Exemple #1
0
    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_scenario10(self):
        """
            Scenario: Successfully comparing predictions with proportional missing strategy and balanced models:
                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 balanced model
                And I wait until the model is ready less than <time_3> secs
                And I create a local model
                When I create a proportional missing strategy prediction for "<data_input>"
                Then the prediction for "<objective>" is "<prediction>"
                And the confidence for the prediction is "<confidence>"
                And I create a proportional missing strategy local prediction for "<data_input>"
                Then the local prediction is "<prediction>"
                And the local prediction's confidence is "<confidence>"
                And I create local probabilities for "<data_input>"
                Then the local probabilities are "<probabilities>"

                Examples:
                | data               | time_1  | time_2 | time_3 | data_input           | objective | prediction     | confidence |

        """
        examples = [
            [
                'data/iris_unbalanced.csv', '10', '10', '10', '{}', '000004',
                'Iris-setosa', '0.25284', '[0.33333, 0.33333, 0.33333]'
            ],
            [
                'data/iris_unbalanced.csv', '10', '10', '10',
                '{"petal length":1, "sepal length":1, "petal width": 1, "sepal width": 1}',
                '000004', 'Iris-setosa', '0.7575', '[1.0, 0.0, 0.0]'
            ]
        ]
        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_balanced_model(self)
            model_create.the_model_is_finished_in_less_than(self, example[3])
            prediction_compare.i_create_a_local_model(self)
            prediction_create.i_create_a_proportional_prediction(
                self, example[4])
            prediction_create.the_prediction_is(self, example[5], example[6])
            prediction_compare.i_create_a_proportional_local_prediction(
                self, example[4])
            prediction_compare.the_local_prediction_is(self, example[6])
            prediction_create.the_confidence_is(self, example[7])
            prediction_compare.the_local_prediction_confidence_is(
                self, example[7])
            prediction_compare.i_create_local_probabilities(self, example[4])
            prediction_compare.the_local_probabilities_are(self, example[8])
    def test_scenario10(self):
        """
            Scenario: Successfully comparing predictions with proportional missing strategy and balanced models:
                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 balanced model
                And I wait until the model is ready less than <time_3> secs
                And I create a local model
                When I create a proportional missing strategy prediction for "<data_input>"
                Then the prediction for "<objective>" is "<prediction>"
                And the confidence for the prediction is "<confidence>"
                And I create a proportional missing strategy local prediction for "<data_input>"
                Then the local prediction is "<prediction>"
                And the local prediction's confidence is "<confidence>"
                And I create local probabilities for "<data_input>"
                Then the local probabilities are "<probabilities>"

                Examples:
                | data               | time_1  | time_2 | time_3 | data_input           | objective | prediction     | confidence |

        """
        examples = [
            ['data/iris_unbalanced.csv', '10', '10', '10', '{}', '000004', 'Iris-setosa', '0.25284', '[0.33333, 0.33333, 0.33333]'],
            ['data/iris_unbalanced.csv', '10', '10', '10', '{"petal length":1, "sepal length":1, "petal width": 1, "sepal width": 1}', '000004', 'Iris-setosa', '0.7575', '[1.0, 0.0, 0.0]']]
        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_balanced_model(self)
            model_create.the_model_is_finished_in_less_than(self, example[3])
            prediction_compare.i_create_a_local_model(self)
            prediction_create.i_create_a_proportional_prediction(self, example[4])
            prediction_create.the_prediction_is(self, example[5], example[6])
            prediction_compare.i_create_a_proportional_local_prediction(self, example[4])
            prediction_compare.the_local_prediction_is(self, example[6])
            prediction_create.the_confidence_is(self, example[7])
            prediction_compare.the_local_prediction_confidence_is(self, example[7])
            prediction_compare.i_create_local_probabilities(self, example[4])
            prediction_compare.the_local_probabilities_are(self, example[8])