def main():
args = getargv()
#quantify output
matrix_map = map.map(args['fi'])
matrix_inten_Top = TopInten(matrix_map, args['method'], args['n'],
args['rank'])
tag = args['method'] + '_' + str(args['n']) + '_' + args['rank']
writematrix(matrix_inten_Top, args, tag)
#probe information
probe_fo = args['fopath'] + args[
'label'] + '_probe_information.txt' if 'label' in args else args[
'fopath'] + 'probe_information.txt'
annot_dir = probe(matrix_map, probe_fo)
annot_file = args['fopath'] + args[
'label'] + '_annotation.txt' if 'label' in args else args[
'fopath'] + 'annotation.txt'
label = args['label'] if 'label' in args else ''
annotate(annot_dir, annot_file, label)
print('Done!')
def main():
# parse command
command_log = 'CIRCexplorer parameters: ' + ' '.join(sys.argv)
if len(sys.argv) == 1:
sys.exit(help_doc)
elif sys.argv[1] == '--version' or sys.argv[1] == '-v':
sys.exit(__version__)
elif sys.argv[1] == 'align':
import align
align.align(docopt(align.__doc__, version=__version__),
command=command_log,
name='align')
elif sys.argv[1] == 'parse':
import parse
parse.parse(docopt(parse.__doc__, version=__version__),
command=command_log,
name='parse')
elif sys.argv[1] == 'annotate':
import annotate
annotate.annotate(docopt(annotate.__doc__, version=__version__),
command=command_log,
name='annotate')
elif sys.argv[1] == 'assemble':
import assemble
assemble.assemble(docopt(assemble.__doc__, version=__version__),
command=command_log,
name='assemble')
elif sys.argv[1] == 'denovo':
import denovo
denovo.denovo(docopt(denovo.__doc__, version=__version__),
command=command_log,
name='denovo')
else:
sys.exit(help_doc)
def test_annotate():
path = 'images/for_compression/marmite_500x500.jpg'
path_annotated = 'images/for_compression/marmite_500x500_annotated.jpg'
copyfile(path, path_annotated)
annotate(path_annotated, terms=10, compression=12.2, fontsize=30)
assert os.path.exists(path_annotated)
os.remove(path_annotated)
def main():
# parse command
command_log = 'CIRCexplorer parameters: ' + ' '.join(sys.argv)
if len(sys.argv) == 1:
sys.exit(help_doc)
elif sys.argv[1] == '--version' or sys.argv[1] == '-v':
sys.exit(__version__)
elif sys.argv[1] == 'align':
import align
align.align(docopt(align.__doc__, version=__version__),
command=command_log, name='align')
elif sys.argv[1] == 'parse':
import parse
parse.parse(docopt(parse.__doc__, version=__version__),
command=command_log, name='parse')
elif sys.argv[1] == 'annotate':
import annotate
annotate.annotate(docopt(annotate.__doc__, version=__version__),
command=command_log, name='annotate')
elif sys.argv[1] == 'assemble':
import assemble
assemble.assemble(docopt(assemble.__doc__, version=__version__),
command=command_log, name='assemble')
elif sys.argv[1] == 'denovo':
import denovo
denovo.denovo(docopt(denovo.__doc__, version=__version__),
command=command_log, name='denovo')
else:
sys.exit(help_doc)
def start():
setgx(newgx())
print '*** SHED SKIN Python-to-C++ Compiler 0.7.1 ***'
print 'Copyright 2005-2010 Mark Dufour; License GNU GPL version 3 (See LICENSE)'
print
# --- some checks
major, minor = sys.version_info[:2]
if (major, minor) not in [(2, 4), (2, 5), (2, 6), (2, 7)]:
print '*ERROR* Shed Skin is not compatible with this version of Python'
sys.exit(1)
if sys.platform == 'win32' and os.path.isdir('c:/mingw'):
print '*ERROR* please rename or remove c:/mingw, as it conflicts with Shed Skin'
sys.exit()
# --- command-line options
try:
opts, args = getopt.getopt(sys.argv[1:], 'vbchef:wad:m:rolsp', ['help', 'extmod', 'nobounds', 'nowrap', 'flags=', 'dir=', 'makefile=', 'random', 'noassert', 'long', 'msvc', 'ann', 'strhash', 'iterations=', 'pypy'])
except getopt.GetoptError:
usage()
for o, a in opts:
if o in ['-h', '--help']: usage()
if o in ['-b', '--nobounds']: getgx().bounds_checking = False
if o in ['-e', '--extmod']: getgx().extension_module = True
if o in ['-a', '--ann']: getgx().annotation = True
if o in ['-d', '--dir']: getgx().output_dir = a
if o in ['-l', '--long']: getgx().longlong = True
if o in ['-w', '--nowrap']: getgx().wrap_around_check = False
if o in ['-r', '--random']: getgx().fast_random = True
if o in ['-o', '--noassert']: getgx().assertions = False
if o in ['-p', '--pypy']: getgx().pypy = True
if o in ['-m', '--makefile']: getgx().makefile_name = a
