def scatter_plot(self, gene_id_list, output_fname='/tmp/scatter_plot.ps'):
"""
02-15-06
1st gene is regarded as X, all others genes are treated as Y
"""
vector_list = []
#gene_id_list may contain some inexistent genes
real_gene_id_list = []
for gene_id in gene_id_list:
if gene_id in self.gene_id2expr_array:
real_gene_id_list.append(gene_id)
vector_list.append(self.gene_id2expr_array[gene_id])
else:
sys.stderr.write("%s doesn't appear in the dataset\n"%(gene_id))
if len(real_gene_id_list)>0:
r.postscript("%s"%output_fname)
axis_range = self.get_min_max(vector_list)
no_of_curves = 1 #counting starts from 1st gene itself.
no_of_curves += 1
r.plot(vector_list[0], vector_list[1], xlab='value of %s'%real_gene_id_list[0], xlim=axis_range, ylim=axis_range, \
ylab='other genes values', col=no_of_curves)
for i in range(2, len(vector_list)):
no_of_curves += 1
r.points(vector_list[0], vector_list[i], col=no_of_curves)
r.legend(axis_range[1], axis_range[1], gene_id_list, col=range(1, no_of_curves+1), lty=1, xjust=1)
r.dev_off()
return output_fname
else:
return None
def plotSkByAtom(self, col='green', pch='x', function=numpy.average,
**other):
from rpy import r
for kmag, SkArray in zip(self.kmags(), self.SkArraysByAtom()):
if function is not None:
SkArray = function(SkArray)
try: len_ = len(SkArray)
except: len_ = 1
r.points(x=[kmag]*len_, y=SkArray,
col=col, pch=pch, **other)
def plot_boxplot_r(self, filename=None, n_highest_weights=1, n_highest_weights_for_quantity=1, weight_threshold=None, logy=False):
from rpy import r
logstring = ''
if logy:
logstring='y'
if filename is not None:
r.pdf(file=filename)
for var, values in self.values_from_mr.iteritems():
plot_one_boxplot_r(values, var, logstring)
if values.ndim == 1:
v = resize(values, (1, values.size))
else:
v = values
ivar = self.get_index_for_quantity(var)
if weight_threshold is not None:
for i in range(0, v.shape[0]):
iw = self.get_index_of_component_weights_over_threshold(ivar, weight_threshold)
if iw.size > 0:
r.points(i+1, v[i:(i+iw.size),iw], col='yellow', cex=0.5)
iw = self.get_index_of_weights_over_threshold(weight_threshold)
if iw.size > 0:
r.points(i+1, v[i:(i+iw.size),iw], col='blue', cex=0.5)
if n_highest_weights_for_quantity > 0:
for i in range(0, v.shape[0]):
r.points(i+1, v[i,self.get_index_of_n_highest_component_weights(ivar, n_highest_weights_for_quantity)], col='green', cex=0.5)
if n_highest_weights > 0:
for i in range(0, v.shape[0]):
r.points(i+1, v[i,self.get_index_of_n_highest_weights(n_highest_weights)], col='red', cex=0.5)
if filename is not None:
r.dev_off()
def plotArray(self, hitDataParam, filename, plotDir=None, labeledPosD=None,
title='', type='png',
label_colors = True, colVecL=None, legend_plot = False, legend_filename=None,
control_color='black', numeric_as_int = False,
grid=True, max_val=0.3, min_val=0.0, cut_data = True):
if plotDir is None:
plotDir = self.plotDir
full_filename = os.path.join(plotDir, filename)
#hitData = copy.deepcopy(hitDataParam)
hitData = hitDataParam
#nrow = len(hitData)
#ncol = len(hitData[0])
nrow = self.nb_row
ncol = self.nb_col
xL = range(1, self.nb_col + 1)
yL = range(1, self.nb_row + 1)
rdev = plot_utilities.RDevice(name = full_filename, title=title, plotType=type,
width=640, height=250)
if label_colors:
# in this case, the data is considered to consist of labels
labelL = []
for i in range(nrow):
for j in range(ncol):
if hitData[i][j] not in labelL:
labelL.append(hitData[i][j])
if colVecL is None:
colVecL = r.rainbow(len(labelL))
colBreaksL = range(len(colVecL) + 1)
if legend_plot:
self.plotLabelLegend(colVecL, plotType=type, filename=legend_filename)
else:
