def plot_squiggle(args, filename, start_times, mean_signals):
"""
Use rpy2 to create a squiggle plot of the read
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
total_time = start_times[-1] - start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([t - t_0 for t in start_times])
r_mean_signals = robjects.FloatVector(mean_signals)
# infer the appropriate number of events given the number of facets
num_events = len(r_mean_signals)
events_per_facet = (num_events / args.num_facets) + 1
# dummy variable to control faceting
facet_category = robjects.FloatVector([(i / events_per_facet) + 1 for i in range(len(start_times))])
# make a data frame of the start times and mean signals
d = {'start': r_start_times, 'mean': r_mean_signals, 'cat': facet_category}
df = robjects.DataFrame(d)
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)})
else:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)}) \
+ ggplot2.theme_bw()
if args.saveas is not None:
plot_file = os.path.basename(filename) + "." + args.saveas
if os.path.isfile(plot_file):
raise Exception('Cannot create plot for %s: plot file %s already exists' % (filename, plot_file))
if args.saveas == "pdf":
grdevices.pdf(plot_file, width = 8.5, height = 11)
elif args.saveas == "png":
grdevices.png(plot_file, width = 8.5, height = 11,
units = "in", res = 300)
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
def _plt_distr(dat,
col,
title='',
splitBy_pfill=True,
pfill='label',
independentpdf=False,
fname='xdistr.pdf'):
df = dat[dat[pfill] != 'NA'] ## remove invalid pairs
n = len(df)
df = {
col: robjects.FloatVector(list(df[col])),
pfill: robjects.StrVector(list(df[pfill]))
}
df = robjects.DataFrame(df)
pp = ggplot2.ggplot(df) + \
ggplot2.ggtitle('%s [Total = %s]' % (title, n))
## Plot1: counts
if splitBy_pfill:
p1 = pp + ggplot2.aes_string(x=col, fill=pfill)
else:
p1 = pp + ggplot2.aes_string(x=col)
## Plot2: density
if splitBy_pfill:
p2 = pp + ggplot2.aes_string(x=col, fill=pfill, y='..density..')
else:
p2 = pp + ggplot2.aes_string(x=col, y='..density..')
p2 = p2 + ggplot2.geom_density(alpha=.5, origin=-500)
if col == 'distance':
p1 = p1 + \
ggplot2.geom_histogram(binwidth=1000, alpha=.5, position='identity', origin=-500) + \
ggplot2.xlim(-1000, 51000)
p2 = p2 + \
ggplot2.geom_histogram(binwidth=1000, alpha=.33, position='identity', origin=-500) + \
ggplot2.xlim(-1000, 51000)
else:
p1 = p1 + \
ggplot2.geom_histogram(alpha=.5, position='identity')
p2 = p2 + \
ggplot2.geom_histogram(alpha=.33, position='identity')
if col == 'correlation':
p1 = p1 + ggplot2.xlim(-1.1, 1.1)
p2 = p2 + ggplot2.xlim(-1.1, 1.1)
if independentpdf:
grdevices = importr('grDevices')
grdevices.pdf(file=fname)
p1.plot()
p2.plot()
grdevices.dev_off()
else:
p1.plot()
p2.plot()
return
def plotStats(data,
outFolder,
tiles,
prop="qual",
prefix="",
high="yellow",
low="blue",
pdf=False,
detail=True):
#overview plot
p = ggplot.ggplot(data)