if o in ['-s', '--strhash']: getgx().fast_hash = True
if o in ['-v', '--msvc']: getgx().msvc = True
if o in ['-i', '--iterations']: getgx().max_iterations = int(a)
if o in ['-f', '--flags']:
if not os.path.isfile(a):
print "*ERROR* no such file: '%s'" % a
sys.exit(1)
getgx().flags = a
# --- argument
if len(args) != 1:
usage()
name = args[0]
if not name.endswith('.py'):
name += '.py'
if not os.path.isfile(name):
print "*ERROR* no such file: '%s'" % name
sys.exit(1)
getgx().main_mod = name[:-3]
# --- analyze & annotate
infer.analyze(name)
annotate.annotate()
cpp.generate_code()
shared.print_errors()
def plotMap(im, vmin=0,vmax=1, cmap='bwr', nocbar=False, title=None,
freqmask=slice(0,2**63-1)):
#see http://matplotlib.org/1.4.2/mpl_toolkits/axes_grid/users/overview.html
pylab.figure(figsize=(16,12))
axmap = pylab.subplot(111)
divider = make_axes_locatable(axmap)
if not nocbar:
cax = divider.append_axes("right", size="5%", pad=0.5)
axins = divider.append_axes("left", size=0.5, pad=0.5, sharey=axmap)
axdel = divider.append_axes("left", size=0.5, pad=0.15, sharey=axmap)
axunr = divider.append_axes("left", size=0.5, pad=0.15, sharey=axmap)
im = axmap.imshow(im, origin='lower', extent=(+0.5,L+0.5,+0.5,L+0.5),
interpolation='nearest', cmap=cmap,
vmin=vmin, vmax=vmax, aspect='equal')
annotate(regions, lobediv, L, axmap)
axmap.set_aspect(1)
cbar = None
if not nocbar:
cbar = pylab.colorbar(im, cax=cax)
if title:
axmap.set_title(title)
def wmean(s):
num = sum((s*weights[:,newaxis])[freqmask], axis=0)
return num/sum(freqweights[freqmask])
#axins.barh(arange(L)+1, wmean(inserts), height=1, color='gray', ec='none')
#axins.set_xlim(0,6)
#axins.set_xticks([0,3,6])
#axins.invert_xaxis()
#axins.text(6*0.9, 1, 'Mean Number of Insertions', rotation='vertical',
# verticalalignment='bottom')
#pylab.setp(axins.get_yticklabels(), visible=False)
#axdel.barh(arange(L)+1, wmean(deletes), height=1, color='gray', ec='none')
#axdel.set_xlim(0,1)
#axdel.set_xticks([0,1])
#axdel.invert_xaxis()
#axdel.text(0.9, 1, 'Frequency of Deletions', rotation='vertical',
# verticalalignment='bottom')
#pylab.setp(axdel.get_yticklabels(), visible=False)
#axunr.barh(arange(L)+1, wmean(unresolveds), height=1,
# color='gray', ec='none')
#axunr.set_xlim(0,1)
#axunr.set_xticks([0,1])
#axunr.invert_xaxis()
#axunr.text(0.9, 1, 'Frequency of Unresolved', rotation='vertical',
# verticalalignment='bottom')
#pylab.setp(axunr.get_yticklabels(), visible=False)
#axmap.set_yticks(axmap.get_xticks())
axmap.set_xlim(0.5,L+0.5)
axmap.set_ylim(0.5,L+0.5)
return axmap, axins, axdel, cbar
def start(gx, main_module_name):
# --- analyze & annotate
t0 = time.time()
analyze(gx, main_module_name)
annotate(gx)
generate_code(gx)
print_errors()
logging.info('[elapsed time: %.2f seconds]', (time.time() - t0))
def start(gx, main_module_name):
# --- analyze & annotate
t0 = time.time()
analyze(gx, main_module_name)
annotate(gx)
generate_code(gx)
print_errors()
logging.info('[elapsed time: %.2f seconds]', (time.time() - t0))
def start(gx, main_module_name):
# --- analyze & annotate
t0 = time.time()
analyze(gx, main_module_name)
annotate(gx)
generate_code(gx)
print_errors()
if not gx.silent:
print '[elapsed time: %.2f seconds]' % (time.time() - t0)
def main():
setgx(newgx())
print '*** SHED SKIN Python-to-C++ Compiler 0.5 ***'
print 'Copyright 2005-2010 Mark Dufour; License GNU GPL version 3 (See LICENSE)'
print
# --- some checks
major, minor = sys.version_info[:2]
if (major, minor) not in [(2, 4), (2, 5), (2, 6)]:
print '*ERROR* Shed Skin is not compatible with this version of Python'
sys.exit(1)
if sys.platform == 'win32' and os.path.isdir('c:/mingw'):
print '*ERROR* please rename or remove c:/mingw, as it conflicts with Shed Skin'
sys.exit()
# --- command-line options
try:
opts, args = getopt.getopt(sys.argv[1:], 'vbchef:wad:m:rl', [
'extmod', 'nobounds', 'nowrap', 'flags=', 'dir=', 'makefile=',
'random', 'long', 'msvc'
])
except getopt.GetoptError:
usage()
for o, a in opts:
if o in ['-h', '--help']: usage()
if o in ['-b', '--nobounds']: getgx().bounds_checking = False
if o in ['-e', '--extmod']: getgx().extension_module = True
if o in ['-a', '--ann']: getgx().annotation = True
if o in ['-d', '--dir']: getgx().output_dir = a
