObj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            result
+    
+    
+    RAISES:
+        TeradataMlException, TypeError, ValueError
+    
+    
+    EXAMPLES:
+        # Notes:
+        #     1. Get the connection to Vantage, before importing the 
+        #        function in user space.
+        #     2. User can import the function, if it is available on 
+        #        Vantage user is connected to.
+        #     3. To check the list of analytic functions available on 
+        #        Vantage user connected to, use 
+        #        "display_analytic_functions()".
+        
+        # Load the example data.
+        load_example_data('unpivot', 'unpivot_input')
+        
+        # Create teradataml DataFrame objects.
+        upvt_inp = DataFrame('unpivot_input')
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+        
+        # Import function  Unpivoting.
+        from teradataml import  Unpivoting
+        
+        # Example 1 : Unpivot the data.
+        upvt1 = Unpivoting(data = upvt_inp, 
+                           id_column = 'sn', 
+                           target_columns = 'city',
+                           accumulate = 'week',
+                           include_nulls = True)
+        
+        # Print the result DataFrame.
+        print( upvt1.result)
+
+        # Example 2 : Unpivot the data with alternate names for the values in
+        #             the AttributeName output column.
+        upvt2= Unpivoting(data = upvt_inp, 
+                          id_column = 'sn',
+                          target_columns = 'city',
+                          alias_names = 'city_us', 
+                          attribute_column = "Attribute", 
+                          value_column = "value",
+                          accumulate = 'week', 
+                          include_nulls = True)
+
+        # Print the result DataFrame.
+        print( upvt2.result)
+
+        # Example 3 : Unpivot the data with multiple target columns and output
+        #             data types.
+        upvt3 = Unpivoting(data = upvt_inp, 
+                           id_column = 'sn', 
+                           target_columns = ['city','pressure'],
+                           attribute_column = "Attribute", 
+                           value_column = "value",
+                           accumulate = 'week', 
+                           include_nulls = True,
+                           indexed_attribute = True, 
+                           include_datatypes = True)
+
+        # Print the result DataFrame.
+        print( upvt3.result)
+    
+        # Example 4 : Unpivot the data with multiple target columns and output
+        #             the input types.
+        upvt4 = Unpivoting(data = upvt_inp, 
+                           id_column = 'sn', 
+                           target_columns = ['city','temp'],
+                           accumulate = 'week', 
+                           include_nulls = True, 
+                           input_types = True)
+                        
+        # Print the result DataFrame.
+        print( upvt4.result)
+
+    """

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

@@ -1,7 +1,7 @@
 def XGBoost(formula=None, data=None, input_columns=None, response_column=None, max_depth=5,
             num_boosted_trees=-1, min_node_size=1, seed=1, model_type='REGRESSION',
-            coverage_factor=1.0, min_impurity=0.0, lambda1=100000,
-            shrinkage_factor=0.1, column_sampling=1.0, iter_num=10, tree_size=-1,
+            coverage_factor=1.0, min_impurity=0.0, lambda1=1, shrinkage_factor=0.5, 
+            column_sampling=1.0, iter_num=10, tree_size=-1, base_score=0.0,
             **generic_arguments):
     """
     DESCRIPTION:
@@ -174,7 +174,7 @@ def XGBoost(formula=None, data=None, input_columns=None, response_column=None, m
             Notes:
                 * The "lambda1" must be in the range [0, 100000].
                 * The value 0 specifies no regularization.
-            Default Value: 100000
+            Default Value: 1
             Types: float OR int
 
         shrinkage_factor:
@@ -185,7 +185,7 @@ def XGBoost(formula=None, data=None, input_columns=None, response_column=None, m
             Notes:
                 * The "shrinkage_factor" is a DOUBLE PRECISION value in the range (0, 1].
                 * The value 1 specifies no shrinkage.
-            Default Value: 0.1
+            Default Value: 0.5
             Types: float
 
         column_sampling:
@@ -217,6 +217,14 @@ def XGBoost(formula=None, data=None, input_columns=None, response_column=None, m
             Default Value: -1
             Types: int
 
+        base_score:
+            Optional Argument.
+            Specifies the initial prediction value for all data points.
+            Note:
+                * The "base_score" must be in the range [-1e50, 1e50].
+            Default Value: 0.0
+            Types: float
+
         **generic_arguments:
             Specifies the generic keyword arguments SQLE functions accept. Below
             are the generic keyword arguments:

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

@@ -1,6 +1,6 @@
 def XGBoostPredict(newdata=None, object=None, id_column=None, num_boosted_tree=1000,
                    iter_num=3, accumulate=None, output_prob=False, model_type="REGRESSION",
-                   output_responses=None,  **generic_arguments):
+                   output_responses=None, detailed=False, **generic_arguments):
     """
     DESCRIPTION:
         The XGBoostPredict() function runs the predictive algorithm based on the model generated
@@ -123,6 +123,12 @@ def XGBoostPredict(newdata=None, object=None, id_column=None, num_boosted_tree=1
                   'Classification'.
             Types: str OR list of str(s)
 
+        detailed:
+            Optional Argument.
+            Specifies whether to output detailed information of each prediction.
+            Default Value: False
+            Types: bool
+
         **generic_arguments:
             Specifies the generic keyword arguments SQLE functions accept. Below
             are the generic keyword arguments: