def assign_labels(model, data_file, cols):
table = []
labels = []
cnter = 0
for row in prep.gen_file_stream(data_file, cols):
table.append(row)
cnter += 1
if cnter % 100000 == 0:
print cnter
data = mx.DataSet()
print 'table size: %d' % len(table)
data.fromArray(np.array(table))
labels += list(model.classify(data, None, None, 1))
del data
table[:] = []
# print len(list(labels))
# process the trailing entries
if len(table) > 0:
data = mx.DataSet()
data.fromArray(np.array(table))
labels += list(model.classify(data, None, None, 1))
return labels
def plotUnivariateNormalMixtureDensity(m, axis, title= None, format= '-b'):
"""
"""
# -5, 10.0, -5.0, 10.0
x = pylab.arange(axis[0],axis[1],0.02)
dat_x = mixture.DataSet()
dat_x.fromList(x)
dat_x.internalInit(m)
#print len(x)
#print len(y)
y = numpy.exp( m.pdf(dat_x) )
#pylab.figure()
pylab.plot(x,y, format) #
pylab.axis(axis)
if title:
pylab.title(title)
else:
pylab.title('Normal Mixture Density Plot')
def testLymphData():
k = 5
d = 11
aux = [0] * d
models = []
for i in range(k):
aux1 = [0] * d
aux2 = [0] * d
aux3 = [0] * d
models.append(
mixture.ProductDistribution(
[mixture.DependenceTreeDistribution(d, aux1, aux2, aux3)]))
pi = [1.0] * k
pi = numpy.array(pi) / k
train = mixture.MixtureModel(k, pi, models)
data = mixture.DataSet()
data.fromFiles(['data/ltree2_2fold.txt'], )
train.modelInitialization(data)
train.EM(data, 100, 0.01, silent=1)
def readSites(fileName):
"""
Flat file parser for the JASPAR .sites format. The files are essentially fasta but
there is a count matrix at the end of the file.
@param fileName: File name of .sites file
@return: DataSet object
"""
f = open(fileName,"r")
seq_head = re.compile("^\>(.*)")
end = re.compile("^[A,C,G,T,a,c,g,t]\s*\[")
seq = []
ids = []
count = 1
for line in f:
line = mixture.chomp(line)
#line = line.upper()
s = seq_head.search(line)
if s:
#print s.groups(1)[0]
tl = s.groups(1)[0].split('\t')
ids.append(str(tl[1])+'_'+str(tl[2]))
#ids.append('seq'+str(count))
#count +=1
#print s.group(1)
elif end.search(line):
break
else:
if len(line) > 0:
line = list(line)
# remove lower case letters, only upper case letters are part of the
# binding site
site = []
for i,s in enumerate(line):
if s.isupper():
site.append(s)
seq.append(site)
#print len(site)
data = mixture.DataSet()
data.fromList(seq, IDs = ids)
return data
def readFastaSequences(fileName, out_type='DataSet'):
"""
Reads a file in fasta format and returns the sequence in a DataSet object
@param fileName: Name of the input file
@param: type of output object: DataSet or ConstrainedDataSet
@return: list of sequence lists
"""
f = open(fileName, "r")
index = -1
seqM = []
nameList = []
partSeq = ""
nameReg = re.compile("^\>(.*)")
try:
while 1 == 1:
line = f.next()
s = nameReg.search(line)
if s:
if index != -1:
if partSeq[len(partSeq) - 2:len(partSeq)] == "//":
partSeq = partSeq[0:len(partSeq) - 2]
partSeq = partSeq.upper(
) # upper case letters by convention
seqM.append(list(partSeq))
partSeq = ""
index += 1
nameList.append(mixture.chomp(s.group(1)))
else:
partSeq += mixture.chomp(line)
except StopIteration:
if partSeq[len(partSeq) - 2:len(partSeq)] == "//":
partSeq = partSeq[0:len(partSeq) - 2]
partSeq = partSeq.upper()
seqM.append(list(partSeq))
if out_type == 'DataSet':
data = mixture.DataSet()
elif out_type == 'ConstrainedDataSet':
data = mixture.ConstrainedDataSet()
else:
raise TypeError, 'Invalid output type ' + str(out_type)
data.fromList(seqM, IDs=nameList)
return data
def readAlnData(fn, reg_str=None, out_type='DataSet'):
"""
Parses a CLUSTALW format .aln multiple alignment file and returns a mixture.DataSet object.
@param reg_str: regular expression for sequence parsing
@param: type of output object: DataSet or ConstrainedDataSet
@return: DataSet object
"""
f = open(fn, 'r')
if reg_str:
parse = re.compile(reg_str)
else:
parse = re.compile("(\w+\|\w+)\s+([\w,\-,.]+)")
d = {}
f.readline() # remove first line
for l in f:
l = mixture.chomp(l)
pat = parse.search(l)
if pat:
k = pat.group(1)
seq = pat.group(2)
if k in d.keys():
d[k] += seq
else:
d[k] = seq
else:
continue
if out_type == 'DataSet':
data = mixture.DataSet()
elif out_type == 'ConstrainedDataSet':
data = mixture.ConstrainedDataSet()
else:
raise TypeError, 'Invalid output type ' + str(out_type)
sIDs = d.keys()
dMatrix = []
for z in d.keys():
dMatrix.append(list(d[z]))
data.fromList(dMatrix, IDs=sIDs)
return data
def readJASPAR(fileName):
"""
Reads a flat file of JASPAR binding sites matrices. JASPAR files are
essentially fasta, but only upper case letters are part of the binding site proper.
Lower case letters are discarded.
"""
f = open(fileName, "r")
seq_head = re.compile("^\>(.*)")
end = re.compile("^[A,C,G,T,a,c,g,t]\s*\[")
seq = []
ids = []
count = 1
for line in f:
line = mixture.chomp(line)
#line = line.upper()
s = seq_head.search(line)
if s:
ids.append('seq' + str(count))
count += 1
#print s.group(1)
elif end.search(line):
break
else:
if len(line) > 0:
line = list(line)
# remove lower case letters, only upper case letters are part of the
# binding site
site = []
for i, s in enumerate(line):
if s.isupper():
site.append(s)
seq.append(site)
#print len(site)
data = mixture.DataSet()
data.fromList(seq, IDs=ids)
return data
import mixture
import random
VNTR = mixture.Alphabet([
'.', '2/4', '2/7', '3/4', '3/7', '4/4', '4/6', '4/7', '4/8', '4/9', '7/7'
])
DIAG = mixture.Alphabet(['.', '0', '8', '1'])
data = mixture.DataSet()
# iq.txt = iq and achievement test fields from pheno.txt
# drd4_len.txt = drd4 vntr types, only number of repeats
data.fromFiles(["filt_WISC_WIAT_DISC_134.txt"]) # ,"DRD4_134_len.txt"
m = mixture.readMixture('pheno_best.py')
print "Without deterministic anealing:"
m.randMaxEM(data, 100, 30, 0.1, tilt=0, silent=0)
print "\nWith deterministic annealing:"
m.randMaxEM(data, 100, 30, 0.1, tilt=1, silent=0)
def plotMixtureEntropy(mix, axis):
"""
@param axis: matlab-like axis coordinates: [x_start, x_end, y_start, y_end]
"""
# -5, 10.0, -5.0, 10.0
x = pylab.arange(axis[0],axis[1]+0.1,0.1)
y = pylab.arange(axis[2],axis[3]+0.1,0.1)
#print x
#print y
#print len(x)
#print len(y)
#X,Y = pylab.meshgrid(x,y)
#z = pylab.exp(-(X*X + Y*Y)) + 0.6*pylab.exp(-((X+1.8)**2 + Y**2))
#pylab.contour(x,y,z)
z = numpy.zeros( (len(y),len(x)),dtype='Float64' )
for i in range(len(y)):
dat = numpy.zeros((len(x),2),dtype='Float64' )
dat[:,1] = y[i]
dat[:,0] = x
#print numpy.exp(mix.pdf(dat))
#print "---------------------------\n",dat
data = mixture.DataSet()
data.fromList(dat)
data.internalInit(mix)
l = mixture.get_posterior(mix,data,logreturn=False)
#print l
#print numpy.exp(mix.pdf(dat)).tolist()
for j in range(len(x)):
z[i,j] = mixture.entropy(l[:,j])
#print dat[j,:] ,":",l[:,j], "=",z[i,j]
#print "---------------------------\n"
#print "z", len(z),'x', len(z[0]) ,'=', len(z) * len(z[0])
print "max",z.max()
#max_val = z.max()
max_val = numpy.log(mix.G) # maximum entropy for a vector of length mix.G
print "theor. max", max_val
step = max_val / 10.0
print "step",step
#pylab.figure(1)
#pylab.contour(x,y,z)
#pylab.figure(2)
#pylab.contour(x,y,z,pylab.arange(0,max_val,step))
#pylab.legend()
# pylab.colorbar()
pylab.contourf(x,y,z,) # pylab.arange(0,max_val,step)
pylab.title('Posterior Entropy Plot')
def plotNormalMixtureDensity(mix, axis, title= None, newfigure=False, fill=True, alpha=1.0):
"""
@param axis: matlab-like axis coordinates: [x_start, x_end, y_start, y_end]
"""
if newfigure == True:
pylab.figure()
# -5, 10.0, -5.0, 10.0
x = pylab.arange(axis[0],axis[1]+0.1,0.1)
y = pylab.arange(axis[2],axis[3]+0.1,0.1)
#print len(x)
#print len(y)
#X,Y = pylab.meshgrid(x,y)
#z = pylab.exp(-(X*X + Y*Y)) + 0.6*pylab.exp(-((X+1.8)**2 + Y**2))
#pylab.contour(x,y,z)
z = numpy.zeros( (len(y),len(x)),dtype='Float64' )
for i in range(len(y)):
ndat = numpy.zeros((len(x),2),dtype='Float64' )
ndat[:,1] = y[i]
ndat[:,0] = x
#print numpy.exp(mix.pdf(dat))
dat = mixture.DataSet()
dat.fromList(ndat)
dat.internalInit(mix)
# XXX pdf is log valued, we want the true value XXX
#print numpy.exp(mix.pdf(dat)).tolist()
z[i,:] = numpy.exp(mix.pdf(dat))
#print "z", len(z),'x', len(z[0]) ,'=', len(z) * len(z[0])
#print "max",z.max()
max_val = z.max()
step = max_val / 40.0
#step = max_val / 200.0
#print "step",step
#pylab.figure(1)
#pylab.contour(x,y,z)
if fill == True:
pylab.contourf(x,y,z,pylab.arange(0,max_val,step),alpha=alpha)
else:
pylab.contour(x,y,z,pylab.arange(0,max_val,step),alpha=alpha)
if title:
pylab.title(title)
else:
pylab.title('Normal Mixture Density Plot')
def gaussian_decomposition(dist, max_comp=5, max_trials=10, max_steps=40):
""" Performs Gaussian decomposition.
