teradataml 20.0.0.2__py3-none-any.whl → 20.0.0.3__py3-none-any.whl

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

@@ -1,4 +1,4 @@
-def TextParser(data=None, object=None, text_column=None, covert_to_lowercase=True, stem_tokens=False,
+def TextParser(data=None, object=None, text_column=None, convert_to_lowercase=True, stem_tokens=False,
                remove_stopwords=False, accumulate=None, delimiter=" \t\n\f\r",
                punctuation="!#$%&()*+,-./:;?@\^_`{|}~", token_col_name=None, **generic_arguments):
     """
@@ -38,7 +38,7 @@ def TextParser(data=None, object=None, text_column=None, covert_to_lowercase=Tru
             Specifies the name of the input data column whose contents are to be tokenized.
             Types: str
 
-        covert_to_lowercase:
+        convert_to_lowercase:
             Optional Argument.
             Specifies whether to convert the text in "text_column" to lowercase.
             Default Value: True
@@ -165,7 +165,7 @@ def TextParser(data=None, object=None, text_column=None, covert_to_lowercase=Tru
         # Example 2 : Convert words in "text_data" column into their root forms.
         TextParser_out = TextParser(data=complaints,
                                     text_column="text_data",
-                                    covert_to_lowercase=True,
+                                    convert_to_lowercase=True,
                                     stem_tokens=True)
 
         # Print the result DataFrame.

teradataml/data/docs/tableoperator/docs_17_20/Image2Matrix.py

@@ -0,0 +1,118 @@
+def Image2Matrix(data=None,
+                 output='gray',
+                 **generic_arguments):
+    """
+    DESCRIPTION:
+        Image2Matrix() function converts an image to a matrix.
+        It converts JPEG or PNG images to matrixes with payload values being the pixel values.
+        Note:
+            * The image size cannot be greater than 16 MB.
+            * The image should not exceed 4,000,000 pixels.
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the teradataml DataFrame which has image details.
+            Types: Teradataml DataFrame
+
+        output:
+            Optional Argument.
+            Specifies the type of output matrix.
+            Default: 'gray'
+            Permitted Values:
+                'gray': Converts the image to a grayscale matrix.
+                'rgb': Converts the image to a RGB matrix.
+            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 Analytic Database
+                function supports, else an exception is raised.
+
+    RETURNS:
+        Instance of Image2Matrix.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as Image2Matrix.<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 UAF analytic functions available
+        #        on Vantage user connected to, use
+        #        "display_analytic_functions()".
+
+        # Check the list of available analytic functions.
+        display_analytic_functions()
+
+        # Import function Image2Matrix.
+        from teradataml import Image2Matrix
+        import teradataml
+
+        # Drop the image table if it is present.
+        try:
+            db_drop_table('imageTable')
+        except:
+            pass
+
+        # Create a table to store the image data.
+        execute_sql('CREATE TABLE imageTable(id INTEGER, image BLOB);')
+
+        # Load the image data into the fileContent variable.
+        file_dir = os.path.join(os.path.dirname(teradataml.__file__), "data")
+        with open(os.path.join(file_dir,'peppers.png'), mode='rb') as file:
+            fileContent = file.read()
+
+        # Insert the image data into the table.
+        sql = 'INSERT INTO imageTable VALUES(?, ?);'
+        parameters = (1, fileContent)
+        execute_sql(sql, parameters)
+
+        # Create a DataFrame for the image table.
+        imageTable = DataFrame('imageTable')
+
+        # Example 1: Convert the image to matrix with gray values.
+        image2matrix = Image2Matrix(data=imageTable.select(['id', 'image']), 
+                                    output='gray')
+
+        # Print the result DataFrame.
+        print(image2matrix.result)
+
+        # Example 2: Convert the image to matrix with rgb values.
+        image2matrix2 = Image2Matrix(data=imageTable.select(['id', 'image']), 
+                                     output='rgb')
+
+        # Print the result DataFrame.
+        print(image2matrix2.result)
+    """

