def load_data(name, *args, **kwargs):
"""Load data from file, URL, or plugin.
Parameters
----------
name: str, pathlib.Path
File path, URL, or alias of extension dataset.
Returns
-------
asreview.ASReviewData:
Inititalized ASReview data object.
"""
# check is file or URL
if Path(name).exists() or is_url(name):
return ASReviewData.from_file(name, *args, **kwargs)
# check if dataset is plugin dataset\
try:
dataset_path = DatasetManager().find(name).get()
return ASReviewData.from_file(dataset_path, *args, **kwargs)
except DataSetNotFoundError:
pass
# Could not find dataset, return None.
raise FileNotFoundError(
f"File, URL, or dataset does not exist: '{name}'")
def from_file(cls, fp, read_fn=None, data_name=None, data_type=None):
"""Create instance from csv/ris/excel file.
It works in two ways; either manual control where the conversion
functions are supplied or automatic, where it searches in the entry
points for the right conversion functions.
Arguments
---------
fp: str, pathlib.Path
Read the data from this file.
read_fn: callable
Function to read the file. It should return a standardized
dataframe.
data_name: str
Name of the data.
data_type: str
What kind of data it is. Special names: 'included', 'excluded',
'prior'.
"""
if is_url(fp):
path = urlparse(fp).path
new_data_name = Path(path.split("/")[-1]).stem
else:
path = str(Path(fp).resolve())
new_data_name = Path(fp).stem
if data_name is None:
data_name = new_data_name
if read_fn is not None:
return cls(read_fn(fp), data_name=data_name, data_type=data_type)
entry_points = {
entry.name: entry
for entry in pkg_resources.iter_entry_points('asreview.readers')
}
best_suffix = None
for suffix, entry in entry_points.items():
if path.endswith(suffix):
if best_suffix is None or len(suffix) > len(best_suffix):
best_suffix = suffix
if best_suffix is None:
raise ValueError(f"Error reading file {fp}, no capabilities for "
"reading such a file.")
read_fn = entry_points[best_suffix].load()
df, column_spec = read_fn(fp)
return cls(df,
column_spec=column_spec,
data_name=data_name,
data_type=data_type)
def from_config(cls, config_file):
if is_url(config_file):
with urlopen(config_file) as f:
config = json.loads(f.read().decode())
elif isinstance(config_file, dict):
config = config_file
else:
with open(config_file, "r") as f:
config = json.load(f)
dataset = cls()
for attr, val in config.items():
setattr(dataset, attr, val)
return dataset
def from_config(cls, config_file):
"""Create DataSet from a JSON configuration file.
Parameters
----------
config_file: str, dict
Can be a link to a config file or one on the disk.
Another option is to supply a dictionary with the metadata.
"""
if is_url(config_file):
with urlopen(config_file) as f:
config = json.loads(f.read().decode())
elif isinstance(config_file, dict):
config = config_file
else:
with open(config_file, "r") as f:
config = json.load(f)
# Set the attributes of the dataset.
dataset = cls()
for attr, val in config.items():
setattr(dataset, attr, val)
return dataset