def test_scenario04(self):
"""
Scenario: Successfully building test predictions from dataset
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML logistic regression resources using dataset to test "<test>" and log predictions in "<output>"
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ./scenario3/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario04.__doc__
examples = [[
'scenario1_lr',
'{"data": "data/iris.csv", "output": "scenario1_lr/predictions.csv", "test": "data/test_iris.csv"}',
'data/test_iris.csv', 'scenario3_lr/predictions.csv',
'check_files/predictions_iris_lr.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
lr_pred.i_create_lr_resources_from_dataset(self,
None,
test=example[2],
output=example[3])
lr_pred.i_check_create_lr_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario24(self):
"""
Scenario: Successfully test predictions remotely from boosted ensemble
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using boosted ensemble in <iterations> iterations to remotely test "<test>" and log predictions in "<output>"
And I check that the ensemble has been created
And I check that the predictions are ready
And I check that the batch prediction is ready
And I check that the bath predictions datset is ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | iterations | test | output |predictions_file |
"""
examples = [[
'scenario1',
'{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'10', 'data/test_iris.csv', 'scenario24/predictions.csv',
'check_files/predictions_iris_boost.csv'
]]
show_doc(self.test_scenario24, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it( \
self, example[0], example[1])
test_pred.i_create_resources_remotely_from_boosted_ensemble( \
self, iterations=example[2], test=example[3],
output=example[4])
test_pred.i_check_create_ensemble(self)
test_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully building test predictions from source
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML multi-label resources using source with objective "<objective>" and model fields "<model_fields>" to test "<test>" and log predictions in "<output>"
And I check that the dataset has been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | objective | model_fields | test | output |predictions_file |
| scenario_mlm_1| {"tag": "my_multilabelm_1", "data": "../data/multilabel_multi.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "./scenario_mlm_1/predictions.csv", "test": "../data/test_multilabel.csv", "ml_fields": "type,class", "model_fields": "-type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P", "objective": "class"} | class | -type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P |../data/test_multilabel.csv | ./scenario_mlm_2/predictions.csv | ./check_files/predictions_ml_comma.csv |
"""
print self.test_scenario2.__doc__
examples = [
['scenario_mlm_1', '{"tag": "my_multilabelm_1", "data": "data/multilabel_multi.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "scenario_mlm_1/predictions.csv", "test": "data/test_multilabel.csv", "ml_fields": "type,class", "model_fields": "-type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P", "objective": "class"}', 'class', '-type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P', 'data/test_multilabel.csv', 'scenario_mlm_2/predictions.csv', 'check_files/predictions_ml_comma.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_create_resources_from_source_with_objective(self, multi_label='multi-label ', objective=example[2], model_fields=example[3], test=example[4], output=example[5])
test_pred.i_check_create_dataset(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[6])
def test_scenario2(self):
"""
Scenario: Successfully building test predictions from source
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using source to find centroids for "<test>" and log predictions in "<output>"
And I check that the dataset has been created
And I check that the cluster has been created
And I check that the centroids are ready
Then the local centroids file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario_c_1| {"data": "../data/diabetes.csv", "output": "./scenario_c_1/centroids.csv", "test": "../data/diabetes.csv"} | ../data/diabetes.csv | ./scenario_c_2/centroids.csv | ./check_files/centroids_diabetes.csv |
"""
print self.test_scenario2.__doc__
examples = [
['scenario_c_1', '{"data": "data/diabetes.csv", "output": "scenario_c_1/centroids.csv", "test": "data/diabetes.csv"}', 'data/diabetes.csv', 'scenario_c_2/centroids.csv', 'check_files/centroids_diabetes.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_cluster.i_create_cluster_resources_from_source(self, test=example[2], output=example[3])
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_cluster(self)
test_cluster.i_check_create_centroids(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario26(self):
"""
Scenario: Successfully building test predictions from ensemble
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
Given I have previously executed "<scenario2>" or reproduce it with arguments <kwargs2>
And I create BigML resources using local ensemble of <number_of_models> models in "<scenario2>" to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |scenario2 | kwargs2 | number_of_models | test | output |predictions_file |
"""
examples = [
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5', '{"number_of_models": 10, "output": "scenario5/predictions.csv", "test": "data/test_iris.csv"}',
'10', 'scenario5', 'data/test_iris.csv', 'scenario26/predictions_p.csv', 'check_files/predictions_iris_e_op_prob.csv', 'data/operating_point_prob.json'],
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5', '{"number_of_models": 10, "output": "scenario5/predictions.csv", "test": "data/test_iris.csv"}',
'10', 'scenario5', 'data/test_iris.csv', 'scenario26/predictions_c.csv', 'check_files/predictions_iris_e_op_conf.csv', 'data/operating_point_conf.json']]
show_doc(self.test_scenario26, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[2], example[3])
test_pred.i_create_resources_from_local_ensemble_with_op( \
self, number_of_models=example[4], directory=example[5],
test=example[6], output=example[7], operating_point=example[9])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[8])
def test_scenario5(self):
"""
Scenario: Successfully building test predictions from models retrieved by tag
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML multi-label resources with labels "<labels>" and objective "<objective>" using models tagged as "<tag>" to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |labels | objective | tag | test | output |predictions_file |
| scenario_mlm_1| {"tag": "my_multilabelm_1", "data": "../data/multilabel_multi.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "./scenario_mlm_1/predictions.csv", "test": "../data/test_multilabel.csv", "ml_fields": "type,class", "model_fields": "-type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P", "objective": "class"} | Adult,Student | class | my_multilabelm_1 | ../data/test_multilabel.csv | ./scenario_mlm_5/predictions.csv | ./check_files/predictions_ml_labels.csv |
"""
print self.test_scenario5.__doc__
examples = [[
'scenario_mlm_1',
'{"tag": "my_multilabelm_1", "data": "data/multilabel_multi.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "scenario_mlm_1/predictions.csv", "test": "data/test_multilabel.csv", "ml_fields": "type,class", "model_fields": "-type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P", "objective": "class"}',
'Adult,Student', 'class', 'my_multilabelm_1',
'data/test_multilabel.csv', 'scenario_mlm_5/predictions.csv',
'check_files/predictions_ml_labels.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
ml_pred.i_predict_ml_from_model_tag_with_labels_with_objective(
self,
labels=example[2],
objective=example[3],
tag=example[4],
test=example[5],
output=example[6])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[7])