Decompose the input distribution into best-fit Gaussian components.
Args:
dist: input distribution in 'mcerp' format.
max_comp: maximum number of Gaussian components.
max_trials: maximum number of trials beforing increasing # of comp. Larger is better/slower.
max_steps: maximum steps in each fitting process. Larger is better/slower.
Return:
mixture: a list of tuple (mu, sigma) for the Gaussian components.
"""
#mix = np.concatenate([np.random.normal(0, 1, [2000]), np.random.normal(6, 2, [4000]), np.random.normal(-3, 1.5, [1000])])
mix = dist._mcpts
data = mixture.DataSet()
data.fromArray(mix)
# TODO: what to set for init std? Sweep? Or some desired value for later analytical solving?
std = 1.
dummy = functools.partial(mixture.NormalDistribution, sigma=std)
best_llh, best_peaks, best_mixture = None, None, None
for i in range(1, 1 + max_comp):
logging.debug('Gaussian Decomposition Iter: {}\n'.format(i))
local_llh, local_peaks, local_mixture = None, None, None
# Try max_trials times init sampling.
for j in range(1, 1 + max_trials):
pi = [1. / i] * i
rand_peaks = np.random.choice(mix, i)
components = [dummy(p) for p in rand_peaks]
m = mixture.MixtureModel(i, pi, components)
# Fixed convergence cretiria here.
_, llh = m.EM(data, max_steps, .1, True)
if local_llh is None:
local_llh = llh
local_peaks = rand_peaks
local_mixture = m
else:
if llh > local_llh:
local_llh = llh
local_peaks = rand_peaks
local_mixture = m
if best_llh is None:
best_llh = local_llh
best_peaks = local_peaks
best_mixture = local_mixture
else:
if local_llh > best_llh:
best_llh = local_llh
best_peaks = local_peaks
best_mixture = local_mixture
logging.debug('BEST MIXTURE ({}):\n{}'.format(best_llh, best_mixture))
# Plot the progress of fitting, cool figure awaits!
#plot_fitting_progress(dummy, len(best_mixture.components), data, best_peaks)
result = []
for (comp, pi) in zip(best_mixture.components, best_mixture.pi):
# comp is a ProductDistribution instance which may have (not in this case) multipul components too.
assert (len(comp.distList) == 1)
for d in comp:
result.append((pi, d.mu, d.sigma))
return result
def build_mix_dat(data):
mixdat = mixture.DataSet()
mixdat.fromArray(data)
return mixdat
def find_threshold(self, user_params):
"""Finds the thresholds for errors given the data using Gaussian Mixture Model
Args:
data: The data to fit
Kwargs:
method: Whether to us [min,median,mean] of data in each bin
thresh: Threshold for find_alpha
bins: Number of pieces of the data we look at
plot: Whether to plot the cdf and the two alpha cutoffs
Returns:
A soft threshold (alpha0) and A strong threshold (alpha1)
Raises:
"""
max_gauss_mixtures = user_params.get("max_gauss_mixtures")
data = self.prob_smoothed
#print data
# http://www.pymix.org/pymix/index.php?n=PyMix.Tutorial
# make two gaussains
gaussian_one = mixture.NormalDistribution(numpy.mean(data),
numpy.std(data))
gaussian_two = mixture.NormalDistribution(10.0 * numpy.mean(data),
numpy.std(data))
mixture_model = mixture.MixtureModel(2, [0.99, 0.01],
[gaussian_one, gaussian_two])
# print mixture_model
EM_tuned = False
while not EM_tuned:
# make mix_data from a random 10% of the original data
index_array = numpy.arange(data.size)
numpy.random.shuffle(index_array)
mix_data = mixture.DataSet()
data_size = numpy.min((int(numpy.floor(data.size / 10.0)), 50000))
mix_data.fromArray(data[index_array[:data_size]])
try:
mixture_model.randMaxEM(mix_data,
max_gauss_mixtures,
40,
0.001,
silent=True)
EM_tuned = True
except AssertionError:
