teradataml 20.0.0.4__py3-none-any.whl → 20.0.0.6__py3-none-any.whl

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

@@ -1,6 +1,9 @@
-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="!#$%&()*+,-./:;?@\^_`{|}~", token_col_name=None, **generic_arguments):
+def TextParser(data=None, object=None, text_column=None, enforce_token_limit=False,
+               convert_to_lowercase=True, stem_tokens=False, remove_stopwords=False,
+               accumulate=None, delimiter=" \t\n\f\r", delimiter_regex=None,
+               punctuation="!#$%&()*+,-./:;?@\^_`{|}~", token_col_name=None,
+               doc_id_column=None, list_positions=False, token_frequency=False,
+               output_by_word=True, **generic_arguments):
     """
     DESCRIPTION:
         The TextParser() function can parse text and perform the following operations:
@@ -38,6 +41,13 @@ def TextParser(data=None, object=None, text_column=None, convert_to_lowercase=Tr
             Specifies the name of the input data column whose contents are to be tokenized.
             Types: str
 
+        enforce_token_limit:
+            Optional Argument.
+            Specifies whether to throw an informative error when finding token larger than
+            64K/32K or silently discard those larger tokens.
+            Default Value: False
+            Types: bool
+
         convert_to_lowercase:
             Optional Argument.
             Specifies whether to convert the text in "text_column" to lowercase.
@@ -71,6 +81,11 @@ def TextParser(data=None, object=None, text_column=None, convert_to_lowercase=Tr
             Default Value: " \\t\\n\\f\\r"
             Types: str
 
+        delimiter_regex:
+            Optional Argument.
+            Specifies a Perl Compatible regular expression that represents the word delimiter.
+            Types: str
+
         punctuation:
             Optional Argument.
             Specifies the punctuation characters to replace with a space in the input text.
@@ -83,6 +98,29 @@ def TextParser(data=None, object=None, text_column=None, convert_to_lowercase=Tr
             the text of the specified column in the "text_column" element.
             Types: str
 
+        doc_id_column:
+            Optional Argument.
+            Specifies the name of the column that uniquely identifies a row in the input table.
+            Types: str
+
+        list_positions:
+            Optional Argument.
+            Specifies whether to output the positions of a word in list form.
+            Default Value: False
+            Types: bool
+        
+        token_frequency:
+            Optional Argument.
+            Specifies whether to output the frequency for each token.
+            Default Value: False
+            Types: bool
+
+        output_by_word:
+            Optional Argument.
+            Specifies whether to output each token in a separate row or all tokens in one.
+            Default Value: True
+            Types: bool
+
         **generic_arguments:
             Specifies the generic keyword arguments SQLE functions accept. Below 
             are the generic keyword arguments:
@@ -170,4 +208,17 @@ def TextParser(data=None, object=None, text_column=None, convert_to_lowercase=Tr
 
         # Print the result DataFrame.
         print(TextParser_out.result)
+
+        # Example 3 : Tokenize  words in "text_data" column using delimiter regex,
+        #             convert tokens to lowercase and output token positions in a list format
+        TextParser_out = TextParser(data=complaints,
+                                    text_column="text_data",
+                                    doc_id_column="doc_id",
+                                    delimeter_regex="[ \t\f\r\n]+",
+                                    list_positions=True,
+                                    convert_to_lowercase=True,
+                                    output_by_word=False)
+ 
+        # Print the result DataFrame.
+        print(TextParser_out.result)
     """

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

@@ -94,7 +94,7 @@ def ACF(data=None, data_filter_expr=None, max_lags=None,
             Default behavior when "alpha" avoided or not a positive
             float: 
                 * The function does not return confidence intervals.
-            Types: float
+            Types: int OR float
 
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions.

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

@@ -169,7 +169,7 @@ def ArimaEstimate(data1=None, data1_filter_expr=None, data2=None,
             at the end to specify the intercept coefficient initial
             value, then the formula is as follows:
                 p+q+P+Q+constant
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         fixed:
             Optional Argument.
@@ -183,7 +183,7 @@ def ArimaEstimate(data1=None, data1_filter_expr=None, data2=None,
             at the end to specify the intercept coefficient initial
             value, then the formula is as follows:
                 p+q+P+Q+constant
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         constant:
             Optional Argument.