if o in ['-l', '--long']: getgx().longlong = True
if o in ['-w', '--nowrap']: getgx().wrap_around_check = False
if o in ['-r', '--random']: getgx().fast_random = True
if o in ['-m', '--makefile']: getgx().makefile_name = a
if o in ['-v', '--msvc']: getgx().msvc = True
if o in ['-f', '--flags']:
if not os.path.isfile(a):
print "*ERROR* no such file: '%s'" % a
sys.exit(1)
getgx().flags = a
# --- argument
if len(args) != 1:
usage()
name = args[0]
if not name.endswith('.py'):
name += '.py'
if not os.path.isfile(name):
print "*ERROR* no such file: '%s'" % name
sys.exit(1)
getgx().main_mod = name[:-3]
# --- analyze & annotate
infer.analyze(name)
annotate.annotate()
cpp.generate_code()
def test_annotate(self):
self.assertEqual(
self.createSetFromString(
annotate.annotate(
"SEM:TRA(0:) SEM:TRA(1:) SEM:TRA(1:) SEM:TRA(1:)",
"漢 漢10漢", "漢 漢 10 漢")),
self.createSetFromString("0-0[sure] 1-1[sure]"))
self.assertEqual(
self.createSetFromString(
annotate.annotate(
"SEM:TRA(0:) GIS:DEM(1:) GIS:DEM(1:) GIS:DEM(1:)",
"漢 漢10漢", "漢 漢 10 漢")),
self.createSetFromString("0-0[sure] 1-1[possible]"))
def generate_features(thread, postNum):
dataset = Dataset('convinceme',annotation_list=['topic'])
directory = "{}/convinceme/output_by_thread".format(data_root_dir)
topic = dataset.discussion_annotations[int(thread)]['topic']
discussion = dataset.load_discussion(thread)
post = discussion.posts[int(postNum)]
try:
post.loadPostStruct({"site": "/convinceme", "thread": int(thread)})
text = post.pst.text
except:
text = post.text.replace('\r', '')
try:
parent = discussion.posts[int(post.parent_id)]
parentText = parent.text
parentAuthor = parent.author
parentSide = parent.side
parentId = "<a href=\"?thread=%s&post=%s\">[see post]</a>" % (thread, post.parent_id)
except:
parentText = "No parent"
parentAuthor = parentSide = parentId = ""
author = post.author
side = post.side
try:
tups = tuples[thread][postNum][:-1] #lose the last one because of an odd spurious bound
except KeyError:
tups = []
for tup in tups:
tup[-1] = tup[-1].replace(' ', '_')
try:
annotatedText = annotate.annotate(text, tups)
return produceHTML(author, side, tups, parentId, parentText, parentAuthor, parentSide, annotatedText)
except:
pdb.set_trace()
return ""
def extractTranscriptAndConcepts(self, video_path, ocr_on):
aux = ""
f2 = open(video_path + "transcript/transcript" + str(self.id) + ".txt")
a = f2.read()
words = tokenize.word_tokenize(a, language='english')
words = [word.lower() for word in words if word.isalpha()]
transcript = ' '.join(words)
if not transcript:
transcript = ''
self.transcript = transcript
f2.close()
if (ocr_on):
aux = ""
f2 = open(video_path + "slides/frameb" + str(self.id) + ".txt")
a = f2.read()
words = tokenize.word_tokenize(a, language='english')
words = [word.lower() for word in words if word.isalpha()]
ocr = ' '.join(words)
if not ocr:
ocr = ''
self.ocr = ocr
f2.close()
annotatedTerms = None
if (ocr_on):
annotatedTerms, depth = annotate.annotate(self.transcript,
self.ocr)
else:
annotatedTerms, depth = annotate.annotate(self.transcript,
self.transcript)
conceptNodeList = []
for j in range(len(annotatedTerms)):
conceptNodeList.append(Concept_Node(j, annotatedTerms[j],
depth[j]))
self.stopwords = []
self.conceptNodes = conceptNodeList
def test_annotate(self):
self.assertEqual(self.createSetFromString(annotate.annotate("SEM:TRA(0:) SEM:TRA(1:) SEM:TRA(1:) SEM:TRA(1:)", "漢 漢10漢", "漢 漢 10 漢")), self.createSetFromString("0-0[sure] 1-1[sure]"))
self.assertEqual(self.createSetFromString(annotate.annotate("SEM:TRA(0:) GIS:DEM(1:) GIS:DEM(1:) GIS:DEM(1:)", "漢 漢10漢", "漢 漢 10 漢")), self.createSetFromString("0-0[sure] 1-1[possible]"))
import pandas as pd
import annotate
import genome_browser
snap_data_notin_grasp = pd.read_csv('snap_data_notin_grasp.txt', sep='\t').rename(columns={'pos_hg38': 'pos', 'rsID': 'rsid'})
# remove protein-coding SNPs
annotate_ob = annotate.annotate(snap_data_notin_grasp, 'hg38')
snap_data_w_annot = annotate_ob.fast_annotate_snp_list()
snap_data_w_annot = snap_data_w_annot.loc[snap_data_w_annot['annotation'] != 'pcexon']
snap_data_w_annot = snap_data_w_annot.sort_values(['query_snp_rsid', 'rsid']).reset_index(drop=True)
snap_data_w_annot.to_csv('snap_data_w_annot.txt', sep='\t', index=False)
print('[INFO] snap_data_w_annot.txt saved!')
