teradataml 20.0.0.1__py3-none-any.whl → 20.0.0.3__py3-none-any.whl

teradataml/data/covid_confirm_sd.csv

@@ -0,0 +1,83 @@
+city,row_axis,cnumber
+SanDiego,1,2
+SanDiego,2,2
+SanDiego,3,2
+SanDiego,4,2
+SanDiego,5,3
+SanDiego,6,3
+SanDiego,7,3
+SanDiego,8,3
+SanDiego,9,3
+SanDiego,10,3
+SanDiego,11,3
+SanDiego,12,5
+SanDiego,13,8
+SanDiego,14,10
+SanDiego,15,16
+SanDiego,16,55
+SanDiego,17,55
+SanDiego,18,60
+SanDiego,19,80
+SanDiego,20,127
+SanDiego,21,127
+SanDiego,22,155
+SanDiego,23,201
+SanDiego,24,226
+SanDiego,25,238
+SanDiego,26,293
+SanDiego,27,341
+SanDiego,28,413
+SanDiego,29,484
+SanDiego,30,515
+SanDiego,31,603
+SanDiego,32,733
+SanDiego,33,849
+SanDiego,34,966
+SanDiego,35,1112
+SanDiego,36,1209
+SanDiego,37,1326
+SanDiego,38,1404
+SanDiego,39,1454
+SanDiego,40,1530
+SanDiego,41,1628
+SanDiego,42,1693
+SanDiego,43,1761
+SanDiego,44,1804
+SanDiego,45,1847
+SanDiego,46,1930
+SanDiego,47,2012
+SanDiego,48,2087
+SanDiego,49,2158
+SanDiego,50,2213
+SanDiego,51,2268
+SanDiego,52,2325
+SanDiego,53,2491
+SanDiego,54,2643
+SanDiego,55,2826
+SanDiego,56,2943
+SanDiego,57,2943
+SanDiego,58,3043
+SanDiego,59,3141
+SanDiego,60,3432
+SanDiego,61,3432
+SanDiego,62,3564
+SanDiego,63,3711
+SanDiego,64,3927
+SanDiego,65,3927
+SanDiego,66,4020
+SanDiego,67,4319
+SanDiego,68,4319
+SanDiego,69,4429
+SanDiego,70,4662
+SanDiego,71,4776
+SanDiego,72,5065
+SanDiego,73,5161
+SanDiego,74,5161
+SanDiego,75,5391
+SanDiego,76,5391
+SanDiego,77,5662
+SanDiego,78,5836
+SanDiego,79,5836
+SanDiego,80,6026
+SanDiego,81,6140
+SanDiego,82,6140

teradataml/data/dataframe_example.json

@@ -143,5 +143,31 @@
     "smoker" : "varchar(4)",
     "region" : "varchar(12)",
     "charges" : "real"
-   }
+   },
+   "grocery_transaction":{
+    "tranid" : "integer",
+    "period" : "varchar(20)",
+    "storeid" : "integer",
+    "region" : "varchar(20)",
+    "item" : "varchar(20)",
+    "sku" : "integer",
+    "category" : "varchar(20)"
+   },
+  "medical_readings": {
+    "patient_id":  "BIGINT",
+    "record_timestamp":  "timestamp",
+    "glucose":  "BIGINT",
+    "blood_pressure":  "BIGINT",
+    "insulin":  "BIGINT",
+    "diabetes_pedigree_function":  "FLOAT",
+    "outcome": "BIGINT"
+  },
+  "patient_profile": {
+    "patient_id":  "BIGINT",
+    "record_timestamp":  "timestamp",
+    "pregnancies":  "BIGINT",
+    "age":  "BIGINT",
+    "bmi":  "FLOAT",
+    "skin_thickness":  "FLOAT"
+  }
 }