def test_scenario09(self):
"""
Scenario: Successfully combining test predictions from existing directories
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I have previously executed "<scenario2>" or reproduce it with arguments <kwargs2>
Given I combine BigML predictions files in "<directory1>" and "<directory2>" into "<output>"
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |scenario2 | kwargs2 | directory1 | directory2 | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | scenario5| {"number_of_models": 10, "output": "./scenario5/predictions.csv", "test": "../data/test_iris.csv"} | ./scenario1 | ./scenario5 | ./scenario8/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario09.__doc__
examples = [[
'scenario1',
'{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5',
'{"number_of_models": 10, "test": "data/test_iris.csv", "output": "scenario5/predictions.csv"}',
'scenario1', 'scenario5', 'scenario8/predictions.csv',
'check_files/predictions_iris.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[2], example[3])
test_pred.i_find_predictions_files(self,
directory1=example[4],
directory2=example[5],
output=example[6])
test_pred.i_check_predictions(self, example[7])
def test_scenario14(self):
"""
Scenario: Successfully building test predictions from start with user-given separator:
Given I create BigML resources uploading train "<data>" file to test "<test>" and log predictions in "<output>" with "<separator>" as test field separator
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | separator | output |predictions_file |
"""
examples = [
['data/iris.csv', 'data/test_iris.tsv', '"\t"', 'scenario14/predictions.csv', 'check_files/predictions_iris.csv']]
show_doc(self.test_scenario14, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_with_separator(self, data=example[0], test=example[1], output=example[3], separator=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario2(self):
"""
Scenario: Successfully building test predictions from source using datasets with max categories
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources with <max_categories> as categories limit and <objective> as objective field using source to test "<test>" and log predictions in "<output>"
And I check that the dataset has been created
And I check that the max_categories datasets have been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |max_categories| objective | test | output |predictions_file |
| scenario_mc_1| {"data": "../data/iris.csv", "max_categories": "1", "objective": "species", "output": "./scenario_mc_1/predictions.csv", "test": "../data/test_iris.csv"} |1| species | ../data/test_iris.csv | ./scenario_mc_2/predictions.csv | ./check_files/predictions_mc.csv |
"""
print self.test_scenario2.__doc__
examples = [
['scenario_mc_1', '{"data": "data/iris.csv", "max_categories": "1", "objective": "species", "output": "scenario_mc_1/predictions.csv", "test": "data/test_iris.csv"}', '1', 'species', 'data/test_iris.csv', 'scenario_mc_2/predictions.csv', 'check_files/predictions_mc.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
max_cat.i_create_all_mc_resources_from_source(self, max_categories=example[2], objective=example[3], test=example[4], output=example[5])
test_pred.i_check_create_dataset(self, suffix=None)
max_cat.i_check_create_max_categories_datasets(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[6])
def setup_scenario06(self):
"""
Scenario: Successfully building test predictions from ensemble
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using ensemble of <number_of_models> models to test "<test>" and log predictions in "<output>"
And I check that the ensemble has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | number_of_models | test | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | 10 | ../data/test_iris.csv | ./scenario5/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.setup_scenario06.__doc__
examples = [[
'scenario1',
'{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'10', 'data/test_iris.csv', 'scenario5/predictions.csv',
'check_files/predictions_iris.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_pred.i_create_resources_from_ensemble(
self,
number_of_models=example[2],
test=example[3],
output=example[4])
test_pred.i_check_create_ensemble(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def setup_scenario1(self):
"""
Scenario: Successfully building test predictions from training data using datasets with max categories
Given I create BigML resources from "<data>" with <max_categories> as categories limit and <objective> as objective field to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the max_categories datasets have been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|data |max_categories | objective | test | output |predictions_file |
|../data/iris.csv |1| species |../data/test_iris.csv | ./scenario_mc_1/predictions.csv | ./check_files/predictions_mc.csv |
"""
print self.setup_scenario1.__doc__
examples = [
['data/iris.csv', '1', 'species', 'data/test_iris.csv', 'scenario_mc_1/predictions.csv', 'check_files/predictions_mc.csv']]
for example in examples:
print "\nTesting with:\n", example
max_cat.i_create_all_mc_resources(self, example[0], max_categories=example[1], objective=example[2], test=example[3], output=example[4])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
max_cat.i_check_create_max_categories_datasets(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def test_scenario1(self):
"""
Scenario: Successfully building test centroid predictions from scratch:
Given I create BigML resources uploading train "<data>" file to find centroids for "<test>" remotely with mapping file "<fields_map>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the cluster has been created
And I check that the source has been created from the test file
And I check that the dataset has been created from the test file
And I check that the batch centroid prediction has been created
And I check that the centroids are ready
Then the local centroids file is like "<predictions_file>"
Examples:
| data | test | fields_map | output |predictions_file |
| ../data/grades.csv | ../data/grades_perm.csv | ../data/grades_fields_map_perm.csv | ./scenario_cb_1_r/centroids.csv | ./check_files/centroids_grades.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/grades.csv', 'data/grades_perm.csv', 'data/grades_fields_map_perm.csv', 'scenario_cb_1_r/centroids.csv', 'check_files/centroids_grades.csv']]
for example in examples:
print "\nTesting with:\n", example
test_cluster.i_create_all_cluster_resources_with_mapping(self, data=example[0], test=example[1], fields_map=example[2], output=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_cluster(self)
test_pred.i_check_create_test_source(self)
test_pred.i_check_create_test_dataset(self)
batch_pred.i_check_create_batch_centroid(self)
test_cluster.i_check_create_centroids(self)
test_pred.i_check_predictions(self, example[4])
def setup_scenario02(self):
"""
Scenario: Successfully building test predictions from start:
Given I create BigML resources uploading train "<data>" file to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
"""
examples = [[
'data/grades.csv', 'data/test_grades.csv',
'scenario1_r/predictions.csv', 'check_files/predictions_grades.csv'
],
[
'data/iris.csv', 'data/test_iris.csv',
'scenario1/predictions.csv',
'check_files/predictions_iris.csv'
]]
show_doc(self.setup_scenario02, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources(self, example[0], example[1],
example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario1(self):
"""
Scenario 1: Successfully building test predictions from scratch:
Given I create BigML resources uploading train "<data>" file to test "<test>" remotely with mapping file "<fields_map>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the source has been created from the test file
And I check that the dataset has been created from the test file