def annotate(cmdline):
from annotate import annotate
survey = model.survey.Survey.load(cmdline['project'])
return annotate(survey)
def annotate_command(options, command_log):
from annotate import annotate
options['--no-fix'] = False
options['--low-confidence'] = False
annotate(options, command=command_log, name='annotate')
def plotContacts(name):
# map from pdb seq index to structural index (ie, from seqres index, to
# resolved residue #)
pdbseq2structMap = indmaps[name]
fullalnseq = fullalnseqs[name] #seq after alignment
aln2fullalnMap = where([c.isupper() or c == '-' for c in fullalnseq])[0]
pdbseq2fullalnMap = where([c not in ".-" for c in fullalnseq])[0]
fullaln2pdbseqMap = -ones(len(fullalnseq), dtype=int)
fullaln2pdbseqMap[pdbseq2fullalnMap] = arange(len(pdbseq2fullalnMap))
aln2structMap = [
pdbseq2structMap[fullaln2pdbseqMap[i]]
if fullaln2pdbseqMap[i] != -1 else -1 for i in aln2fullalnMap
]
pdbseq = [x for x in fullalnseq if x not in ".-"]
alnseq = [x for x in fullalnseq if x not in "." and not x.islower()]
distances = load(os.path.join(distpath, name + '.npy'))
L = int(((1 + sqrt(1 + 8 * len(distances))) / 2) + 0.5)
stroke = PathEffects.withStroke(linewidth=3, foreground="w")
#form matrix
distancesM = zeros((L, L), dtype=float)
distancesM[triu_indices(L, k=1)] = distances
distancesM = distancesM + distancesM.T
########################################
# first, plot the raw contact map for the entire sequence
# that is, the contact map size will be equal to the length of the seqres
# header (minus junk) #shows inserts as red, missing residues as blue, and
# deletes as dotted lines (or colored lines?)
pylab.figure(figsize=(12, 12))
ax = pylab.axes()
trans = transforms.blended_transform_factory(ax.transAxes, ax.transData)
sL = len(pdbseq2structMap)
pairs = ((i, j) for i in range(sL - 1) for j in range(i + 1, sL))
distmat = zeros((sL, sL)) * nan
for n, (i, j) in enumerate(pairs):
if pdbseq2structMap[i] == -1 or pdbseq2structMap[j] == -1:
continue
distmat[i, j] = distancesM[pdbseq2structMap[i], pdbseq2structMap[j]]
distmat[j, i] = distancesM[pdbseq2structMap[j], pdbseq2structMap[i]]
contacts = distmat < cutoff
contacts[diag([i != -1 for i in pdbseq2structMap])] = True
cim = ones(distmat.shape + (3, ))
cim[contacts] = ones(3) * 0.4
pylab.imshow(cim,
origin='lower',
extent=(+0.5, sL + 0.5, +0.5, sL + 0.5),
interpolation='nearest')
#annotate inserts relative to alignment (red)
inserts = where([c.islower() for c in pdbseq])[0]
fillGroups(inserts, sL, (0.7, 0.4, 0.4, 0.3))
#annotate missign residues (blue)
missing = where([i == -1 for i in pdbseq2structMap])[0]
fillGroups(missing, sL, (0.4, 0.4, 0.7, 0.3))
#map from alignment index to *closest* pdb seq index
def remap(i, s):
return searchsorted(pdbseq2fullalnMap, aln2fullalnMap[i], side=s)
#annotate regions
xregions = [(n, remap(s, 'left'), remap(e - 1, 'left') + 1)
for n, s, e in regions]
annotate(xregions, remap(lobediv, 'left'), sL, pylab.gca(), zorder=1)
#plot lines at deletion points (green)
deletepos = searchsorted(pdbseq2fullalnMap,
where([x == '-' for x in fullalnseq])[0])
#for d in set(deletepos):
# pylab.axvline(d+0.5, color='g', zorder=9)
# pylab.axhline(d+0.5, color='g', zorder=9)
transY = transforms.blended_transform_factory(ax.transAxes, ax.transData)
altern = False
for d, g in groupby(deletepos):
pylab.axvline(d + 0.5, color='g', zorder=9)
pylab.axhline(d + 0.5, color='g', zorder=9)
pylab.text(0.005 + altern * 0.01,
d + 0.5,
str(len(list(g))),
verticalalignment='center',
horizontalalignment='right',
transform=transY,
path_effects=[stroke],
color='g',
zorder=100)
altern = not altern
#plot seqeunce
altern = 0
for n, c in enumerate(pdbseq):
pylab.text(1.02 + altern * 0.014,
n + 1,
c,
verticalalignment='center',
horizontalalignment='center',
transform=transY,
zorder=100)
altern = (altern + 1) % 6
#plot dotted line around alignment region
start = remap(0, 'left') - 0.5
end = remap(-1, 'right') + 1.5
pylab.fill([start, start, end, end], [start, end, end, start],
fill=False,
ls='dashed',
zorder=10)
pylab.title(name + ", full PDB sequence ({}A)".format(cutoff))
pylab.subplots_adjust(bottom=0.05, right=0.90, top=0.95, left=0.05)
########################################
#next, plot just the aligned part
pylab.figure(figsize=(12, 12))
ax = pylab.axes()
trans = transforms.blended_transform_factory(ax.transAxes, ax.transData)
aL = len(aln2fullalnMap)
#first, get the aligned distance map
#need map from aln index to structure index
adistmat = zeros((aL, aL)) * nan
for i, j in [(i, j) for i in range(aL - 1) for j in range(i + 1, aL)]:
xi = aln2structMap[i]
xj = aln2structMap[j]
if xi == -1 or xj == -1:
continue
adistmat[i, j] = distancesM[xi, xj]
adistmat[j, i] = distancesM[xi, xj]
#set diagonal for aligned residues
for i in range(aL):