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

@@ -0,0 +1,132 @@
+def CFilter(data = None, target_column = None, transaction_id_columns = None,
+            partition_columns = None, max_distinct_items = 100,
+            **generic_arguments):
+    
+    """
+    DESCRIPTION:
+        Function calculates several statistical measures of how likely 
+        each pair of items is to be purchased together.
+    
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+        
+        target_column:
+            Required Argument.
+            Specifies name of the column from the "data" containing data for filtration.
+            Types: str
+        
+        transaction_id_columns:
+            Required Argument.
+            Specifies the name of the columns in "data" containing transaction id that defines the groups of items listed
+            in the input columns that are purchased together.
+            Types: str OR list of Strings (str)
+        
+        partition_columns:
+            Optional Argument.
+            Specifies the name of the column in "data" to partition the data on.
+            Types: str OR list of Strings (str)
+        
+        max_distinct_items:
+            Optional Argument.
+            Specifies the maximum size of the item set. 
+            Default Value: 100
+            Types: int
+        
+        **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 CFilter.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as CFilterObj.<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("dataframe", ["grocery_transaction"])
+        
+        # Create teradataml DataFrame objects.
+        df = DataFrame.from_table("grocery_transaction")
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+        
+        # Import function CFilter.
+        from teradataml import CFilter
+        
+        # Example 1: CFilter function to calculate the statistical measures
+        #            of how likely each pair of items is to be purchased together, without
+        #            specifying the partition_columns.
+        CFilter_out = CFilter(data=df, 
+                              target_column='item',
+                              transaction_id_columns = 'tranid',
+                              max_distinct_items=100)
+        
+        # Print the result DataFrame.
+        print(CFilter_out.result)
+
+        # Example 2: CFilter function to calculate the statistical measures
+        #            of how likely each pair of items is to be purchased together,
+        #            specifying the partition_columns.
+        CFilter_out2 = CFilter(data=df, 
+                               target_column='item', 
+                               transaction_id_columns = 'tranid',
+                               partiton_columns='storeid',
+                               max_distinct_items=100)
+
+        # Print the result DataFrame.
+        print(CFilter_out2.result)
+    """

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

@@ -0,0 +1,162 @@
+def  NaiveBayes(data = None, response_column = None, numeric_inputs = None,
+                categorical_inputs = None, attribute_name_column = None,
+                attribute_value_column = None, attribute_type = None,
+                numeric_attributes = None, categorical_attributes = None,
+                **generic_arguments):
+    """
+    DESCRIPTION:
+        Function generates classification model using NaiveBayes 
+        algorithm.
+        The Naive Bayes classification algorithm uses a training dataset with known discrete outcomes
+        and either discrete or continuous numeric input variables, along with categorical variables, to generate a model.
+        This model can then be used to predict the outcomes of future observations based on their input variable values.
+    
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame .
+            Types: teradataml DataFrame
+        
+        response_column:
+            Required Argument.
+            Specifies the name of the column in "data" containing response values.
+            Types: str
+        
+        numeric_inputs:
+            Optional Argument.
+            Specifies the names of the columns in "data" containing numeric attributes values.
+            Types: str OR list of Strings (str)
+        
+        categorical_inputs:
+            Optional Argument.
+            Specifies the names of the columns in "data" containing categorical attributes values.
+            Types: str OR list of Strings (str)
+        
+        attribute_name_column:
+            Optional Argument.
+            Specifies the names of the columns in "data" containing attributes names.
+            Types: str
+        
+        attribute_value_column:
+            Optional Argument.
+            Specifies the names of the columns in "data" containing attributes values.
+            Types: str
+        
+        attribute_type:
+            Optional Argument, Required if "data" is in sparse format and
+            both "numeric_attributes" and "categorical_attributes" are not provided.
+            Specifies the attribute type. 
+            Permitted Values: 
+                * ALLNUMERIC - if all the attributes are of numeric type.
+                * ALLCATEGORICAL - if all the attributes are of categorical type.
+            Types: str
+        
+        numeric_attributes:
+            Optional Argument.
+            Specifies the numeric attributes names.
+            Types: str OR list of strs
+        
+        categorical_attributes:
+            Optional Argument.
+            Specifies the categorical attributes names.
+            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 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  NaiveBayes.
+        Output teradataml DataFrames can be accessed using attribute 
+        references, such as  NaiveBayesObj.<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")
+        
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+        
+        # Import function  NaiveBayes.
+        from teradataml import  NaiveBayes, Unpivoting
+        
+        # Example 1: NaiveBayes function to generate classification model 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'])
+        
+        # Print the result DataFrame.
+        print( NaiveBayes_out.result)
+
+        # Example 2: NaiveBayes function to generate classification model using Sparse input.
+        
+        # Unpivoting the data for sparse input to naive bayes.
+        upvt_data = 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')
+
+        NaiveBayes_out = NaiveBayes(data=upvt_data.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'])
+
+        # Print the result DataFrame.
+        print( NaiveBayes_out.result)
+    """

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

@@ -16,6 +16,8 @@ def OutlierFilterFit(data=None, target_columns=None, group_columns=None, lower_p
             * For information about PTCs, see Teradata Vantage™ - Analytics
               Database International Character Set Support.
             * This function does not support KanjiSJIS or Graphic data types.
+            * This function does not support "data_partition_column" and "data_order_column" 
+              if the corresponding Vantage version is greater than or equal to 17.20.03.20.
 
 
     PARAMETERS: