def test_scenario1(self):
"""
Scenario: Successfully creating a prediction using a public model:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
And I make the model public
And I wait until the model is ready less than <time_3> secs
And I check the model status using the model's public url
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | objective | prediction |
| ../data/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | 000004 | Iris-setosa |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '{"petal width": 0.5}', '000004', 'Iris-setosa']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.make_the_model_public(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.model_from_public_url(self)
prediction_create.i_create_a_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
def test_scenario2(self):
"""
Scenario: Successfully creating a model from a dataset list and predicting with it using median:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
And I create a local multi model
When I create a local multimodel batch prediction using median for <input_data>
Then the local prediction is <prediction>
Examples:
| data | time_1 | time_2 | time_3 | input_data | prediction
| ../data/grades.csv | 10 | 10 | 10 | {'Tutorial': 99.47, 'Midterm': 53.12, 'TakeHome': 87.96} | 50
"""
print self.test_scenario2.__doc__
examples = [
["data/grades.csv", "10", "10", "10", '{"Tutorial": 99.47, "Midterm": 53.12, "TakeHome": 87.96}', 50]
]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
world.list_of_models = [world.model]
compare_pred.i_create_a_local_multi_model(self)
compare_pred.i_create_a_local_mm_median_batch_prediction(self, example[4])
compare_pred.the_local_prediction_is(self, example[5])
def test_scenario5(self):
"""
Scenario: Successfully creating a centroid and the associated dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a cluster
And I wait until the cluster is ready less than <time_3> secs
When I create a centroid for "<data_input>"
And I check the centroid is ok
Then the centroid is "<centroid>"
And I create a dataset from the cluster and the centroid
And I wait until the dataset is ready less than <time_2> secs
And I check that the dataset is created for the cluster and the centroid
Examples:
| data | time_1 | time_2 | time_3 | data_input | centroid |
| ../data/diabetes.csv | 10 | 20 | 20 | {"pregnancies": 0, "plasma glucose": 118, "blood pressure": 84, "triceps skin thickness": 47, "insulin": 230, "bmi": 45.8, "diabetes pedigree": 0.551, "age": 31, "diabetes": "true"} | Cluster 3 |
"""
print self.test_scenario5.__doc__
examples = [
['data/diabetes.csv', '10', '20', '20', '{"pregnancies": 0, "plasma glucose": 118, "blood pressure": 84, "triceps skin thickness": 47, "insulin": 230, "bmi": 45.8, "diabetes pedigree": 0.551, "age": 31, "diabetes": "true"}', 'Cluster 3']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
cluster_create.i_create_a_cluster(self)
cluster_create.the_cluster_is_finished_in_less_than(self, example[3])
prediction_create.i_create_a_centroid(self, example[4])
prediction_create.the_centroid_is(self, example[5])
def test_scenario4(self):
"""
Scenario: Successfully creating a source from a batch prediction:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create a batch prediction for the dataset with the model
And I wait until the batch prediction is ready less than <time_4> secs
Then I create a source from the batch prediction
And I wait until the source is ready less than <time_1> secs
Examples:
| data | time_1 | time_2 | time_3 | time_4 |
| ../data/iris.csv | 30 | 30 | 50 | 50 |
"""
print self.test_scenario4.__doc__
examples = [
['data/diabetes.csv', '30', '30', '50', '50']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
batch_pred_create.i_create_a_batch_prediction(self)
batch_pred_create.the_batch_prediction_is_finished_in_less_than(self, example[4])
batch_pred_create.i_create_a_source_from_batch_prediction(self)
source_create.the_source_is_finished(self, example[1])
def test_scenario5(self):
"""
Scenario: Successfully creating a local prediction from an Ensemble:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an ensemble of <number_of_models> models and <tlp> tlp
And I wait until the ensemble is ready less than <time_3> secs
And I create a local Ensemble
When I create a local ensemble prediction using median with confidence for "<data_input>"
Then the local prediction is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | number_of_models | tlp | data_input |prediction |
| ../data/grades.csv | 10 | 10 | 50 | 2 | 1 | {} | 67.5 |
"""
print self.test_scenario5.__doc__
examples = [
['data/grades.csv', '30', '30', '50', '2', '1', '{}', 69.0934]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
ensemble_create.i_create_an_ensemble(self, example[4], example[5])
ensemble_create.the_ensemble_is_finished_in_less_than(self, example[3])
ensemble_create.create_local_ensemble(self)
prediction_create.create_local_ensemble_prediction_using_median_with_confidence(self, example[6])
compare_pred.the_local_prediction_is(self, example[7])
def test_scenario5(self):
"""
Scenario: Successfully comparing association sets:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I update the source with params "<options>"
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the association is ready less than <time_3> secs
And I create a local association
When I create an association set for "<data_input>"
Then the association set is like the contents of "<association_set_file>"
And I create a local association set for "<data_input>"
Then the local association set is like the contents of "<association_set_file>"
"""
examples = [
['data/groceries.csv', '20', '20', '30', '{"fields": {"00000": {"optype": "text", "term_analysis": {"token_mode": "all", "language": "en"}}}}', 'data/associations/association_set.json', '{"field1": "cat food"}']]
show_doc(self.test_scenario5, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_create.i_update_source_with(self, example[4])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
association_create.i_create_an_association_from_dataset(self)
association_create.the_association_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_association(self)
prediction_create.i_create_an_association_set(self, example[6])
prediction_compare.the_association_set_is_like_file(self, example[5])
prediction_compare.i_create_a_local_association_set(self, example[6])
prediction_compare.the_local_association_set_is_like_file(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully creating a model with missing values and translate the tree model into a set of IF-THEN rules:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
And I create a local model
And I translate the tree into IF_THEN rules
Then I check the output is like "<expected_file>" expected file
Examples:
| data | time_1 | time_2 | time_3 | expected_file |
| data/iris_missing2.csv | 10 | 10 | 10 | data/model/if_then_rules_iris_missing2_MISSINGS.txt |
"""
print self.test_scenario2.__doc__
examples = [["data/iris_missing2.csv", "10", "10", "10", "data/model/if_then_rules_iris_missing2_MISSINGS.txt"]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model_with_missing_splits(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_model(self)
inspect_model.i_translate_the_tree_into_IF_THEN_rules(self)
inspect_model.i_check_if_the_output_is_like_expected_file(self, example[4])
def test_scenario2(self):
"""
Scenario 2: Successfully creating Topic Model from a dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create topic model from a dataset
And I wait until the topic model is ready less than <time_3> secs
And I update the topic model name to "<topic_model_name>"
When I wait until the topic_model is ready less than <time_4> secs
Then the topic model name is "<topic_model_name>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | topic_model_name | params
| ../data/spam.csv | 100 | 100 | 200 | 500 | my new topic model name | '{"fields": {"000001": {"optype": "text", "term_analysis": {"case_sensitive": true, "stem_words": true, "use_stopwords": false, "language": "en"}}}}'
"""
print self.test_scenario2.__doc__
examples = [