if aln2structMap[i] != -1:
adistmat[i, i] = 0
acontacts = adistmat < cutoff
acim = ones(adistmat.shape + (3, ))
acim[acontacts] = ones(3) * 0.4
pylab.imshow(acim,
origin='lower',
extent=(+0.5, aL + 0.5, +0.5, aL + 0.5),
interpolation='nearest')
#plot unresolved and deleted regions
unresolved = where([aln2structMap[n] == -1 for n in range(len(alnseq))])[0]
fillGroups(unresolved, aL, (0.4, 0.4, 0.7, 0.3))
deleted = where([c == '-' for c in alnseq])[0]
fillGroups(deleted, aL, (0.4, 0.7, 0.4, 0.3))
with open(os.path.join(outpath, 'unresolvedCounts'), 'at') as f:
print(repr((name, list(unresolved))), file=f)
with open(os.path.join(outpath, 'deleteCounts'), 'at') as f:
print(repr((name, list(deleted))), file=f)
#plot insertions (lines, red)
insertpos = searchsorted(aln2fullalnMap,
where([x.islower() for x in fullalnseq])[0])
#for d in set(insertpos):
# pylab.axvline(d+0.5, color='r', zorder=9)
# pylab.axhline(d+0.5, color='r', zorder=9)
transY = transforms.blended_transform_factory(ax.transAxes, ax.transData)
altern = False
insertlist = [(d, len(list(g))) for d, g in groupby(insertpos)]
for d, n in insertlist[1:-1]: #first and last are just sequence extension
pylab.axvline(d + 0.5, color='r', zorder=9)
pylab.axhline(d + 0.5, color='r', zorder=9)
pylab.text(0.005 + altern * 0.01,
d + 0.5,
str(n),
verticalalignment='center',
horizontalalignment='right',
transform=transY,
path_effects=[stroke],
color='r',
zorder=100)
altern = not altern
with open(os.path.join(outpath, 'insertCounts'), 'at') as f:
print(repr((name, insertlist)), file=f)
#annotate regions
annotate(regions, lobediv, aL, pylab.gca())
pylab.title(name + ", aligned sequence only ({}A)".format(cutoff))
pylab.subplots_adjust(bottom=0.05, right=0.90, top=0.95, left=0.05)
return adistmat
import annotate
import pandas as pd
# annotate SNPs in GRASP database
grasp_sub = pd.read_csv("grasp_sub.txt",
sep="\t",
converters={
"PMID": str,
"NHLBIkey": str
}).rename(columns={
'chr(hg19)': 'chr',
'pos(hg19)': 'pos'
})
annotate_ob = annotate.annotate(grasp_sub, 'hg19')
grasp_sub_w_annot = annotate_ob.fast_annotate_snp_list()
grasp_sub_w_annot = grasp_sub_w_annot.sort_values(["ID"
]).reset_index(drop=True)
grasp_sub_w_annot.to_csv("grasp_sub_w_annot.txt", sep="\t", index=False)
print("[INFO] save to grasp_sub_w_annot.txt")
def annotate(args):
import annotate
annotate.annotate(args)
def annotate(cmdline):
from annotate import annotate
survey = model.survey.Survey.load(cmdline['project'])
return annotate(survey)
def SCanalysis(Ur, I, m, S, text1, text2, text3, text4, text5, files,
dataFunct, LimUr, LimUc, pf1, pf2):
"""
SCanalysis Calculate supercapacitor capacitance and equivalent serial resistance
SCanalysis(I,Ur,m,S,'text1','text2','text3','text4','text5',files,[Ur1 Ur2],[Uc1 Uc2],pf1,pf2)
Parameters:
Ur[V] - Nominal voltage (to which SC is charged)
I [mA] - Discharge current
a) Scalar (e.g.21.5) Analysis for single current is performed
b) Vector (e.g.[10 17.8 31.6 56.2 100]) Performs multi cycle - multi current analysis.
m[mg] - Mass of active material. Should be zero if not used.
S[cm2] - Area of one electrode. Should be zero if not used.
text1..text5 - Five comment lines that will be printed at plots
files - File name filter.Files that match the filter are sorted according to the file name.
Each file should contain data for one discharge cycle.
Care should be taken to ensure that sorting order corresponds to the cycles order,
e.g.name files as '17_04_25_Data_001.txt' ... '17_04_25_Data_100.txt'.In this case
'fnames' field should be set to *Data*.txt,where '*' matches any number of characters.
If vector of discharge currents is defined,files field should be defined as cell array,
having same number of elements as the I vector (and optionally one additional element),
where each element defines file name filter for corresponding current measurements,
e.g.: {‘I_15mA*.txt’ ‘I_22mA*.txt’}
If additional file is defined, it should contain repeated measurement for the first current.
Data from that file is shown with red cross at plots.
dataFunct - Handle of function for reading data from file. Function should accept two parameters,
file name and discharge current. If data contains measured current, discharge current
could be discarded. Function should return N-by-3 array, where first column contains
time in seconds, second voltage in volts and third current in amperes.
[Ur1 Ur2] - Resistance calculation start and end voltage.Voltage is specified as a percentage of
nominal voltage Ur,e.g.[0.9 0.7]. Straight-line approximation is applied to the discharge
curve between Ur1 and Ur2. Equivalent serial resistance is calculated from the voltage drop
at the discharge start time, which is the determined from the value of the straight line
at the discharge start time.