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

@@ -95,7 +95,7 @@ def ArimaXEstimate(data1=None, data1_filter_expr=None, data2=None,
             MA coefficients, the seasonal SAR regression
             coefficients and the SMA coefficients. The formula is
             as follows: 'p+q+P+Q+CONSTANT-length-init-list'
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         fixed:
             Optional Argument.
@@ -107,7 +107,7 @@ def ArimaXEstimate(data1=None, data1_filter_expr=None, data2=None,
             If an intercept is needed, one more value is added at
             the end to specify the intercept coefficient initial value.
             The formula is as follows: 'p+q+P+Q+CONSTANT-length-fixed-list'
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         constant:
             Optional Argument.

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

@@ -57,7 +57,7 @@ def DFFT(data=None, data_filter_expr=None, zero_padding_ok=True,
             obtained by sampling at a rate of 10,000 hertz.
             Note:
                 Applicable only when "freq_style" is set to 'K_HERTZ'.
-            Types: float
+            Types: int OR float
 
         algorithm:
             Optional Argument.

teradataml/data/docs/uaf/docs_17_20/DFFT2.py

@@ -56,7 +56,7 @@ def DFFT2(data=None, data_filter_expr=None, zero_padding_ok=True,
             column index.
             Note:
                 Applicable only when "freq_style" is set to 'K_HERTZ'.
-            Types: float
+            Types: int OR float
 
         algorithm:
             Optional Argument.

teradataml/data/docs/uaf/docs_17_20/DFFT2Conv.py

@@ -54,7 +54,7 @@ def DFFT2Conv(data=None, data_filter_expr=None, conv=None,
             were obtained by sampling at a rate of 10,000 hertz.
             Note:
                 * Applicable only when "freq_style" is set to 'K_HERTZ'.
-            Types: float
+            Types: int OR float
 
         output_fmt_content:
             Optional Argument.

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

@@ -55,7 +55,7 @@ def DFFTConv(data=None, data_filter_expr=None, conv=None,
             Value should be greater than 0.
             Notes:
                 * Applicable only when "freq_style" is set to 'K_HERTZ'.
-            Types: float
+            Types: int OR float
 
         output_fmt_content:
             Optional Argument.

teradataml/data/docs/uaf/docs_17_20/FilterFactory1d.py

@@ -57,27 +57,27 @@ def FilterFactory1d(filter_id=None, filter_type=None,
             A smaller value produces faster drop off at the cost of more coefficients.
             Not used when "filter_length" is supplied.
             Default is bandwidth from "filter_length".
-            Types: float
+            Types: int OR float
 
         low_cutoff:
             Optional Argument.
             Specifies  the lower frequency that change between a passband
             and stopband occurs. It must be greater
             than 0. It is not used by default with 'HIGHPASS' filter.
-            Types: float
+            Types: int OR float
 
         high_cutoff:
             Optional Argument.
             Specifies the higher frequency that change
             between a passband and stopband occurs. It must be greater
             than 0 and not used by default with 'LOWPASS' filter.
-            Types: float
+            Types: int OR float
 
         sampling_frequency:
             Required Argument.
             Specifies the frequency that the data to be filtered was
             sampled. It must be greater than 0.
-            Types: float
+            Types: int OR float
 
         filter_description:
             Optional Argument.

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

@@ -40,8 +40,8 @@ def GenseriesSinusoids(data=None, data_filter_expr=None, periodicities=None,
             Specifies the periodicity as a comma-separated list, which
             contains one or more floating point values representing 
             periodicities.
-            Types: float, list of float
-
+            Types: int, list of int, float, list of float
+            
         output_fmt_index_style:
             Optional Argument.
             Specifies the index style of the output format.

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

@@ -53,7 +53,7 @@ def GoldfeldQuandt(data=None, data_filter_expr=None,
                 * not specified, then split-point index is calculate as:
                     start_idx = (N - omit) / 2
                     Where, 'N' is the total number of entries in the data series.
-            Types: float
+            Types: int OR float
 
         omit:
             Required Argument.
@@ -66,7 +66,7 @@ def GoldfeldQuandt(data=None, data_filter_expr=None,
                     Where 'N' is the total number of entries in the data series
                 * greater than 1.0, then "omit" is interpreted as number of 
                   central points to omit.
-            Types: float
+            Types: int OR float
 
         significance_level:
             Required Argument.