# in this case, the data is numeric.
if cut_data:
max_rel_cell_count = max_val
min_rel_cell_count = 0.0
for i in range(nrow):
for j in range(ncol):
hitData[i][j] = max(min_rel_cell_count, min(max_rel_cell_count, hitData[i][j]))
else:
max_rel_cell_count = max([max(x) for x in hitData.tolist() ])
min_rel_cell_count = min([min(x) for x in hitData.tolist() ])
if numeric_as_int:
nb_colors = max_rel_cell_count
else:
nb_colors = 500
if colVecL is None:
pattern = [(0,0,0),(0.7,0,0),(1,1,0),(1,1,1)]
colVecL = colors.make_colors(pattern, nb_colors)
colBreaksL = [1.0/ (len(colVecL) - 1) * x * (max_rel_cell_count - min_rel_cell_count) + min_rel_cell_count for x in range(len(colVecL) + 1)]
if legend_plot:
self.plotNumLegend(colVecL, colBreaksL, 16, filename=legend_filename, type=type, int_labels=numeric_as_int, legendDir = plotDir)
axisSize = .8
r("par(mar=c(1.6,1.6,0.1,0.1))")
r.image(xL, yL, r.t(hitData), axes = False, ann=False, cex=1, col=colVecL, breaks=colBreaksL)
r.box()
if not labeledPosD is None:
for label in labeledPosD.keys():
posL = labeledPosD[label]
if len(posL) > 0:
xlL = [(int(x)-1) % self.nb_col + 1 for x in posL]
ylL = [(int(x)-1) / self.nb_col + 1 for x in posL]
r.points(xlL, ylL, pch=label, col=control_color, cex=axisSize)
print
print xlL
print ylL
print
# grid
if grid:
for i in range(self.nb_col):
r.abline(h=i+.5, lty=3, lwd=1, col='grey')
for i in range(self.nb_row):
r.abline(v=i+.5, lty=3, lwd=1, col='grey')
r.axis(1, at=xL, labels=[str(x) for x in xL], tick=False, line=-1.0, cex_axis=axisSize)
r.axis(2, at=yL, labels=[str(y) for y in yL], tick=False, line=-1.0, cex_axis=axisSize)
rdev.close()
return
def plotBundle(self, bundleD, full_filename, colorsD=None, bundlePointsD=None, legendL=None, title=None, y_max=None):
if y_max is None:
y_max = 0.4
if legendL is None:
legendL = bundleD.keys()
legendL.sort()
if title is None:
title = 'data'
bundleIdL = bundleD.keys()
bundleIdL.sort()
if colorsD is None:
colorsL = r.rainbow(len(bundleIdL))
colorsD = dict(zip(bundleIdL, colorsL))
colorsL = [colorsD[x] for x in bundleIdL]
time_min = min([len(bundleD[x]) for x in bundleD.keys()])
timeVec = [0.5 * x for x in range(time_min)]
try:
r.png(full_filename, width=800, height=600)
oldPar = r.par(xpd = True, mar = [x + y for (x,y) in zip(r.par()['mar'], [0,0,0,6])])
print 'plot %s' % full_filename
r.plot(timeVec, timeVec,
type='n',
main=title, ylim=(0, y_max),
xlab="time in hours after transfection", ylab="Relative Cell Counts",
pch=20, lwd=1, lty = 1,
cex=1.0, cex_lab=1.2, cex_main=1.5)
for bundleId in bundleIdL:
if not bundlePointsD is None:
r.points(timeVec, bundlePointsD[bundleId],
col=colorsD[bundleId], pch=20,
lwd=1)
r.lines(timeVec, bundlePointsD[bundleId],
col=colorsD[bundleId],
lwd=1, lty = 1)
r.lines(timeVec, bundleD[bundleId],
col=colorsD[bundleId],
lwd=3, lty = 1)
r.legend(max(timeVec) * 1.1, y_max, legend=legendL, fill=colorsL, cex=1.0, bg= 'whitesmoke')
r.par(oldPar)
r.grid(col="darkgrey")
r.dev_off()
except:
r.dev_off()
print full_filename + ' has not been printed.'
return
print "top modes:"
print "%6s %6s %7s %9s"%('kmag', 'Sk', 'kmag/L', 'L/kmag')
for Sk, kmag in zip(v_sk, v_kmag)[-10:]:
print "%6.3f %6.3f %7.5f %9.5f"%(kmag, Sk, kmag/L, L/kmag)
r.plot(v_kmag, v_sk,
xlab="", ylab="", type="l",
ylim=(0., 15)
#ylim=(0., 15000)
)
# plots a line at each k-vector point.
for kmag in v_kmag:
r.abline(v=kmag, lty=3, col="lightgray")
# plots each individual k-vector
for kmag, SkArray in zip(v_kmag, StructCorr.SkArrays()):
r.points(x=[kmag]*len(SkArray), y=SkArray,
col="blue", pch="x")