p = p + ggplot.aes_string(x="x", y="y", col=prop) \
+ ggplot.geom_point(size=0.1) \
+ ggplot.facet_wrap(robjects.Formula("~ tile")) \
+ ggplot.scale_colour_gradient(high=high, low=low) \
+ ggplot.ggtitle("Overview %s" % (prop))
if prefix:
fileName = "%s_overview_%s.png" % (prefix, prop)
else:
fileName = "overview_%s.png" % (prop)
p.save(os.path.join(outFolder, fileName), scale=2)
#detail plots
if detail:
detailFolder = os.path.join(outFolder, "detailPlots")
for t in tiles:
p = ggplot.ggplot(data.rx(data.rx2("tile").ro == t, True))
p = p + ggplot.aes_string(x="x", y="y", col=prop) \
+ ggplot.geom_point(size=1) \
+ ggplot.facet_wrap(robjects.Formula("~ tile")) \
+ ggplot.scale_colour_gradient(high=high, low=low) \
+ ggplot.ggtitle("%i %s" % (t, prop))
if prefix:
fileName = "%s_%i_%s.png" % (prefix, t, prop)
else:
fileName = "%i_%s.png" % (t, prop)
p.save(os.path.join(detailFolder, fileName), scale=2)
if pdf:
fileName = "%s%i_%s.pdf" % (prefix, t, prop)
p.save(os.path.join(detailFolder, fileName), scale=2)
def makeDistanceBox( alldata, figurename, feature="distance") :
alldata["distance"] = alldata.het + alldata.hom
r_dataframe = com.convert_to_r_dataframe(alldata)
p = ggplot2.ggplot(r_dataframe) + \
ggplot2.aes_string(x="factor(continent)", y=feature) + \
ggplot2.geom_boxplot() + \
ggplot2.ggtitle("Distance from Reference by Continent") + \
ggplot2.theme(**mytheme) #+ \
#ggplot2.theme(**{'axis.text.x': ggplot2.element_text(angle = 45)}) + \
#ggplot2.facet_grid( robjects.Formula('RVIS_type ~ .') )
grdevices.png(figurename)
p.plot()
grdevices.dev_off()
def plot_summary(barcodes_obs, barcode_table, directory, expt_id):
barcodes, counts, matches = get_vectors(barcodes_obs, barcode_table)
df = DataFrame({'barcode': barcodes, 'count': counts, 'matched': matches})
p = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='factor(matched)', y='count / 1000000') + \
ggplot2.geom_boxplot(outlier_size = 0) + \
ggplot2.geom_jitter() + \
ggplot2.ggtitle(label = expt_id) + \
ggplot2.ggplot2.xlab(label = "") + \
ggplot2.scale_y_continuous(name = "Count\n(million reads)")
filename = "{0}/{1}.png".format(directory, expt_id)
grdevices.png(filename=filename, width=4, height=5, unit='in', res=300)
p.plot()
grdevices.dev_off()
def direct_taxon_abundance_box_plot(data, plot_file_path, title, xlabel, ylabel):
grdevices.pdf(file=plot_file_path)
gp = ggplot2.ggplot(data)
pp = gp \
+ ggplot2.aes_string(x='genotype', y='abundance') \
+ ggplot2.geom_boxplot() \
+ ggplot2.ggtitle(title) \
+ ggplot2.labs(x=xlabel, y=ylabel) \
+ ggplot2.geom_jitter(position=ggplot2.position_jitter(w=0.1)) \
+ ggplot2.geom_point()
pp.plot()
grdevices.dev_off()
def plot_cels(expr, expt_names, expt_name_idx, cel_names, outdir = None):
"""Makes correlation plots between CEL files for the same cell type"""
fsize = 10
names_1 = []
names_2 = []
cors = []
titles = []
for ex_idx, ex in enumerate(expt_names):