teradataml/data/docs/uaf/docs_17_20/CopyArt.py

@@ -0,0 +1,145 @@
+def CopyArt(data=None, database_name = None,
+            table_name = None, map_name = None,
+            **generic_arguments):
+    """
+    DESCRIPTION:
+        CopyArt() function creates a copy of an existing analytics result table (ART).
+
+    PARAMETERS:
+        data:
+            Required Argument.
+            Specifies the ART data to be copied.
+            Types: DataFrame
+
+        database_name:
+            Required Argument.
+            Specifies the name of the destination database for copied ART.
+            Types: str
+
+        table_name:
+            Required Argument.
+            Specifies the name of the destination table for copied ART.
+            Types: str
+
+        map_name:
+            Optional Argument.
+            Specifies the name of the map for the destination ART.
+            By default, it refers to the map of the 'data'.
+            Types: str
+
+        **generic_arguments:
+            Specifies the generic keyword arguments of UAF functions.
+            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.
+                    Note that, when UAF function is executed, an
+                    analytic result table (ART) is created.
+                    Default Value: False
+                    Types: bool
+
+                volatile:
+                    Optional Argument.
+                    Specifies whether to put the results of the
+                    function in a volatile ART or not. When set to
+                    True, results are stored in a volatile ART,
+                    otherwise not.
+                    Default Value: False
+                    Types: bool
+
+                output_table_name:
+                    Optional Argument.
+                    Specifies the name of the table to store results.
+                    If not specified, a unique table name is internally
+                    generated.
+                    Types: str
+
+                output_db_name:
+                    Optional Argument.
+                    Specifies the name of the database to create output
+                    table into. If not specified, table is created into
+                    database specified by the user at the time of context
+                    creation or configuration parameter. Argument is ignored,
+                    if "output_table_name" is not specified.
+                    Types: str
+    
+    RETURNS:
+        Instance of CopyArt.
+        Output teradataml DataFrames can be accessed using attribute
+        references, such as obj.<attribute_name>.
+        Output teradataml DataFrame attribute name is:
+            1. 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 UAF analytic functions available
+        #        on Vantage user connected to, use
+        #        "display_analytic_functions()".
+
+        # Check the list of available UAF analytic functions.
+        display_analytic_functions(type="UAF")
+
+        # Import function CopyArt.
+        from teradataml import CopyArt, AutoArima
+
+        # Load the example data.
+        load_example_data("uaf", ["blood2ageandweight"])
+
+        # Create teradataml DataFrame object.
+        data = DataFrame.from_table("blood2ageandweight")
+
+        # Create teradataml TDSeries object.
+        data_series_df = TDSeries(data=data,
+                                  id="PatientID",
+                                  row_index="SeqNo",
+                                  row_index_style="SEQUENCE",
+                                  payload_field="BloodFat",
+                                  payload_content="REAL")
+
+        # Execute AutoArima function to create ART.
+        uaf_out = AutoArima(data=data_series_df,
+                            start_pq_nonseasonal=[1, 1],
+                            seasonal=False,
+                            constant=True,
+                            algorithm="MLE",
+                            fit_percentage=80,
+                            stepwise=True,
+                            nmodels=7,
+                            fit_metrics=True,
+                            residuals=True)
+
+        # Example 1: Execute CopyArt function to copy ART to a destination table name
+        #            with persist option.
+        res = CopyArt(data=uaf_out.result,
+                      database_name="alice",
+                      table_name="copied_table",
+                      persist=True)
+        print(res.result)
+
+        # Example 2: Execute CopyArt function to copy ART to a destination table name.
+        res = CopyArt(data=uaf_out.result,
+                      database_name="alice",
+                      table_name="copied_table2")
+
+        # Print the result DataFrame.
+        print(res.result)
+
+        # Example 3: Copy ART to a destination table name using uaf object.
+        res = uaf_out.copy(database_name="alice",
+                           table_name="copied_table3")
+
+        # Print the result DataFrame.
+        print(res.result)
+
+    """

teradataml/data/docs/uaf/docs_17_20/DickeyFuller.py

@@ -1,5 +1,5 @@
 def DickeyFuller(data=None, data_filter_expr=None, algorithm=None, 
-                 max_lags=None, drift_trend_formula=None, 
+                 max_lags=0,
                  **generic_arguments):
     """
     DESCRIPTION:
@@ -10,18 +10,23 @@ def DickeyFuller(data=None, data_filter_expr=None, algorithm=None,
         other factors.
 