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | fields_map | output |predictions_file |
| ../data/grades.csv | ../data/test_grades.csv | ../data/grades_fields_map.csv | ./scenario_r1_r/predictions.csv | ./check_files/predictions_grades.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/grades.csv', 'data/test_grades.csv', 'data/grades_fields_map.csv', 'scenario_r1_r/predictions.csv', 'check_files/predictions_grades.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_batch_map(self, data=example[0], test=example[1], fields_map=example[2], output=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_batch_pred.i_check_create_test_source(self)
test_batch_pred.i_check_create_test_dataset(self)
test_batch_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario11(self):
"""
Scenario: Successfully building test predictions from dataset specifying objective field and model fields
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using dataset, objective field <objective> and model fields <fields> to test "<test>" and log predictions in "<output>"
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file | objective | fields |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ./scenario11/predictions.csv | ./check_files/predictions_iris_b.csv | 0 | "petal length","petal width" |
"""
print self.test_scenario11.__doc__
examples = [[
'scenario1',
'{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'data/test_iris.csv', 'scenario11/predictions.csv',
'check_files/predictions_iris_b.csv', '0',
'"petal length","petal width"'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_pred.i_create_resources_from_dataset_objective_model(
self,
objective=example[5],
fields=example[6],
test=example[2],
output=example[3])
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario07(self):
"""
Scenario: Successfully building test predictions from models file
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I have previously executed "<scenario2>" or reproduce it with arguments <kwargs2>
And I create BigML resources using models in file "<models_file>" to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |scenario2 | kwargs2 | models_file | test | output |predictions_file |
"""
print self.test_scenario07.__doc__
examples = [
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5', '{"number_of_models": 10, "test": "data/test_iris.csv", "output": "scenario5/predictions.csv"}',
'scenario5/models', 'data/test_iris.csv', 'scenario6/predictions.csv', 'check_files/predictions_iris.csv']]
show_doc(self.test_scenario07, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[2], example[3])
test_pred.i_create_resources_from_models_file(self, multi_label=None, models_file=example[4], test=example[5], output=example[6])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[7])
def test_scenario14(self):
"""
Scenario: Successfully building test predictions from start with user-given separator:
Given I create BigML resources uploading train "<data>" file to test "<test>" and log predictions in "<output>" with "<separator>" as test field separator
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | separator | output |predictions_file |
| ../data/iris.csv | ../data/test_iris.tsv | "\t" |./scenario14/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario14.__doc__
examples = [[
'data/iris.csv', 'data/test_iris.tsv', '"\t"',
'scenario14/predictions.csv', 'check_files/predictions_iris.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_with_separator(
self,
data=example[0],
test=example[1],
output=example[3],
separator=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario21(self):
"""
Scenario 1: Successfully building test predictions from ensemble
And I create BigML resources from "<data>" using ensemble of <number_of_models> models to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the ensemble has been created
And I check that the models in the ensembles have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|data | number_of_models | test | output | predictions_file |
"""
examples = [
['data/grades.csv', '5', 'data/test_grades.csv', 'scenario21/predictions.csv', 'check_files/predictions_grades_e.csv']]
show_doc(self.test_scenario21, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_resources_in_prod_from_ensemble( \
self, data=example[0], number_of_models=example[1],
test=example[2], output=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_ensemble(self)
test_pred.i_check_create_models_in_ensembles(self,
in_ensemble=True)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario15(self):
"""
Scenario: Successfully building test predictions from start with different prediction file format:
Given I create BigML resources uploading train "<data>" file to test "<test>" and log predictions in "<output>" with prediction options "<options>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |options |predictions_file |
| ../data/iris.csv | ../data/test_iris.csv |./scenario15/predictions.csv |--prediction-header --prediction-fields 'petal length,petal width' --prediction-info full | ./check_files/predictions_iris_h.csv |
"""
print self.test_scenario15.__doc__
examples = [[
'data/iris.csv', 'data/test_iris.csv',
'scenario15/predictions.csv',
'--prediction-header --prediction-fields \'petal length,petal width\' --prediction-info full',
'check_files/predictions_iris_h.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_with_options(self,
data=example[0],
test=example[1],
output=example[2],
options=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario1(self):
"""
Scenario: Successfully building test predictions from dataset specifying objective field and model fields
Given I create a BigML dataset from "<data>" and store logs in "<output_dir>"
And I check that the source has been created
And I check that the dataset has been created
And I create BigML resources using dataset, objective field <objective> and model fields <fields> to test "<test>" and log predictions in "<output>"
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|data | output_dir | test | output |predictions_file | objective | fields |
| ../data/iris_2fb.csv| ./scénario1 | ../data/test_iris2fb.csv | ./scénario1/predictions.csv | ./check_files/predictions_iris_2fb.csv | spécies | "pétal width" |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris_2fb.csv', u'scénario1', 'data/test_iris2fb.csv', u'scénario1/predictions.csv', 'check_files/predictions_iris_2fb.csv', u'spécies', u'"pétal width"']]
for example in examples:
print "\nTesting with:\n", example
dataset_adv.i_create_dataset(self, data=example[0], output_dir=example[1])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_create_resources_from_dataset_objective_model(self, objective=example[5], fields=example[6], test=example[2], output=example[3])
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario17(self):
"""
Scenario: Successfully building test predictions from local model
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using local model in "<scenario>" to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ./scenario17/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario17.__doc__
examples = [[
'scenario1',
'{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'data/test_iris.csv', 'scenario17/predictions.csv',
'check_files/predictions_iris.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_pred.i_create_resources_from_local_model(self,
directory=example[0],
test=example[2],
output=example[3])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def setup_scenario02(self):
"""
Scenario: Successfully building test predictions from start:
Given I create BigML logistic regression resources uploading train "<data>" file to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris.csv | ../data/test_iris.csv | ./scenario1_lr/predictions.csv | ./check_files/predictions_iris_lr.csv |
"""
print self.setup_scenario02.__doc__
examples = [