# Indices of CEL files (columns of expr) corresponding to that cell type
tmp_idx = expt_name_idx[ex]
plot_idx = 0
for i in range(len(tmp_idx)):
name1 = re.sub('_', '.', cel_names[tmp_idx[i]])
for j in range(i + 1, len(tmp_idx)):
name2 = re.sub('_', '.', cel_names[tmp_idx[j]])
plot_idx += 1
cor = np.corrcoef(expr[:, tmp_idx[i]], expr[:, tmp_idx[j]])[0, 1]
names_1.append(name1)
names_2.append(name2)
cors.append(cor)
titles.append(ex + '-' + str(plot_idx))
df = ro.DataFrame({'x':ro.FloatVector(expr[:, tmp_idx[i]]),
'y':ro.FloatVector(expr[:, tmp_idx[j]])})
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x = 'x', y = 'y') + \
ggplot2.geom_point(size = 1) + \
ggplot2.scale_x_continuous(name1) + ggplot2.scale_y_continuous(name2) + \
ggplot2.theme_bw() + ggplot2.ggtitle('{:s}-{:d} ({:.4f})'.format(ex, plot_idx, cor)) + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.title.x':ggplot2.element_text(size = 8),
'axis.text.y':ggplot2.element_text(size = fsize),
'axis.title.y':ggplot2.element_text(size = 8, angle = 90),
'plot.title':ggplot2.element_text(size = fsize)})
if outdir is None:
gp.plot()
else:
if not os.path.isdir(outdir):
os.makedirs(outdir)
outfile = os.path.join(outdir, ex + '-' + str(plot_idx) + '.png')
ro.r.ggsave(filename = outfile, plot = gp, width = 85, height = 85, unit = 'mm')
df = pd.DataFrame({'name1':names_1, 'name2':names_2, 'cor':cors}, index = titles)
if not outdir is None:
df.to_csv(os.path.join(outdir, 'cor_summary.txt'), sep = '\t')
return df
def ridge_cv_plot(val_err, lam_range):
"""
Source: http://rpy.sourceforge.net/rpy2/doc-2.3/html/graphics.html
"""
base = importr('base')
df = pd.DataFrame(val_err, columns = lam_range)
df = pd.melt(df)
df_r = com.convert_to_r_dataframe(df)
# Create boxplot
gp = ggplot2.ggplot(df_r)
pp = gp + \
ggplot2.aes_string(x='factor(variable)', y='value') + \
ggplot2.geom_boxplot() + \
ggplot2.ggtitle("Validation Error by Lambda")
pp.plot()
return
def plot_summary(barcodes_obs, barcode_table, directory, expt_id):
barcodes, counts, matches = get_vectors(barcodes_obs, barcode_table)
df = DataFrame({'barcode': barcodes,
'count': counts,
'matched': matches})
p = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='factor(matched)', y='count / 1000000') + \
ggplot2.geom_boxplot(outlier_size = 0) + \
ggplot2.geom_jitter() + \
ggplot2.ggtitle(label = expt_id) + \
ggplot2.ggplot2.xlab(label = "") + \
ggplot2.scale_y_continuous(name = "Count\n(million reads)")
filename = "{0}/{1}.png".format(directory, expt_id)
grdevices.png(filename=filename, width=4, height=5, unit='in', res=300)
p.plot()
grdevices.dev_off()
##text_log+="average: "+str(rmean(test23)[0])+end
##text_log+="sum: "+str(rsum(test23)[0])+end
#
#roughbin= round(ma[0]/100)
#bins=round(roughbin/100)*100
#ma2=rmax(ed)
#dataf_subset = dataf.rx(dataf.rx2("contig").ro >= 18, true)
scales = importr('scales')
gp = ggplot2.ggplot(dataf)
#geom_histogram(aes(y = ..density..))