# pymix likes to throw assertion errors when it has small machine precision errors...
print "Caught an assertion error in pymix, randomizing input and trying again"
except:
print "pymix failed to find mixture model, using single gaussian"
gaussian_two = mixture.NormalDistribution(
numpy.mean(data), numpy.std(data))
EM_tuned = True
#print mixture_model
# hacky, no good api access to the model components
gauss_one_mean = float(
str(mixture_model.components[0][0]).split('[')[1].split(',')[0])
gauss_one_std = float(
str(mixture_model.components[0][0]).split(', ')[1].split(']')[0])
gauss_two_mean = float(
str(mixture_model.components[1][0]).split('[')[1].split(',')[0])
gauss_two_std = float(
str(mixture_model.components[1][0]).split(', ')[1].split(']')[0])
print "Gauss1: mu: %f, std: %f" % (gauss_one_mean, gauss_one_std)
print "Gauss2: mu: %f, std: %f" % (gauss_two_mean, gauss_two_std)
#print "Using threshold %f" % threshold
# inv normal cdf
if gauss_one_mean > gauss_two_mean or mixture_model.pi[1] < 0.60:
self.thresh_main_mean = gauss_one_mean
self.thresh_main_std = gauss_one_std
else:
self.thresh_main_mean = gauss_two_mean
self.thresh_main_std = gauss_two_std
def main():
logger.debug('App started')
parser = argparse.ArgumentParser(description='Key processing tool')
parser.add_argument('-t',
'--threads',
dest='threads',
type=int,
default=None,
help='Number of threads to use for cert download')
parser.add_argument('--debug',
dest='debug',
action='store_const',
const=True,
help='enables debug mode')
parser.add_argument('--verbose',
dest='verbose',
action='store_const',
const=True,
help='enables verbose mode')
parser.add_argument('--dump-json',
dest='dump_json',
action='store_const',
const=True,
help='dumps JSON of the filtered certificates')
parser.add_argument('--dump-cert',
dest='dump_cert',
action='store_const',
const=True,
help='dumps PEM of the filtered certificates')
parser.add_argument(
'-f',
'--filter-org',
dest='filter_org',
help='Filter out certificates issued with given organization - regex')
parser.add_argument(
'--filter-domain',
dest='filter_domain',
help='Filter out certificates issued for the given domain - regex')
parser.add_argument('--pubs',
dest='pubs',
nargs=argparse.ZERO_OR_MORE,
help='File with public keys (PEM)')
parser.add_argument('--certs',
dest='certs',
nargs=argparse.ZERO_OR_MORE,
help='File with certificates (PEM)')
parser.add_argument('--ossl',
dest='ossl',
type=int,
default=None,
help='OpenSSL generator')
parser.add_argument('--per-key-stat',
dest='per_key_stat',
action='store_const',
const=True,
help='Print prob matching for each key')
parser.add_argument('--subs',
dest='subs',
action='store_const',
const=True,
help='Plot random subgroups charts')
parser.add_argument('--subs-k',
dest='subs_k',
type=int,
default=5,
help='Size of the subset')
parser.add_argument('--subs-n',
dest='subs_n',
type=int,
default=1000,
help='Number of subsets to sample')
parser.add_argument('--pca-src',
dest='pca_src',
action='store_const',
const=True,
help='Plot PCA sampled distribution vs collected one')
parser.add_argument(
'--pca-src-n',
dest='pca_src_n',
type=int,
default=10000,
help='Number of subsets to sample from source distributions')
parser.add_argument('--pca-src-k',
dest='pca_src_k',
type=int,
default=3,
help='Size of the subset from the source distribution')
parser.add_argument('--pca-grp',
dest='pca_grp',
action='store_const',
const=True,
help='Plot PCA on the input keys (groups)')
parser.add_argument('--mixture',
dest='mixture',
action='store_const',
const=True,
help='Mixture distribution on masks - sources')
parser.add_argument('--distrib',
dest='distrib',
action='store_const',
const=True,
help='Plot distributions - to the PDF')
parser.add_argument('--distrib-mix',
dest='distribmix',
action='store_const',
const=True,
help='Plot distributions groups mixed with sources')
parser.add_argument('--key-dist',
dest='plot_key_dist',
action='store_const',
const=True,
help='Plots key mask distribution')
parser.add_argument('files',
nargs=argparse.ZERO_OR_MORE,
default=[],
help='file with ssl-dump json output')
args = parser.parse_args()
last_src_id = 0
src_names = []
masks_db = []
masks_src = []
cert_db = []
keys_db = []
# Input = ssl-dump output
if len(args.files) > 0:
# Cert Organization Filtering
re_org = None if args.filter_org is None else re.compile(
args.filter_org, re.IGNORECASE)
# Domain filtering
re_dom = None if args.filter_domain is None else re.compile(
args.filter_domain, re.IGNORECASE)
# Process files
for fl in args.files:
with open(fl, mode='r') as fh:
data = fh.read()
# Parse json out
if '-----BEGIN JSON-----' in data:
if '-----END JSON-----' not in data:
raise ValueError('BEGIN JSON present but END JSON not')
match = re.search(
r'-----BEGIN JSON-----(.+?)-----END JSON-----', data,
re.MULTILINE | re.DOTALL)
if match is None:
raise ValueError('Could not extract JSON')
data = match.group(1)
json_data = json.loads(data)
for cert in json_data:
org = cert['org']
if org is None:
org = ''
if re_org is not None and re_org.match(org) is None:
if args.verbose:
print('Organization filtered out %s' % org)
continue
if re_dom is not None:
dom_match = re_dom.match(cert['cn']) is not None
for alt in cert['alts']:
dom_match |= re_dom.match(alt) is not None
if not dom_match:
if args.verbose:
print('Domain filtered out %s' % cert['cn'])
continue
cert_db.append(cert)
masks_db.append(cert['pubkey']['mask'])
masks_src.append(last_src_id)
src_names.append(fl)
last_src_id += 1
if args.verbose:
print('Certificate database size %d' % len(cert_db))
