def main(argv):
# Define args
args: Namespace = get_args(argv)
# Initialize Relevance Pipeline and run in train/inference mode
rp = ClassificationPipeline(args=args)
rp.run()
def setUp(
self,
output_dir: str = OUTPUT_DIR,
root_data_dir: str = ROOT_DATA_DIR,
feature_config_fname: str = FEATURE_CONFIG_FNAME,
model_config_fname: str = MODEL_CONFIG_FNAME,
):
self.output_dir = output_dir
self.root_data_dir = root_data_dir
self.feature_config_fname = feature_config_fname
self.model_config_fname = model_config_fname
self.file_io = LocalIO()
# Make temp output directory
self.file_io.make_directory(self.output_dir, clear_dir=True)
# Fix random seed values for repeatability
tf.keras.backend.clear_session()
np.random.seed(123)
tf.random.set_seed(123)
random.seed(123)
# Setup arguments
self.args: Namespace = get_args([])
self.args.models_dir = output_dir
self.args.logs_dir = output_dir
# Setting small batch size less than testing data size
self.args.batch_size = 32
# Load feature config
self.args.feature_config = os.path.join(
self.root_data_dir, "configs", self.feature_config_fname
)
self.feature_config = self.file_io.read_yaml(self.args.feature_config)
# Load model_config
self.args.model_config = os.path.join(
self.root_data_dir, "configs", self.model_config_fname
)
self.model_config = self.file_io.read_yaml(self.args.model_config)
# Setup logging
outfile: str = os.path.join(self.args.logs_dir, "output_log.csv")
self.logger = setup_logging(reset=True,
file_name=outfile,
log_to_file=True)
self.run_default_pipeline(data_format="csv")