def load_sparse_matrix(input_format,filepath):
"""
Load a scipy.sparse.csr_matrix from an input file of the specified format.
Parameters
----------
input_format : str
Specifies the file format:
- tsv
- csv
- mm (MatrixMarket)
- npz (scipy.sparse.csr_matrix serialized with mrec.sparse.savez())
- fsm (mrec.sparse.fast_sparse_matrix)
filepath : str
The file to load.
"""
if input_format == 'tsv':
return loadtxt(filepath)
elif input_format == 'csv':
return loadtxt(filepath,delimiter=',')
elif input_format == 'mm':
return mmread(filepath).tocsr()
elif input_format == 'npz':
return loadz(filepath).tocsr()
elif input_format == 'fsm':
return fast_sparse_matrix.load(filepath).X
raise ValueError('unknown input format: {0}'.format(input_format))
def load_fast_sparse_matrix(input_format,filepath):
"""
Load a fast_sparse_matrix from an input file of the specified format,
by delegating to the appropriate static method.
Parameters
----------
input_format : str
Specifies the file format:
- tsv
- csv
- mm (MatrixMarket)
- fsm (mrec.sparse.fast_sparse_matrix)
filepath : str
The file to load.
"""
if input_format == 'tsv':
return fast_sparse_matrix.loadtxt(filepath)
elif input_format == 'csv':
return fast_sparse_matrix.loadtxt(filepath,delimiter=',')
elif input_format == 'mm':
return fast_sparse_matrix.loadmm(filepath)
elif input_format == 'fsm':
return fast_sparse_matrix.load(filepath)
raise ValueError('unknown input format: {0}'.format(input_format))
def load_fast_sparse_matrix(input_format, filepath):
"""
Load a fast_sparse_matrix from an input file of the specified format,
by delegating to the appropriate static method.
Parameters
----------
input_format : str
Specifies the file format:
- tsv
- csv
- mm (MatrixMarket)
- fsm (mrec.sparse.fast_sparse_matrix)
filepath : str
The file to load.
"""
if input_format == 'tsv':
return fast_sparse_matrix.loadtxt(filepath)
elif input_format == 'csv':
return fast_sparse_matrix.loadtxt(filepath, delimiter=',')
elif input_format == 'mm':
return fast_sparse_matrix.loadmm(filepath)
elif input_format == 'fsm':
return fast_sparse_matrix.load(filepath)
raise ValueError('unknown input format: {0}'.format(input_format))
def load_sparse_matrix(input_format, filepath):
"""
Load a scipy.sparse.csr_matrix from an input file of the specified format.
Parameters
----------
input_format : str
Specifies the file format:
- tsv
- csv
- mm (MatrixMarket)
- npz (scipy.sparse.csr_matrix serialized with mrec.sparse.savez())
- fsm (mrec.sparse.fast_sparse_matrix)
filepath : str
The file to load.
"""
if input_format == 'tsv':
return loadtxt(filepath)
elif input_format == 'csv':
return loadtxt(filepath, delimiter=',')
elif input_format == 'mm':
return mmread(filepath).tocsr()
elif input_format == 'npz':
return loadz(filepath).tocsr()
elif input_format == 'fsm':
return fast_sparse_matrix.load(filepath).X
raise ValueError('unknown input format: {0}'.format(input_format))
def save_sparse_matrix(data,fmt,filepath):
"""
Save a scipy sparse matrix in the specified format. Row and column
indices will be converted to 1-indexed if you specify a plain text
format (tsv, csv, mm).
Parameters
----------
data : scipy sparse matrix to save
fmt : str
Specifies the file format to write:
- tsv
- csv
- mm (MatrixMarket)
- npz (save as npz archive of numpy arrays)
- fsm (mrec.sparse.fast_sparse_matrix)
filepath : str
The file to load.
"""
if fmt == 'tsv':
row,col = data.nonzero()
out = open(filepath,'w')
for u,i,v in izip(row,col,data.data):
print >>out,'{0}\t{1}\t{2}'.format(u+1,i+1,v)
elif fmt == 'csv':
row,col = data.nonzero()
out = open(filepath,'w')
for u,i,v in izip(row,col,data.data):
print >>out,'{0},{1},{2}'.format(u+1,i+1,v)
elif fmt == 'mm':
mmwrite(filepath,data)
elif fmt == 'npz':
return savez(data,filepath)
elif fmt == 'fsm':
fast_sparse_matrix.load(dataset).save(filepath)
else:
raise ValueError('unknown output format: {0}'.format(fmt))