Special cases:
[1 t] - Ur1 is voltage at first sample after the discharge current was applied;
Ur2 is voltage t seconds later. 3rd order polynomial approximation is used to
determine the voltage drop at the discharge start time.
[Uc1 Uc2] - Capacitance calculation start and end voltage.Voltage is specified as a percentage
of nominal voltage Ur,e.g.[0.9 0.7].
Special cases:
[1 Uc2] - Uc1 is voltage at first sample after the discharge current was applied
[1 0] - Uc1 is voltage drop at the discharge start time,Uc2 is voltage of last
recorded discharge curve sample
pf1 - Plot Frequency. Discharge curve plot will be generated each pF1 cycles.
pf2 - Plot Frequency. Cumulative discharge curve plot will be generated and discharge curve will be
plotted each pf2 cycles.
Stored values (in file 'Results.mat'):
C - Capacitance
Cs_m - Specific capacitance per mass
Cs_a - Specific capacitance per area
R - Equivalent serial resistance
Rd - Discharge resistance,calculated from self-discharge curve during initial 5s rest period
nl - Discharge curve nonlinearity,calculated as mean square deviation from the ideal (linear)
discharge curve.
Pd - Specific power density, per mass.
E - Specific energy, per mass.
"""
############# ADD VALIDATION HERE
noCurrents = len(I) if type(I) is tuple else 1
noFileGroups = len(files) if type(files) is tuple else 1
# Determine number of cycles
f = glob.glob(files[0]) if type(files) is tuple else glob.glob(files)
noCycles = len(f)
if noCycles == 0:
print(
'No data files selected, check current folder and input number 10, files.'
)
return
# Prealocate result arrays
C = np.zeros((noCycles, noFileGroups))
Cs_m = np.zeros((noCycles, noFileGroups))
Cs_a = np.zeros((noCycles, noFileGroups))
R = np.zeros((noCycles, noFileGroups))
Rd = np.zeros((noCycles, noFileGroups))
nl = np.zeros((noCycles, noFileGroups))
Pd = np.zeros((noCycles, noFileGroups))
E = np.zeros((noCycles, noFileGroups))
# Currents
for fileIdx in range(noFileGroups):
if fileIdx < noCurrents: # if noFileGroups == noCurrents + 1, then measurement is repeated for the first current (repeatability)
I0 = I[fileIdx] if type(I) is tuple else I
fileSuffix = str(I0) + "_mA"
additionalCurrent = False
else: # repeated measurement for first current
I0 = I[0]
fileSuffix = str(I0) + "_mA_2nd"
additionalCurrent = True
# Replace '.' with '_'
fileSuffix = fileSuffix.replace('.', '_')
# File list
f = glob.glob(
files[fileIdx]) if type(files) is tuple else glob.glob(files)
if len(f) != noCycles:
raise ValueError(
"All currents should have the same number of cycles (" +
str(I0) + " mA: " + str(len(f)) + ", should be " +
str(noCycles))
f.sort() # sorted list of file names
for n in range(noCycles):
(c1, r1, rd1, nl1, pd,
e) = C_R.C_R(f[n], dataFunct, I0 / 1000, n + 1, noCycles, fileIdx,
noCurrents, LimUr, LimUc, pf1, pf2)
C[n, fileIdx] = c1
R[n, fileIdx] = r1
Rd[n, fileIdx] = rd1
nl[n, fileIdx] = nl1
Pd[n, fileIdx] = pd
E[n, fileIdx] = e
if m > 0:
Cs_m[:, fileIdx] = C[:, fileIdx] / (m / 1000) # mass in mg
Pd[:, fileIdx] = Pd[:, fileIdx] / (m / 1000)
E[:, fileIdx] = E[:, fileIdx] / (m / 1000)
if S > 0:
Cs_a[:, fileIdx] = C[:, fileIdx] / S
baseX = 0.7
baseY = 0.4
fontSize = 11
# CAPACITANCE PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(C[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Capacitance")
ax.set_xlabel("Cycle")
ax.set_ylabel("C[F]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_C_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
# ESR PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(R[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("ESR")
ax.set_xlabel("Cycle")
ax.set_ylabel("R[\u03A9]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_ESR_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
# SELF-DISCHARGE RESISTANCE PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(Rd[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Self-discharge resistance")
ax.set_xlabel("Cycle")
ax.set_ylabel("Rd[\u03A9]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_Rd_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
# DISCHARGE CURVE NON-LINEARITY PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(nl[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Discharge curve non-linearity")
ax.set_xlabel("Cycle")
ax.set_ylabel("MSE")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_Nl_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
# Cumulative discharge plot by currents
h = plt.figure(num=C_R.C_R.cumulativeDischargePlot.number)
plt.legend(loc='upper right')
plt.savefig(fname="_discharge_" + fileSuffix, dpi=300)
del C_R.C_R.cumulativeDischargePlot
if noCurrents > 1:
plt.close(h)
if m > 0:
# SPECIFIC CAPACITANCE PLOT (by mass)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(Cs_m[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Specific capacitance")
ax.set_xlabel("Cycle")
ax.set_ylabel("Cs_m[F/g]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Cs_m_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
