teradataml 20.0.0.8__py3-none-any.whl

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

@@ -0,0 +1,281 @@
+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, detailed=False, **generic_arguments):
+    """
+    DESCRIPTION:
+        The XGBoostPredict() function runs the predictive algorithm based on the model generated
+        by XGBoost(). The XGBoost() function, also known as eXtreme Gradient Boosting, performs
+        classification or regression analysis on datasets.
+
+        XGBoostPredict() performs prediction for test input data using multiple simple trees in
+        the trained model. The test input data should have the same attributes as used during
+        the training phase, which can be up to 2046. These attributes are used to score based
+        on the trees in the model.
+
+        The output contains prediction for each data point in the test data based on regression
+        or classification. The prediction probability is computed based on the majority vote
+        from participating trees. A higher probability implies a more confident prediction by
+        the model. Majority of the trees result in the same prediction.
+
+        Notes:
+            * The processing time is controlled by (proportional to):
+                * The number of boosted trees used for prediction from the model (controlled
+                  by "num_boosted_trees").
+                * The number of iterations (sub-trees) used for prediction from the model
+                  in each boosted tree (controlled by "iter_num").
+
+            A careful choice of these parameters can be used to control the processing time.
+            When the boosted trees size grows more than what can fit in memory, the trees are
+            cached in a local spool space, which may impact the performance of the function
+            compared to the case when all trees fit in memory.
+
+    PARAMETERS:
+        newdata:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the input data.
+            Types: teradataml DataFrame
+
+        object:
+            Required Argument.
+            Specifies the teradataml DataFrame containing the model data generated by XGBoost()
+            function or the instance of XGBoost.
+            Types: teradataml DataFrame or XGBoost
+
+        id_column:
+            Required Argument.
+            Specifies the input data column name that contains a unique
+            identifier for each test point in the test set.
+            Note:
+                * Input column names with double quotation marks are not allowed for this function.
+            Types: str
+
+        num_boosted_tree:
+            Optional Argument.
+            Specifies how many boosted trees to use to make predictions.
+            A combination of both 'task_Index' and 'tree_num' in the model table determines
+            the AMPID and number of trees generated by that AMP. As we order the model table
+            with these two arguments, the number of boosted trees that are loaded are based
+            on this order.
+            For example, if there are two AMPs on the system and AMP 1 ('task_index': 0) generates
+            three boosted trees ('tree_num':1,2,3), while AMP 2 ('task_index': 1) generate two boosted
+            trees ('tree_num': 1,2). Then, "num_boosted_tree"(4) loads three boosted trees from AMP1
+            ('task_index': 0) and one boosted tree from AMP2 ('task_index': 1).
+            As one boosted tree is skipped altogether from loading it in memory and making predictions,
+            this results in a faster elapsed time for queries compared to loading all trees in memory.
+            However, this can also lead to loss in prediction accuracy. In addition, any unique tree
+            is determined by 'task_index', 'tree_id' and 'iter_num' in the model table.
+            Default Value: 1000
+            Types: int
+
+        iter_num:
+            Optional Argument.
+            Specifies how many iterations to load for each boosted tree to make predictions.
+            For example, AMP1 ('task_index':0) generates three boosted trees ('tree_num': 1,2,3)
+            with each tree having four iterations ('iter':1,2,3,4). There are 12 trees in total.
+            "iter_num"(2) only loads two iterations per boosted tree, that is, only six trees
+            are loaded for this example.
+            As some trees are skipped from being loaded in memory and predictions are made
+            without them, this results in a faster elapsed time for queries compared to
+            loading all trees in memory, but also lead to loss in prediction accuracy.
+            Default Value: 3
+            Types: int
+
+        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)
+
+        output_prob:
+            Optional Argument.
+            Specifies whether the function should output the probability for each
+            "output_responses".
+            Notes:
+                * If "output_prob" is true and "output_responses" are not provided,
+                  output the probability of the predicted class.
+                * The "output_prob" argument works only when "model_type" is
+                  'Classification'.
+            Default Value: False
+            Types: bool
+
+        model_type:
+            Optional Argument.
+            Specifies whether the analysis is a regression (continuous response variable) or
+            a multiple-class classification (predicting result from the number of classes).
+            For 'Classification', output the prediction column as integers. These integral
+            values represent different categories, and so are better observed as an integer
+            column. To make the output schema for prediction column as an integer, set
+            "model_type" as 'Classification'.
+            Permitted Values:
+                * Regression
+                * Classification
+            Default Value: Regression
+            Types: str
+
+        output_responses:
+            Optional Argument.
+            Specifies the classes for which to output probabilities.
+            Notes:
+                * If "output_prob" is true and "output_responses" are not provided,
+                  output the probability of the predicted class.
+                * The "output_responses" argument works only when "model_type" is
+                  '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:
+                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 XGBoostPredict.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as XGBoostPredictObj.<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")
+        load_example_data("byom", "iris_input")
+
+        # Create teradataml DataFrame objects.