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

@@ -37,7 +37,7 @@ def HoltWintersForecaster(data=None, data_filter_expr=None, forecast_periods=Non
             the forecasting, else the "alpha" value is estimated using
             goodness-of-fit metrics. Value must be greater than or equal
             to 0 and less than or equal to 1.
-            Types: float
+            Types: int OR float 
 
         beta:
             Optional Argument.
@@ -47,7 +47,7 @@ def HoltWintersForecaster(data=None, data_filter_expr=None, forecast_periods=Non
             the forecasting, else the "beta" value is estimated using
             goodness-of-fit metrics. Value must be greater than or equal
             to 0 and less than or equal to 1.
-            Types: float
+            Types: int OR float
 
         gamma:
             Optional Argument.
@@ -57,7 +57,7 @@ def HoltWintersForecaster(data=None, data_filter_expr=None, forecast_periods=Non
             the forecasting, else the "gamma" value is estimated using
             goodness-of-fit metrics. Value must be greater than or equal
             to 0 and less than or equal to 1.
-            Types: float
+            Types: int OR float
 
         seasonal_periods:
             Optional Argument.
@@ -74,14 +74,14 @@ def HoltWintersForecaster(data=None, data_filter_expr=None, forecast_periods=Non
             Specifies the initialization value used as part of the fitting
             and forecasting operations. If not specified, then the initialization
             value is calculated as an additive level.
-            Types: float
+            Types: int OR float
 
         init_trend:
             Optional Argument.
             Specifies the initialization value used as part of the fitting
             and forecasting operations. If not specified, then the initialization
             value is calculated as an additive trend.
-            Types: float
+            Types: int OR float
 
         init_season:
             Optional Argument.
@@ -89,7 +89,7 @@ def HoltWintersForecaster(data=None, data_filter_expr=None, forecast_periods=Non
             specified, the initialization value is used as part of the
             fitting and forecasting operations, else the initialization
             value is calculated as a multiplicative seasonality.
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         model:
             Required Argument.

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

@@ -68,7 +68,7 @@ def LineSpec(data=None, data_filter_expr=None, freq_style="K_INTEGRAL",
             A value of 10000.0 indicates that the sample points were obtained
             by sampling at a rate of 10,000 hertz. This hertz interpretation
             applies to both the ROW_I and COLUMN_I indices.
-            Types: float
+            Types: int OR float
 
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions. 

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

@@ -92,7 +92,7 @@ def LinearRegr(data=None, data_filter_expr=None, variables_count=2,
             Note:
                 Applicable only when "coeff_stats" is set to True.
             Default Value: 0.9
-            Types: float
+            Types: int OR float
 
         model_stats:
             Optional Argument.

teradataml/data/docs/uaf/docs_17_20/Matrix2Image.py

@@ -70,28 +70,28 @@ def Matrix2Image(data=None, data_filter_expr=None, image="PNG", type=None,
             scaled. By default, the MIN and MAX values of the
             payload are used as the range. Used when "type" is 'GRAY'
             or 'COLORMAP'.
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         red:
             Optional Argument.
             Specifies the range of the first payload value. By
             default, the MIN and MAX values of the payload are 
             used as the range. It is only used when "type" is 'RGB'.
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         green:
             Optional Argument.
             Specifies the range of the second payload value.By
             default, the MIN and MAX values of the payload are 
             used as the range. It is only used when "type" is 'RGB'.
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         blue:
             Optional Argument.
             Specifies the range of the third payload value. By
             default, the MIN and MAX values of the payload are 
             used as the range. It is only used when "type" is 'RGB'.
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         flip_x:
             Optional Argument.

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

@@ -71,7 +71,7 @@ def MultivarRegr(data=None, data_filter_expr=None, variables_count=None,
             Note:
                 Applicable only when "coeff_stats" is set to 1.
             Default Value: 0.9
-            Types: float
+            Types: int OR float
 
         model_stats:
             Optional Argument.

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

@@ -64,7 +64,7 @@ def PACF(data=None, data_filter_expr=None,
             Specifies confidence intervals for the given level. For example, if 0.05 is entered,
             then 95% confidence intervals are returned for standard deviation computed according
             to Bartlett’s formula.
-            Types: float
+            Types: int OR float
 
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions. 

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

@@ -51,7 +51,7 @@ def PowerSpec(data=None, data_filter_expr=None, freq_style=None,
             points were obtained by sampling at a rate of 10,000 hertz.
             Note:
                 * Only used with "freq_style" set to 'K_HERTZ'.
-            Types: float
+            Types: int OR float
 
         zero_padding_ok:
             Optional Argument.
@@ -111,7 +111,7 @@ def PowerSpec(data=None, data_filter_expr=None, freq_style=None,
             hertz.
             Note:
                 * Use when "window_name" is set to 'TUKEY'.
-            Types: float
+            Types: int OR float
 
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions.