['data/spam.csv', '100', '100', '10000', '500', 'my new topic model name', '{"fields": {"000001": {"optype": "text", "term_analysis": {"case_sensitive": true, "stem_words": true, "use_stopwords": false, "language": "en"}}}}']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_create.i_update_source_with(self, example[6])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
topic_create.i_create_a_topic_model(self)
topic_create.the_topic_model_is_finished_in_less_than(self, example[3])
topic_create.i_update_topic_model_name(self, example[5])
topic_create.the_topic_model_is_finished_in_less_than(self, example[4])
topic_create.i_check_topic_model_name(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully creating a model and exporting it:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
And I export the <"pmml"> model to file "<expected_file>"
Then I check the model is stored in "<expected_file>" file in <"pmml">
Examples:
| data | time_1 | time_2 | time_3 | expected_file | pmml
| data/iris.csv | 10 | 10 | 10 | tmp/model/iris.json | false
| data/iris_sp_chars.csv | 10 | 10 | 10 | tmp/model/iris_sp_chars.pmml | true
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', '30', '30', '30', 'tmp/model/iris.json', False],
['data/iris_sp_chars.csv', '30', '30', '30', 'tmp/model/iris_sp_chars.pmml', True]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.i_export_model(self, example[5], example[4])
model_create.i_check_model_stored(self, example[4], example[5])
def test_scenario3(self):
"""
Scenario: Successfully creating a batch projection:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a pca
And I wait until the pca is ready less than <time_3> secs
When I create a batch projection for the dataset with the pca
And I wait until the batch projection is ready less than <time_4> secs
And I download the created projections file to "<local_file>"
Then the batch projection file is like "<projections_file>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | local_file | predictions_file |
| ../data/iris.csv | 30 | 30 | 50 | 50 | ./tmp/batch_projections.csv |./data/batch_projections.csv |
"""
print self.test_scenario3.__doc__
examples = [
['data/iris.csv', '30', '30', '50', '50', 'tmp/batch_projections.csv', 'data/batch_projections.csv']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
pca_create.i_create_a_pca(self)
pca_create.the_pca_is_finished_in_less_than(self, example[3])
batch_proj_create.i_create_a_batch_projection(self)
batch_proj_create.the_batch_projection_is_finished_in_less_than(self, example[4])
batch_proj_create.i_download_projections_file(self, example[5])
batch_proj_create.i_check_projections(self, example[6])
def test_scenario2(self):
"""
Scenario: Successfully creating a projection:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a pca
And I wait until the pca is ready less than <time_3> secs
When I create a projection for "<data_input>"
Then the projection is "<projection>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | projection |
| ../data/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | '{"PC-0": 0.46547, "PC-1": 0.13724, "PC-2": -0.01666, "PC-3": 3.28995, "PC-4": 4.60383, "PC-5": 2.22108}' |
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', '30', '30', '30', '{"petal width": 0.5}', '{"PC2": 0.1593, "PC3": -0.01286, "PC1": 0.91648, "PC6": 0.27284, "PC4": 1.29255, "PC5": 0.75196}']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
pca_create.i_create_a_pca(self)
pca_create.the_pca_is_finished_in_less_than(self, example[3])
projection_create.i_create_a_projection(self, example[4])
projection_create.the_projection_is(self, example[5])
print "\nEnd of tests in: %s\n-------------------\n" % __name__
def test_scenario2(self):
"""
Scenario: Successfully comparing centroids with configuration options:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a cluster with options "<options>"
And I wait until the cluster is ready less than <time_3> secs
And I create a local cluster
When I create a centroid for "<data_input>"
Then the centroid is "<centroid>" with distance "<distance>"
And I create a local centroid for "<data_input>"
Then the local centroid is "<centroid>" with distance "<distance>"
Examples:
| data | time_1 | time_2 | time_3 | options | data_input | centroid | distance | full_data_input
"""
examples = [
['data/iris.csv', '20', '20', '30', '{"summary_fields": ["sepal width"]}', '{"petal length": 1, "petal width": 1, "sepal length": 1, "species": "Iris-setosa"}', 'Cluster 2', '1.16436', '{"petal length": 1, "petal width": 1, "sepal length": 1, "species": "Iris-setosa"}'],
['data/iris.csv', '20', '20', '30', '{"default_numeric_value": "zero"}', '{"petal length": 1}', 'Cluster 4', '1.41215', '{"petal length": 1, "petal width": 0, "sepal length": 0, "sepal width": 0, "species": ""}']]
show_doc(self.test_scenario2, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
cluster_create.i_create_a_cluster_with_options(self, example[4])
cluster_create.the_cluster_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_cluster(self)
prediction_create.i_create_a_centroid(self, example[8])
prediction_create.the_centroid_is_with_distance(self, example[6], example[7])
prediction_compare.i_create_a_local_centroid(self, example[5])
prediction_compare.the_local_centroid_is(self, example[6], example[7])
def test_scenario5(self):
"""
Scenario: Successfully comparing association sets:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I update the source with params "<options>"
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the association is ready less than <time_3> secs
And I create a local association
When I create an association set for "<data_input>"
Then the association set is like the contents of "<association_set_file>"
And I create a local association set for "<data_input>"
Then the local association set is like the contents of "<association_set_file>"
"""
examples = [
['data/groceries.csv', '20', '20', '30', '{"fields": {"00000": {"optype": "text", "term_analysis": {"token_mode": "all", "language": "en"}}}}', 'data/associations/association_set.json', '{"field1": "cat food"}']]
show_doc(self.test_scenario5, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_create.i_update_source_with(self, example[4])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
association_create.i_create_an_association_from_dataset(self)
association_create.the_association_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_association(self)
prediction_create.i_create_an_association_set(self, example[6])
prediction_compare.the_association_set_is_like_file(self, example[5])
prediction_compare.i_create_a_local_association_set(self, example[6])
prediction_compare.the_local_association_set_is_like_file(self, example[5])
def test_scenario3(self):
"""
Scenario: Successfully comparing scores from anomaly detectors:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an anomaly detector
And I wait until the anomaly detector is ready less than <time_3> secs
And I create a local anomaly detector
When I create an anomaly score for "<data_input>"
Then the anomaly score is "<score>"
And I create a local anomaly score for "<data_input>"
Then the local anomaly score is "<score>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | score |
"""
examples = [
['data/tiny_kdd.csv', '20', '20', '30', '{"000020": 255.0, "000004": 183.0, "000016": 4.0, "000024": 0.04, "000025": 0.01, "000026": 0.0, "000019": 0.25, "000017": 4.0, "000018": 0.25, "00001e": 0.0, "000005": 8654.0, "000009": "0", "000023": 0.01, "00001f": 123.0}', '0.69802']]
show_doc(self.test_scenario3, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
anomaly_create.i_create_an_anomaly(self)
anomaly_create.the_anomaly_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_anomaly(self)
prediction_create.i_create_an_anomaly_score(self, example[4])
prediction_create.the_anomaly_score_is(self, example[5])
prediction_compare.i_create_a_local_anomaly_score(self, example[4])
prediction_compare.the_local_anomaly_score_is(self, example[5])
def test_scenario3(self):
"""
Scenario: Successfully creating a Fields object and a modified fields structure from a file:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a Fields object from the dataset with objective column "<objective_column>"