['data/iris.csv', 'data/test_iris.csv', 'scenario1_lr/predictions.csv', 'check_files/predictions_iris_lr.csv']]
for example in examples:
print "\nTesting with:\n", example
lr_pred.i_create_all_lr_resources(self, example[0], example[1], example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
lr_pred.i_check_create_lr_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario19(self):
"""
Scenario: Successfully building test predictions from start using median:
Given I create BigML resources uploading train "<data>" file using the median to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/grades.csv | ../data/test_grades.csv | ./scenario19/predictions.csv | ./check_files/predictions_grades_median.csv |
"""
print self.test_scenario19.__doc__
examples = [[
'data/grades.csv', 'data/test_grades.csv',
'scenario19/predictions.csv',
'check_files/predictions_grades_median.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_with_median(self,
data=example[0],
test=example[1],
output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario1(self):
"""
Scenario: Successfully building test centroid predictions from scratch:
Given I create BigML resources uploading train "<data>" file to find centroids for "<test>" remotely with mapping file "<fields_map>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the cluster has been created
And I check that the source has been created from the test file
And I check that the dataset has been created from the test file
And I check that the batch centroid prediction has been created
And I check that the centroids are ready
Then the local centroids file is like "<predictions_file>"
Examples:
| data | test | fields_map | output |predictions_file |
| ../data/grades.csv | ../data/grades_perm.csv | ../data/grades_fields_map_perm.csv | ./scenario_cb_1_r/centroids.csv | ./check_files/centroids_grades.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/grades.csv', 'data/grades_perm.csv', 'data/grades_fields_map_perm.csv', 'scenario_cb_1_r/centroids.csv', 'check_files/centroids_grades.csv']]
for example in examples:
print "\nTesting with:\n", example
test_cluster.i_create_all_cluster_resources_with_mapping(self, data=example[0], test=example[1], fields_map=example[2], output=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_cluster(self)
test_pred.i_check_create_test_source(self)
test_pred.i_check_create_test_dataset(self)
batch_pred.i_check_create_batch_centroid(self)
test_cluster.i_check_create_centroids(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario8(self):
"""
Scenario: Successfully building test predictions from model with operating point
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML remote batch predictions one by one using model to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |
operating_point | test | output |predictions_file |
"""
examples = [
['scenario_r1', '{"data": "data/iris.csv", "output": "scenario_r1/predictions.csv", "test": "data/test_iris.csv"}', 'data/test_iris.csv', 'scenario_r8/predictions.csv', 'check_files/predictions_iris.csv']]
print self.test_scenario8.__doc__
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it( \
self, example[0], example[1])
test_batch_pred.i_create_resources_from_model_remote_no_batch( \
self, test=example[2], output=example[3])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario2(self):
"""
Given I create BigML resources uploading train "<data>" file to test "<test>" remotely with proportional missing strategy and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the source has been created from the test file
And I check that the dataset has been created from the test file
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris.csv | ../data/test_iris_nulls.csv | ./scenario_mis_2/predictions.csv | ./check_files/predictions_iris_nulls.csv
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', 'data/test_iris_nulls.csv', 'scenario_mis_2/predictions.csv', 'check_files/predictions_iris_nulls.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_remote_proportional(self, data=example[0], test=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_test_source(self)
test_pred.i_check_create_test_dataset(self)
test_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario5(self):
"""
Scenario: Successfully building test predictions from models retrieved by tag
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML multi-label resources using models tagged as "<tag>" to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | tag | test | output |predictions_file |
| scenario_ml_6| {"tag": "my_multilabel_5", "data": "../data/multilabel.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "./scenario_ml_6/predictions.csv", "test": "../data/test_multilabel.csv"} | my_multilabel_5 | ../data/test_multilabel.csv | ./scenario_ml_5/predictions.csv | ./check_files/predictions_ml_comma.csv |
"""
print self.test_scenario5.__doc__
examples = [[
'scenario_ml_6',
'{"tag": "my_multilabel_5", "data": "data/multilabel.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "scenario_ml_6/predictions.csv", "test": "data/test_multilabel.csv"}',
'my_multilabel_5', 'data/test_multilabel.csv',
'scenario_ml_5/predictions.csv',
'check_files/predictions_ml_comma.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
ml_pred.i_predict_ml_from_model_tag(self,
tag=example[2],
test=example[3],
output=example[4])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def setup_scenario02(self):
"""
Scenario: Successfully building test predictions from start:
Given I create BigML logistic regression resources uploading train "<data>" file to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris.csv | ../data/test_iris.csv | ./scenario1_lr/predictions.csv | ./check_files/predictions_iris_lr.csv |
"""
print self.setup_scenario02.__doc__
examples = [[
'data/iris.csv', 'data/test_iris.csv',
'scenario1_lr/predictions.csv',
'check_files/predictions_iris_lr.csv'
]]
for example in examples:
print "\nTesting with:\n", example
lr_pred.i_create_all_lr_resources(self, example[0], example[1],
example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
lr_pred.i_check_create_lr_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def setup_scenario1(self):
"""
Scenario: Successfully building multi-label test predictions from start:
Given I create BigML multi-label resources tagged as "<tag>" with "<label_separator>" label separator and <number_of_labels> labels uploading train "<data>" file with "<training_separator>" field separator to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|tag |label_separator |number_of_labels | data |training_separator | test | output |predictions_file |
|my_multilabel_1|:|7| ../data/multilabel.csv |,| ../data/test_multilabel.csv | ./scenario_ml_1/predictions.csv | ./check_files/predictions_ml.csv |
"""
print self.setup_scenario1.__doc__
examples = [[
'my_multilabel_1', ':', '7', 'data/multilabel.csv', ',',
'data/test_multilabel.csv', 'scenario_ml_1/predictions.csv',
'check_files/predictions_ml.csv'
]]
for example in examples:
print "\nTesting with:\n", example
ml_pred.i_create_all_ml_resources(self,
tag=example[0],
label_separator=example[1],
number_of_labels=example[2],
data=example[3],
training_separator=example[4],
test=example[5],
output=example[6])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[7])
def test_scenario5(self):
"""
Scenario 5: Successfully building test predictions from dataset and prediction format info
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using a model to test the previous test dataset remotely with prediction headers and fields "<fields>" and log predictions in "<output>"
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | fields | output |predictions_file |
| scenario_r1| {"data": "../data/iris.csv", "output": "./scenario_r1/predictions.csv", "test": "../data/test_iris.csv"} | sepal length,sepal width | ./scenario_r4/predictions.csv | ./check_files/predictions_iris_format.csv |
"""