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

@@ -43,18 +43,18 @@ def PowerTransform(data=None, data_filter_expr=None, back_transform=False,
         p:
             Required Argument.
             Specifies the power to use in the transform equation.
-            Types: float
+            Types: int OR float
 
         b:
             Required Argument.
             Specifies the logarithm to be applied for the transform equation.
-            Types: float
+            Types: int OR float
 
         lambda1:
             Required Argument.
             Specifies the parameter used to decide the preferred
             power transform operation during the Box-Cox transformation.
-            Types: float
+            Types: int OR float
 
         output_fmt_index_style:
             Optional Argument.

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

@@ -56,7 +56,7 @@ def Resample(data=None, data_filter_expr=None, timecode_start_value=None,
                 Provide either arguments "timecode_start_value" and
                 "timecode_duration", or arguments "sequence_start_value"
                 and "sequence_duration".
-            Types: float
+            Types: int OR float
 
         sequence_duration:
             Optional Argument.
@@ -65,7 +65,7 @@ def Resample(data=None, data_filter_expr=None, timecode_start_value=None,
                 Provide either arguments "timecode_start_value" and
                 "timecode_duration", or arguments "sequence_start_value"
                 and "sequence_duration".
-            Types: float
+            Types: int OR float
 
         interpolate:
             Required Argument.
@@ -84,7 +84,7 @@ def Resample(data=None, data_filter_expr=None, timecode_start_value=None,
             Note:
                 * Applicable only when "interpolate" set to 'WEIGHTED'.
                 * The interpolated value is calculated as: Y_t  =  Y_{t_LEFT} * (1 - WEIGHT) + (Y-{t_RIGHT} * WEIGHT).
-            Types: float
+            Types: int OR float
 
         spline_params_method:
             Optional Argument.
@@ -106,7 +106,7 @@ def Resample(data=None, data_filter_expr=None, timecode_start_value=None,
                 * Used only when "interpolate" set to 'SPLINE'.
                 * Used only when "spline_params_method" set to 'CLAMPED'.
             Default Value: 0.0
-            Types: float
+            Types: int OR float
 
         spline_params_ypn:
             Optional Argument.
@@ -116,7 +116,7 @@ def Resample(data=None, data_filter_expr=None, timecode_start_value=None,
                 * Used only when "interpolate" set to 'SPLINE'.
                 * Used only when "spline_params_method" set to 'CLAMPED'.
             Default Value: 0.0
-            Types: float
+            Types: int OR float
 
         output_fmt_index_style:
             Optional Argument.

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

@@ -49,7 +49,7 @@ def SAX(data=None, data_filter_expr=None, window_type='GLOBAL',
                   the specified value will apply to all payloads.
                 * If "mean" specifies multiple values, each value will be 
                   applied to its corresponding payload.
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         std_dev:
             Optional Argument.
@@ -62,7 +62,7 @@ def SAX(data=None, data_filter_expr=None, window_type='GLOBAL',
                   the specified value will apply to all payloads.
                 * If "std_dev" specifies multiple values, each value will be
                   applied to its corresponding payload.
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         window_size:
             Optional Argument, Required if "window_type" is SLIDING.
@@ -124,7 +124,7 @@ def SAX(data=None, data_filter_expr=None, window_type='GLOBAL',
         breakpoints:
             Optional Argument.
             Specifies the breakpoints to form the SAX code based on "data".
-            Types: float, list of float
+            Types: int, list of int, float, list of float
 
         output_fmt_index_style:
             Optional Argument.

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

@@ -47,7 +47,7 @@ def SignifPeriodicities(data=None, data_filter_expr=None,
             Required Argument.
             Specifies the significant periodicities to perform 
             tests for each period.
-            Types: float OR list of float
+            Types: int, list of int, float, list of float
 
         **generic_arguments:
             Specifies the generic keyword arguments of UAF functions.

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

@@ -36,7 +36,7 @@ def SimpleExp(data=None, data_filter_expr=None, forecast_periods=None,
             is not specified, the value of 'alpha' is estimated by using
             goodness-of-fit metrics. Value must be greater than or equal to
             0 and less than or equal to 1.
-            Types: float
+            Types: int OR float
 
         prediction_intervals:
             Optional Argument.