if args.dump_json:
print(json.dumps(cert_db))
if args.dump_cert:
for cert in cert_db:
print cert['cert']
# public key list processing
if args.pubs is not None:
for pubf in args.pubs:
with open(pubf, mode='r') as fh:
data = fh.read()
keys = []
for match in re.finditer(
r'-----BEGIN PUBLIC KEY-----(.+?)-----END PUBLIC KEY-----',
data, re.MULTILINE | re.DOTALL):
key = match.group(0)
keys.append(key)
print('File %s keys num: %d' % (pubf, len(keys)))
# pubkey -> mask
for key in keys:
pub = serialization.load_pem_public_key(
key, utils.get_backend())
mask = keys_basic.compute_key_mask(pub.public_numbers().n)
keys_db.append(pub)
masks_db.append(mask)
masks_src.append(last_src_id)
src_names.append(pubf)
last_src_id += 1
# extract public key from certificate
if args.certs is not None:
for certf in args.certs:
with open(certf, mode='r') as fh:
data = fh.read()
certs = []
for match in re.finditer(
r'-----BEGIN CERTIFICATE-----(.+?)-----END CERTIFICATE-----',
data, re.MULTILINE | re.DOTALL):
cert = match.group(0)
certs.append(cert)
# cert -> mask
for cert in certs:
x509 = utils.load_x509(str(cert))
pub = x509.public_key()
mask = keys_basic.compute_key_mask(pub.public_numbers().n)
keys_db.append(pub)
masks_db.append(mask)
masks_src.append(last_src_id)
src_names.append(certf)
last_src_id += 1
# generate openssl keys on the fly
if args.ossl is not None:
for i in range(0, args.ossl):
print('Generating RSA1024 key %03d' % i)
key = OpenSSL.crypto.PKey()
key.generate_key(OpenSSL.crypto.TYPE_RSA, 1024)
key_pem = OpenSSL.crypto.dump_privatekey(
OpenSSL.crypto.FILETYPE_PEM, key)
priv = serialization.load_pem_private_key(key_pem, None,
utils.get_backend())
mask = keys_basic.compute_key_mask(
priv.public_key().public_numbers().n)
keys_db.append(priv.public_key())
masks_db.append(mask)
masks_src.append(last_src_id)
src_names.append('ossl-%d' % args.ossl)
last_src_id += 1
# Load statistics
st = key_stats.KeyStats()
st.load_tables()
if args.verbose:
print('Source stats: ')
for src in st.sources_cn:
print(' %30s: %08d' % (src, st.sources_cn[src]))
print('Group stats:')
for grp in st.groups:
print(' %30s: %02d' % (grp, st.get_group_size(grp)))
# mask indices
mask_map, mask_max, mask_map_x, mask_map_y, mask_map_last_x, mask_map_last_y = keys_basic.generate_pubkey_mask_indices(
)
print('Max mask 1D config: [%d]' % mask_max)
print('Max mask 2D config: [%d, %d]' % (mask_map_last_x, mask_map_last_y))
# masks processing part
if len(masks_db) == 0:
return
# Simple match
if args.per_key_stat:
print('Per-key matching: ')
for idx, mask in enumerate(masks_db):
print('Key %02d, mask: %s' % (idx, mask))
res = []
for src in st.table_prob:
val = st.table_prob[src][mask]
res.append((src, val if val is not None else 0))
print_res(res, st)
# Total key matching
use_loglikelihood = True
print('Fit for all keys in one distribution:')
total_weights = src_total_match = comp_total_match_dict(
masks_db, st, loglikelihood=use_loglikelihood)
res = key_val_to_list(src_total_match)
print_res(res, st, loglikelihood=use_loglikelihood)
res = st.res_src_to_group(res)
# bar_chart(res=res, title='Fit for all keys')
# Avg + mean
print('Avg + mean:')
src_total_match = {} # source -> [p1, p2, p3, p4, ..., p_keynum]
for src in st.table_prob:
src_total_match[src] = []
for idx, mask in enumerate(masks_db):
val = keys_basic.aggregate_mask(st.sources_masks_prob[src], mask)
if use_loglikelihood:
if total_weights[src] is not None:
src_total_match[src].append(val + total_weights[src])
else:
src_total_match[src].append(-9999.9)
else:
src_total_match[src].append(val * total_weights[src])
pass
pass
res = []
devs = []
for src in st.sources:
m = np.mean(src_total_match[src])
s = np.std(src_total_match[src])
res.append((src, m))
devs.append(s)
# Total output
print_res(res, st, error=devs, loglikelihood=use_loglikelihood)
# bar_chart(res=res, error=devs, title='Avg for all keys + error')
# PCA on the keys - groups
keys_grp_vec = []
for idx, mask in enumerate(masks_db):
keys_grp_vec.append([])
for src in st.groups:
keys_grp_vec[idx].append(0)
for idxs, src in enumerate(st.sources):
grp = st.src_to_group(src)
prob = st.table_prob[src][mask]
keys_grp_vec[idx][st.get_group_idx(grp)] += prob
if args.pca_grp:
X = np.array(keys_grp_vec)
pca = PCA(n_components=2)
pca.fit(X)
X_transformed = pca.transform(X)
print('PCA mean: %s, components: ' % pca.mean_)
print(pca.components_)
masks_src_np = np.array(masks_src)
plt.rcdefaults()
colors = matplotlib.cm.rainbow(np.linspace(0, 1, last_src_id))
for src_id in range(0, last_src_id):
plt.scatter(X_transformed[masks_src_np == src_id, 0],
X_transformed[masks_src_np == src_id, 1],
label=src_names[src_id],
color=colors[src_id],
alpha=0.25,
marker=',')
plt.legend(loc="best", shadow=False, scatterpoints=1)
plt.show()
# Random subset
if args.subs:
masks_db_tup = []
for idx, mask in enumerate(masks_db):
masks_db_tup.append((idx, mask, masks_src[idx]))
# Many random subsets, top groups
subs_size = args.subs_k
subs_count = args.subs_n
groups_cnt = {}
subs_data = []
subs_data_mark = []
dsrc_num = last_src_id + 1
# Take subs_count samples fro the input masks_db, evaluate it, prepare for PCA
for i in range(0, subs_count):
masks = random_subset(masks_db_tup, subs_size)
src_total_match = comp_total_match_dict([x[1] for x in masks], st)
res = key_val_to_list(src_total_match)
total = 0.0
for tup in res:
total += tup[1]
# data vectors for PCA
tmp_data = []
for idx, tmp_src in enumerate(st.sources):
val = src_total_match[tmp_src]
val = long(math.floor(val * (1000.0 / total)))
tmp_data.append(val)