print self.test_scenario5.__doc__
examples = [
['scenario_r1', '{"data": "data/iris.csv", "output": "scenario_r1/predictions.csv", "test": "data/test_iris.csv"}', 'sepal length,sepal width', 'scenario_r4/predictions.csv', 'check_files/predictions_iris_format.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_create_resources_from_model_batch(self, fields=example[2], output=example[3])
test_batch_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario2(self):
"""
Scenario: Successfully building test predictions from source
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML multi-label resources using source to test "<test>" and log predictions in "<output>"
And I check that the dataset has been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario_ml_1| {"tag": "my_multilabel_1", "data": "../data/multilabel.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "./scenario_ml_1/predictions.csv", "test": "../data/test_multilabel.csv"} | ../data/test_multilabel.csv | ./scenario_ml_2/predictions.csv | ./check_files/predictions_ml_comma.csv |
"""
print self.test_scenario2.__doc__
examples = [[
'scenario_ml_1',
'{"tag": "my_multilabel_1", "data": "data/multilabel.csv", "label_separator": ":", "number_of_labels": 7, "training_separator": ",", "output": "scenario_ml_1/predictions.csv", "test": "data/test_multilabel.csv"}',
'data/test_multilabel.csv', 'scenario_ml_2/predictions.csv',
'check_files/predictions_ml_comma.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_pred.i_create_resources_from_source(self,
multi_label='multi-label',
test=example[2],
output=example[3])
test_pred.i_check_create_dataset(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario1(self):
"""
Scenario: Successfully building test predictions with proportional missing strategy:
Given I create BigML resources uploading train "<data>" file to test "<test>" with proportional missing strategy and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris.csv | ../data/test_iris_nulls.csv | ./scenario_mis_1/predictions.csv | ./check_files/predictions_iris_nulls.csv |
"""
print self.test_scenario1.__doc__
examples = [[
'data/iris.csv', 'data/test_iris_nulls.csv',
'scenario_mis_1/predictions.csv',
'check_files/predictions_iris_nulls.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_proportional(self,
data=example[0],
test=example[1],
output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def setup_scenario1(self):
"""
Scenario: Successfully building test predictions from training data using datasets with max categories
Given I create BigML resources from "<data>" with <max_categories> as categories limit and <objective> as objective field to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the max_categories datasets have been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|data |max_categories | objective | test | output |predictions_file |
|../data/iris.csv |1| species |../data/test_iris.csv | ./scenario_mc_1/predictions.csv | ./check_files/predictions_mc.csv |
"""
print self.setup_scenario1.__doc__
examples = [
['data/iris.csv', '1', 'species', 'data/test_iris.csv', 'scenario_mc_1/predictions.csv', 'check_files/predictions_mc.csv']]
for example in examples:
print "\nTesting with:\n", example
max_cat.i_create_all_mc_resources(self, example[0], max_categories=example[1], objective=example[2], test=example[3], output=example[4])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
max_cat.i_check_create_max_categories_datasets(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def test_scenario10(self):
"""
Scenario: Successfully combining test predictions from existing directories
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I have previously executed "<scenario2>" or reproduce it with arguments <kwargs2>
And I combine BigML predictions files in "<directory1>" and "<directory2>" into "<output>" with method "<method>"
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |scenario2 | kwargs2 | directory1 | directory2 | output |predictions_file | method |
"""
examples = [
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5', '{"number_of_models": 10, "output": "scenario5/predictions.csv", "test": "data/test_iris.csv"}',
'scenario1', 'scenario5', 'scenario9/predictions_c.csv', 'check_files/predictions_iris.csv', '"confidence weighted"'],
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5', '{"number_of_models": 10, "output": "scenario5/predictions.csv", "test": "data/test_iris.csv"}',
'scenario1', 'scenario5', 'scenario9/predictions_p.csv', 'check_files/predictions_iris_p.csv', '"probability weighted"'],
['scenario1_r', '{"data": "data/grades.csv", "output": "scenario1_r/predictions.csv", "test": "data/test_grades.csv"}',
'scenario1_r', '{"data": "data/grades.csv", "output": "scenario1_r/predictions.csv", "test": "data/test_grades.csv"}',
'scenario1_r', 'scenario1_r', 'scenario10/predictions_c.csv', 'check_files/predictions_grades.csv', '"confidence weighted"'],
['scenario1_r', '{"data": "data/grades.csv", "output": "scenario1_r/predictions.csv", "test": "data/test_grades.csv"}',
'scenario1_r', '{"data": "data/grades.csv", "output": "scenario1_r/predictions.csv", "test": "data/test_grades.csv"}',
'scenario1_r', 'scenario1_r', 'scenario10/predictions_p.csv', 'check_files/predictions_grades_p.csv', '"probability weighted"']]
show_doc(self.test_scenario10, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[2], example[3])
test_pred.i_find_predictions_files_with_method(self, directory1=example[4], directory2=example[5], output=example[6], method=example[8])
test_pred.i_check_predictions(self, example[7])
def test_scenario2(self):
"""
Scenario: Successfully building test predictions from source using datasets with max categories
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources with <max_categories> as categories limit and <objective> as objective field using source to test "<test>" and log predictions in "<output>"
And I check that the dataset has been created
And I check that the max_categories datasets have been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |max_categories| objective | test | output |predictions_file |
| scenario_mc_1| {"data": "../data/iris.csv", "max_categories": "1", "objective": "species", "output": "./scenario_mc_1/predictions.csv", "test": "../data/test_iris.csv"} |1| species | ../data/test_iris.csv | ./scenario_mc_2/predictions.csv | ./check_files/predictions_mc.csv |
"""
print self.test_scenario2.__doc__
examples = [
['scenario_mc_1', '{"data": "data/iris.csv", "max_categories": "1", "objective": "species", "output": "scenario_mc_1/predictions.csv", "test": "data/test_iris.csv"}', '1', 'species', 'data/test_iris.csv', 'scenario_mc_2/predictions.csv', 'check_files/predictions_mc.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
max_cat.i_create_all_mc_resources_from_source(self, max_categories=example[2], objective=example[3], test=example[4], output=example[5])
test_pred.i_check_create_dataset(self, suffix=None)
max_cat.i_check_create_max_categories_datasets(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[6])
def test_scenario15(self):
"""
Scenario: Successfully building test predictions from start with different prediction file format:
Given I create BigML resources uploading train "<data>" file to test "<test>" and log predictions in "<output>" with prediction options "<options>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |options |predictions_file |
"""
examples = [
['data/iris.csv', 'data/test_iris.csv', 'scenario15/predictions.csv', '--prediction-header --prediction-fields \'petal length,petal width\' --prediction-info full', 'check_files/predictions_iris_h.csv']]
show_doc(self.test_scenario15, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_with_options(self, data=example[0], test=example[1], output=example[2], options=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario8(self):
"""
Scenario: Successfully building test predictions from model with operating point
