def setUp(self):
validation_size = 0.2
# Get the ground truth CSV file from script's parameters.
self.galaxy_csv_file = os.environ["VIRTUAL_ENV"] + "/data/csv/galaxy/galaxy.csv"
self.galaxy_images_path = os.environ["VIRTUAL_ENV"] + "/data/images/"
# Create instance of data set loading strategies.
galaxy_label_data_set_strategy = GalaxyDataSetLabelStrategy()
# Set the context to galaxy label data set loading strategy.
context = Context(galaxy_label_data_set_strategy)
context.set_strategy(galaxy_label_data_set_strategy)
self.label_dataset = context.load_dataset(csv_file=self.galaxy_csv_file, one_hot=False,
validation_size=np.float32(validation_size))
def main():
"""
Program's entry point.
"""
# The desired validation size.
validation_size = 0.2
# Get the ground truth CSV file from script's parameters.
galaxy_csv_file = os.environ["VIRTUAL_ENV"] + "/data/csv/galaxy/galaxy.csv"
galaxy_feature_csv_file = os.environ[
"VIRTUAL_ENV"] + "/data/csv/galaxy/galaxy_feature_vectors.csv"
spam_feature_csv_file = os.environ[
"VIRTUAL_ENV"] + "/data/csv/spam/spam.csv"
galaxy_images_path = os.environ["VIRTUAL_ENV"] + "/data/images/"
galaxy_feature_vector_export_path = os.environ[
"VIRTUAL_ENV"] + "/data/csv/galaxy/exported_personal_galaxy_feature_vectors.csv"
galaxy_mlp_export_path = os.environ[
"VIRTUAL_ENV"] + "/data/models/exports/MLP/my_mlp"
# Create instance of data set loading strategies.
galaxy_image_data_set_strategy = GalaxyDataSetImageStrategy()
galaxy_feature_data_set_strategy = GalaxyDataSetFeatureStrategy()
galaxy_label_data_set_strategy = GalaxyDataSetLabelStrategy()
spam_feature_dataset_strategy = SpamDataSetFeatureStrategy()
# Set the context to galaxy image data set loading strategy.
context = Context(galaxy_image_data_set_strategy)
img_dataset = context.load_dataset(
csv_file=galaxy_csv_file,
one_hot=True,
validation_size=np.float32(validation_size))
# Set the context to galaxy feature data set loading strategy.
context.set_strategy(galaxy_feature_data_set_strategy)
feature_oneHot_dataset = context.load_dataset(
csv_file=galaxy_feature_csv_file,
one_hot=True,
validation_size=np.float32(0.2))
feature_dataset = context.load_dataset(csv_file=galaxy_feature_csv_file,
one_hot=False,
validation_size=np.float32(0.2))
# Set the context to galaxy label data set loading strategy.
context.set_strategy(galaxy_label_data_set_strategy)
label_dataset = context.load_dataset(
csv_file=galaxy_csv_file,
one_hot=False,
validation_size=np.float32(validation_size))
context.set_strategy(spam_feature_dataset_strategy)
spam_feature_dataset = context.load_dataset(
csv_file=spam_feature_csv_file,
one_hot=False,
validation_size=np.float32(validation_size))
# For TP02, set the discretization strategy and discretize data.
preprocessor_context = DiscretizerContext(
SupervisedDiscretizationStrategy())
supervised_discretised_dataset = preprocessor_context.discretize(
data_set=feature_dataset, validation_size=np.float32(validation_size))
preprocessor_context.set_strategy(UnsupervisedDiscretizationStrategy())
unsupervised_discretised_dataset = preprocessor_context.discretize(
data_set=feature_dataset, validation_size=np.float32(validation_size))
# Process galaxies.
galaxy_processor = GalaxyProcessor(galaxy_images_path)
features = galaxy_processor.process_galaxy(label_dataset)
# Save extracted features to file.
np.savetxt(galaxy_feature_vector_export_path, features, delimiter=",")
print("File saved in directory " + galaxy_feature_vector_export_path)