# ggplot2.geom_density()+\
# pp = gp + ggplot2.aes_string(x='%s(contrrr)') + ggplot2.geom_histogram()+ggplot2.scale_y_sqrt()
bins=10
teest3=robjects.r('theme(axis.text.x=element_text(angle=90))')
pp = gp + \
ggplot2.aes_string(x='Length') + \
ggplot2.geom_histogram()+\
ggplot2.ggtitle("Found IS fragment lengths")+ \
ggplot2.scale_x_continuous(name="fragment lengths, bin="+str(bins),breaks=scales.pretty_breaks(20)) +\
ggplot2.scale_y_continuous(labels=scales.comma,name="Count",breaks=scales.pretty_breaks(10))+ \
teest3
pp.plot()
robjects.r.ggsave("/Users/security/science/dna_subj_hist.pdf")
def show1():
open1()
r.source('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/R/head1.r',encoding="utf-8")
data = DataFrame.from_csvfile('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/temp/day1.csv')
pp = ggplot2.ggplot(data)+ggplot2.aes_string(x='project', y='time',fill = 'project')+ggplot2.geom_bar(stat ='identity')+ggplot2.ggtitle("今日项目时间分布图")+ggplot2.labs(x='项目',y='时间 (min)')+ggplot2.theme(**{'axis.text.x': ggplot2.element_text(angle = 45)})
pp.plot()
heat_demand = np.zeros(37)
Bdim = robjects.FloatVector([12,6])
for i,BO in enumerate(range(0,361,10)):
res = ECR(Building_Orientation = BO,
Building_Dim = Bdim)
heat_demand[i] = res[2][0]
# Transfor to R data types
hd = robjects.FloatVector([h for h in heat_demand])
bo = robjects.FloatVector([b for b in range(0,361,10)])
# Create a python dictionary
p_datadic = {'Heat_Demand': hd,
'Building_Orientation': bo}
# Create R data.frame
r_dataf = robjects.DataFrame(p_datadic)
# plot with ggplot2
gp = ggplot2.ggplot(r_dataf)
pp = gp + ggplot2.aes_string(y= 'Heat_Demand', x= 'Building_Orientation') + \
ggplot2.geom_line(colour = "red", size = 1) + \
ggplot2.coord_polar(direction = -1, start = -pi/2) + \
ggplot2.ggtitle("Heat demand for all possible buildimg orientations") + \
ggplot2.scale_x_continuous(breaks=robjects.FloatVector(range(0, 360, 15)))
pp.plot()
grdevices.dev_off()
def plot_collectors_curve(args, start_times, read_lengths):
"""
Use rpy2 to create a collectors curve of the run
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([float(t - t_0) / float(3600) + 0.00000001 \
for t in start_times])
r_read_lengths = robjects.IntVector(read_lengths)
# compute the cumulative based on reads or total base pairs
if args.plot_type == 'reads':
y_label = "Total reads"
cumulative = \
r.cumsum(robjects.IntVector([1] * len(start_times)))
elif args.plot_type == 'basepairs':
y_label = "Total base pairs"
cumulative = r.cumsum(r_read_lengths)
# make a data frame of the lists
d = {'start': r_start_times,
'lengths': r_read_lengths,
'cumul': cumulative}
df = robjects.DataFrame(d)
if args.savedf:
robjects.r("write.table")(df, file=args.savedf, sep="\t")
# title
total_reads = len(read_lengths)
total_bp = sum(read_lengths)
plot_title = "Yield: " \
+ str(total_reads) + " reads and " \
+ str(total_bp) + " base pairs."
# plot
gp = ggplot2.ggplot(df)
pp = gp + ggplot2.aes_string(x='start', y='cumul') \
+ ggplot2.geom_step(size=2) \
+ ggplot2.scale_x_continuous('Time (hours)') \
+ ggplot2.scale_y_continuous(y_label) \
+ ggplot2.ggtitle(plot_title)
# extrapolation
if args.extrapolate:
start = robjects.ListVector({'a': 1, 'b': 1})
pp = pp + ggplot2.stat_smooth(fullrange='TRUE', method='nls',
formula='y~a*I((x*3600)^b)',
se='FALSE', start=start) \
+ ggplot2.xlim(0, float(args.extrapolate))
if args.theme_bw:
pp = pp + ggplot2.theme_bw()
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width = 8.5, height = 8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width = 8.5, height = 8.5,
units = "in", res = 300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
def main():
'''
maine
'''
