def setUp(self):
current_working_dir = os.getcwd() # Should be this package.
input_folder = current_working_dir + "/SampleClassifierDataFolder"
argument_processing_service = ArgumentProcessingService(input_folder)
arguments = argument_processing_service.handleInputFolder()
data_formatting_service = DataFormattingService(arguments)
self.arguments = data_formatting_service.formatData()
def handleInputFolderProcessing(input_folder):
argument_processing_service = ArgumentProcessingService(input_folder)
processed_arguments = argument_processing_service.handleInputFolder()
if not processed_arguments:
log.error("Exiting program, invalid data sent in target folder.")
return None
return processed_arguments
def formatRandomizedDataForIndividualCombo(self, is_classifier, algorithm,
hyperparams, input_folder):
random_data_generator = RandomizedDataGenerator(
RandomizedDataGenerator.GENERATED_DATA_FOLDER)
random_data_generator.generateRandomizedFiles(
3, 1000, 150, is_classifier, self.INDIVIDUAL_MONTE_CARLO_PERMS, .8,
algorithm, hyperparams)
argument_processing_service = ArgumentProcessingService(input_folder)
return argument_processing_service.handleInputFolder()
def testInputTextFileCorrectlyParsed(self):
input_folder = self.current_working_dir + "/SampleClassifierDataFolder"
argument_processing_service = ArgumentProcessingService(input_folder)
arguments = argument_processing_service.handleInputFolder()
assert arguments is not None
assert len(arguments) == 3
assert (len(arguments.get(argument_processing_service.RESULTS)) + 1) == \
len(arguments.get(argument_processing_service.FEATURES).keys())
assert arguments.get(argument_processing_service.IS_CLASSIFIER)
def runMLAnalysis(self, is_classifier):
random_data_generator = RandomizedDataGenerator(
RandomizedDataGenerator.GENERATED_DATA_FOLDER)
random_data_generator.generateRandomizedFiles(3, 1000, 150,
is_classifier, 10, .8)
input_folder = self.current_working_dir + "/" + RandomizedDataGenerator.GENERATED_DATA_FOLDER
argument_processing_service = ArgumentProcessingService(input_folder)
ml_service = MachineLearningService(
argument_processing_service.handleInputFolder())
return ml_service.analyze(input_folder)
def testTrimmingExistingFeatures(self):
input_folder = self.current_working_dir + "/SampleClassifierDataFolder"
argument_processing_service = ArgumentProcessingService(input_folder)
inputs = argument_processing_service.handleInputFolder()
ml_service = MachineLearningService(inputs)
gene_list_combos = ml_service.determineGeneListCombos()
trainer = RandomForestTrainer(True)
trimmed_combos = ml_service.fetchValidGeneListCombos(
input_folder, gene_list_combos, trainer)
assert len(trimmed_combos) == (len(gene_list_combos) - 1)
def processArguments(self, is_classifier, analyze_all, num_features):
random_data_generator = RandomizedDataGenerator(
RandomizedDataGenerator.GENERATED_DATA_FOLDER)
random_data_generator.generateRandomizedFiles(5,
50,
num_features,
is_classifier,
10,
.8,
analyze_all=analyze_all)
input_folder = self.current_working_dir + "/" + RandomizedDataGenerator.GENERATED_DATA_FOLDER
argument_processing_service = ArgumentProcessingService(input_folder)
arguments = argument_processing_service.handleInputFolder()
return arguments
def formatRandomizedData(self, is_classifier, analyze_all,
use_static_features):
random_data_generator = RandomizedDataGenerator(
RandomizedDataGenerator.GENERATED_DATA_FOLDER)
random_data_generator.generateRandomizedFiles(
3,
1000,
150,
is_classifier,
self.MONTE_CARLO_PERMS,
.8,
analyze_all=analyze_all,
use_static_features=use_static_features)
input_folder = self.current_working_dir + "/" + RandomizedDataGenerator.GENERATED_DATA_FOLDER
argument_processing_service = ArgumentProcessingService(input_folder)
argument_processing_service.log.setLevel(logging.DEBUG)
return argument_processing_service.handleInputFolder()
def formatRandomizedData(self, is_classifier, num_cell_lines):
randomized_data_path = self.current_working_dir + "/" + RandomizedDataGenerator.GENERATED_DATA_FOLDER
processed_arguments = {}
for i in range(self.NUM_DRUGS):
drug_name = self.DRUG_DIRECTORY + SafeCastUtil.safeCast(i + 1, str)
drug_path = randomized_data_path + "/" + drug_name
if drug_name not in os.listdir(randomized_data_path):
os.mkdir(drug_path)
random_data_generator = RandomizedDataGenerator(drug_path)
random_data_generator.generateRandomizedFiles(3, num_cell_lines, 150, is_classifier, 2, .8,
use_static_features=True)
argument_processing_service = ArgumentProcessingService(drug_path)
processed_args = argument_processing_service.handleInputFolder()
processed_args.recs_config.viability_acceptance = 0.1
processed_arguments[drug_name] = processed_args
ml_service = MachineLearningService(processed_args)
combos = [ml_service.generateFeatureSetString(combo) for combo in ml_service.determineGeneListCombos()]
self.setupDrugData(combos, ml_service, drug_path)
return processed_arguments
def instantiateDataFormattingService(self, input_folder):
argument_processing_service = ArgumentProcessingService(input_folder)
arguments = argument_processing_service.handleInputFolder()
self.data_formatting_service = DataFormattingService(arguments)