| | |
- SVMSparsePredict(object=None, newdata=None, sample_id_column=None, attribute_column=None, value_column=None, accumulate_label=None, output_class_num=1, output_prob=True, output_responses=None, **generic_arguments)
- DESCRIPTION:
The SVMSparsePredict() function takes the model generated by the
SVMSparse() trainer function and a set of test samples (in sparse
format) and outputs a prediction for each sample.
PARAMETERS:
object:
Required Argument.
Specifies the teradataml DataFrame containing the model data
generated by SVMSparse() function or instance of SVMSparse.
Types: teradataml DataFrame or SVMSparse
newdata:
Required Argument.
Specifies the teradataml DataFrame containing the input test data.
Types: teradataml DataFrame
sample_id_column:
Required Argument.
Specifies the name of the newdata column that contains the
identifiers of the test samples. The newdata table must be
partitioned by this column.
Types: str
attribute_column:
Required Argument.
Specifies the name of the newdata column that contains the
attributes of the test samples.
Types: str
value_column:
Optional Argument.
Specifies the name of the newdata column that contains the
attribute values. By default, each attribute has the value 1.
Types: str
accumulate_label:
Optional Argument.
Specifies the names of the newdata columns to copy to the
output teradataml DataFrame.
Types: str OR list of Strings (str)
output_class_num:
Optional Argument.
Specifies the number of class labels to appear in the output
teradataml DataFrame, with its corresponding prediction confidence.
Valid only for multiple-class models.
Default Value: 1
Types: int
output_prob:
Optional Argument.
Specifies whether to display output probability for the predicted
category.
Default Value: True
Types: bool
output_responses:
Optional Argument.
Specifies responses for which to output probabilities.
Types: str OR list of Strings (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 SQLE Engine
function supports, else an exception is raised.
RETURNS:
Instance of SVMSparsePredict.
Output teradataml DataFrames can be accessed using attribute
references, such as SVMSparsePredictObj.<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 the Vantage user is connected to.
# 3. To check the list of analytic functions available on the Vantage user connected to,
# use "display_analytic_functions()".
# Load the data to run the example.
load_example_data("SVMSparsePredict",["svm_iris_input_train","svm_iris_input_test"])
# Create teradataml DataFrame
svm_iris_input_train = DataFrame.from_table("svm_iris_input_train")
svm_iris_input_test = DataFrame.from_table("svm_iris_input_test")
# Create SparseSVMTrainer object
svm_train = SVMSparse(data=svm_iris_input_train,
sample_id_column='id',
attribute_column='attribute',
label_column='species',
value_column='value1',
max_step=150,
seed=0)
# Check the list of available analytic functions.
display_analytic_functions()
# Import function SVMSparsePredict.
from teradataml import SVMSparsePredict
# Example 1: Instance of SVMTrainer is passed as input to object argument.
svm_sparse_predict_result1 = teradataml.SVMSparsePredict(newdata=svm_iris_input_test,
object=svm_train,
attribute_column='attribute',
sample_id_column='id',
value_column='value1',
accumulate_label='species')
# Print the result DataFrame
print(svm_sparse_predict_result1.result)
# Example 2: teradataml DataFrame containing the model data generated by SVMSparse
# is passed as input to object argument.
svm_sparse_predict_result2 = teradataml.SVMSparsePredict(newdata=svm_iris_input_test,
object=svm_train.model_table,
attribute_column='attribute',
sample_id_column='id',
value_column='value1',
accumulate_label='species')
# Print the result DataFrame
print(svm_sparse_predict_result2.result)
# Example 3: Predict the species and display probability for "setosa" and "virginica".
svm_sparse_predict_result3 = teradataml.SVMSparsePredict(newdata=svm_iris_input_test,
object=svm_train.model_table,
attribute_column='attribute',
sample_id_column='id',
value_column='value1',
accumulate_label='species',
output_prob= True,
output_responses= ['setosa', 'virginica'])
# Print the result DataFrame.
print(svm_sparse_predict_result3.result)
|