         The following procedure is an example of how to use DickeyFuller() function:
-            * Run regression tests.
-            * Determine the algorithm for Dickey Fuller statistic data.
-            * Run DickeyFuller() function using the algorithm.
-            * (Result shows series contains unit roots) Use DIFF() and
-              SeasonalNormalize() functions to remove unit roots.
+            * Run DickeyFuller() on the time series being modeled.
+            * Retrieve the results of the DickeyFuller() test to determine if the
+              time series contains any unit roots.
+            * If unit roots are present, use a technique such as differencing such as Diff()
+              or seasonal normalization, such as SeasonalNormalize(), to create a new series,
+              then rerun the DickeyFuller() test to verify that the differenced or
+              seasonally-normalized series unit root are removed.
+            * If the result shows unit roots, use Diff() and SeasonalNormalize()
+              to remove unit roots.
 
 
     PARAMETERS:
         data:
             Required Argument.
-            Speciifes a single logical-runtime series as an input.
-            Types: TDSeries
+            Specifies a single logical-runtime series as an input or TDAnalyticResult which
+            contains ARTFITRESIDUALS layer.
+            Types: TDSeries, TDAnalyticResult
 
         data_filter_expr:
             Optional Argument.
@@ -34,26 +39,18 @@ def DickeyFuller(data=None, data_filter_expr=None, algorithm=None,
             Permitted Values:
                 * NONE: Random walk
                 * DRIFT: Random walk with drift
-                * TREND: Random walk with linear trend
                 * DRIFTNTREND: Random walk with drift and trend
-                * FORMULA: Random walk with selected drift, trend and
-                           auxiliary lags
+                * SQUARED: Random walk with drift, trend, and
+                           quadratic trend.
             Types: str
 
         max_lags:
             Optional Argument.
             Specifies the maximum number of lags to use with the regression
-            equation.
+            equation. Range is [0, 100]
+            DefaultValue: 0
             Types: int
 
-        drift_trend_formula:
-            Optional Argument.
-            Specifies the formula used to represent the drift and trend portions
-            of the regression.
-            Note:
-                * Valid only when "algorithm" is set to 'formula'.
-            Types: str
-
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions.
             Below are the generic keyword arguments:
@@ -136,7 +133,7 @@ def DickeyFuller(data=None, data_filter_expr=None, algorithm=None,
         #             for the presence of the unit roots using random walk with
         #             linear trend for regression.
         uaf_out = DickeyFuller(data=data_series_df,
-                               algorithm='TREND')
+                               algorithm='DRIFT')
 
         # Print the result DataFrame.
         print(uaf_out.result)

teradataml/data/jsons/sqle/17.20/TD_TextParser.json

@@ -80,7 +80,7 @@
 			"description": "Specifies whether to convert input text to lowercase.",
 			"datatype": "BOOLEAN",
 			"allowsLists": false,
-			"rName": "covert.to.lowercase",
+			"rName": "convert.to.lowercase",
 			"useInR": true,
 			"rOrderNum": 4
 		},