# Command Line Stuff...
myCommandLine = CommandLine()
outdir = myCommandLine.args['outDir']
group1 = myCommandLine.args['group1']
group2 = myCommandLine.args['group2']
batch = myCommandLine.args['batch']
matrix = myCommandLine.args['matrix']
prefix = myCommandLine.args['prefix']
formula = myCommandLine.args['formula']
print("running DESEQ2 %s" % prefix, file=sys.stderr)
# make the quant DF
quantDF = pd.read_table(matrix, header=0, sep='\t', index_col=0)
df = pandas2ri.py2ri(quantDF)
# import formula
formulaDF = pd.read_csv(formula,header=0, sep="\t",index_col=0)
sampleTable = pandas2ri.py2ri(formulaDF)
if "batch" in list(formulaDF):
design = Formula("~ batch + condition")
else:
design = Formula("~ condition")
# import DESeq2
from rpy2.robjects.packages import importr
import rpy2.robjects.lib.ggplot2 as ggplot2
methods = importr('methods')
deseq = importr('DESeq2')
grdevices = importr('grDevices')
qqman = importr('qqman')
### RUN DESEQ2 ###
R.assign('df', df)
R.assign('sampleTable', sampleTable)
R.assign('design',design)
R('dds <- DESeqDataSetFromMatrix(countData = df, colData = sampleTable, design = design)')
R('dds <- DESeq(dds)')
R('name <- grep("condition", resultsNames(dds), value=TRUE)')
###
###
# Get Results and shrinkage values
res = R('results(dds, name=name)')
resLFC = R('lfcShrink(dds, coef=name)')
vsd = R('vst(dds,blind=FALSE)')
resdf = robjects.r['as.data.frame'](res)
reslfc = robjects.r['as.data.frame'](resLFC)
dds = R('dds')
### Plotting section ###
# plot MA and PC stats for the user
plotMA = robjects.r['plotMA']
plotDisp = robjects.r['plotDispEsts']
plotPCA = robjects.r['plotPCA']
plotQQ = robjects.r['qq']
# get pca data
if "batch" in list(formulaDF):
pcaData = plotPCA(vsd, intgroup=robjects.StrVector(("condition", "batch")), returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
else:
print(vsd)
pcaData = plotPCA(vsd, intgroup="condition", returnData=robjects.r['T'])
percentVar = robjects.r['attr'](pcaData, "percentVar")
# arrange
data_folder = os.path.join(os.getcwd(), outdir)
qcOut = os.path.join(data_folder, "%s_QCplots_%s_v_%s.pdf" % (prefix,group1,group2))
grdevices.pdf(file=qcOut)
x = "PC1: %s" % int(percentVar[0]*100) + "%% variance"
y = "PC2: %s" % int(percentVar[1]*100) + "%% variance"
if "batch" in list(formulaDF):
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition", shape="batch") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
else:
pp = ggplot2.ggplot(pcaData) + \
ggplot2.aes_string(x="PC1", y="PC2", color="condition") + \
ggplot2.geom_point(size=3) + \
robjects.r['xlab'](x) + \
robjects.r['ylab'](y) + \
ggplot2.theme_classic() + \
ggplot2.coord_fixed()
pp.plot()
plotMA(res, ylim=robjects.IntVector((-3,3)), main="MA-plot results")
plotMA(resLFC, ylim=robjects.IntVector((-3,3)), main="MA-plot LFCSrhinkage")
plotQQ(reslfc.rx2('pvalue'), main="LFCSrhinkage pvalue QQ")
hh = ggplot2.ggplot(resdf) + \
ggplot2.aes_string(x="pvalue") + \
ggplot2.geom_histogram() + \
ggplot2.theme_classic() + \
ggplot2.ggtitle("pvalue distribution")
hh.plot()
plotDisp(dds, main="Dispersion Estimates")
grdevices.dev_off()
data_folder = os.path.join(os.getcwd(), outdir)
lfcOut = os.path.join(data_folder, "%s_%s_v_%s_deseq2_results_shrinkage.tsv" % (prefix,group1,group2))
resOut = os.path.join(data_folder, "%s_%s_v_%s_deseq2_results.tsv" % (prefix,group1,group2))
robjects.r['write.table'](reslfc, file=lfcOut, quote=False, sep="\t")
robjects.r['write.table'](resdf, file=resOut, quote=False, sep="\t")
number_of_peaks = len(dataf[0])
cvI = []
newRow = []