And I import a summary fields file "<summary_file>" as a fields structure
Then I check the new field structure has field "<field_id>" as "<optype>"
Examples:
| data | time_1 | objective_column | summary_file| field_id | optype | time_2
| ../data/iris.csv | 10 | 0 | fields_summary_modified.csv | 000000 | categorical | 10
"""
print self.test_scenario3.__doc__
examples = [
['data/iris.csv', '10', '0', 'data/fields/fields_summary_modified.csv', '000000', 'categorical', '10']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[6])
fields_steps.create_fields_from_dataset(self, example[2])
fields_steps.import_summary_file(self, example[3])
fields_steps.check_field_type(self, example[4], example[5])
def test_scenario1(self):
"""
Scenario 1: Successfully creating a local model from an exported file:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
And I export the "<pmml>" model to "<exported_file>"
When I create a local model from the file "<exported_file>"
Then the model ID and the local model ID match
Examples:
| data | time_1 | time_2 | time_3 | pmml | exported_file
| ../data/iris.csv | 10 | 10 | 10 | False | ./tmp/model.json
"""
print self.test_scenario1.__doc__
examples = [[
'data/iris.csv', '10', '10', '10', False, './tmp/model.json'
]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.i_export_model(self, example[4], example[5])
model_create.i_create_local_model_from_file(self, example[5])
model_create.check_model_id_local_id(self)
def test_scenario2(self):
"""
Scenario: Successfully comparing centroids with configuration options:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a cluster with options "<options>"
And I wait until the cluster is ready less than <time_3> secs
And I create a local cluster
When I create a centroid for "<data_input>"
Then the centroid is "<centroid>" with distance "<distance>"
And I create a local centroid for "<data_input>"
Then the local centroid is "<centroid>" with distance "<distance>"
Examples:
| data | time_1 | time_2 | time_3 | options | data_input | centroid | distance | full_data_input
"""
examples = [
['data/iris.csv', '30', '30', '30', '{"summary_fields": ["sepal width"]}', '{"petal length": 1, "petal width": 1, "sepal length": 1, "species": "Iris-setosa"}', 'Cluster 2', '1.16436', '{"petal length": 1, "petal width": 1, "sepal length": 1, "species": "Iris-setosa"}'],
['data/iris.csv', '20', '20', '30', '{"default_numeric_value": "zero"}', '{"petal length": 1}', 'Cluster 4', '1.41215', '{"petal length": 1, "petal width": 0, "sepal length": 0, "sepal width": 0, "species": ""}']]
show_doc(self.test_scenario2, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
cluster_create.i_create_a_cluster_with_options(self, example[4])
cluster_create.the_cluster_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_cluster(self)
prediction_create.i_create_a_centroid(self, example[8])
prediction_create.the_centroid_is_with_distance(self, example[6], example[7])
prediction_compare.i_create_a_local_centroid(self, example[5])
prediction_compare.the_local_centroid_is(self, example[6], example[7])
def test_scenario2(self):
"""
Scenario 2: Successfully creating a local ensemble from an exported file:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an ensemble
And I wait until the ensemble is ready less than <time_3> secs
And I export the ensemble to "<exported_file>"
When I create a local ensemble from the file "<exported_file>"
Then the ensemble ID and the local ensemble ID match
Examples:
| data | time_1 | time_2 | time_3 | exported_file
| ../data/iris.csv | 10 | 10 | 50 | ./tmp/ensemble.json
"""
print self.test_scenario2.__doc__
examples = [['data/iris.csv', '10', '10', '50', './tmp/ensemble.json']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
ensemble_create.i_create_an_ensemble(self)
ensemble_create.the_ensemble_is_finished_in_less_than(
self, example[3])
ensemble_create.i_export_ensemble(self, example[4])
ensemble_create.i_create_local_ensemble_from_file(self, example[4])
ensemble_create.check_ensemble_id_local_id(self)
def test_scenario1(self):
"""
Scenario: Successfully creating an evaluation:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create an evaluation for the model with the dataset
And I wait until the evaluation is ready less than <time_4> secs
Then the measured "<measure>" is <value>
Examples:
| data | time_1 | time_2 | time_3 | time_4 | measure | value |
| ../data/iris.csv | 30 | 30 | 30 | 30 | average_phi | 1 |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '50', '50', '50', '50', 'average_phi', '1']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
evaluation_create.i_create_an_evaluation(self)
evaluation_create.the_evaluation_is_finished_in_less_than(self, example[4])
evaluation_create.the_measured_measure_is_value(self, example[5], example[6])
def test_scenario10(self):
"""
Scenario: Successfully comparing predictions for linear regression:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a linear regression with objective "<objective>" and "<params>"
And I wait until the linear regression is ready less than <time_3> secs
And I create a local linear regression
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
And I create a local prediction for "<data_input>"
Then the local prediction is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | objective | prediction | params
"""
examples = [
[
'data/grades.csv', '10', '50', '60',
'{"000000": 1, "000001": 1, "000002": 1}', '000005', 29.63024,
'{"input_fields": ["000000", "000001", "000002"]}'
],
[
'data/iris.csv', '10', '50', '60',
'{"000000": 1, "000001": 1, "000004": "Iris-virginica"}',
'000003', 1.21187,
'{"input_fields": ["000000", "000001", "000004"]}'
],
[
'data/movies.csv', '10', '50', '60', '{"000007": "Action"}',
'000009', 4.33333, '{"input_fields": ["000007"]}'
],
[
'data/movies.csv', '10', '50', '60', '{"000006": "1999"}',
'000009', 3.28427,
'{"input_fields": ["000006"], "bias": false}'
]
]
show_doc(self.test_scenario10, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
linear_create.i_create_a_linear_regression_with_objective_and_params( \
self, example[5], example[7])
linear_create.the_linear_regression_is_finished_in_less_than( \
self, example[3])
prediction_compare.i_create_a_local_linear(self)
prediction_create.i_create_a_linear_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
prediction_compare.i_create_a_local_linear_prediction(
self, example[4])
prediction_compare.the_local_prediction_is(self, example[6])
def test_scenario2(self):
"""
Scenario 2: Successfully creating Topic Model from a dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create topic model from a dataset
And I wait until the topic model is ready less than <time_3> secs
And I update the topic model name to "<topic_model_name>"
When I wait until the topic_model is ready less than <time_4> secs
Then the topic model name is "<topic_model_name>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | topic_model_name | params
| ../data/spam.csv | 100 | 100 | 200 | 500 | my new topic model name | '{"fields": {"000001": {"optype": "text", "term_analysis": {"case_sensitive": true, "stem_words": true, "use_stopwords": false, "language": "en"}}}}'
"""
print self.test_scenario2.__doc__
examples = [
['data/spam.csv', '100', '100', '10000', '500', 'my new topic model name', '{"fields": {"000001": {"optype": "text", "term_analysis": {"case_sensitive": true, "stem_words": true, "use_stopwords": false, "language": "en"}}}}']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_create.i_update_source_with(self, example[6])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
topic_create.i_create_a_topic_model(self)
topic_create.the_topic_model_is_finished_in_less_than(self, example[3])
topic_create.i_update_topic_model_name(self, example[5])
topic_create.the_topic_model_is_finished_in_less_than(self, example[4])
topic_create.i_check_topic_model_name(self, example[5])
def test_scenario1(self):
"""
Scenario: Successfully creating and reading a public dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I make the dataset public
And I wait until the dataset is ready less than <time_3> secs
When I get the dataset status using the dataset's public url
