def __train_test_val_split(self):
y = self.__same_length_vectors[Data_Fields.get_target()]
binary_fields = [
field for field in Data_Fields.get_binary_vars()
if field in Config.DATA_FIELDS_IN_ANALYSIS
]
continuous_fields = [
field for field in Data_Fields.get_continuous_vars()
if field in Config.DATA_FIELDS_IN_ANALYSIS
]
predictors_names = binary_fields + continuous_fields
predictors_vectors_tuple = tuple(
[self.__same_length_vectors[name] for name in predictors_names])
X = np.stack(predictors_vectors_tuple, axis=1)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.1,
random_state=42)
X_train, X_val, y_train, y_val = train_test_split(X_train,
y_train,
test_size=0.2,
random_state=42)
self.X_train = X_train
self.X_val = X_val
self.X_test = X_test
self.y_train = y_train
self.y_val = y_val
self.y_test = y_test
self.predictors_names = predictors_names
def __init__(self):
self.__class__.WORK_DIR = 'C:/Users/normy/corona_classifier_files/classification'
self.__class__.COMMON_FILES_DIR = 'C:/Users/normy/PycharmProjects/corona_classifier/common_files'
self.__class__.RAW_DATA_PATH = 'C:/Users/normy/PycharmProjects/covidclinicaldata/data'
self.__class__.PICKLE_PATH = os.path.join(self.WORK_DIR,
'pickle_files')
self.__class__.YAML_FILE_DIR = os.path.join(os.path.dirname(__file__),
'yaml_files')
self.__class__.COMMON_YAML_FILE_DIR = os.path.join(
self.COMMON_FILES_DIR, 'yaml_files')
self.__class__.OUTPUT_PATH = os.path.join(self.WORK_DIR, 'outputs')
self.__class__.DATA_FIELDS_IN_ANALYSIS = [
Data_Fields.get_target(), *Data_Fields.get_binary_vars(),
*Data_Fields.get_continuous_vars()
]
static_values = self.load_yaml(self.YAML_FILE_DIR, 'static_values')
self.__class__.DATA_FIELD_MISSING_VALUES_THRESHOLD = static_values[
'data_field_missing_values_threshold']
self.__class__.BOOTSTRAP_PATIENT_ENLARGEMENT_SIZE = static_values[
'bootstrap_patient_enlargement_size']
self.__class__.MODEL_THRESHOLDS = static_values['model_thresholds']
self.__class__.CONTINUOUS_FIELDS_THRESHOLDS = self.load_yaml(
self.COMMON_YAML_FILE_DIR, 'continuous_fields_thresholds')
def __binary_one_hot_encoding(self):
data_fields = Data_Fields.get_binary_vars()
data_fields.append(Data_Fields.get_target())
for patient in self.__patients:
for field in data_fields:
if getattr(patient, field) is None:
continue
elif getattr(patient, field) not in ('TRUE', 'Positive'):
setattr(patient, field, 0)
else:
setattr(patient, field, 1)