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML remote batch predictions one by one using model to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |
operating_point | test | output |predictions_file |
"""
examples = [
['scenario_r1', '{"data": "data/iris.csv", "output": "scenario_r1/predictions.csv", "test": "data/test_iris.csv"}', 'data/test_iris.csv', 'scenario_r8/predictions.csv', 'check_files/predictions_iris.csv']]
print self.test_scenario8.__doc__
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it( \
self, example[0], example[1])
test_batch_pred.i_create_resources_from_model_remote_no_batch( \
self, test=example[2], output=example[3])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario24(self):
"""
Scenario: Successfully test predictions remotely from boosted ensemble
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using boosted ensemble in <iterations> iterations to remotely test "<test>" and log predictions in "<output>"
And I check that the ensemble has been created
And I check that the predictions are ready
And I check that the batch prediction is ready
And I check that the bath predictions datset is ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | iterations | test | output |predictions_file |
"""
examples = [
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}', '10', 'data/test_iris.csv', 'scenario24/predictions.csv', 'check_files/predictions_iris_boost.csv']]
show_doc(self.test_scenario24, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it( \
self, example[0], example[1])
test_pred.i_create_resources_remotely_from_boosted_ensemble( \
self, iterations=example[2], test=example[3],
output=example[4])
test_pred.i_check_create_ensemble(self)
test_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def test_scenario1(self):
"""
Scenario 1: Successfully building test predictions from scratch:
Given I create BigML resources uploading train "<data>" file to test "<test>" remotely with mapping file "<fields_map>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the source has been created from the test file
And I check that the dataset has been created from the test file
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | fields_map | output |predictions_file |
| ../data/grades.csv | ../data/test_grades.csv | ../data/grades_fields_map.csv | ./scenario_r1_r/predictions.csv | ./check_files/predictions_grades.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/grades.csv', 'data/test_grades.csv', 'data/grades_fields_map.csv', 'scenario_r1_r/predictions.csv', 'check_files/predictions_grades.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_batch_map(self, data=example[0], test=example[1], fields_map=example[2], output=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_batch_pred.i_check_create_test_source(self)
test_batch_pred.i_check_create_test_dataset(self)
test_batch_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def setup_scenario02(self):
"""
Scenario: Successfully building test predictions from start:
Given I create BigML resources uploading train "<data>" file to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
"""
examples = [
['data/grades.csv', 'data/test_grades.csv', 'scenario1_r/predictions.csv', 'check_files/predictions_grades.csv'],
['data/iris.csv', 'data/test_iris.csv', 'scenario1/predictions.csv', 'check_files/predictions_iris.csv']]
show_doc(self.setup_scenario02, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources(self, example[0], example[1], example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario4(self):
"""
Scenario 4: Successfully building test predictions from dataset
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using dataset to test the previous test dataset remotely and log predictions in "<output>"
And I check that the model has been created
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario_r1| {"data": "../data/iris.csv", "output": "./scenario_r1/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ./scenario_r3/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario4.__doc__
examples = [[
'scenario_r1',
'{"data": "data/iris.csv", "output": "scenario_r1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario_r3/predictions.csv', 'check_files/predictions_iris.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_pred.i_create_resources_from_dataset_batch(self,
output=example[2])
test_pred.i_check_create_model(self)
test_batch_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario1(self):
"""
Scenario: Successfully building test predictions with missing-splits model:
Given I create BigML resources uploading train "<data>" file to test "<test>" with a missing-splits model and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris_missing.csv | ../data/test_iris_missing.csv | ./scenario_mspl_1/predictions.csv | ./check_files/predictions_iris_missing.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris_missing.csv', 'data/test_iris_missing.csv', 'scenario_mspl_1/predictions.csv', 'check_files/predictions_iris_missing.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_missing_splits(self, data=example[0], test=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario5(self):
"""
Scenario 5: Successfully building test predictions from dataset and prediction format info
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using a model to test the previous test dataset remotely with prediction headers and fields "<fields>" and log predictions in "<output>"
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | fields | output |predictions_file |
| scenario_r1| {"data": "../data/iris.csv", "output": "./scenario_r1/predictions.csv", "test": "../data/test_iris.csv"} | sepal length,sepal width | ./scenario_r4/predictions.csv | ./check_files/predictions_iris_format.csv |
"""
print self.test_scenario5.__doc__
examples = [[
'scenario_r1',
'{"data": "data/iris.csv", "output": "scenario_r1/predictions.csv", "test": "data/test_iris.csv"}',
'sepal length,sepal width', 'scenario_r4/predictions.csv',
'check_files/predictions_iris_format.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_pred.i_create_resources_from_model_batch(self,
fields=example[2],
output=example[3])
test_batch_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario03(self):
"""
Scenario: Successfully building test predictions from source
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML logistic regression resources using source to test "<test>" and log predictions in "<output>"
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1_lr/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ./scenario2/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario03.__doc__
examples = [
['scenario1_lr', '{"data": "data/iris.csv", "output": "scenario1_lr/predictions.csv", "test": "data/test_iris.csv"}', 'data/test_iris.csv', 'scenario2_lr/predictions.csv', 'check_files/predictions_iris_lr.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
lr_pred.i_create_lr_resources_from_source(self, None, test=example[2], output=example[3])
test_pred.i_check_create_dataset(self, suffix=None)
lr_pred.i_check_create_lr_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario07(self):
"""
Scenario: Successfully building batch test predictions from model with customized output
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML deepnet resources using model to test "<test>" as a batch prediction with output format "<batch-output>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test |batch_output | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ../data/batch_output.json | ./scenario6_dn/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario07.__doc__
examples = [[
'scenario1_dn',
'{"data": "data/iris.csv", "output": "scenario1_dn/predictions.csv", "test": "data/test_iris.csv"}',
'data/test_iris.csv', 'data/batch_output.json',
'scenario6_dn/predictions.csv',
'check_files/predictions_iris_dn_prob.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