+        titanic = DataFrame.from_table("titanic")
+        iris_input = DataFrame("iris_input")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: This example takes titanic data as input, and generates the Regression
+        #            model using XGBoost(). Using XGBoostPredict() function to predict the
+        #            fare with the Regression model generated by XGBoost().
+
+        # Create 2 samples of input data - sample 1 will have 80% of total rows and
+        # sample 2 will have 20% of total rows.
+        titanic_sample = titanic.sample(frac=[0.8, 0.2])
+
+        # Create train dataset from sample 1 by filtering on "sampleid" and drop
+        # "sampleid" column as it is not required for training model.
+        titanic_train = titanic_sample[titanic_sample.sampleid == "1"].drop("sampleid", axis = 1)
+
+        # Create test dataset from sample 2 by filtering on "sampleid" and
+        # drop "sampleid" column as it is not required for scoring.
+        titanic_test = titanic_sample[titanic_sample.sampleid == "2"].drop("sampleid", axis = 1)
+
+        XGBoost_out_1 = XGBoost(data=titanic_train,
+                                input_columns=["age", "survived", "pclass"],
+                                response_column = 'fare',
+                                max_depth=3,
+                                lambda1 = 1000.0,
+                                model_type='Regression',
+                                seed=-1,
+                                shrinkage_factor=0.1,
+                                iter_num=2)
+
+        # XGBoostPredict() predicts the result using generated Regression model by
+        # XGBoost() and "newdata".
+        XGBoostPredict_out_1 = XGBoostPredict(newdata=titanic_test,
+                                              object=XGBoost_out_1.result,
+                                              id_column='passenger',
+                                              object_order_column=['task_index', 'tree_num',
+                                                                   'iter', 'tree_order'])
+
+        # Print the result DataFrame.
+        print(XGBoostPredict_out_1.result)
+
+        # Example 2: This example takes titanic data, and generates the Classification
+        #            model using XGBoost(). Using XGBoostPredict() function to predict the fare
+        #            with the Classification model generated by XGBoost(). Provides the classes for
+        #            which to output the probabilities.
+
+        # Create 2 samples of input data - sample 1 will have 80% of total rows and
+        # sample 2 will have 20% of total rows.
+        iris_sample = iris_input.sample(frac=[0.8, 0.2])
+
+        # Create train dataset from sample 1 by filtering on "sampleid" and drop
+        # "sampleid" column as it is not required for training model.
+        iris_train = iris_sample[iris_sample.sampleid == "1"].drop("sampleid", axis = 1)
+
+        # Create test dataset from sample 2 by filtering on "sampleid" and
+        # drop "sampleid" column as it is not required for scoring.
+        iris_test = iris_sample[iris_sample.sampleid == "2"].drop("sampleid", axis = 1)
+
+        # Training the model.
+        XGBoost_out_2 = XGBoost(data=iris_train,
+                                input_columns=['sepal_length', 'sepal_width', 'petal_length', 'petal_width'],
+                                response_column = 'species',
+                                max_depth=3,
+                                lambda1 = 10000.0,
+                                model_type='Classification',
+                                seed=-1,
+                                shrinkage_factor=0.1,
+                                iter_num=2)
+
+        # XGBoostPredict() predicts the result using generated Classification model by
+        # XGBoost() and XGBoost object as input.
+        XGBoostPredict_out_2 = XGBoostPredict(newdata=iris_test,
+                                              object=XGBoost_out_2,
+                                              id_column='id',
+                                              model_type='Classification',
+                                              num_boosted_trees=3,
+                                              iter_num=2,
+                                              output_prob=True,
+                                              output_responses=['1', '2', '3'],
+                                              object_order_column=['task_index', 'tree_num', 'iter',
+                                                                   'class_num', 'tree_order'])
+
+        # Print the result DataFrame.
+        print(XGBoostPredict_out_2.result)
+    """

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

@@ -0,0 +1,220 @@
+def ZTest(data=None, alpha=0.05, first_sample_column=None, second_sample_column=None,
+          alternate_hypothesis="two-tailed", first_sample_variance=None,
+          second_sample_variance=None, mean_under_h0=0, sample_name_column=None,
+          sample_value_column=None, first_sample_name=None, second_sample_name=None,
+          **generic_arguments):
+    
+    """
+    DESCRIPTION:
+        ZTest() function tests the equality of two means under the assumption that the
+        population variances are known. For large samples, sample variances
+        approximate population variances, so it uses sample variances
+        instead of population variances in the test statistic.
+
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the input teradataml DataFrame.
+            Types: teradataml DataFrame
+
+        alpha:
+            Optional Argument.
+            Specifies the value of alpha in hypothesis test function.
+            Default Value: 0.05
+            Types: float
+
+        first_sample_column:
+            Optional Argument.
+            Specifies the first sample column in Z-Test.
+            Types: str
+
+        second_sample_column:
+            Optional Argument.