# MAXIMUM POWER DENSITY PLOT (by mass)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(Pd[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Maximum power density")
ax.set_xlabel("Cycle")
ax.set_ylabel("Pdm[W/g]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Pdm_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
# ENERGY DENSITY PLOT (by mass)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(E[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Energy density")
ax.set_xlabel("Cycle")
ax.set_ylabel("Ed[J/g]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Ed_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
if S > 0:
# SPECIFIC CAPACITANCE PLOT (by area)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(Cs_a[:, fileIdx], 'b', linewidth=2)
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Specific capacitance")
ax.set_xlabel("Cycle")
ax.set_ylabel("Cs_a[F/cm\u00B2]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Cs_m_" + fileSuffix, dpi=300)
if noCurrents > 1:
plt.close(h)
# CURRENT INFLUENCE ANALYSIS
if noCurrents > 1:
baseX = 0.7
baseY = 0.4
fontSize = 11
# CAPACITANCE PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, C[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], C[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Capacitance")
ax.set_xlabel("I[mA]")
ax.set_ylabel("C[F]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_C", dpi=300)
# ESR PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, R[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], R[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("ESR")
ax.set_xlabel("I[mA]")
ax.set_ylabel("R[\u03A9]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_ESR", dpi=300)
# SELF-DISCHARGE RESISTANCE PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, Rd[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], Rd[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Self-discharge resistance")
ax.set_xlabel("I[mA]")
ax.set_ylabel("Rd[\u03A9]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_Rd", dpi=300)
# DISCHARGE CURVE NON-LINEARITY PLOT
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, nl[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], nl[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Discharge curve non-linearity")
ax.set_xlabel("I[mA]")
ax.set_ylabel("MSE")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1, text2,
text3, text4, text5)
plt.savefig(fname="_Nl", dpi=300)
if m > 0:
# SPECIFIC CAPACITANCE PLOT (by mass)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, Cs_m[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], Cs_m[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Specific capacitance")
ax.set_xlabel("I[mA]")
ax.set_ylabel("Cs_m[F/g]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Cs_m", dpi=300)
# MAXIMUM POWER DENSITY PLOT (by mass)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, Pd[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], Pd[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Maximum power density")
ax.set_xlabel("I[mA]")
ax.set_ylabel("Pdm[W/g]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Pdm", dpi=300)
if noCurrents > 1:
plt.close(h)
# ENERGY DENSITY PLOT (by mass)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, E[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], E[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Energy density")
ax.set_xlabel("I[mA]")
ax.set_ylabel("Ed[J/g]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Ed", dpi=300)
if noCurrents > 1:
plt.close(h)
if S > 0:
# SPECIFIC CAPACITANCE PLOT (by area)
h = plt.figure(figsize=[10, 6], dpi=96)
ax = h.add_subplot(1, 1, 1)
ax.plot(I, Cs_a[noCycles - 1, 0:noCurrents], 'b', linewidth=2)
if additionalCurrent:
ax.plot(I[0], Cs_a[noCycles - 1, noFileGroups - 1], 'rx')
bottom, top = plt.ylim()
plt.ylim(0, 1.05 * top)
ax.set_title("Specific capacitance")
ax.set_xlabel("I[mA]")
ax.set_ylabel("Cs_a[F/cm\u00B2]")
plt.grid(axis="both", color=(0.25, 0.25, 0.25), linestyle=':')
annotate.annotate(baseX, baseY, fontSize, I0, Ur, m, S, text1,
text2, text3, text4, text5)
plt.savefig(fname="_Cs_m", dpi=300)
if noCurrents > 1:
plt.close(h)
# Cumulative discharge plot
plt.figure(num=C_R.C_R.dischargeIplot.number)
plt.legend(loc='upper right')
plt.savefig(fname="_discharge_I_", dpi=300)
plt.show() # display all figures
def start():
setgx(newgx())
# --- command-line options
try:
opts, args = getopt.getopt(sys.argv[1:], 'vbchef:wad:m:rolspxngL:', [
'help', 'extmod', 'nobounds', 'nowrap', 'flags=', 'debug=',
'makefile=', 'random', 'noassert', 'long', 'msvc', 'ann',
'strhash', 'pypy', 'traceback', 'silent', 'nogcwarns', 'lib'
])
except getopt.GetoptError:
usage()
for o, a in opts:
if o in ['-h', '--help']: usage()
if o in ['-b', '--nobounds']: getgx().bounds_checking = False
if o in ['-e', '--extmod']: getgx().extension_module = True
if o in ['-a', '--ann']: getgx().annotation = True
if o in ['-d', '--debug']: getgx().debug_level = int(a)
if o in ['-l', '--long']: getgx().longlong = True
if o in ['-g', '--nogcwarns']: getgx().gcwarns = False
if o in ['-w', '--nowrap']: getgx().wrap_around_check = False