dn_pred.i_create_dn_resources_from_model_remote_with_options(
self,
test=example[2],
output=example[4],
options_file=example[3])
batch_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def setup_scenario1(self):
"""
Scenario: Successfully building multi-label test predictions from start:
Given I create BigML multi-label resources tagged as "<tag>" with "<label_separator>" label separator and <number_of_labels> labels uploading train "<data>" file with "<training_separator>" field separator and "<ml_fields>" as multi-label fields using model_fields "<model_fields>" and objective "<objective>" to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the models have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|tag |label_separator |number_of_labels | data |training_separator | ml_fields | model_fields | objective | test | output |predictions_file |
|my_multilabelm_1|:|7| ../data/multilabel_multi.csv |, | type,class | -type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P | class |../data/test_multilabel.csv | ./scenario_mlm_1/predictions.csv | ./check_files/predictions_ml.csv |
"""
print self.setup_scenario1.__doc__
examples = [
['my_multilabelm_1', ':', '7', 'data/multilabel_multi.csv', ',', 'type,class', '-type,-type - W,-type - A,-type - C,-type - S,-type - R,-type - T,-type - P', 'class', 'data/test_multilabel.csv', 'scenario_mlm_1/predictions.csv', 'check_files/predictions_ml.csv']]
for example in examples:
print "\nTesting with:\n", example
ml_pred.i_create_all_mlm_resources(self, tag=example[0], label_separator=example[1], number_of_labels=example[2], data=example[3], training_separator=example[4], ml_fields=example[5], model_fields=example[6], objective=example[7], test=example[8], output=example[9])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self)
test_pred.i_check_create_models(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[10])
def test_scenario01(self):
"""
Scenario: Successfully building deepnet test predictions from start with no headers:
Given I create BigML deepnet resources uploading train "<data>" file with no headers to test "<test>" with no headers and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the deepnet model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris_nh.csv | ../data/test_iris_nh.csv | ./scenario1_dn_nh/predictions.csv | ./check_files/predictions_iris_dn.csv |
"""
print self.test_scenario01.__doc__
examples = [[
'data/iris_nh.csv', 'data/test_iris_nh.csv',
'scenario1_dn_nh/predictions.csv',
'check_files/predictions_iris_dn.csv'
]]
for example in examples:
print "\nTesting with:\n", example
dn_pred.i_create_all_dn_resources_with_no_headers(
self, example[0], example[1], example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
dn_pred.i_check_create_dn_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario2(self):
"""
Scenario: Successfully building test predictions from source
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using source to find centroids for "<test>" and log predictions in "<output>"
And I check that the dataset has been created
And I check that the cluster has been created
And I check that the centroids are ready
Then the local centroids file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario_c_1| {"data": "../data/diabetes.csv", "output": "./scenario_c_1/centroids.csv", "test": "../data/diabetes.csv"} | ../data/diabetes.csv | ./scenario_c_2/centroids.csv | ./check_files/centroids_diabetes.csv |
"""
print self.test_scenario2.__doc__
examples = [[
'scenario_c_1',
'{"data": "data/diabetes.csv", "output": "scenario_c_1/centroids.csv", "test": "data/diabetes.csv"}',
'data/diabetes.csv', 'scenario_c_2/centroids.csv',
'check_files/centroids_diabetes.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
test_cluster.i_create_cluster_resources_from_source(
self, test=example[2], output=example[3])
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_cluster(self)
test_cluster.i_check_create_centroids(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario09(self):
"""
Scenario: Successfully combining test predictions from existing directories
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I have previously executed "<scenario2>" or reproduce it with arguments <kwargs2>
Given I combine BigML predictions files in "<directory1>" and "<directory2>" into "<output>"
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |scenario2 | kwargs2 | directory1 | directory2 | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | scenario5| {"number_of_models": 10, "output": "./scenario5/predictions.csv", "test": "../data/test_iris.csv"} | ./scenario1 | ./scenario5 | ./scenario8/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario09.__doc__
examples = [
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5', '{"number_of_models": 10, "test": "data/test_iris.csv", "output": "scenario5/predictions.csv"}',
'scenario1', 'scenario5', 'scenario8/predictions.csv', 'check_files/predictions_iris.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[2], example[3])
test_pred.i_find_predictions_files(self, directory1=example[4], directory2=example[5], output=example[6])
test_pred.i_check_predictions(self, example[7])
def test_scenario1(self):
"""
Scenario: Successfully building test centroids from scratch:
Given I create BigML resources uploading train "<data>" file to create centroids for "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the cluster has been created
And I check that the centroids are ready
Then the local centroids file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/grades.csv | ../data/grades.csv | ./scenario_c_1_r/centroids.csv | ./check_files/centroids_grades.csv |
| ../data/diabetes.csv | ../data/diabetes.csv | ./scenario_c_1/centroids.csv | ./check_files/centroids_diabetes.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/grades.csv', 'data/grades.csv', 'scenario_c_1_r/centroids.csv', 'check_files/centroids_grades.csv'],
['data/diabetes.csv', 'data/diabetes.csv', 'scenario_c_1/centroids.csv', 'check_files/centroids_diabetes.csv']]
for example in examples:
print "\nTesting with:\n", example
test_cluster.i_create_all_cluster_resources(self, data=example[0], test=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_cluster(self)
test_cluster.i_check_create_centroids(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario18(self):
"""
Scenario: Successfully building test predictions from ensemble
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
Given I have previously executed "<scenario2>" or reproduce it with arguments <kwargs2>
And I create BigML resources using local ensemble of <number_of_models> models in "<scenario2>" to test "<test>" and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |scenario2 | kwargs2 | number_of_models | test | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | scenario5| {"number_of_models": 10, "output": "./scenario5/predictions.csv", "test": "../data/test_iris.csv"} | 10 | ../data/test_iris.csv | ./scenario18/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario18.__doc__
examples = [
['scenario1', '{"data": "data/iris.csv", "output": "scenario1/predictions.csv", "test": "data/test_iris.csv"}',
'scenario5', '{"number_of_models": 10, "output": "scenario5/predictions.csv", "test": "data/test_iris.csv"}',
'10', 'scenario5', 'data/test_iris.csv', 'scenario18/predictions.csv', 'check_files/predictions_iris.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[2], example[3])
test_pred.i_create_resources_from_local_ensemble(self, number_of_models=example[4], directory=example[5], test=example[6], output=example[7])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[8])
def test_scenario4(self):
"""
Scenario: Successfully building ensembles test predictions from models file with max categories
