def run():
parser = argparse.ArgumentParser(description='Calcuclate embeddings')
parser.add_argument('input', help='Input containing osm samples')
parser.add_argument('output', help='File to safe embeddings in')
parser.add_argument('--model',
help='Embedding model to us',
default="NLE",
type=str)
parser.add_argument('--ftmodel',
help='Path to fasttext model',
type=str,
default="")
parser.add_argument('--db_cred',
help='Credentials for database',
type=str,
default="")
parser.add_argument('--njobs',
help='Number of threads to use',
default=1,
type=int)
args = parser.parse_args()
# create model
if args.model == "fasttext":
model = FastTextModel(args.ftmodel)
elif args.model == 'NLE':
db = PostgresDB(read_db_config(args.db_cred))
model = NLEModel(args.output, args.njobs, db)
else:
raise Exception("Model not found")
data = read_samples(args.input)
# train model
model.train(data)
# save model
model.save_model(args.output + "_" + args.model)
def main(argv):
if len(argv) < 2:
sys.stderr.write("not enough arguments\n");
sys.exit(-1);
mode= argv[1]
if mode == "mle":
print "Reading data from stdin..."
samples= util.read_samples(sys.stdin)
print "MLE = %f" % (Pareto2.mle(samples))
else:
if len(argv) < 4:
sys.stderr.write("not enough arguments\n")
sys.exit(-1)
alpha= float(argv[2])
beta= float(argv[3])
p= Pareto2(alpha, beta)
if mode == "exp":
print "%f" % (p.expectation())
else:
if len(argv) < 5:
sys.stderr.write("not enough arguments\n")
sys.exit(-1)
size= int(argv[4])
if mode == "pdf":
for x in range(size):
print "%d\t%.20f" % (x, p.pdf(x))
elif mode == "cdf":
for x in range(size):
print "%d\t%.20f" % (x, p.cdf(x))
elif mode == "random":
freq= {}
samples= []
for i in range(size):
if (i % 1000) == 0:
print >> sys.stderr, "\rGenerating samples %d/%d" % \
(i+1, size),
r= p.random()
samples.append(r)
print >> sys.stderr, "\rGenerating samples %d/%d" % \
(i+1, size)
mean= 0
for r in sorted(samples):
mean+= r
mean/= size
print "# mean = %f" % (mean)
for r in samples:
print "%d" % (r)
else:
sys.stderr.write("unknown mode \"%s\"\n" % (mode))
def main(mode, argv):
if mode == "mle":
if len(argv) > 0:
xmin= int(argv[0])
else:
xmin= 1
samples= util.read_samples(sys.stdin)
print "xmin = %d" % (xmin)
print "MLE = %f" % (Zipf.mle(samples, xmin))
return 0
else:
if len(argv) < 3:
sys.stderr.write("not enough arguments\n")
return -1
alpha= float(argv[0])
N= int(argv[1])
xmin= int(argv[2])
z= Zipf(alpha, N, xmin)
if mode == "exp":
print "%f" % (z.expectation())
return 0
elif mode == "pdf":
for i in range(xmin, N+1):
print "%d\t%.20f" % (i, z.pmf(i))
return 0
elif mode == "cdf":
for i in range(xmin, N+1):
print "%d\t%.20f" % (i, z.cdf(i))
return 0
elif mode == "random":
if len(argv) < 4:
sys.stderr.write("not enough arguments\n")
return -1
size= int(argv[3])
freq= {}
samples= []
for i in range(size):
if (i % 1000) == 0:
print >> sys.stderr, "\rGenerating samples %d/%d" % \
(i+1, size),
r= z.random()
samples.append(r)
print >> sys.stderr, "\rGenerating samples %d/%d" % \
(i+1, size)
mean= 0
for r in sorted(samples):
mean+= r
mean/= size
print "# mean = %f" % (mean)
for r in samples:
print "%d" % (r)
#print >> sys.stderr, "\rfinished :-)"
else:
sys.stderr.write("invalid mode \"%s\"\n" % (mode));
return