def draw_tfbs_similarity_ls_histogram(self, tfbs_similarity_ls, output_fname):
sys.stderr.write("Drawing histogram for tfbs_similarity_ls...")
if len(tfbs_similarity_ls)>10:
r.png('%s'%output_fname)
r.hist(tfbs_similarity_ls, main='histogram',xlab='tfbs_similarity',ylab='freq')
r.dev_off()
sys.stderr.write("Done.\n")
else:
sys.stderr.write("too short: %s, aborted\n"%tfbs_similarity_ls)
def funcionprincipal(dato,variable,opciones):
from rpy import r
diccionario={}
diccionario["Histograma"]={}
lista = dato.query(variable)
import random
nombrefichero="/tmp/driza"+str(random.randint(1,99999))+".png"
diccionario["Histograma"]["ruta"]=nombrefichero
r.png(nombrefichero) #Directorio temporal de la config
r.hist(lista,main=variable,xlab=variable, nclass=int(opciones[u"NúmeroIntervalos"]))
r.dev_off()
return diccionario
def test():
a = N.random.normal(0.0, 1.0, 500)
hist = r.hist(a)
breaks = N.array(hist['breaks'])
dhist = N.zeros(breaks.shape, N.float)
dhist[:-1] = hist['density']
xdens, ydens, ydenslow, ydenshigh = bootdensity(a, -5.0, 5.0, 100, 0.95)
xg = (N.arange(1000) / 500.0 - 1.0) * 5.0
yg = gaussian.gaussian(xg, 1.0, 0.0, 1.0)
pgaqt()
pgsetup()
pgenv(-5.0, 5.0, 0.0, 0.5)
pgbin(breaks, dhist, False)
pgxsci('yellow')
pgbin(breaks, dhist-2*(N.sqrt(dhist*1000)/1000.0), False)
pgbin(breaks, dhist+2*(N.sqrt(dhist*1000)/1000.0), False)
pgxsci('black')
pgline(xdens, ydens)
#pgxsci('lightgray')
#for i in range(100):
# pgline(xdens, ydensboot[i])
pgxsci('green')
pgline(xdens, ydenslow)
pgxsci('red')
pgline(xdens, ydenshigh)
pgxsci('blue')
pgline(xg, yg)
pgclos()
def transform_one_file(self, src_pathname, delimiter, outputdir, b_instance, threshold, type, no_of_valids):
"""
08-09-05
add type
08-29-05
add no_of_valids to cut genes with too few valid values
"""
reader = csv.reader(file(src_pathname), delimiter=delimiter)
filename = os.path.basename(src_pathname)
output_filename = os.path.join(outputdir, filename)
std_list = []
for row in reader:
gene_id = row[0]
new_row = []
mask_ls = []
for i in range(1, len(row)):
if row[i] == 'NA':
new_row.append(1e20)
mask_ls.append(1)
elif row[i] == '':
#ignore empty entry
continue
else:
value = float(row[i])
if type==1:
if value<=10:
value = 10
value = math.log(value)
new_row.append(value)
mask_ls.append(0)
ma_array = array(new_row, mask=mask_ls)
if self.debug:
print "The data vector is ",ma_array
print "Its mask is ", ma_array.mask()
if len(ma_array.compressed())>=no_of_valids: #at least two samples, otherwise, correlation can't be calculated
#08-29-05 no_of_valids controls not too many NA's, which is for graph_modeling
std = MLab.std(ma_array.compressed()) #disregard the NAs
if self.debug:
print "std is ",std
raw_input("Continue?(Y/n)")
std_list.append(std)
del reader
if len(std_list)>100:
r.png('%s.png'%output_filename)
r.hist(std_list, main='histogram',xlab='std',ylab='freq')
r.dev_off()
def main(args):
sourcefiles = get_src_files(args.get('in'))
hashofhos = None
parsedfiles = []
for i in range(len(sourcefiles) - 1):
queryfile = sourcefiles[i]
subjectfile = sourcefiles[i + 1]
if hashofhos:
idfile = 'keepids.tmp'
fw = open(idfile, 'w')
for id in hashofhos.keys():
fw.write(id + '\n')
fw.flush()
fw.close()
outfile = 'red_' + get_basename(queryfile) + '.aa'
os.system('reduce_fasta_file.py -f %s -i %s -o %s' %
(queryfile, idfile, outfile))
queryfile = outfile
blastout = blast(queryfile, subjectfile)
parsedfile, hashofhos = parse_blastout(blastout, args)
parsedfiles.append(parsedfile)
infomsg("hits: %s" % len(hashofhos))
Homologs = integrate_all_homologs(parsedfiles, args)
# stats
no = []
for sid, orthlist in Homologs.iteritems():
n = len(orthlist) + 1
# infomsg( str(n) )
no.append(n)
from rpy import r
outfile = 'hist_size_homol_sets.pdf'
title = 'Size of Homologous Sets'
x = 'number of homologs'
y = 'frequency'
r.pdf(outfile)
r.hist(no, xlab=x, ylab=y, main=title, col='grey', breaks=max(no))
r.dev_off()
def main( args ):
sourcefiles = get_src_files( args.get('in') )
hashofhos = None
parsedfiles = []
for i in range( len(sourcefiles)-1 ):
queryfile = sourcefiles[i]
subjectfile = sourcefiles[i+1]
if hashofhos:
idfile = 'keepids.tmp'
fw = open( idfile, 'w' )
for id in hashofhos.keys(): fw.write( id + '\n')
fw.flush()
fw.close()
outfile = 'red_' + get_basename(queryfile) + '.aa'
os.system( 'reduce_fasta_file.py -f %s -i %s -o %s' %(queryfile,idfile,outfile) )
