| | |
- ColumnTransformer(input_data=None, bincode_fit_data=None, function_fit_data=None, nonlinearcombine_fit_data=None, onehotencoding_fit_data=None, ordinalencoding_fit_data=None, outlierfilter_fit_data=None, polynomialfeatures_fit_data=None, rownormalize_fit_data=None, scale_fit_data=None, simpleimpute_fit_data=None, fillrowid_column_name=None, **generic_arguments)
- DESCRIPTION:
The ColumnTransformer() function transforms the input data columns in a single operation.Provide only
the FIT dataframes generated by the Fit analytic functions, and the function runs all transformations
that user require in a single operation.
The function performs the following transformations:
* Scale Transform
* Bincode Transform
* Function Transform
* NonLinearCombine Transform
* OutlierFilter Transform
* PolynomialFeatures Transform
* RowNormalize Transform
* OrdinalEncoding Transform
* OneHotEncoding Transform
* SimpleImpute Transform
User must create the FIT dataframe before using the function and must be provided in the same order
as in the training data sequence to transform the dataset. The FIT dataframe can have maximum of
128 columns.
Note:
* ColumnTransformer() function works only with python 3.6 and above.
PARAMETERS:
input_data:
Required Argument.
Specifies the teradataml DataFrame that contains input data.
Types: teradataml DataFrame
bincode_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the BincodeFit() function.
Types: teradataml DataFrame
function_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the Fit() function.
Types: teradataml DataFrame
nonlinearcombine_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the NonLinearCombineFit() function.
One can pass multiple NonLinearCombineFit() function's output using argument names
as nonlinearcombine_fit_data1, nonlinearcombine_fit_data2 and so on.
Notes:
* Function considers the arguments which are in sequence and ignores the arguments
which are out of sequence.
Example - If arguments are nonlinearcombine_fit_data, nonlinearcombine_fit_data1,
nonlinearcombine_fit_data2, nonlinearcombine_fit_data4, the function considers only
nonlinearcombine_fit_data, nonlinearcombine_fit_data1 and nonlinearcombine_fit_data2
for processing and ignores nonlinearcombine_fit_data4 since it is out of sequence.
* Argument sequence starts from "nonlinearcombine_fit_data", followed by
"nonlinearcombine_fit_data1", "nonlinearcombine_fit_data2", so on..
Types: teradataml DataFrame
onehotencoding_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the OneHotEncodingFit() function.
Types: teradataml DataFrame
ordinalencoding_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the OrdinalEncodingFit() function.
Types: teradataml DataFrame
outlierfilter_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the OutlierFilterFit() function.
Types: teradataml DataFrame
polynomialfeatures_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the PolynomialFeaturesFit() function.
Types: teradataml DataFrame
rownormalize_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the RowNormalizeFit() function.
Types: teradataml DataFrame
scale_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the ScaleFit() function.
Types: teradataml DataFrame
simpleimpute_fit_data:
Optional Argument.
Specifies the teradataml DataFrame generated by the SimpleImputeFit() function.
Types: teradataml DataFrame
fillrowid_column_name:
Optional Argument.
Specifies the name for the output column in which unique identifiers for each row are
populated.
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: 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 ColumnTransformer.
Output teradataml DataFrames can be accessed using attribute
references, such as ColumnTransformerObj.<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"])
# Create teradataml DataFrame objects.
titanic = DataFrame.from_table("titanic")
# Check the list of available analytic functions.
display_analytic_functions()
# Example 1: Perform Bincode transformation and OneHotEncoding transformation using fit functions and
# ColumnTransformer() function.
bin_code = BincodeFit(data=titanic,
target_columns='age',
method_type='Equal-Width',
nbins=2,
label_prefix='label_prefix')
one_hot_encoding = OneHotEncodingFit(data=titanic,
is_input_dense=True,
target_column="sex",
categorical_values=["male", "female"],
other_column="other")
ColumnTransformer_out = ColumnTransformer(fillrowid_column_name="output_value",
input_data=titanic,
bincode_fit_data=bin_code.output,
onehotencoding_fit_data=one_hot_encoding.result)
# Print the result DataFrame.
print(ColumnTransformer_out.result)
# Example 2: Perform multiple NonLinearCombineFit transformation using fit function and
# ColumnTransformer() function.
# Create multiple NonLinearCombineFit objects and pass those to ColumnTransformer.
NonLinearCombineFit_out1 = NonLinearCombineFit(data = titanic,
target_columns = ["sibsp", "parch"],
formula = "Y=(X0+X1+1)",
result_column = "total_cost")
NonLinearCombineFit_out2 = NonLinearCombineFit(data = titanic,
target_columns = [ "fare"],
formula = "Y=(X0+1)",
result_column = "total_fare_cost2")
NonLinearCombineFit_out3 = NonLinearCombineFit(data = titanic,
target_columns = [ "fare"],
formula = "Y=(X0+3)",
result_column = "total_fare_cost3")
ColumnTransformer_out2 = ColumnTransformer(input_data=titanic,
nonlinearcombine_fit_data=NonLinearCombineFit_out1.result,
nonlinearcombine_fit_data_order_column=['parch'],
nonlinearcombine_fit_data1=NonLinearCombineFit_out2.result,
nonlinearcombine_fit_data1_order_column=['fare'],
nonlinearcombine_fit_data2=NonLinearCombineFit_out3.result)
# Print the result DataFrame.
print(ColumnTransformer_out2.result)
# Example 3: Perform BincodeFit transformation along with OrdinalEncodingFit and
# OneHotEncodingFit transformation using fit functions and ColumnTransformer()
# function.
# Create BincodeFit object along with OrdinalEncodingFit and OneHotEncodingFit
# objects, and pass those to ColumnTransformer.
bin_code = BincodeFit(data=titanic,
target_columns='age',
method_type='Equal-Width',
nbins=2,
label_prefix='label_prefix')
one_hot_encoding = OneHotEncodingFit(data=titanic,
is_input_dense=True,
target_column="embarked",
categorical_values=["c", "s"],
other_column="other")
ordinal_encodingfit = OrdinalEncodingFit(target_column='sex', data=titanic)
ColumnTransformer_out3 = ColumnTransformer(fillrowid_column_name="output_value",
input_data=titanic,
bincode_fit_data=bin_code.output,
onehotencoding_fit_data=one_hot_encoding.result,
ordinalencoding_fit_data=ordinal_encodingfit.result)
# Print the result DataFrame.
print(ColumnTransformer_out3.result)
|