def largevis(edgelist_filename, outdim=2, alpha=-1):
""" Use LargeVis for embedding
This function is Clustit's interface to the LargeVis model
for embedding large-scale and high-dimensional data.
:param edgelist_filename: The filename of the edgelist with the similarities or distances
:type edgelist_filename: string
:param outdim: The number of output dimensions, default is 2.
:type outdim: int
:returns: The resulting embedding of the input data
:rtype: pandas.DataFrame
"""
LargeVis.loadgraph(edgelist_filename)
_run_largevis(outdim, alpha)
#get output data from LargeVis
temp_file = "/tmp/largevis_tempfile.txt"
try:
LargeVis.save(temp_file)
data_frame = pandas.read_csv(temp_file, sep=" ", index_col=0)
finally:
delete_temp_file(temp_file)
return data_frame
def largevis(edgelist_filename, outdim=2, alpha=-1.0):
""" Use LargeVis for embedding
This function is Clustit's interface to the LargeVis model
for embedding large-scale and high-dimensional data.
:param edgelist_filename: The filename of the edgelist with the similarities or distances
:type edgelist_filename: string
:param outdim: The number of output dimensions, default is 2.
:type outdim: int
:returns: The resulting embedding of the input data
:rtype: pandas.DataFrame
"""
LargeVis.loadgraph(edgelist_filename)
_run_largevis(outdim, alpha)
#get output data from LargeVis
temp_file = "/tmp/largevis_tempfile.txt"
try:
LargeVis.save(temp_file)
names = get_column_names(outdim)
data_frame = pandas.read_csv(temp_file, sep=" ", names=names, header=0)
finally:
#delete_temp_file(temp_file)
pass
return data_frame
def largevisproc(i_file, o_file, sim):
import LargeVis
outdim = 2
threads = 24
samples = -1
prop = -1
alpha = -1
trees = -1
neg = -1
neigh = -1
gamma = -1
perp = -1
if sim: LargeVis.loadgraph(i_file)
else: LargeVis.loadfile(i_file)
Y = LargeVis.run(outdim, threads, samples, prop, alpha, trees, neg, neigh,
gamma, perp)
LargeVis.save(o_file)
import LargeVis
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('-fea', default = 1, type = int, help = 'whether to visualize high-dimensional feature vectors or networks')
parser.add_argument('-input', default = '', help = 'input file')
parser.add_argument('-output', default = '', help = 'output file')
parser.add_argument('-outdim', default = -1, type = int, help = 'output dimensionality')
parser.add_argument('-threads', default = -1, type = int, help = 'number of training threads')
parser.add_argument('-samples', default = -1, type = int, help = 'number of training mini-batches')
parser.add_argument('-prop', default = -1, type = int, help = 'number of propagations')
parser.add_argument('-alpha', default = -1, type = float, help = 'learning rate')
parser.add_argument('-trees', default = -1, type = int, help = 'number of rp-trees')
parser.add_argument('-neg', default = -1, type = int, help = 'number of negative samples')
parser.add_argument('-neigh', default = -1, type = int, help = 'number of neighbors in the NN-graph')
parser.add_argument('-gamma', default = -1, type = float, help = 'weight assigned to negative edges')
parser.add_argument('-perp', default = -1, type = float, help = 'perplexity for the NN-grapn')
args = parser.parse_args()
if args.fea == 1:
LargeVis.loadfile(args.input)
else:
LargeVis.loadgraph(args.input)
Y = LargeVis.run(args.outdim, args.threads, args.samples, args.prop, args.alpha, args.trees, args.neg, args.neigh, args.gamma, args.perp)
LargeVis.save(args.output)
#!/usr/bin/env python
import LargeVis
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--fea', default=1, type=int, help='whether to visualize high-dimensional feature vectors or networks')
parser.add_argument('--input', default='', help='input file', required=True)
parser.add_argument('--output', default='', help='output file', required=True)
parser.add_argument('--outdim', default=-1, type=int, help='output dimensionality')
parser.add_argument('--threads', default=-1, type=int, help='number of training threads')
parser.add_argument('--samples', default=-1, type=int, help='number of training mini-batches')
parser.add_argument('--prop', default=-1, type=int, help='number of propagations')
parser.add_argument('--alpha', default=-1, type=float, help='learning rate')
parser.add_argument('--trees', default=-1, type=int, help='number of rp-trees')
parser.add_argument('--neg', default=-1, type=int, help='number of negative samples')
parser.add_argument('--neigh', default=-1, type=int, help='number of neighbors in the NN-graph')
parser.add_argument('--gamma', default=-1, type=float, help='weight assigned to negative edges')
parser.add_argument('--perp', default=-1, type=float, help='perplexity for the NN-grapn')
args = parser.parse_args()
if args.fea == 1:
LargeVis.loadfile(args.input)
else:
LargeVis.loadgraph(args.input)
Y = LargeVis.run(args.outdim, args.threads, args.samples, args.prop, args.alpha, args.trees, args.neg, args.neigh, args.gamma, args.perp)
LargeVis.save(args.output)
out.write("{}\t{}\n".format(*features.shape))
for row in tq(features):
out.write('\t'.join(row.astype(str))+'\n')
del features
# now run Large Vis! (in 2D mode)
LargeVis.loadfile(args.temp+"lv_format.txt")
# samples only matters for graph layout
samples = -1
gamma = -1
Y = LargeVis.run(2, args.threads, samples, args.prop, args.alpha, args.trees, args.neg, args.neigh, gamma, args.perp)
if args.sampling == 'by_year':
filename = '.{}.year_lv_coords'.format(args.sample_size)
else:
filename = '.{}.lv_coords'.format(args.sample_size)
LargeVis.save(args.input+filename)
donestring = """
-----PROCESSING COMPLETE-----
2D Embedding saved as: {}
""".format(args.input+filename)
if args.sampling is not None:
donestring += "\nRandom indices saves as as: {}".format(args.input+idx_filename)
print(donestring)