def get_shard_size(self):
"""Gets size of shards on disk."""
if not len(self.metadata_df):
raise ValueError("No data in dataset.")
sample_y = load_from_disk(
os.path.join(self.data_dir,
next(self.metadata_df.iterrows())[1]['y']))
return len(sample_y)
def __len__(self):
"""
Finds number of elements in dataset.
"""
total = 0
for _, row in self.metadata_df.iterrows():
y = load_from_disk(os.path.join(self.data_dir, row['ids']))
total += len(y)
return total
def get_data_shape(self):
"""
Gets array shape of datapoints in this dataset.
"""
if not len(self.metadata_df):
raise ValueError("No data in dataset.")
sample_X = load_from_disk(
os.path.join(self.data_dir,
next(self.metadata_df.iterrows())[1]['X']))
return np.shape(sample_X)[1:]
def get_shard(self, i):
"""Retrieves data for the i-th shard from disk."""
row = self.metadata_df.iloc[i]
X = np.array(load_from_disk(os.path.join(self.data_dir, row['X'])))
if row['y'] is not None:
y = np.array(load_from_disk(os.path.join(self.data_dir, row['y'])))
else:
y = None
if row['w'] is not None:
# TODO (ytz): Under what condition does this exist but the file itself doesn't?
w_filename = os.path.join(self.data_dir, row['w'])
if os.path.exists(w_filename):
w = np.array(load_from_disk(w_filename))
else:
w = np.ones(y.shape)
else:
w = None
ids = np.array(load_from_disk(os.path.join(self.data_dir, row['ids'])),
dtype=object)
return (X, y, w, ids)
def iterate(dataset):
for _, row in dataset.metadata_df.iterrows():
X = np.array(
load_from_disk(os.path.join(dataset.data_dir, row['X'])))
ids = np.array(load_from_disk(
os.path.join(dataset.data_dir, row['ids'])),
dtype=object)
# These columns may be missing is the dataset is unlabelled.
if row['y'] is not None:
y = np.array(
load_from_disk(os.path.join(dataset.data_dir,
row['y'])))
else:
y = None
if row['w'] is not None:
w_filename = os.path.join(dataset.data_dir, row['w'])
if os.path.exists(w_filename):
w = np.array(load_from_disk(w_filename))
else:
w = np.ones(y.shape)
else:
w = None
yield (X, y, w, ids)
def load_metadata(self):
try:
tasks_filename, metadata_filename = self._get_metadata_filename()
with open(tasks_filename) as fin:
tasks = json.load(fin)
metadata_df = pd.read_csv(metadata_filename, compression='gzip')
metadata_df = metadata_df.where((pd.notnull(metadata_df)), None)
return tasks, metadata_df
except Exception as e:
pass
# Load obsolete format -> save in new format
metadata_filename = os.path.join(self.data_dir, "metadata.joblib")
if os.path.exists(metadata_filename):
tasks, metadata_df = load_from_disk(metadata_filename)
del metadata_df['task_names']
del metadata_df['basename']
save_metadata(tasks, metadata_df, self.data_dir)
return tasks, metadata_df
raise ValueError("No Metadata Found On Disk")