Then the dataset's status is FINISHED
Examples:
| data | time_1 | time_2 | time_3 |
| ../data/iris.csv | 10 | 10 | 10 |
"""
print self.test_scenario1.__doc__
examples = [['data/iris.csv', '10', '10', '10']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file_from_stdin(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
dataset_create.make_the_dataset_public(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[3])
dataset_create.build_local_dataset_from_public_url(self)
dataset_create.dataset_status_finished(self)
def test_scenario1(self):
"""
Scenario: Successfully creating a batch prediction:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create a batch prediction for the dataset with the model
And I wait until the batch prediction is ready less than <time_4> secs
And I download the created predictions file to "<local_file>"
Then the batch prediction file is like "<predictions_file>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | local_file | predictions_file |
| ../data/iris.csv | 30 | 30 | 50 | 50 | ./tmp/batch_predictions.csv |./data/batch_predictions.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '30', '30', '50', '50', 'tmp/batch_predictions.csv', 'data/batch_predictions.csv']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
batch_pred_create.i_create_a_batch_prediction(self)
batch_pred_create.the_batch_prediction_is_finished_in_less_than(self, example[4])
batch_pred_create.i_download_predictions_file(self, example[5])
batch_pred_create.i_check_predictions(self, example[6])
def test_scenario5(self):
"""
Scenario: Successfully comparing projections for PCAs:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a PCA with "<params>"
And I wait until the PCA is ready less than <time_3> secs
And I create a local PCA
When I create a projection for "<input_data>"
Then the projection is "<projection>"
And I create a local projection for "<data_input>"
Then the local projection is "<projection>"
Examples:
| data | time_1 | time_2 | time_3 | input_data | projection | params
"""
examples = [
[
'data/iris.csv', '30', '30', '120', '{}',
'{"PC2": 0, "PC3": 0, "PC1": 0, "PC6": 0, "PC4": 5e-05, "PC5": 0}',
'{}'
],
[
'data/iris.csv', '30', '30', '120', '{"petal length": 1}',
'{"PC2": 0.08708, "PC3": 0.20929, "PC1": 1.56084, "PC6": -1.34463, "PC4": 0.7295, "PC5": -1.00876}',
'{}'
],
[
'data/iris.csv', '30', '30', '120',
'{"species": "Iris-versicolor"}',
'{"PC2": 1.8602, "PC3": -2.00864, "PC1": -0.61116, "PC6": -0.66983, "PC4": -2.44618, "PC5": 0.43414}',
'{}'
],
[
'data/iris.csv', '30', '30', '120',
'{"petal length": 1, "sepal length": 0, "petal width": 0, "sepal width": 0, "species": "Iris-versicolor"}',
'{"PC2": 7.18009, "PC3": 6.51511, "PC1": 2.78155, "PC6": 0.21372, "PC4": -1.94865, "PC5": 0.57646}',
'{}'
]
]
show_doc(self.test_scenario5, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
pca_create.i_create_a_pca_with_params(self, example[6])
pca_create.the_pca_is_finished_in_less_than(self, example[3])
compare_predictions.create_local_pca(self)
projection_create.i_create_a_projection(self, example[4])
projection_create.the_projection_is(self, example[5])
compare_predictions.i_create_a_local_projection(self, example[4])
compare_predictions.the_local_projection_is(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully creating local association object:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an association from a dataset
And I wait until the association is ready less than <time_3> secs
And I create a local association
When I get the rules for <"item_list">
Then the first rule is "<JSON_rule>"
Examples:
| data | time_1 | time_2 | time_3 | item_list | JSON_rule |
| ../data/tiny_mushrooms.csv | 10 | 20 | 50 | ["Edible"] | {'p_value': 2.08358e-17, 'confidence': 1, 'lift': 1.12613, 'lhs': [14], 'leverage': 0.07885, 'lhs_cover': [0.704, 176], 'rhs_cover': [0.888, 222], 'rhs': [1], 'support': [0.704, 176], 'rule_id': u'000038'}
"""
print self.test_scenario2.__doc__
examples = [
['data/tiny_mushrooms.csv', '10', '20', '50', ["Edible"], {'p_value': 5.26971e-31, 'confidence': 1, 'rhs_cover': [0.488, 122], 'leverage': 0.24986, 'rhs': [19], 'rule_id': u'000002', 'lift': 2.04918, 'lhs': [0, 21, 16, 7], 'lhs_cover': [0.488, 122], 'support': [0.488, 122]}]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
association_create.i_create_an_association_from_dataset(self)
association_create.the_association_is_finished_in_less_than(self, example[3])
association_create.i_create_a_local_association(self)
association_create.i_get_rules_for_item_list(self, example[4])
association_create.the_first_rule_is(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully creating a Fields object and a summary fields file:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a Fields object from the dataset with objective column "<objective_column>"
And I export a summary fields file "<summary_file>"
Then I check that the file "<summary_file>" is like "<expected_file>"
Examples:
| data | time_1 | objective_column | summary_file| expected_file | time_2
| ../data/iris.csv | 10 | 0 | fields_summary.csv | data/fields/fields_summary.csv | 10
"""
print self.test_scenario2.__doc__
examples = [[
'data/iris.csv', '10', '0', 'fields_summary.csv',
'data/fields/fields_summary.csv', '10'
]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[5])
fields_steps.create_fields_from_dataset(self, example[2])
fields_steps.generate_summary(self, example[3])
fields_steps.check_summary_like_expected(self, example[3],
example[4])
def test_scenario2(self):
"""
Scenario: Successfully creating a model and exporting it:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
And I export the <"pmml"> model to file "<expected_file>"
Then I check the model is stored in "<expected_file>" file in <"pmml">
Examples:
| data | time_1 | time_2 | time_3 | expected_file | pmml
| data/iris.csv | 10 | 10 | 10 | tmp/model/iris.json | false
| data/iris_sp_chars.csv | 10 | 10 | 10 | tmp/model/iris_sp_chars.pmml | true
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', '30', '30', '30', 'tmp/model/iris.json', False],
['data/iris_sp_chars.csv', '30', '30', '30', 'tmp/model/iris_sp_chars.pmml', True]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.i_export_model(self, example[5], example[4])
model_create.i_check_model_stored(self, example[4], example[5])
def test_scenario3(self):
"""
Scenario: Successfully creating a Fields object and a modified fields structure from a file:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a Fields object from the dataset with objective column "<objective_column>"
And I import a summary fields file "<summary_file>" as a fields structure
Then I check the new field structure has field "<field_id>" as "<optype>"
Examples:
| data | time_1 | objective_column | summary_file| field_id | optype | time_2
| ../data/iris.csv | 10 | 0 | fields_summary_modified.csv | 000000 | categorical | 10
"""
print self.test_scenario3.__doc__
examples = [[
'data/iris.csv', '10', '0',
'data/fields/fields_summary_modified.csv', '000000', 'categorical',
'10'
]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[6])
fields_steps.create_fields_from_dataset(self, example[2])
fields_steps.import_summary_file(self, example[3])
fields_steps.check_field_type(self, example[4], example[5])
def test_scenario2(self):
"""
Scenario: Successfully creating a prediction from a source in a remote location
Given I create a data source using the url "<url>"
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
Examples:
| url | time_1 | time_2 | time_3 | data_input | objective | prediction |
| s3://bigml-public/csv/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | 000004 | Iris-setosa |
"""
print self.test_scenario2.__doc__
examples = [
['s3://bigml-public/csv/iris.csv', '10', '10', '10', '{"petal width": 0.5}', '000004', 'Iris-setosa']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_create_using_url(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
prediction_create.i_create_a_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
def test_scenario5(self):
"""
Scenario: Successfully comparing centroids with summary fields:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a cluster with options "<options>"
