def main(argv):
# Define args
args: Namespace = get_args(argv)
# Initialize Relevance Pipeline and run in train/inference mode
rp = RankingPipeline(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,
):
self.output_dir = output_dir
self.root_data_dir = root_data_dir
self.feature_config_fname = feature_config_fname
# Make temp output directory
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
# Load model_config
self.model_config = 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)
def create_parse_args(data_dir, feature_config, model_config, logs_dir,
num_folds, use_testset_in_folds):
argv = [
"--data_dir", data_dir, "--feature_config", feature_config, "--kfold",
str(num_folds), "--include_testset_in_kfold",
str(use_testset_in_folds), "--run_id", "testing_kfold_cs",
"--data_format", "csv", "--execution_mode", "train_inference_evaluate",
"--num_epochs", "1", "--model_config", model_config, "--batch_size",
"4", "--logs_dir", logs_dir, "--max_sequence_size", "25",
"--train_pcent_split", "1.0", "--val_pcent_split", "-1",
"--test_pcent_split", "-1"
]
args = get_args(argv)
return args
def train_ml4ir(data_dir, feature_config, model_config, logs_dir):
"""
Train a pointwise ranker, listwise loss model using ml4ir
"""
argv = [
"--data_dir", data_dir, "--feature_config", feature_config,
"--loss_type", "listwise", "--scoring_type", "listwise", "--run_id",
"test_command_line", "--data_format", "csv", "--execution_mode",
"train_evaluate", "--loss_key", "rank_one_listnet", "--num_epochs",
"150", "--model_config", model_config, "--batch_size", "1",
"--logs_dir", logs_dir, "--max_sequence_size", "25",
"--train_pcent_split", "1.0", "--val_pcent_split", "-1",
"--test_pcent_split", "-1", "--early_stopping_patience", "25",
"--metrics_keys", "MRR", "categorical_accuracy", "--monitor_metric",
"categorical_accuracy"
]
args = get_args(argv)
rp = RankingPipeline(args=args)
rp.run()