# PCA on groups.
# if want PCA on sources, use subs_data.append(tmp_data)
subs_data.append(tmp_data)
# res_grp_val = st.res_src_to_group(zip(st.sources, tmp_data))
# subs_data.append([x[1] for x in res_grp_val])
subs_dsources = {}
max_dsrc = (0, 0)
for dsrc in [x[2] for x in masks]:
if dsrc not in subs_dsources:
subs_dsources[dsrc] = 0
subs_dsources[dsrc] += 1
for dsrc in subs_dsources:
if subs_dsources[dsrc] > max_dsrc[1]:
max_dsrc = (dsrc, subs_dsources[dsrc])
tmp_mark = max_dsrc[0]
if max_dsrc[1] == subs_size:
tmp_mark = max_dsrc[0]
else:
tmp_mark = last_src_id
subs_data_mark.append(tmp_mark)
for tup in res:
src = tup[0]
score = long(math.floor(tup[1] * (1000.0 / total)))
if score == 0:
continue
grp = st.src_to_group(src)
if grp not in groups_cnt:
groups_cnt[grp] = score
else:
groups_cnt[grp] += score
if src not in groups_cnt:
groups_cnt[src] = score
else:
groups_cnt[src] += score
# Equalize group sizes
for grp in st.groups:
grp = grp.lower()
if grp in groups_cnt:
groups_cnt[grp] /= float(st.get_group_size(grp))
# best group only
# best_src = res[0][0]
# best_grp = st.src_to_group(best_src)
# if best_grp not in groups_cnt:
# groups_cnt[best_grp] = 1
# else:
# groups_cnt[best_grp] += 1
print('Combinations: (N, k)=(%d, %d) = %d' %
(subs_count, subs_size, scipy.misc.comb(subs_count, subs_size)))
sources = st.groups
values = []
for source in sources:
val = groups_cnt[source] if source in groups_cnt else 0
values.append(val)
bar_chart(sources,
values,
xlabel='# of occurrences as top group (best fit)',
title='Groups vs. %d random %d-subsets' %
(subs_count, subs_size))
# PCA stuff
X = np.array(subs_data)
pca = PCA(n_components=2)
pU, pS, pV = pca._fit(X)
X_transformed = pca.transform(X)
subs_data_mark_pca = np.array(subs_data_mark)
print('Sources: ')
print(st.sources)
print('PCA input data shape %d x %d' %
(len(subs_data), len(subs_data[0])))
print('PCA mean: \n%s \nPCA components: \n' % pca.mean_)
print(pca.components_)
print('PCA components x: ')
for x in pca.components_[0]:
print x
print('\nPCA components y: ')
for y in pca.components_[1]:
print y
# print('\nPCA U,S,V')
# print(pU)
# print(pS)
# print(pV)
colors = ['blue', 'red', 'green', 'gray', 'yellow']
plt.rcdefaults()
for src_id in range(0, dsrc_num):
plt.scatter(X_transformed[subs_data_mark_pca == src_id, 0],
X_transformed[subs_data_mark_pca == src_id, 1],
color=colors[src_id],
alpha=0.5 if src_id < dsrc_num - 1 else 0.2)
plt.legend(loc="best", shadow=False, scatterpoints=1)
# plt.scatter([x[0] for x in X_transformed],
# [x[1] for x in X_transformed],
# alpha=0.5)
plt.show()