And I wait until the cluster is ready less than <time_3> secs
And I create a local cluster
When I create a centroid for "<data_input>"
Then the centroid is "<centroid>" with distance "<distance>"
And I create a local centroid for "<data_input>"
Then the local centroid is "<centroid>" with distance "<distance>"
Examples:
| data | time_1 | time_2 | time_3 | options | data_input | centroid | distance |
| ../data/iris.csv | 20 | 20 | 30 | {"summary_fields": ["sepal width"]} |{"petal length": 1, "petal width": 1, "sepal length": 1, "species": "Iris-setosa"} | Cluster 2 | 1.1643644909783857 |
"""
print self.test_scenario5.__doc__
examples = [
['data/iris.csv', '20', '20', '30', '{"summary_fields": ["sepal width"]}', '{"petal length": 1, "petal width": 1, "sepal length": 1, "species": "Iris-setosa"}', 'Cluster 2', '1.1643644909783857']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
cluster_create.i_create_a_cluster_with_options(self, example[4])
cluster_create.the_cluster_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_cluster(self)
prediction_create.i_create_a_centroid(self, example[5])
prediction_create.the_centroid_is_with_distance(self, example[6], example[7])
prediction_compare.i_create_a_local_centroid(self, example[5])
prediction_compare.the_local_centroid_is(self, example[6], example[7])
def test_scenario2(self):
"""
Scenario: Successfully creating a Fields object and a summary fields file:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a Fields object from the dataset with objective column "<objective_column>"
And I export a summary fields file "<summary_file>"
Then I check that the file "<summary_file>" is like "<expected_file>"
Examples:
| data | time_1 | objective_column | summary_file| expected_file | time_2
| ../data/iris.csv | 10 | 0 | fields_summary.csv | data/fields/fields_summary.csv | 10
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', '10', '0', 'fields_summary.csv', 'data/fields/fields_summary.csv', '10']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[5])
fields_steps.create_fields_from_dataset(self, example[2])
fields_steps.generate_summary(self, example[3])
fields_steps.check_summary_like_expected(self, example[3], example[4])
def test_scenario1(self):
"""
Scenario: Successfully exporting a dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I download the dataset file to "<local_file>"
Then file "<local_file>" is like file "<data>"
Examples:
| data | time_1 | time_2 | local_file |
| ../data/iris.csv | 30 | 30 | ./tmp/exported_iris.csv |
"""
print self.test_scenario1.__doc__
examples = [['data/iris.csv', '30', '30', 'tmp/exported_iris.csv']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
dataset_create.i_export_a_dataset(self, example[3])
dataset_create.files_equal(self, example[3], example[0])
def test_scenario1(self):
"""
Scenario: Successfully creating a split dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a dataset extracting a <rate> sample
And I wait until the dataset is ready less than <time_3> secs
When I compare the datasets' instances
Then the proportion of instances between datasets is <rate>
Examples:
| data | time_1 | time_2 | time_3 | rate |
| ../data/iris.csv | 10 | 10 | 10 | 0.8 |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '0.8']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self,
example[2])
dataset_create.i_create_a_split_dataset(self, example[4])
dataset_create.the_dataset_is_finished_in_less_than(self,
example[3])
dataset_create.i_compare_datasets_instances(self)
dataset_create.proportion_datasets_instances(self, example[4])
def test_scenario2(self):
"""
Scenario: Successfully creating a single dataset multi-dataset:
Given I create a data source with "<params>" uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a multi-dataset with sample rates <rates>
And I wait until the multi-dataset is ready less than <time_3> secs
When I compare the datasets' instances
Then the proportion of instances between datasets is <rate>
Examples:
| data | time_1 | time_2 | time_3 | rate |rates
| ../data/iris.csv | 10 | 10 | 10 | 0.2 |[0.2]
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '0.2', '[0.2]']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file_with_args(self, example[0], '{}')
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self,
example[2])
dataset_create.i_create_a_multidataset(self, example[5])
dataset_create.the_dataset_is_finished_in_less_than(self,
example[3])
dataset_create.i_compare_datasets_instances(self)
dataset_create.proportion_datasets_instances(self, example[4])
def test_scenario3(self):
"""
Scenario: Successfully comparing scores from anomaly detectors:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an anomaly detector
And I wait until the anomaly detector is ready less than <time_3> secs
And I create a local anomaly detector
When I create an anomaly score for "<data_input>"
Then the anomaly score is "<score>"
And I create a local anomaly score for "<data_input>"
Then the local anomaly score is "<score>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | score |
"""
examples = [
['data/tiny_kdd.csv', '30', '30', '30', '{"000020": 255.0, "000004": 183.0, "000016": 4.0, "000024": 0.04, "000025": 0.01, "000026": 0.0, "000019": 0.25, "000017": 4.0, "000018": 0.25, "00001e": 0.0, "000005": 8654.0, "000009": "0", "000023": 0.01, "00001f": 123.0}', '0.69802']]
show_doc(self.test_scenario3, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
anomaly_create.i_create_an_anomaly(self)
anomaly_create.the_anomaly_is_finished_in_less_than(self, example[3])
prediction_compare.i_create_a_local_anomaly(self)
prediction_create.i_create_an_anomaly_score(self, example[4])
prediction_create.the_anomaly_score_is(self, example[5])
prediction_compare.i_create_a_local_anomaly_score(self, example[4])
prediction_compare.the_local_anomaly_score_is(self, example[5])
def test_scenario1(self):
"""
Scenario: Successfully creating a sample from a dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a sample from a dataset
And I wait until the sample is ready less than <time_3> secs
And I update the sample name to "<sample_name>"
When I wait until the sample is ready less than <time_4> secs
Then the sample name is "<sample_name>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | sample_name |
| ../data/iris.csv | 10 | 10 | 10 | 10 | my new sample name |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '10', 'my new sample name']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
sample_create.i_create_a_sample_from_dataset(self)
sample_create.the_sample_is_finished_in_less_than(self, example[3])
sample_create.i_update_sample_name(self, example[5])
sample_create.the_sample_is_finished_in_less_than(self, example[4])
sample_create.i_check_sample_name(self, example[5])
def test_scenario1(self):
"""
Scenario: Successfully creating a prediction using a public model:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
And I make the model public
And I wait until the model is ready less than <time_3> secs
And I check the model status using the model's public url
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | objective | prediction |
| ../data/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | 000004 | Iris-setosa |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '{"petal width": 0.5}', '000004', 'Iris-setosa']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.make_the_model_public(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.model_from_public_url(self)
prediction_create.i_create_a_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
def test_scenario5(self):
"""
Scenario: Successfully creating a centroid and the associated dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a cluster
And I wait until the cluster is ready less than <time_3> secs
When I create a centroid for "<data_input>"
And I check the centroid is ok
Then the centroid is "<centroid>"
And I create a dataset from the cluster and the centroid
And I wait until the dataset is ready less than <time_2> secs
And I check that the dataset is created for the cluster and the centroid
Examples:
| data | time_1 | time_2 | time_3 | data_input | centroid |