queryfile = outfile
blastout = blast( queryfile, subjectfile )
parsedfile, hashofhos = parse_blastout( blastout, args )
parsedfiles.append( parsedfile )
infomsg( "hits: %s" %len(hashofhos) )
Homologs = integrate_all_homologs( parsedfiles, args )
# stats
no = []
for sid, orthlist in Homologs.iteritems():
n = len(orthlist) + 1
# infomsg( str(n) )
no.append(n)
from rpy import r
outfile = 'hist_size_homol_sets.pdf'
title = 'Size of Homologous Sets'
x = 'number of homologs'
y = 'frequency'
r.pdf( outfile )
r.hist(no, xlab=x, ylab=y, main=title, col='grey', breaks=max(no))
r.dev_off()
def draw_hist_gene_freq(self, files, frequency_presence_vector_gene_id_ls, exponent, output_dir):
"""
12-23-05
12-26-05 if it's not empty, then draw it
12-26-05 add an enrich_index_no_of_genes_filename_ls
01-05-06 have >10 items, then draw it
"""
sys.stderr.write("Drawing gene frequency histogram for each dataset...\n")
#initialize a structure to store frequency list in each dataset
dataset_index_gene_freq_ls = []
for i in range(len(files)):
dataset_index_gene_freq_ls.append([])
for row in frequency_presence_vector_gene_id_ls:
frequency = row[0]
for i in range(1, len(row)-1):
if row[i] == 1:
dataset_index_gene_freq_ls[i-1].append(frequency) #WATCH i-1
#12-26-05
enrich_index_no_of_genes_filename_ls = []
functor = lambda x: math.pow(x, exponent)
for i in range(len(files)):
sys.stderr.write("%s\t%s"%('\x08'*20, i))
output_fname = os.path.join(output_dir, files[i])
#12-26-05
enrich_index_no_of_genes_filename_ls.append([sum(map(functor, dataset_index_gene_freq_ls[i])), len(dataset_index_gene_freq_ls[i]), files[i]])
if len(dataset_index_gene_freq_ls[i])>10: #01-05-06 have >10 items, then draw it
r.png("%s.png"%output_fname)
r.hist(dataset_index_gene_freq_ls[i], main='histogram',xlab='gene frequency',ylab='no of genes', labels=r.TRUE)
r.dev_off()
#12-26-05
enrich_index_no_of_genes_filename_ls.sort()
enrich_index_output_fname = os.path.join(output_dir, 'enrich_index.csv')
writer = csv.writer(open(enrich_index_output_fname, 'w'), delimiter ='\t')
for row in enrich_index_no_of_genes_filename_ls:
writer.writerow(row)
del writer
sys.stderr.write('Done.\n')
def transform_one_file(self, src_pathname, delimiter, outputdir, b_instance, threshold, type, no_of_valids):
"""
08-09-05
add type
08-29-05
add no_of_valids to cut genes with too few valid values
01-05-06
deal with blank files
"""
reader = csv.reader(file(src_pathname), delimiter=delimiter)
filename = os.path.basename(src_pathname)
output_filename = os.path.join(outputdir, filename)
cor_list = []
counter=0 #01-05-06
for row in reader:
if counter>0:
cor = float(row[3])
cor_list.append(cor)
counter += 1
del reader
if len(cor_list)>100:
r.png('%s.png'%output_filename)
r.hist(cor_list, main='histogram',xlab='cor',ylab='freq')
r.dev_off()
def plot(self, filename, list_to_plot, main_lab, xlab):
max_length = max(list_to_plot)
r.pdf(filename)
r.hist(list_to_plot, breaks=range(max_length + 1), las=1, main=main_lab, xlab=xlab)
r.dev_off()
from AlgoDPA import *
from rpy import r
import sys, sqlite3, scipy, pickle
import matplotlib.pyplot as plt
sys.path.append('/media/FreeAgent GoFlex Drive/research/attacks/resources')
dpaKey1 = pickle.load(open('../serial/[50].p', 'rb'))
dpaKey2 = pickle.load(open('../serial/[12].p', 'rb'))
peaks1 = [y for x in dpaKey1.peaks.values() for y in x]
peaks2 = [y for x in dpaKey2.peaks.values() for y in x]
pp = peaks1+peaks2
#plt.hist(pp)
r.png('output.png')
r.hist(pp)
r.dev_off()
#plt.savefig('../graphs/[50,12]_combinedHypoCurrentDistribution.png')
pch=21, col='blue', bg='lightblue', type='o')
# second plot
x = range(1,11)
y = [i**2 for i in x]
z = [i**3 for i in x]
r.plot(x, y, main='My second plot', xlab='x', ylab='y', type='l', col='blue')
r.lines(x, z, col='red')
# cosine function, save to file
import math
r.png('cosine.png')
x = r.seq(0,50, by=0.1)
y = [math.cos(i) for i in x]
r.plot(x, y, main='COS(X)', xlab='x', ylab='cos(x)', type='l', col='blue')
r.dev_off()
# histogram
x = range(10) + range(3,6) + range(5,10)
r.hist(x, main='A histogram', xlab='x', col='lightblue')
# adust plotting area
from rpy import r
x = range(1,11)
y = [i**2 for i in x]
z = [i**3 for i in x]
r.plot(x, y, main='My second plot', xlab='x', ylab='y', type='l',
col='blue', ylim=r.range(y,z))
r.lines(x, z, col='red')