def train_test_split_none(*arrays, **kwargs):
"""extend train_test_split to take None arrays
and support split by group names.
"""
nones = []
new_arrays = []
for idx, arr in enumerate(arrays):
if arr is None:
nones.append(idx)
else:
new_arrays.append(arr)
if kwargs["shuffle"] == "None":
kwargs["shuffle"] = None
group_names = kwargs.pop("group_names", None)
if group_names is not None and group_names.strip():
group_names = [name.strip() for name in group_names.split(",")]
new_arrays = indexable(*new_arrays)
groups = kwargs["labels"]
n_samples = new_arrays[0].shape[0]
index_arr = np.arange(n_samples)
test = index_arr[np.isin(groups, group_names)]
train = index_arr[~np.isin(groups, group_names)]
rval = list(
chain.from_iterable(
(safe_indexing(a, train), safe_indexing(a, test)) for a in new_arrays
)
)
else:
rval = train_test_split(*new_arrays, **kwargs)
for pos in nones:
rval[pos * 2: 2] = [None, None]
return rval
def main(inputs,
infile_array,
outfile_train,
outfile_test,
infile_labels=None,
infile_groups=None):
"""
Parameter
---------
inputs : str
File path to galaxy tool parameter
infile_array : str
File paths of input arrays separated by comma
infile_labels : str
File path to dataset containing labels
infile_groups : str
File path to dataset containing groups
outfile_train : str
File path to dataset containing train split
outfile_test : str
File path to dataset containing test split
"""
warnings.simplefilter('ignore')
with open(inputs, 'r') as param_handler:
params = json.load(param_handler)
input_header = params['header0']
header = 'infer' if input_header else None
array = pd.read_csv(infile_array,
sep='\t',
header=header,
parse_dates=True)
# train test split
if params['mode_selection']['selected_mode'] == 'train_test_split':
options = params['mode_selection']['options']
shuffle_selection = options.pop('shuffle_selection')
options['shuffle'] = shuffle_selection['shuffle']
if infile_labels:
header = 'infer' if shuffle_selection['header1'] else None
col_index = shuffle_selection['col'][0] - 1
df = pd.read_csv(infile_labels,
sep='\t',
header=header,
parse_dates=True)
labels = df.iloc[:, col_index].values
options['labels'] = labels
train, test = train_test_split(array, **options)
# cv splitter
else:
train, test = _get_single_cv_split(params,
array,
infile_labels=infile_labels,
infile_groups=infile_groups)
print("Input shape: %s" % repr(array.shape))
print("Train shape: %s" % repr(train.shape))
print("Test shape: %s" % repr(test.shape))
train.to_csv(outfile_train, sep='\t', header=input_header, index=False)
test.to_csv(outfile_test, sep='\t', header=input_header, index=False)
def main(
inputs,
infile_array,
outfile_train,
outfile_test,
infile_labels=None,
infile_groups=None,
):
"""
Parameter
---------
inputs : str
File path to galaxy tool parameter
infile_array : str
File paths of input arrays separated by comma
infile_labels : str
File path to dataset containing labels
infile_groups : str
File path to dataset containing groups
outfile_train : str
File path to dataset containing train split
outfile_test : str
File path to dataset containing test split
"""
warnings.simplefilter("ignore")
with open(inputs, "r") as param_handler:
params = json.load(param_handler)
input_header = params["header0"]
header = "infer" if input_header else None
array = pd.read_csv(infile_array,
sep="\t",
header=header,
parse_dates=True)
# train test split
if params["mode_selection"]["selected_mode"] == "train_test_split":
options = params["mode_selection"]["options"]
shuffle_selection = options.pop("shuffle_selection")
options["shuffle"] = shuffle_selection["shuffle"]
if infile_labels:
header = "infer" if shuffle_selection["header1"] else None
col_index = shuffle_selection["col"][0] - 1
df = pd.read_csv(infile_labels,
sep="\t",
header=header,
parse_dates=True)
labels = df.iloc[:, col_index].values
options["labels"] = labels
train, test = train_test_split(array, **options)
# cv splitter
else:
train, test = _get_single_cv_split(params,
array,
infile_labels=infile_labels,
infile_groups=infile_groups)
print("Input shape: %s" % repr(array.shape))
print("Train shape: %s" % repr(train.shape))
print("Test shape: %s" % repr(test.shape))
train.to_csv(outfile_train, sep="\t", header=input_header, index=False)
test.to_csv(outfile_test, sep="\t", header=input_header, index=False)
