Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added delimiter keyword argument to all np.{load, save}txt() function calls. #3

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added delimiter keyword argument to all np.{load, save}txt() function calls. #3

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 11 additions & 8 deletions antk/core/loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -600,13 +600,14 @@ def load(filename):
"""
return import_data(filename)

def import_data(filename):
def import_data(filename, delimiter=','):
'''
Decides how to load data into python matrices by file extension.
Raises :any:`UnsupportedFormatError` if extension is not one of the supported
extensions (mat, sparse, binary, dense, sparsetxt, densetxt, index).

:param filename: (str) A file of an accepted format representing a matrix.
:delimiter: (str) Used to delimit fields in data files.
:return: A numpy matrix, scipy sparse csr_matrix, or any:`IndexVector`.
'''
extension = filename.split(slash)[-1].split('.')[-1].strip()
Expand All @@ -626,12 +627,12 @@ def import_data(filename):
elif extension == 'binary' or extension == 'dense':
return _matload(filename)
elif extension == 'sparsetxt':
X = np.loadtxt(filename)
X = np.loadtxt(filename, delimiter=delimiter)
if X.shape[1] != 3:
raise SparseFormatError('Sparse Format: row col val')
return sps.csr_matrix((X[:, 2], (X[:, 0], X[:, 1])))
elif extension == 'densetxt':
return np.loadtxt(filename)
return np.loadtxt(filename, delimiter=delimiter)
else:
raise UnsupportedFormatError('Supported extensions: '
'mat, sparse, binary, sparsetxt, densetxt, index')
Expand All @@ -650,14 +651,15 @@ def save(filename, data):
"""
export_data(filename, data)

def export_data(filename, data):
def export_data(filename, data, delimiter=','):
"""
Decides how to save data by file extension.
Raises :any:`UnsupportedFormatError` if extension is not one of the supported
extensions (mat, sparse, binary, dense, index).
Data contained in .mat files should be saved in a matrix named *data*.

:param filename: A file of an accepted format representing a matrix.
:delimiter: (str) User to delimit fields in data files.
:param data: A numpy array, scipy sparse matrix, or :any:`IndexVector` object.
"""
extension = filename.split(slash)[-1].split('.')[-1].strip()
Expand All @@ -678,15 +680,15 @@ def export_data(filename, data):
elif extension == 'densetxt':
if sps.issparse(data):
raise UnsupportedFormatError('Only numpy 2d arrays may be saved in .densetxt format')
np.savetxt(filename, data)
np.savetxt(filename, data, delimiter=delimiter)
elif extension == 'sparsetxt':
if not sps.issparse(data):
raise UnsupportedFormatError('Only scipy sparse matrices may be saved in .sparsetxt format.')
indices = list(data.nonzero())
indices.append(data.data)
data = [m.reshape((-1,1)) for m in indices]
data = np.concatenate(data, axis=1)
np.savetxt(filename, data)
np.savetxt(filename, data, delimiter=delimiter)
else:
raise UnsupportedFormatError('Supported extensions: '
'mat, sparse, binary, dense, index, sparsetxt, densetxt')
Expand Down Expand Up @@ -830,7 +832,7 @@ def makedirs(datadirectory, sub_directory_list=('train', 'dev', 'test')):
os.system('mkdir ' + datadirectory + sub)


def read_data_sets(directory, folders=('train', 'dev', 'test'), hashlist=(), mix=False):
def read_data_sets(directory, folders=('train', 'dev', 'test'), hashlist=(), mix=False, delimiter=','):
"""
:param directory: (str) Root directory containing data to load.
:param folders: (dict) The subfolders of *directory* to read data from.
Expand All @@ -841,6 +843,7 @@ def read_data_sets(directory, folders=('train', 'dev', 'test'), hashlist=(), mix
It you do not provide a hashlist then anything with
the privileged prefixes labels_ or features_ will be loaded.
:param mix: (boolean) Whether to shuffle during mini-batching.
:delimiter: (str) Used to delimit fields in data files.
:return: A :any:`DataSets` object.

:examples:
Expand Down Expand Up @@ -913,7 +916,7 @@ def read_data_sets(directory, folders=('train', 'dev', 'test'), hashlist=(), mix
prefix_ = prefix + '_'
descriptor = (filename.split('.')[0]).split(prefix_)[-1]
if (not hashlist) or (descriptor in hashlist):
dataset_map[prefix][descriptor] = import_data(directory + folder + slash + filename)
dataset_map[prefix][descriptor] = import_data(directory + folder + slash + filename, delimiter=delimiter)
datasets_map[folder] = dataset_map
return DataSets(datasets_map, mix=mix)

Expand Down