if o in ['-r', '--random']: getgx().fast_random = True
if o in ['-o', '--noassert']: getgx().assertions = False
if o in ['-p', '--pypy']: getgx().pypy = True
if o in ['-m', '--makefile']: getgx().makefile_name = a
if o in ['-n', '--silent']: getgx().silent = True
if o in ['-s', '--strhash']: getgx().fast_hash = True
if o in ['-v', '--msvc']: getgx().msvc = True
if o in ['-x', '--traceback']: getgx().backtrace = True
if o in ['-L', '--lib']: getgx().libdirs = [a] + getgx().libdirs
if o in ['-f', '--flags']:
if not os.path.isfile(a):
print "*ERROR* no such file: '%s'" % a
sys.exit(1)
getgx().flags = a
if not getgx().silent:
print '*** SHED SKIN Python-to-C++ Compiler 0.9.2 ***'
print 'Copyright 2005-2011 Mark Dufour; License GNU GPL version 3 (See LICENSE)'
print
# --- some checks
major, minor = sys.version_info[:2]
if (major, minor) not in [(2, 4), (2, 5), (2, 6), (2, 7)]:
print '*ERROR* Shed Skin is not compatible with this version of Python'
sys.exit(1)
if sys.platform == 'win32' and os.path.isdir('c:/mingw'):
print '*ERROR* please rename or remove c:/mingw, as it conflicts with Shed Skin'
sys.exit()
# --- argument
if len(args) != 1:
usage()
name = args[0]
if not name.endswith('.py'):
name += '.py'
if not os.path.isfile(name):
print "*ERROR* no such file: '%s'" % name
sys.exit(1)
getgx().main_mod = name[:-3]
# --- analyze & annotate
t0 = time.time()
infer.analyze(name)
annotate.annotate()
cpp.generate_code()
shared.print_errors()
if not getgx().silent:
print '[elapsed time: %.2f seconds]' % (time.time() - t0)
def annotate_command(options, command_log):
from annotate import annotate
options['--no-fix'] = False
options['--low-confidence'] = False
options['<circ_dir>'] = options['--output']
annotate(options, command=command_log, name='annotate')
def computeMatrix(dir_path, num_chunks):
#stopwords = nltk.corpus.stopwords.words('english')
'''features from annotation'''
'''i = 0
docs = []
for i in range(0, num_chunks):
aux =""
auxList = []
f = open(dir_path+"annotation/anotation"+str(i)+".txt")
a = f.readlines()
for y in a:
if(y != "--"):
#print(y)
auxList = auxList + dbpedia.getResourcesAndCategories(y.replace("\n",""))
#print(auxList)
else:
auxList.append(y)
for x in auxList:
x = x.replace("http://pt.dbpedia.org/resource/","")
x = x.replace("http://dbpedia.org/resource/", "")
x = x.replace("http://dbpedia.org/resource/Category:","")
x = x.replace("_","")
x = x.replace(" ","")
aux = aux +" "+ x
aux = aux.replace("\n","")
docs.append(aux)
#print(docs)
#print("aaa")
vectorizer = TfidfVectorizer(encoding='utf-8',sublinear_tf=True)
X = vectorizer.fit_transform(docs)
print('saiu')
afinity_matrix2 = cosine_distances(X)
'''
# Using the pre-trained word2vec model trained using Google news corpus of 3 billion running words.
# The model can be downloaded here: https://bit.ly/w2vgdrive (~1.4GB)
# Feel free to use to your own model.
googlenews_model_path = 'document_similarity/data/GoogleNews-vectors-negative300.bin'
stopwords_path = "document_similarity/data/stopwords_en.txt"
stopwords = []
model = KeyedVectors.load_word2vec_format(googlenews_model_path,
binary=True)
with open(stopwords_path, 'r') as fh:
stopwords = fh.read().split(",")
ds = DocSim.DocSim(model, stopwords=stopwords)
'''features from transcription'''
docsA = []
docs2 = []
simMatrixT = []
avg_depths = []
previousAnnotation = ['empty']
previousDepth = [1000]
stemmer = PorterStemmer()
docsT = []
for i in range(0, num_chunks):
aux = ""
f2 = open(dir_path + "transcript/transcript" + str(i) + ".txt")
a = f2.read()
words = tokenize.word_tokenize(a, language='english')
words = [word.lower() for word in words if word.isalpha()]
preAnnotateText = ' '.join(words)
if (not preAnnotateText):
preAnnotateText = 'chemestry dog wolf bug'
docsT.append(preAnnotateText)
annotatedTerms, depth = annotate.annotate(preAnnotateText)
if not annotatedTerms:
annotatedTerms = previousAnnotation
depth = previousDepth
else:
previousAnnotation = annotatedTerms
previousDepth = depth
print(annotatedTerms)
docsA.append(annotatedTerms)
avg_depths.append(depth)
for i in range(0, num_chunks):
source_doc = docsT[i]
target_docs = []
auxSimMT = []
for j in range(0, num_chunks):
target_docs.append(docsT[j])
sim_scores = ds.calculate_similarity(source_doc, target_docs)
for sim in sim_scores:
auxSimMT.append(float(sim['score']))
#print(len(auxSimMT))
simMatrixT.append(auxSimMT)
#words=[stemmer.stem(word) for word in words ]
#aux = ' '.join(words)
#docs2.append(aux)
#source_doc = "how to delete an invoice"
#target_docs = ['delete a invoice', 'how do i remove an invoice', "purge an invoice"]
#vectorizer2 = TfidfVectorizer(stop_words=stopwords, encoding='utf-8',sublinear_tf=True)
#X2 = vectorizer2.fit_transform(docs2)
'''distance_matrix_A = []
auxVector = []
for i in range(0, num_chunks):
for j in range(0, num_chunks):
intersection_size = len(set(docsA[i]).intersection(docsA[j]))
auxVector.append(float(intersection_size/len(docsA[i])))
distance_matrix_A.append(auxVector)'''
#afinity_matrix = cosine_distances(X2)
#print(distance_matrix_A)
#print(simMatrixT)
return simMatrixT, docsA, avg_depths
