def test_scenario7(self):
"""
Scenario: Successfully building feature selection for a category from dataset:
Given I create BigML dataset uploading train "<data>" file with attributes "<attributes>" in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I create BigML feature selection <kfold>-fold cross-validations improving "<metric>" for category "<category>"
And I check that the <kfold>-datasets have been created
And I check that the <kfold>-models have been created
And I check that all the <kfold>-fold cross-validations have been created
Then the best feature selection is "<selection>", with "<metric>" of <metric_value>
Examples:
| data | attributes | output | kfold | metric | category | selection | metric_value
| ../data/spam.csv | ../data/spam_attributes.json |./scenario_a_9/evaluation | 2 | recall | spam | Message | 61.24%
"""
print self.test_scenario7.__doc__
examples = [
['data/spam.csv', 'data/spam_attributes.json', 'scenario_a_9/evaluation', '2', 'recall', 'spam', 'Message', '61.24%']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_dataset_with_attributes(self, data=example[0], attributes=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self)
test_pred.i_create_kfold_cross_validation_metric_category(self, k_folds=example[3], metric=example[4], category=example[5])
test_pred.i_check_create_kfold_datasets(self, example[3])
test_pred.i_check_create_kfold_models(self, example[3])
test_pred.i_check_create_all_kfold_cross_validations(self, example[3])
test_pred.i_check_feature_selection(self, example[6], example[4], example[7])
def test_scenario7(self):
"""
Scenario: Successfully building feature selection for a category from dataset:
Given I create BigML dataset uploading train "<data>" file with attributes "<attributes>" in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I create BigML feature selection <kfold>-fold cross-validations improving "<metric>" for category "<category>"
And I check that the <kfold>-datasets have been created
And I check that the <kfold>-models have been created
And I check that all the <kfold>-fold cross-validations have been created
Then the best feature selection is "<selection>", with "<metric>" of <metric_value>
Examples:
| data | attributes | output | kfold | metric | category | selection | metric_value
| ../data/spam.csv | ../data/spam_attributes.json |./scenario_a_9/evaluation | 2 | recall | spam | Message | 58.69%
"""
print self.test_scenario7.__doc__
examples = [
['data/spam.csv', 'data/spam_attributes.json', 'scenario_a_9/evaluation', '2', 'recall', 'spam', 'Message', '58.69%']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_dataset_with_attributes(self, data=example[0], attributes=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self)
test_pred.i_create_kfold_cross_validation_metric_category(self, k_folds=example[3], metric=example[4], category=example[5])
test_pred.i_check_create_kfold_datasets(self, example[3])
test_pred.i_check_create_kfold_models(self, example[3])
test_pred.i_check_create_all_kfold_cross_validations(self, example[3])
test_pred.i_check_feature_selection(self, example[6], example[4], example[7])
def setup_scenario02(self):
"""
Scenario: Successfully building text source from local file:
Given I create BigML dataset uploading train "<data>" file with attributes "<attributes>" in "<output>"
And I check that the source has been created
Then I check that the dataset has been created
Examples:
| data | attributes | output |
| ../data/spam.csv | ../data/spam_attributes.json | scenario2_td/topic_distributions.csv |
"""
print self.setup_scenario02.__doc__
examples = [
['data/spam.csv', 'data/spam_attributes.json', 'scenario2_td/topic_distributions.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_dataset_with_attributes( \
self, data=example[0], attributes=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
def setup_scenario02(self):
"""
Scenario: Successfully building text source from local file:
Given I create BigML dataset uploading train "<data>" file with attributes "<attributes>" in "<output>"
And I check that the source has been created
Then I check that the dataset has been created
Examples:
| data | attributes | output |
| ../data/spam.csv | ../data/spam_attributes.json | scenario2_td/topic_distributions.csv |
"""
print self.setup_scenario02.__doc__
examples = [[
'data/spam.csv', 'data/spam_attributes.json',
'scenario2_td/topic_distributions.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_dataset_with_attributes( \
self, data=example[0], attributes=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)