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using models in file "<models_file>" to test "<test>" and log predictions with combine method in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs |models_file| test | output |predictions_file |
| scenario_mc_1| {"data": "../data/iris.csv", "max_categories": "1", "objective": "species", "output": "./scenario_mc_1/predictions.csv", "test": "../data/test_iris.csv"} | scenario_mc_1/models | ../data/test_iris.csv | ./scenario_mc_4/predictions.csv | ./check_files/predictions_mc.csv |
"""
print self.test_scenario4.__doc__
examples = [
[
"scenario_mc_1",
'{"data": "data/iris.csv", "max_categories": "1", "objective": "species", "output": "scenario_mc_1/predictions.csv", "test": "data/test_iris.csv"}',
"scenario_mc_1/models",
"data/test_iris.csv",
"scenario_mc_4/predictions.csv",
"check_files/predictions_mc.csv",
]
]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
max_cat.i_create_all_mc_resources_from_models(
self, models_file=example[2], test=example[3], output=example[4]
)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[5])
def test_scenario19(self):
"""
Scenario: Successfully building test predictions from start using median:
Given I create BigML resources uploading train "<data>" file using the median to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/grades.csv | ../data/test_grades.csv | ./scenario19/predictions.csv | ./check_files/predictions_grades_median.csv |
"""
print self.test_scenario19.__doc__
examples = [
['data/grades.csv', 'data/test_grades.csv', 'scenario19/predictions.csv', 'check_files/predictions_grades_median.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_with_median(self, data=example[0], test=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario2(self):
"""
Scenario: Successfully building test predictions from scratch:
Given I create BigML resources uploading train "<data>" file to test "<test>" remotely with a missing-splits model and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the source has been created from the test file
And I check that the dataset has been created from the test file
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris_missing.csv | ../data/test_iris_missing.csv | ./scenario_mspl_2/predictions.csv | ./check_files/predictions_iris_missing.csv
"""
print self.test_scenario2.__doc__
examples = [[
'data/iris_missing.csv', 'data/test_iris_missing.csv',
'scenario_mspl_2/predictions.csv',
'check_files/predictions_iris_missing.csv'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_remote_missing_splits(
self, data=example[0], test=example[1], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_test_source(self)
test_pred.i_check_create_test_dataset(self)
test_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario01(self):
"""
Scenario: Successfully building test predictions from start with no headers:
Given I create BigML resources uploading train "<data>" file with no headers to test "<test>" with no headers and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file |
| ../data/iris_nh.csv | ../data/test_iris_nh.csv | ./scenario1_nh/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario01.__doc__
examples = [
['data/iris_nh.csv', 'data/test_iris_nh.csv', 'scenario1_nh/predictions.csv', 'check_files/predictions_iris.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_all_resources_with_no_headers(self, example[0], example[1], example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario07(self):
"""
Scenario: Successfully building batch test predictions from model
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML logistic regression resources using model to test "<test>" as a batch prediction and log predictions in "<output>"
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario1| {"data": "../data/iris.csv", "output": "./scenario1/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ./scenario6_lr/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario07.__doc__
examples = [[
'scenario1_lr',
'{"data": "data/iris.csv", "output": "scenario1_lr/predictions.csv", "test": "data/test_iris.csv"}',
'data/test_iris.csv', 'scenario6_lr/predictions_p.csv',
'check_files/predictions_iris_lr_op_prob.csv',
'data/operating_point_prob.json'
]]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(
self, example[0], example[1])
lr_pred.i_create_lr_resources_from_model_with_op(
self,
test=example[2],
output=example[3],
operating_point=example[5])
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
def test_scenario4(self):
"""
Scenario 4: Successfully building test predictions from dataset
Given I have previously executed "<scenario>" or reproduce it with arguments <kwargs>
And I create BigML resources using dataset to test the previous test dataset remotely and log predictions in "<output>"
And I check that the model has been created
And I check that the batch prediction has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|scenario | kwargs | test | output |predictions_file |
| scenario_r1| {"data": "../data/iris.csv", "output": "./scenario_r1/predictions.csv", "test": "../data/test_iris.csv"} | ../data/test_iris.csv | ./scenario_r3/predictions.csv | ./check_files/predictions_iris.csv |
"""
print self.test_scenario4.__doc__
examples = [
['scenario_r1', '{"data": "data/iris.csv", "output": "scenario_r1/predictions.csv", "test": "data/test_iris.csv"}', 'scenario_r3/predictions.csv', 'check_files/predictions_iris.csv']]
for example in examples:
print "\nTesting with:\n", example
test_pred.i_have_previous_scenario_or_reproduce_it(self, example[0], example[1])
test_pred.i_create_resources_from_dataset_batch(self, output=example[2])
test_pred.i_check_create_model(self)
test_batch_pred.i_check_create_batch_prediction(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario2(self):
"""
Scenario: Successfully building predictions for data streamed to stdin:
Given I create BigML resources uploading train "<data>" file to test "<test>" read from stdin with name "<name>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the model has been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
| data | test | output |predictions_file | name |
| ../data/iris.csv | ../data/test_iris.csv | ./scenario_st_2/predictions.csv | ./check_files/predictions_iris.csv | Source name: áéí |
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', 'data/test_iris.csv', 'scenario_st_2/predictions.csv', 'check_files/predictions_iris.csv', 'Source name: áéí']]
for example in examples:
print "\nTesting with:\n", example
stdin.i_create_all_resources_to_test_from_stdin(self, data=example[0], test=example[1], name=example[4], output=example[2])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_model(self)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[3])
def test_scenario21(self):
"""
Scenario 1: Successfully building test predictions from ensemble
And I create BigML resources from "<data>" using ensemble of <number_of_models> models to test "<test>" and log predictions in "<output>"
And I check that the source has been created
And I check that the dataset has been created
And I check that the ensemble has been created
And I check that the models in the ensembles have been created
And I check that the predictions are ready
Then the local prediction file is like "<predictions_file>"
Examples:
|data | number_of_models | test | output | predictions_file |
"""
examples = [[
'data/grades.csv', '5', 'data/test_grades.csv',
'scenario21/predictions.csv',
'check_files/predictions_grades_e.csv'
]]
show_doc(self.test_scenario21, examples)
for example in examples:
print "\nTesting with:\n", example
test_pred.i_create_resources_in_prod_from_ensemble( \
self, data=example[0], number_of_models=example[1],
test=example[2], output=example[3])
test_pred.i_check_create_source(self)
test_pred.i_check_create_dataset(self, suffix=None)
test_pred.i_check_create_ensemble(self)
test_pred.i_check_create_models_in_ensembles(self,
in_ensemble=True)
test_pred.i_check_create_predictions(self)
test_pred.i_check_predictions(self, example[4])