teradataml/data/jsons/sqle/20.00/TD_KMeans.json

@@ -0,0 +1,250 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "1",
+  "json_content_version": "1",
+  "function_name": "TD_KMeans",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Model Training",
+  "function_alias_name": "TD_KMeans",
+  "function_r_name": "aa.td_kmeans",
+  "short_description": "fastpath function to generate clustering model using KMeans algorithm.",
+  "long_description": "fastpath function to generate clustering model containing cluster centroids using KMeans algorithm.",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The relation that contains input data.",
+      "description": "The relation that contains input data.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "data",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InitialCentroidsTable",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "The relation that contains set of initial centroids.",
+      "description": "The relation that contains set of initial centroids.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "centroids.table",
+      "useInR": true,
+      "rOrderNum": 2
+    }
+  ],
+  "output_tables": [
+    {
+      "isOutputTable": true,
+      "omitPossible": true,
+      "name": "ModelTable",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the name of the table in which the generated KMeans model can be stored.",
+      "description": "Specifies the name of the table in which the generated KMeans model can be stored.",
+      "datatype": "TABLE_NAME",
+      "allowsLists": false,
+      "rName": "model.table",
+      "useInR": true,
+      "rOrderNum": 3
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "IdColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the column which is unique identifier of input row.",
+      "description": "Specifies the column which is unique identifier of input row.",
+      "datatype": "COLUMNS",
+      "allowsLists": false,
+      "rName": "id.column",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "NUMERIC","AIVECTOR","BYTE","VARBYTE"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "TargetColumns",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the columns/features to be used to cluster the data.",
+      "description": "Specifies the columns/features to be used to cluster the data.",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "target.columns",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "lowerBound": 1,
+      "upperBound": 2147483647,
+      "lowerBoundType": "EXCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "NumClusters",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the number of clusters to be produced. This argument is not allowed with InitialCentroidsTable provided.",
+      "description": "Specifies the number of clusters to be produced. This argument is not allowed with InitialCentroidsTable provided.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "num.clusters",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "lowerBound": 0,
+      "upperBound": 2147483647,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "Seed",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the random seed the algorithm uses for repeatable results. The algorithm uses the seed to randomly sample the input table rows as initial clusters.",
+      "description": "Specify the random seed the algorithm uses for repeatable results. The algorithm uses the seed to randomly sample the input table rows as initial clusters.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "seed",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "defaultValue": 0.0395,
+      "lowerBound": 0,
+      "upperBound": 1.797e+308,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "StopThreshold",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the convergence threshold. When the centroids move by less than this amount, the algorithm has converged.",
+      "description": "Specify the convergence threshold. When the centroids move by less than this amount, the algorithm has converged.",
+      "datatype": "DOUBLE",
+      "allowsLists": false,
+      "rName": "threshold",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "defaultValue": 10,
+      "lowerBound": 1,
+      "upperBound": 2147483647,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "MaxIterNum",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the maximum number of iterations that the algorithm runs before quitting if the convergence threshold has not been met.",
+      "description": "Specify the maximum number of iterations that the algorithm runs before quitting if the convergence threshold has not been met.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "iter.max",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "defaultValue": 1,
+      "lowerBound": 1,
+      "upperBound": 2147483647,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "NumInit",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "The number of times, the k-means algorithm will be run with different initial centroid seeds. The function will emit out the model having the least value of Total Within Cluster Squared Sum.",
+      "description": "The number of times, the k-means algorithm will be run with different initial centroid seeds. The function will emit out the model having the least value of Total Within Cluster Squared Sum.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "num.init",
+      "useInR": true,
+      "rOrderNum": 10
+    },
+    {
+      "defaultValue": false,
+      "name": "OutputClusterAssignment",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies whether to output Cluster Assignment.",
+      "description": "Specifies whether to output Cluster Assignment.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "output.cluster.assignment",
+      "useInR": true,
+      "rOrderNum": 11
+    },
+    {
+      "permittedValues": [
+        "RANDOM",
+        "KMEANS++"
+      ],
+      "defaultValue": "RANDOM",
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "InitialCentroidsMethod",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the initialization method to be used for selecting initial set of centroids.",
+      "description": "Specifies the initialization method to be used for selecting initial set of centroids.",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "initialcentroids.method",
+      "useInR": true,
+      "rOrderNum": 12
+    },
+    {
+      "defaultValue": 1,
+      "lowerBound": 1,
+      "upperBound": 4096,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "EmbeddingSize",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the embedding size of the vectors.",
+      "description": "Specify the embedding size of the vectors.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "embedding.size",
+      "useInR": true,
+      "rOrderNum": 13
+    }
+  ]
+}