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

@@ -67,7 +67,7 @@ def Smoothma(data=None, data_filter_expr=None, ma=None, window=None,
             faster.
             Note:
                 * Applicable only when "ma" is set to 'EXPONENTIAL'.
-            Types: float
+            Types: int OR float
 
         weights:
             Optional Argument.
@@ -80,7 +80,7 @@ def Smoothma(data=None, data_filter_expr=None, ma=None, window=None,
             value if it is not specified.
             Note:
                 * Applicable only when "ma" is set to 'MEAN'.
-            Types: float
+            Types: int OR float
 
         well_known:
             Optional Argument.
@@ -109,7 +109,7 @@ def Smoothma(data=None, data_filter_expr=None, ma=None, window=None,
             For example, pad=4.5 applies a pad value of 4.5 for a series less than "window".
             Note:
                 * Applicable only when "ma" is set to 'MEAN' or 'MEDIAN'.
-            Types: float
+            Types: int, float
 
         output_fmt_index_style:
             Optional Argument.

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

@@ -59,7 +59,7 @@ def UNDIFF(data1=None, data1_filter_expr=None, data2=None,
         initial_values:
             Optional Argument.
             Specifies the starting values for the undifferencing operation.
-            Types: float OR list of float
+            Types: int, list of int, float OR list of float
 
         input_fmt_input_mode:
             Optional Argument.

teradataml/data/jsons/byom/onnxembeddings.json

@@ -105,6 +105,7 @@
       "datatype": "STRING",
       "allowsLists": false,
       "rName": "model.output.tensor",
+      "permittedValues": ["sentence_embedding","token_embeddings"],
       "useInR": true,
       "rOrderNum": 5
     },

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

@@ -124,8 +124,8 @@
       "name": "Delimiter",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "A character or string that separates words in the input text. The default value is the set of all whitespace characters which includes the characters for space, tab, newline, carriage return and some others.",
-      "description": "A  character or string that separates words in the input text. The default value is the set of all whitespace characters which includes the characters for space, tab, newline, carriage return and some others.",
+      "rDescription": "A character or string  or a regular expression that separates words in the input text. The default value is the set of all whitespace characters which includes the characters for space, tab, newline, carriage return and some others.",
+      "description": "A  character or string  or a regular expression that separates words in the input text. The default value is the set of all whitespace characters which includes the characters for space, tab, newline, carriage return and some others.",
       "datatype": "STRING",
       "allowsLists": false,
       "rName": "delimiter",
@@ -139,8 +139,8 @@
       "name": "Punctuation",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "A string that specifies the punctuation characters for the function to remove before evaluating the input text. The default characters to remove are: `~#^&*()-",
-      "description": "A string that specifies the punctuation characters for the function to remove before evaluating the input text. The default characters to remove are: `~#^&*()-",
+      "rDescription": "A string  or a regular expression that specifies the punctuation characters for the function to remove before evaluating the input text. The default characters to remove are: `~#^&*()-",
+      "description": "A string  or a regular expression that specifies the punctuation characters for the function to remove before evaluating the input text. The default characters to remove are: `~#^&*()-",
       "datatype": "STRING",
       "allowsLists": false,
       "rName": "punctuation",
@@ -154,8 +154,8 @@
       "name": "Reset",
       "alternateNames": [],
       "isRequired": false,
-      "rDescription": "A string that specifies the character or string that ends a sentence. The default sentence-ending characters are: .,?! At the end of a sentence, the function discards any partial n-grams and searches for the next n-gram at the beginning of the next sentence. An n-gram cannot span two sentences.",
-      "description": "A string expression that specifies the character or string that ends a sentence. The default sentence-ending characters are: .,?! At the end of a sentence, the function discards any partial n-grams and searches for the next n-gram at the beginning of the next sentence. An n-gram cannot span two sentences.",
+      "rDescription": "A string  or a regular expression that specifies the character or string that ends a sentence. The default sentence-ending characters are: .,?! At the end of a sentence, the function discards any partial n-grams and searches for the next n-gram at the beginning of the next sentence. An n-gram cannot span two sentences.",
+      "description": "A string  or a regular expression that specifies the character or string that ends a sentence. The default sentence-ending characters are: .,?! At the end of a sentence, the function discards any partial n-grams and searches for the next n-gram at the beginning of the next sentence. An n-gram cannot span two sentences.",
       "datatype": "STRING",
       "allowsLists": false,
       "rName": "reset",