# plots the standard deviation of the by-kvector lists.
for kmag, SkArray in zip(v_kmag, StructCorr.SkArrays()):
r.points(x=kmag, y=numpy.std(SkArray),
col="red", pch="s")
# plots it using the average of all k-vectors -- this should line up
# exactly
#for kmag, SkArray in zip(v_kmag, StructCorr.SkArrays()):
# r.points(x=kmag, y=numpy.average(SkArray),
# col="green", pch="x")
import code ; code.interact(local=locals(), banner="" )
def plot(outfile, data, out_format='png'):
w = int(round(len(data)/4.0))
if out_format == 'png':
r.png(outfile, width=w*100, height=1000, res=72)
elif out_format == 'pdf':
r.pdf(outfile, width=w, height=10)
else:
raise Exception('Unrecognised format: ' + str(out_format))
print("total: " + str(len(data)))
series = []
points = {'translate': [], 'preprocessing': []}
for dat in data:
points['translate'].append(float(dat['translate']))
points['preprocessing'].append(float(dat['preprocessing']))
xlabels = []
for k, v in data[0].iteritems():
if k not in ["problem", 'translate', 'preprocessing']:
series.append(k)
points[k] = []
index = 0
for dat in data:
for k in series:
if dat[k] != 'no-plan':
points[k].append(float(dat[k]) + \
points['translate'][index] + \
points['preprocessing'][index])
else:
points[k].append(-1000)
xlabels.append(dat['problem'])
index += 1
max_value = max(iter([max(iter(points[k])) for k in series]))
yrange = (0, max_value)
legend_labels = []
x = [i for i in range(1,len(points['translate'])+1)]
y = [-1000 for i in x]
r.par(mar=(7,5,4,2))
r.plot(x, y, main='', xlab="", ylab='',
xaxt='n', yaxt='n', pch=0, ylim=yrange,
mgp=(5,1,0))
r.mtext("Problem", side=1, line=5)
r.mtext("CPU Time (s)", side=2, line=3)
pch_start = 1
pch_index = pch_start
# plotting "translate"
#r.plot(x, points['translate'], main='',
# xlab='', ylab='Time (s)',
# xaxt='n', yaxt='n',
# pch=0, ylim=yrange)
#legend_labels.append('translate')
r.lines(x, points['translate'], lty=1)
# preprocessing -- Removed since it's insignificant
#r.points(x, points['preprocessing'], pch=pch_index)
#pch_index =+ 1
# planner output
for k in series:
if k != 'translate' and k != 'preporcessing':
r.points(x, points[k], pch=pch_index)
pch_index += 1
legend_labels.append("FD+" + k.upper())
# put x-axis labels
for i in range(0, len(xlabels)):
r.axis(side=1, at=i+1, labels=xlabels[i], las=2)
# put y-axis labels
base, step = get_y_step(max_value)
print("base: " + str(base) + " -- step: " + str(step))
y = base
for i in range(0, step):
r.axis(side=2, at=y, labels=str(y), las=2)
y += base
# legend
r.legend(1, max_value, legend_labels, pch=[i for i in range(pch_start, pch_index)])
r.dev_off()
def plot(outfile, data, out_format='png'):
w = int(round(len(data) / 4.0))
if out_format == 'png':
r.png(outfile, width=w * 100, height=1000, res=72)
elif out_format == 'pdf':
r.pdf(outfile, width=w, height=10)
else:
raise Exception('Unrecognised format: ' + str(out_format))
print("total: " + str(len(data)))
series = []
points = {'translate': [], 'preprocessing': []}
for dat in data:
points['translate'].append(float(dat['translate']))
points['preprocessing'].append(float(dat['preprocessing']))
xlabels = []
for k, v in data[0].iteritems():
if k not in ["problem", 'translate', 'preprocessing']:
series.append(k)
points[k] = []
index = 0
for dat in data:
for k in series:
if dat[k] != 'no-plan':
points[k].append(float(dat[k]) + \
points['translate'][index] + \
points['preprocessing'][index])
else:
points[k].append(-1000)
xlabels.append(dat['problem'])
index += 1
max_value = max(iter([max(iter(points[k])) for k in series]))
yrange = (0, max_value)
legend_labels = []
x = [i for i in range(1, len(points['translate']) + 1)]
y = [-1000 for i in x]
r.par(mar=(7, 5, 4, 2))
r.plot(x,
y,
main='',
xlab="",
ylab='',
xaxt='n',
yaxt='n',
pch=0,
ylim=yrange,
mgp=(5, 1, 0))
r.mtext("Problem", side=1, line=5)
r.mtext("CPU Time (s)", side=2, line=3)
pch_start = 1
pch_index = pch_start
# plotting "translate"
#r.plot(x, points['translate'], main='',
# xlab='', ylab='Time (s)',
# xaxt='n', yaxt='n',
# pch=0, ylim=yrange)
#legend_labels.append('translate')
r.lines(x, points['translate'], lty=1)
# preprocessing -- Removed since it's insignificant
#r.points(x, points['preprocessing'], pch=pch_index)
#pch_index =+ 1
# planner output
for k in series:
if k != 'translate' and k != 'preporcessing':
r.points(x, points[k], pch=pch_index)
pch_index += 1
legend_labels.append("FD+" + k.upper())
# put x-axis labels
for i in range(0, len(xlabels)):
r.axis(side=1, at=i + 1, labels=xlabels[i], las=2)
# put y-axis labels
base, step = get_y_step(max_value)
print("base: " + str(base) + " -- step: " + str(step))
y = base
for i in range(0, step):
r.axis(side=2, at=y, labels=str(y), las=2)
y += base
# legend
r.legend(1,
max_value,
legend_labels,
pch=[i for i in range(pch_start, pch_index)])
r.dev_off()