| ../data/diabetes.csv | 10 | 20 | 20 | {"pregnancies": 0, "plasma glucose": 118, "blood pressure": 84, "triceps skin thickness": 47, "insulin": 230, "bmi": 45.8, "diabetes pedigree": 0.551, "age": 31, "diabetes": "true"} | Cluster 3 |
"""
print self.test_scenario5.__doc__
examples = [
['data/diabetes.csv', '10', '20', '20', '{"pregnancies": 0, "plasma glucose": 118, "blood pressure": 84, "triceps skin thickness": 47, "insulin": 230, "bmi": 45.8, "diabetes pedigree": 0.551, "age": 31, "diabetes": "true"}', 'Cluster 3']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
cluster_create.i_create_a_cluster(self)
cluster_create.the_cluster_is_finished_in_less_than(self, example[3])
prediction_create.i_create_a_centroid(self, example[4])
prediction_create.the_centroid_is(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully creating an evaluation for an ensemble:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an ensemble of <number_of_models> models and <tlp> tlp
And I wait until the ensemble is ready less than <time_3> secs
When I create an evaluation for the ensemble with the dataset
And I wait until the evaluation is ready less than <time_4> secs
Then the measured "<measure>" is <value>
Examples:
| data | time_1 | time_2 | number_of_models | tlp | time_3 | time_4 | measure | value |
| ../data/iris.csv | 30 | 30 | 5 | 1 | 50 | 30 | average_phi | 0.98029 |
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', '50', '50', '5', '1', '80', '80', 'average_phi', '0.98029']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
ensemble_create.i_create_an_ensemble(self, example[3], example[4])
ensemble_create.the_ensemble_is_finished_in_less_than(self, example[5])
evaluation_create.i_create_an_evaluation_ensemble(self)
evaluation_create.the_evaluation_is_finished_in_less_than(self, example[6])
evaluation_create.the_measured_measure_is_value(self, example[7], example[8])
def test_scenario6(self):
"""
Scenario: Successfully creating an anomaly score:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an anomaly detector from a dataset
And I wait until the anomaly detector is ready less than <time_3> secs
When I create an anomaly score for "<data_input>"
Then the anomaly score is "<score>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | score |
| ../data/tiny_kdd.csv | 10 | 10 | 100 | {"src_bytes": 350} | 0.92618 |
| ../data/iris_sp_chars.csv | 10 | 10 | 100 | {"pétal&width\u0000": 300} | 0.90198 |
"""
print self.test_scenario6.__doc__
examples = [
['data/tiny_kdd.csv', '10', '10', '100', '{"src_bytes": 350}', '0.92846'],
['data/iris_sp_chars.csv', '10', '10', '100', '{"pétal&width\u0000": 300}', '0.89313']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
anomaly_create.i_create_an_anomaly(self)
anomaly_create.the_anomaly_is_finished_in_less_than(self, example[3])
prediction_create.i_create_an_anomaly_score(self, example[4])
prediction_create.the_anomaly_score_is(self, example[5])
def test_scenario1(self):
"""
Scenario: Successfully creating and reading a public dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I make the dataset public
And I wait until the dataset is ready less than <time_3> secs
When I get the dataset status using the dataset's public url
Then the dataset's status is FINISHED
Examples:
| data | time_1 | time_2 | time_3 |
| ../data/iris.csv | 10 | 10 | 10 |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
dataset_create.make_the_dataset_public(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[3])
dataset_create.build_local_dataset_from_public_url(self)
dataset_create.dataset_status_finished(self)
def test_scenario7(self):
"""
Scenario: Successfully creating a Topic Model:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I update the source with params "<params>"
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
When I create a Topic Model from a dataset
Then I wait until the Topic Model is ready less than <time_3> secs
Examples:
| data | time_1 | time_2 | time_3 | params
| ../data/movies.csv | 10 | 10 | 100 | {"fields": {"genre": {"optype": "items", "item_analysis": {"separator": "$"}}, "title": {"optype": "text"}}}
"""
print self.test_scenario7.__doc__
examples = [
['data/movies.csv', '10', '10', '100', '{"fields": {"000007": {"optype": "items", "item_analysis": {"separator": "$"}}, "000006": {"optype": "text"}}}']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_create.i_update_source_with(self, data=example[4])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
topic_create.i_create_a_topic_model(self)
topic_create.the_topic_model_is_finished_in_less_than(self, example[3])
def test_scenario1(self):
"""
Scenario: Successfully creating a prediction with a user's project connection:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And the source is in the project
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | objective | prediction |
| ../data/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | 000004 | Iris-setosa |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '{"petal width": 0.5}', '000004', 'Iris-setosa']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file_with_project_conn(self, example[0])
source_create.the_source_is_finished(self, example[1])
assert world.source['project'] == world.project_id
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
assert world.dataset['project'] == world.project_id
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
assert world.model['project'] == world.project_id
prediction_create.i_create_a_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
assert world.prediction['project'] == world.project_id
def test_scenario1(self):
"""
Scenario: Successfully creating a local prediction from an Ensemble:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an ensemble of <number_of_models> models and <tlp> tlp
And I wait until the ensemble is ready less than <time_3> secs
And I create a local Ensemble
When I create a local ensemble prediction with confidence for "<data_input>"
Then the local prediction is "<prediction>"
And the local prediction's confidence is "<confidence>"
Examples:
| data | time_1 | time_2 | time_3 | number_of_models | tlp | data_input |prediction | confidence
| ../data/iris.csv | 10 | 10 | 50 | 5 | 1 | {"petal width": 0.5} | Iris-versicolor | 0.3687
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '50', '5', '1', '{"petal width": 0.5}', 'Iris-versicolor', '0.3687']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
ensemble_create.i_create_an_ensemble(self, example[4], example[5])
ensemble_create.the_ensemble_is_finished_in_less_than(self, example[3])
ensemble_create.create_local_ensemble(self)
prediction_create.create_local_ensemble_prediction_with_confidence(self, example[6])
compare_pred.the_local_prediction_is(self, example[7])
compare_pred.the_local_prediction_confidence_is(self, example[8])
def test_scenario5(self):
"""
Scenario: Successfully creating a batch anomaly score from an anomaly detector:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an anomaly detector
And I wait until the anomaly detector is ready less than <time_3> secs
When I create a batch anomaly score
And I check the batch anomaly score is ok
And I wait until the batch anomaly score is ready less than <time_4> secs
And I download the created anomaly score file to "<local_file>"
Then the batch anomaly score file is like "<predictions_file>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | local_file | predictions_file |
| ../data/tiny_kdd.csv | 30 | 30 | 50 | 50 | ./tmp/batch_predictions.csv |./data/batch_predictions_a.csv |
"""
print self.test_scenario5.__doc__
examples = [
['data/tiny_kdd.csv', '30', '30', '50', '50', 'tmp/batch_predictions.csv', 'data/batch_predictions_a.csv']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
anomaly_create.i_create_an_anomaly(self)
anomaly_create.the_anomaly_is_finished_in_less_than(self, example[3])
batch_pred_create.i_create_a_batch_prediction_with_anomaly(self)
batch_pred_create.the_batch_anomaly_score_is_finished_in_less_than(self, example[4])
batch_pred_create.i_download_anomaly_score_file(self, example[5])
batch_pred_create.i_check_predictions(self, example[6])
def test_scenario1(self):
"""