+            Specifies the second sample column in Z-Test.
+            Types: str
+
+        alternate_hypothesis:
+            Optional Argument.
+            Specifies the alternate hypothesis.
+            Permitted Values:
+                * lower-tailed - Alternate hypothesis (H 1): μ < μ0.
+                * upper-tailed - Alternate hypothesis (H 1): μ > μ0.
+                * two-tailed - Rejection region is on two sides of sampling distribution
+                               of test statistic.
+                               Two-tailed test considers both lower and upper tails of
+                               distribution of test statistic.
+                               Alternate hypothesis (H 1): μ ≠ μ0
+            Default Value: "two-tailed"
+            Types: str
+
+        first_sample_variance:
+            Optional Argument.
+            Specifies the first sample variance.
+            Types: float
+
+        second_sample_variance:
+            Optional Argument.
+            Specifies the second sample variance.
+            Types: float
+
+        mean_under_h0:
+            Optional Argument.
+            Specifies the mean under the null hypothesis.
+            Default Value: 0
+            Types: float
+
+        sample_name_column:
+            Optional Argument.
+            Specifies the column in the "data" containing the names of the samples 
+            included in the Z-Test.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+        
+        sample_value_column:
+            Optional Argument.
+            Specifies the column in the "data" containing the values for each sample member.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+        
+        first_sample_name:
+            Optional Argument.
+            Specifies the name of the first sample included in the Z-Test.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+        
+        second_sample_name:
+            Optional Argument.
+            Specifies the name of the second sample included in the Z-Test.
+            Note:
+                * This argument is used when data contains sample names in a column
+                  and sample values in another column.
+            Types: str
+
+        **generic_arguments:
+            Specifies the generic keyword arguments SQLE functions accept.
+            Below are the generic keyword arguments:
+                persist:
+                    Optional Argument.
+                    Specifies whether to persist the results of the function in a table or not.
+                    When set to True, results are persisted in a table; otherwise, results
+                    are garbage collected at the end of the session.
+                    Default Value: False
+                    Types: boolean
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the function in a volatile table or not.
+                    When set to True, results are stored in a volatile table, otherwise not.
+                    Default Value: False
+                    Types: boolean
+
+            Function allows the user to partition, hash, order or local order the input
+            data. These generic arguments are available for each argument that accepts
+            teradataml DataFrame as input and can be accessed as:
+                * "<input_data_arg_name>_partition_column" accepts str or list of str (Strings)
+                * "<input_data_arg_name>_hash_column" accepts str or list of str (Strings)
+                * "<input_data_arg_name>_order_column" accepts str or list of str (Strings)
+                * "local_order_<input_data_arg_name>" accepts boolean
+            Note:
+                These generic arguments are supported by teradataml if the underlying SQL Engine
+                function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of ZTest.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as ZTestObj.<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"])
+        load_example_data('ztest', 'boston2cols')
+
+        # Create teradataml DataFrame object.
+        titanic_data = DataFrame.from_table("titanic")
+        bostonCol = DataFrame.from_table("boston2cols")
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Example 1: Perform ZTest analysis on input data column that
+        #            contains data for the first sample population and
+        #            variance of the first sample population.
+        obj = ZTest(data=titanic_data,
+                    first_sample_column='age',
+                    first_sample_variance=5)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # Example 2: Perform ZTest analysis on input data column that
+        #            contains data for the first and second sample
+        #            population and variance of the first and second sample
+        #            population by specifying data_partition_column as ANY.
+
+        # To partition data using ANY, one must import 'PartitionKind' module first,
+        # then pass PartitionKind.ANY as input to "data_partition_column" argument.
+        from teradataml import PartitionKind
+        obj = ZTest(data=titanic_data,
+                    alpha=0.5,
+                    data_partition_column=PartitionKind.ANY,
+                    data_order_column='pclass',
+                    first_sample_column='age',
+                    second_sample_column='parch',
+                    alternate_hypothesis='two-tailed',
+                    first_sample_variance=5,
+                    second_sample_variance=8,
+                    mean_under_h0=0)
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # Example 3: Perform ZTest analysis on input data column that
+        #            contains data for the first and second sample
+        #            population and variance of the first and second sample
+        #            population by specifying sample_name_column, sample_value_column,
+        #            first_sample_name and second_sample_name.
+        obj = ZTest(data=bostonCol,
+                    first_sample_name='NOX',
+                    second_sample_name='RM',
+                    sample_name_column='groupName',
+                    sample_value_column='groupValue')
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+        # ExPerform ZTest analysis on input data column that
+        #            contains data for the first sample population and
+        #            variance of the first sample population by specifying
+        #            sample_name_column, sample_value_column.
+        obj = ZTest(data=boston,
+                    first_sample_name='NOX',
+                    sample_name_column='groupName',
+                    sample_value_column='groupValue')
+
+        # Print the result DataFrame.
+        print(obj.result)
+
+
+
+    """