def write_dataframe(frame, name, directory=None):
config = Config()
if directory is None:
path = os.path.join(config.artifacts_directory, f"{name}.csv")
else:
path = os.path.join(directory, f"{name}.csv")
frame.to_csv(path, index=False, sep=config.delimiter)
checksum = DataManager.checksum(path)
return checksum
def __init__(self, directory):
self.config = Config()
self.logger = Logger(__name__)
self.logger.info(f"Loading data from {directory}...")
self.target_column_name = self.config.target_column
self.feature_column_names = None
self.is_single_file = self.config.csv_name is not None
self.raw_data = self.read_all_data(directory)
if self.raw_data is None: return
self.logger.info(f"Done read [{len(self.raw_data)}] points.")
def __init__(self, directory):
self.config = Config()
self.logger = Logger(__name__)
self.logger.info(f"Loading data from {directory}...")
self.target_column_name = self.config.target_column
self.feature_column_names = None
self._label_encoder = self.load_labelencoder()
self.is_single_file = self.config.csv_name is not None
self.raw_data = self.read_all_data(directory)
if self.raw_data is None: return
nclasses = self.num_classes()
self.logger.info(
f"Done read [{len(self.raw_data)}] points with [{nclasses}] classes."
)
if nclasses == 1:
self.logger.info("Data must have at least 2 classes.")
self.raw_data = None
def __init__(self, is_infer_only=False):
self.config = Config()
self.logger = Logger(__name__)
self._model = self.load_model()
self._label_encoder = self.load_labelencoder()
def __init__(self, name):
self.config = Config()
self.logger_name = name
self.logger = logging.getLogger(name)
if self.config.is_info or self.config.is_verbose:
self.logger.setLevel(logging.INFO)