Scenario 1: Successfully creating an optiml from a dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an optiml from a dataset
And I wait until the optiml is ready less than <time_3> secs
And I update the optiml name to "<optiml_name>"
When I wait until the optiml is ready less than <time_4> secs
Then the optiml name is "<optiml_name>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | optiml_name |
| ../data/iris.csv | 10 | 10 | 2000 | 20 | my new optiml name |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10000', '20', 'my new optiml name']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_an_optiml_with_objective_and_params( \
self, parms='{"max_training_time": %s, "model_types": '
'["model", "logisticregression"]}' % \
(int(float(example[3])/1000) - 1))
model_create.the_optiml_is_finished_in_less_than(self, example[3])
model_create.i_update_optiml_name(self, example[5])
model_create.the_optiml_is_finished_in_less_than(self, example[4])
model_create.i_check_optiml_name(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully creating a batch prediction for an ensemble:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an ensemble of <number_of_models> models and <tlp> tlp
And I wait until the ensemble is ready less than <time_3> secs
When I create a batch prediction for the dataset with the ensemble
And I wait until the batch prediction is ready less than <time_4> secs
And I download the created predictions file to "<local_file>"
Then the batch prediction file is like "<predictions_file>"
Examples:
| data | time_1 | time_2 | number_of_models | tlp | time_3 | time_4 | local_file | predictions_file |
| ../data/iris.csv | 30 | 30 | 5 | 1 | 80 | 50 | ./tmp/batch_predictions.csv | ./data/batch_predictions_e.csv |
"""
print self.test_scenario2.__doc__
examples = [
['data/iris.csv', '30', '30', '5', '1', '80', '50', 'tmp/batch_predictions.csv', 'data/batch_predictions_e.csv']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
ensemble_create.i_create_an_ensemble(self, example[3], example[4])
ensemble_create.the_ensemble_is_finished_in_less_than(self, example[5])
batch_pred_create.i_create_a_batch_prediction_ensemble(self)
batch_pred_create.the_batch_prediction_is_finished_in_less_than(self, example[6])
batch_pred_create.i_download_predictions_file(self, example[7])
batch_pred_create.i_check_predictions(self, example[8])
def test_scenario2(self):
"""
Scenario: Successfully obtaining parsing error counts:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I update the source with params "<params>"
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
When I ask for the error counts in the fields
Then the error counts dict is "<error_values>"
Examples:
| data | time_1 | params | time_2 |error_values |
| ../data/iris_missing.csv | 30 | {"fields": {"000000": {"optype": "numeric"}}} |30 |{"000000": 1} |
"""
print self.test_scenario2.__doc__
examples = [
['data/iris_missing.csv', '30', '{"fields": {"000000": {"optype": "numeric"}}}', '30', '{"000000": 1}']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_create.i_update_source_with(self, example[2])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self,
example[3])
dataset_read.i_get_the_errors_values(self)
dataset_read.i_get_the_properties_values(
self, 'error counts', example[4])
def test_scenario1(self):
"""
Scenario: Successfully creating a local prediction from an Ensemble:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an ensemble of <number_of_models> models and <tlp> tlp
And I wait until the ensemble is ready less than <time_3> secs
And I create a local Ensemble
When I create a local ensemble prediction with confidence for "<data_input>"
Then the local prediction is "<prediction>"
And the local prediction's confidence is "<confidence>"
And the local probabilities are "<probabilities>"
Examples:
| data | time_1 | time_2 | time_3 | number_of_models | tlp | data_input |prediction | confidence
| ../data/iris.csv | 10 | 10 | 50 | 5 | 1 | {"petal width": 0.5} | Iris-versicolor | 0.3687 | [0.3403, 0.4150, 0.2447]
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '50', '5', '1', '{"petal width": 0.5}', 'Iris-versicolor', '0.415', '["0.3403", "0.4150", "0.2447"]' ]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
ensemble_create.i_create_an_ensemble(self, example[4], example[5])
ensemble_create.the_ensemble_is_finished_in_less_than(self, example[3])
ensemble_create.create_local_ensemble(self)
prediction_create.create_local_ensemble_prediction_with_confidence(self, example[6])
compare_pred.the_local_prediction_is(self, example[7])
compare_pred.the_local_prediction_confidence_is(self, example[8])
compare_pred.the_local_probabilities_are(self, example[9])
def test_scenario5(self):
"""
Scenario: Successfully creating a local prediction from an Ensemble:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an ensemble of <number_of_models> models and <tlp> tlp
And I wait until the ensemble is ready less than <time_3> secs
And I create a local Ensemble
When I create a local ensemble prediction using median with confidence for "<data_input>"
Then the local prediction is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | number_of_models | tlp | data_input |prediction |
| ../data/grades.csv | 10 | 10 | 50 | 2 | 1 | {} | 67.5 |
"""
print self.test_scenario5.__doc__
examples = [[
'data/grades.csv', '30', '30', '50', '2', '1', '{}', 69.0934
]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
ensemble_create.i_create_an_ensemble(self, example[4], example[5])
ensemble_create.the_ensemble_is_finished_in_less_than(
self, example[3])
ensemble_create.create_local_ensemble(self)
prediction_create.create_local_ensemble_prediction_using_median_with_confidence(
self, example[6])
compare_pred.the_local_prediction_is(self, example[7])
def test_scenario1(self):
"""
Scenario: Successfully creating a model from a dataset list:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I store the dataset id in a list
And I create a dataset
And I wait until the dataset is ready less than <time_3> secs
And I store the dataset id in a list
Then I create a model from a dataset list
And I wait until the model is ready less than <time_4> secs
And I check the model stems from the original dataset list
Examples:
| data | time_1 | time_2 | time_3 | time_4 |
| ../data/iris.csv | 10 | 10 | 10 | 10
"""
print self.test_scenario1.__doc__
examples = [["data/iris.csv", "10", "10", "10", "10"]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
multimodel_create.i_store_dataset_id(self)
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[3])
multimodel_create.i_store_dataset_id(self)
model_create.i_create_a_model_from_dataset_list(self)
model_create.the_model_is_finished_in_less_than(self, example[4])
multimodel_create.i_check_model_datasets_and_datasets_ids(self)
def test_scenario10(self):
"""
Scenario: Successfully comparing predictions for fusions:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model with "<params>"
And I wait until the model is ready less than <time_3> secs
And I create a model with "<params>"
And I wait until the model is ready less than <time_3> secs
And I create a model with "<params>"
And I wait until the model is ready less than <time_3> secs
And I retrieve a list of remote models tagged with "<tag>"
And I create a fusion from a list of models
And I wait until the fusion is ready less than <time_4> secs
And I create a local fusion
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
And I create a local prediction for "<data_input>"
Then the local prediction is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | params| tag | data_input | objective | prediction | params
"""
examples = [[
'data/iris_unbalanced.csv', '10', '10', '120', '120',
'{"tags":["my_fusion_tag"]}', 'my_fusion_tag',
'{"petal width": 4}', '000004', 'Iris-virginica'
],
[
'data/grades.csv', '10', '10', '120', '120',
'{"tags":["my_fusion_tag_reg"]}', 'my_fusion_tag_reg',
'{"Midterm": 20}', '000005', 43.65286
]]
show_doc(self.test_scenario10, examples)
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
model_create.i_create_a_model_with(self, example[5])
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.i_create_a_model_with(self, example[5])
model_create.the_model_is_finished_in_less_than(self, example[3])