# PCA against defined sources with known distributions?
# Creates "background distribution" we want to match to
if args.pca_src:
# Four axes, returned as a 2-d array
plt.rcdefaults()
#f, axarr = plt.subplots(len(st.sources), 1)
src_k = args.pca_src_k
src_n = args.pca_src_n
# prepare PDF
ppdf = PdfPages('test.pdf') # todo-filenae-from-set
sources_to_test = st.sources[20:25] + [
x for x in st.sources if 'micro' in x.lower()
]
# compute for each source
src_mark_idx = len(subs_data_mark)
subs_data_src = subs_data
subs_data_mark_src = subs_data_mark
for src_idx, source in enumerate(sources_to_test):
# cur_plot = axarr[src_idx]
cur_plot = plt
print('Plotting PCA source %s %d/%d' %
(source, src_idx + 1, len(sources_to_test)))
# Extend subs_data_src with draws from the source distribution
for i in range(0, src_n):
masks = []
for tmpk in range(0, src_k):
masks.append(st.sample_source_distrib(source))
src_total_match = comp_total_match_dict(masks, st)
res = key_val_to_list(src_total_match)
total = 0.0
for tup in res:
total += tup[1]
# data vectors for PCA
tmp_data = []
for idx, tmp_src in enumerate(st.sources):
val = src_total_match[tmp_src]
val = long(math.floor(val * (1000.0 / total)))
tmp_data.append(val)
# PCA on groups.
# if want PCA on sources, use subs_data.append(tmp_data)
subs_data_src.append(tmp_data)
subs_data_mark_src.append(src_mark_idx)
# PCA stuff
X = np.array(subs_data_src)
pca = PCA(n_components=2)
pU, pS, pV = pca._fit(X)
X_transformed = pca.transform(X)
subs_data_mark_pca = np.array(subs_data_mark_src)
colors = ['blue', 'red', 'green', 'gray', 'yellow']
# plot input sources
for src_id in range(0, dsrc_num):
cur_plot.scatter(
X_transformed[subs_data_mark_pca == src_id, 0],
X_transformed[subs_data_mark_pca == src_id, 1],
color=colors[src_id],
alpha=0.5 if src_id < dsrc_num - 1 else 0.2)
# plot the source stuff
cur_plot.scatter(
X_transformed[subs_data_mark_pca == src_mark_idx, 0],
X_transformed[subs_data_mark_pca == src_mark_idx, 1],
color='gray',
marker='+',
alpha=0.05)
cur_plot.legend(loc="best", shadow=False, scatterpoints=1)
cur_plot.title('Src [%s] input: %s' % (source,
(', '.join(src_names))))
cur_plot.savefig(ppdf, format='pdf')
cur_plot.clf()
print('Finalizing PDF...')
# plt.savefig(ppdf, format='pdf')
ppdf.close()
pass
if args.distrib:
# Plotting distributions for groups, to the PDF
plt.rcdefaults()
ppdf = PdfPages('groups_distrib.pdf')
# Compute for each source
range_ = st.masks
range_idx = np.arange(len(st.masks))
for grp_idx, grp in enumerate(st.groups):
cur_data = st.groups_masks_prob[grp]
raw_data = [cur_data[x] for x in st.masks]
cur_plot = plt
logger.debug('Plotting distribution %02d/%02d : %s ' %
(grp_idx + 1, len(st.groups), grp))
axes = cur_plot.gca()
axes.set_xlim([0, len(st.masks)])
cur_plot.bar(range_idx, raw_data, linewidth=0, width=0.4)
cur_plot.title('%s (%s)' % (grp, get_group_desc(grp, st)))
cur_plot.savefig(ppdf, format='pdf')
cur_plot.clf()
# Print input data - per source
max_src = max(masks_src)
bars = []
for src_id in range(max_src + 1):
axes = plt.gca()
axes.set_xlim([0, len(st.masks)])
map_data = {}
for mask in st.masks:
map_data[mask] = 0.0
for mask_idx, mask in enumerate(masks_db):
if masks_src[mask_idx] == src_id:
map_data[mask] += 1
raw_data = []
for mask in st.masks:
raw_data.append(map_data[mask])
b1 = plt.bar(range_idx, raw_data, linewidth=0, width=0.4)
bars.append(b1)
plt.title('Source %d' % src_id)
plt.savefig(ppdf, format='pdf')
plt.clf()
# Group distribution + source:
if args.distribmix:
width = 0.25
range_idx = np.arange(len(st.masks))
# One source to the graph
max_src = max(masks_src)
cur_plot = plt
for src_id in range(max_src + 1):
bars = []
logger.debug('Plotting mix distribution src %d ' % src_id)
map_data = {}
for mask in st.masks:
map_data[mask] = 0.0
for mask_idx, mask in enumerate(masks_db):
if masks_src[mask_idx] == src_id:
map_data[mask] += 1
raw_data = []
for mask in st.masks:
raw_data.append(map_data[mask])
raw_data = np.array(raw_data)
raw_data /= float(sum(raw_data))
for grp_idx, grp in enumerate(st.groups):
logger.debug(
' - Plotting mix distribution %02d/%02d : %s ' %
(grp_idx + 1, len(st.groups), grp))
# Source
fig, ax = plt.subplots()
b1 = ax.bar(range_idx + width,
raw_data,
linewidth=0,
width=width,
color='r')
bars.append(b1)
# Group
cur_data2 = st.groups_masks_prob[grp]
raw_data2 = [cur_data2[x] for x in st.masks]
bar1 = ax.bar(range_idx,
raw_data2,
linewidth=0,
width=width,
color='b')
bars.append(bar1)
ax.legend(tuple([x[0] for x in bars]),
tuple(['Src %d' % src_id, grp]))
ax.set_xlim([0, len(st.masks)])
cur_plot.title('%s + source %d' % (grp, src_id))
cur_plot.savefig(ppdf, format='pdf')
cur_plot.clf()
logger.info('Finishing PDF')
ppdf.close()
pass
if args.mixture:
# http://www.pymix.org/pymix/index.php?n=PyMix.Tutorial#bayesmix
# 1. Create mixture model = add discrete distributions to the package
dists = []
alphabet = mixture.Alphabet(st.masks)
taken_src = []
for src in st.sources:
if 'openssl 1.0.2g' == src or 'microsoft .net' == src:
pass
else:
continue
print(' - Source: %s' % src)
taken_src.append(src)
probs = []
for m in st.masks:
probs.append(st.sources_masks_prob[src][m])
d = mixture.DiscreteDistribution(len(alphabet),
probs,
alphabet=alphabet)
dists.append(d)
# 2. Create the model, for now, with even distribution among components.
comp_weights = [1.0 / len(dists)] * len(dists)
mmodel = mixture.MixtureModel(len(dists), comp_weights, dists)
print '-' * 80
print mmodel
print '-' * 80
# dump mixtures to the file
mixture.writeMixture(mmodel, 'src.mix')
# 3. Input data - array of input masks
masks_data = [[x] for x in masks_db]
data = mixture.DataSet()
data.fromList(masks_data)
data.internalInit(mmodel)
print masks_data
print data
print '---------'
# 4. Compute EM
# if there is a distribution in the input data which has zero matching inputs,
# an exception will be thrown. Later - discard such source from the input...
print mmodel.modelInitialization(data, 1)
print('EM start: ')
ress = []
for r in range(10):
mmodel.modelInitialization(data, 1)
emres = mmodel.EM(data, 1000, 0.00000000000000001)
ress.append(emres)
emres = max(ress, key=lambda x: x[1])
# print mmodel.randMaxEM(data, 10, 40, 0.1)
print emres
# Plot
plt.rcdefaults()
# plt.plot(range(0, len(emres[0][3])), [2.71828**x for x in emres[0][3]], 'o')
# plt.plot(range(0, len(emres[0][3])), emres[0][3], 'k')
# plt.show()
for i in range(0, 5):
print('-------')
for idx, src in enumerate(emres[0]):
print('- i:%02d src: %02d, val: %s' % (i, idx, src[i]))
colors = matplotlib.cm.rainbow(np.linspace(0, 1, len(taken_src)))
range_ = range(0, len(emres[0][0]))
bars = []
for idx, src in enumerate(emres[0]):
b1 = plt.bar(range_, [2.71828**x for x in src], color=colors[idx])
bars.append(b1)
plt.legend(tuple(bars), tuple(taken_src))
plt.grid(True)
plt.show()
# for src in emres[0]:
# plt.plot(range(0, len(src)), [2.71828**x for x in src], 'o')
# # plt.grid(True)
# # plt.show()
#
# # plt.scatter(mask_map_last_x, mask_map_last_y, c='red', s=scale, alpha=0.3)
# # plt.legend()
# plt.grid(True)
# plt.show()
# Chisquare
for source in st.sources_masks:
cn = st.sources_cn[source]
# chi = chisquare()
# gen = keys_basic.generate_pubkey_mask()
# 2D Key plot
if args.plot_key_dist:
plot_key_mask_dist(masks_db, st)
def clustering(k, feature_cols, feature_domains, header, table, seeds,
result_file):
best_loglike = None
best_model = None
# Giant random seeding loop,
data = mx.DataSet()
data.fromArray(table)
for r in range(1):
# weights = np.random.random_sample(k)
# weights_norm = weights / sum(weights)
weights_norm = [1.0 / k] * k
components = []
for i in range(k):
products = []
for j in range(table.shape[1]):
col_type = prep.get_col_type(feature_cols[j], header)
col_id = feature_cols[j]
if col_type == 'cat':
vals = feature_domains[col_id].keys()
cnt_vals = len(vals)
rand_dist = np.random.random_sample(cnt_vals)
dist = mx.DiscreteDistribution(cnt_vals,
rand_dist / sum(rand_dist),
mx.Alphabet(vals))
elif col_type == 'num':
min_val = feature_domains[col_id]['min']
max_val = feature_domains[col_id]['max']
# mean = random.uniform(min_val, max_val)
mean = seeds[header[col_id][0]][i]
stdev = (max_val - min_val) / 2.0 / k
dist = mx.NormalDistribution(mean, stdev)
else:
sys.exit(1)
products.append(dist)
comp = mx.ProductDistribution(products)
components.append(comp)
mix_table = mx.MixtureModel(k, weights_norm, components)
print mix_table
#loglike = mix_table.randMaxEM(data,1,50,50)
#print loglike
#print mix_table
if not best_loglike or loglike > best_loglike:
# best_loglike = loglike
best_model = copy.copy(mix_table)
#data.internalInit(mix)
# mix_table.modelInitialization(data)
# print best_loglike
# print best_model
labels = best_model.classify(data, None, None, 1)
## output clustering results
# count cluster sizes on sampled data
f = open(result_file + '.stats', 'w')
cnt = {}
for l in labels:
cnt[l] = 1 if l not in cnt else cnt[l] + 1
for l in cnt:
f.write('%s %d %f%%\n' %
(l, cnt[l], cnt[l] * 100.0 / sum(cnt.values())))
f.close()
mx.writeMixture(best_model, result_file + '.model')
return best_model