model_create.i_create_a_model_with(self, example[5])
model_create.the_model_is_finished_in_less_than(self, example[3])
prediction_compare.i_retrieve_a_list_of_remote_models(
self, example[6])
model_create.i_create_a_fusion(self)
model_create.the_fusion_is_finished_in_less_than(self, example[4])
prediction_compare.i_create_a_local_fusion(self)
prediction_create.i_create_a_fusion_prediction(self, example[7])
prediction_create.the_prediction_is(self, example[8], example[9])
prediction_compare.i_create_a_local_prediction(self, example[7])
prediction_compare.the_local_prediction_is(self, example[9])
def test_scenario1(self):
"""
Scenario: Successfully exporting a dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I download the dataset file to "<local_file>"
Then file "<local_file>" is like file "<data>"
Examples:
| data | time_1 | time_2 | local_file |
| ../data/iris.csv | 30 | 30 | ./tmp/exported_iris.csv |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '30', '30', 'tmp/exported_iris.csv']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
dataset_create.i_export_a_dataset(self, example[3])
dataset_create.files_equal(self, example[3], example[0])
def test_scenario2(self):
"""
Scenario: Successfully creating a prediction from a source in a remote location
Given I create a data source using the url "<url>"
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
Examples:
| url | time_1 | time_2 | time_3 | data_input | objective | prediction |
| s3://bigml-public/csv/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | 000004 | Iris-setosa |
"""
print self.test_scenario2.__doc__
examples = [[
's3://bigml-public/csv/iris.csv', '10', '10', '10',
'{"petal width": 0.5}', '000004', 'Iris-setosa'
]]
for example in examples:
print "\nTesting with:\n", example
source_create.i_create_using_url(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
prediction_create.i_create_a_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
def test_scenario1(self):
"""
Scenario: Successfully creating an statistical test from a dataset:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an statistical test from a dataset
And I wait until the statistical test is ready less than <time_3> secs
And I update the statistical test name to "<test_name>"
When I wait until the statistical test is ready less than <time_4> secs
Then the statistical test name is "<correlation_name>"
Examples:
| data | time_1 | time_2 | time_3 | time_4 | test_name |
| ../data/iris.csv | 10 | 10 | 10 | 10 | my new statistical test name |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '10', 'my new statistical test name']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
statistical_tst_create.i_create_a_tst_from_dataset(self)
statistical_tst_create.the_tst_is_finished_in_less_than(self, example[3])
statistical_tst_create.i_update_tst_name(self, example[5])
statistical_tst_create.the_tst_is_finished_in_less_than(self, example[4])
statistical_tst_create.i_check_tst_name(self, example[5])
def test_scenario1(self):
"""
Scenario: Successfully creating a prediction in DEV mode:
Given I want to use api in DEV mode
When I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And the source has DEV True
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | objective | prediction |
| ../data/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | 000004 | Iris-setosa |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '{"petal width": 0.5}', '000004', 'Iris-setosa']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_read.source_has_dev(self, True)
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
prediction_create.i_create_a_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
def test_scenario6(self):
"""
Scenario: Successfully creating an anomaly score:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create an anomaly detector from a dataset
And I wait until the anomaly detector is ready less than <time_3> secs
When I create an anomaly score for "<data_input>"
Then the anomaly score is "<score>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | score |
| ../data/tiny_kdd.csv | 10 | 10 | 100 | {"src_bytes": 350} | 0.92618 |
| ../data/iris_sp_chars.csv | 10 | 10 | 100 | {"pétal&width\u0000": 300} | 0.90198 |
"""
print self.test_scenario6.__doc__
examples = [
['data/tiny_kdd.csv', '10', '10', '100', '{"src_bytes": 350}', '0.92846'],
['data/iris_sp_chars.csv', '10', '10', '100', '{"pétal&width\u0000": 300}', '0.89313']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
anomaly_create.i_create_an_anomaly(self)
anomaly_create.the_anomaly_is_finished_in_less_than(self, example[3])
prediction_create.i_create_an_anomaly_score(self, example[4])
prediction_create.the_anomaly_score_is(self, example[5])
def test_scenario2(self):
"""
Scenario: Successfully obtaining parsing error counts:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I update the source with params "<params>"
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
When I ask for the error counts in the fields
Then the error counts dict is "<error_values>"
Examples:
| data | time_1 | params | time_2 |error_values |
| ../data/iris_missing.csv | 30 | {"fields": {"000000": {"optype": "numeric"}}} |30 |{"000000": 1} |
"""
print self.test_scenario2.__doc__
examples = [
['data/iris_missing.csv', '30', '{"fields": {"000000": {"optype": "numeric"}}}', '30', '{"000000": 1}']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_create.i_update_source_with(self, example[2])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self,
example[3])
dataset_read.i_get_the_errors_values(self)
dataset_read.i_get_the_properties_values(
self, 'error counts', example[4])
def test_scenario1(self):
"""
Scenario: Successfully creating a prediction in DEV mode:
Given I want to use api in DEV mode
When I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And the source has DEV True
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a model
And I wait until the model is ready less than <time_3> secs
When I create a prediction for "<data_input>"
Then the prediction for "<objective>" is "<prediction>"
Examples:
| data | time_1 | time_2 | time_3 | data_input | objective | prediction |
| ../data/iris.csv | 10 | 10 | 10 | {"petal width": 0.5} | 000004 | Iris-setosa |
"""
print self.test_scenario1.__doc__
examples = [
['data/iris.csv', '10', '10', '10', '{"petal width": 0.5}', '000004', 'Iris-setosa']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
source_read.source_has_dev(self, True)
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(self, example[2])
model_create.i_create_a_model(self)
model_create.the_model_is_finished_in_less_than(self, example[3])
prediction_create.i_create_a_prediction(self, example[4])
prediction_create.the_prediction_is(self, example[5], example[6])
def test_scenario1(self):
"""
Scenario: Successfully creating datasets for first centroid of a cluster:
Given I create a data source uploading a "<data>" file
And I wait until the source is ready less than <time_1> secs
And I create a dataset
And I wait until the dataset is ready less than <time_2> secs
And I create a cluster
And I wait until the cluster is ready less than <time_3> secs
When I create a dataset associated to centroid "<centroid_id>"
And I wait until the dataset is ready less than <time_4> secs
Then the dataset is associated to the centroid "<centroid_id>" of the cluster
Examples:
| data | time_1 | time_2 | time_3 | centroid_id | time_4 |
| ../data/iris.csv | 10 | 10 | 40 | 000001 | 10 |
"""
print self.test_scenario1.__doc__
examples = [['data/iris.csv', '10', '10', '40', '000001', '10']]
for example in examples:
print "\nTesting with:\n", example
source_create.i_upload_a_file(self, example[0])
source_create.the_source_is_finished(self, example[1])
dataset_create.i_create_a_dataset(self)
dataset_create.the_dataset_is_finished_in_less_than(
self, example[2])
cluster_create.i_create_a_cluster(self)
cluster_create.the_cluster_is_finished_in_less_than(
self, example[3])
dataset_create.i_create_a_dataset_from_cluster(self, example[4])
dataset_create.the_dataset_is_finished_in_less_than(
self, example[5])
dataset_create.is_associated_to_centroid_id(self, example[4])