for i in range(1,number_of_peaks+1):
row = dataf.rx(i,True)
rowA = np.array(row)
newRow.append(rowA[2:])
cvI.append(cv(rowA[2:]))
#cv.append(rowA[2:].std()/rowA[2:].mean())
cv_r=robjects.conversion.py2ri(cvI)
df_cv = {'CV' : cv_r}
dataf_cv = robjects.DataFrame(df_cv)
dtf_cv = robjects.r.melt(dataf_cv)
d=dataf.cbind(dtf_cv.rx(2))
d.names[tuple(d.colnames).index('value')] = 'CV'
#d = base.merge_data_frame(dataf,dtf_cv.rx(2))
utilis.write_csv(d, options.csv_output)
dc = dtf_cv.cbind(n_peak = robjects.IntVector(range(1,number_of_peaks+1)))
#n_peak = robjects.IntVector(1,number_of_peaks)
gp = ggplot2.ggplot(dc)
pp=gp+ggplot2.aes_string(x='n_peak',y='value') + ggplot2.geom_point()+ggplot2.theme_bw()+ ggplot2.ggtitle('Coefficient of Variation')+ \
ggplot2.scale_x_continuous("Number of Peaks")+ ggplot2.scale_y_continuous("CV")
r.X11()
pp.plot()
def _plot_with_rpy2(self, regions, filename):
from rpy2 import robjects
import rpy2.robjects.lib.ggplot2 as ggplot2
from rpy2.robjects.lib import grid
from rpy2.robjects.packages import importr
grdevices = importr('grDevices')
base = importr('base')
grdevices.pdf(file=filename + '.pdf')
t = [x for x in range(-self.num_bins, self.num_bins + 1)]
for region in regions[:self.num_regs]:
if not np.any(region.weighted):
logger.warning(
"Warning: No data for region located on bin " + str(region.bin) + ". Not plotting this one.")
continue
middle = (len(region.weighted[0]) - 1) / 2
if middle < self.num_bins:
logger.error("Warning: There are less bins calculated for regions than you want to plot.")
sys.exit(1)
d = {'map': robjects.StrVector(
[str(m) for sublist in [[x] * len(t) for x in range(len(region.weighted))] for m in sublist]),
't': robjects.FloatVector(t * len(region.weighted)),
'e': robjects.FloatVector([i for sublist in region.weighted for i in
sublist[middle - self.num_bins:middle + self.num_bins + 1]]),
'p': robjects.FloatVector([-np.log10(x) for sublist in region.pvalues for x in
sublist[middle - self.num_bins:middle + self.num_bins + 1]]),
'c': robjects.FloatVector([-np.log10(x) for sublist in region.corrected_pvalues for x in
sublist[middle - self.num_bins:middle + self.num_bins + 1]])}
dataf = robjects.DataFrame(d)
gp = ggplot2.ggplot(dataf) # first yellow second red
p1 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='e', group='map', colour='map'),
alpha=0.8) + ggplot2.scale_y_continuous(trans='log2') + ggplot2.ggtitle(
"\n".join(wrap("Bin " + str(region.bin) + " : " + str(region.positions)))) + ggplot2.labs(
y="log Intensity") + ggplot2.theme_classic() + ggplot2.theme(
**{'axis.title.x': ggplot2.element_blank(), 'axis.text.y': ggplot2.element_text(angle=45),
'axis.text.x': ggplot2.element_blank(),
'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
p2 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='p', group='map', colour='map'),
alpha=0.8) + ggplot2.labs(
y="-log10(p-value)") + ggplot2.theme_classic() + ggplot2.theme(
**{'axis.title.x': ggplot2.element_blank(), 'axis.text.x': ggplot2.element_blank(),
'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
p3 = gp + ggplot2.geom_line(mapping=ggplot2.aes_string(x='t', y='c', group='map', colour='map'),
alpha=0.8) + ggplot2.labs(y="-log10(q-value)",
x='bins (' + str(self.bin_res) + ' bp each)') + \
ggplot2.geom_hline(mapping=ggplot2.aes_string(yintercept=str(-np.log10(self.threshold))),
colour='black', alpha=0.8, linetype='dashed') + ggplot2.theme_classic() + \
ggplot2.theme(**{'legend.position': 'none'}) + ggplot2.scale_colour_brewer(palette="Set1")
g1 = ggplot2.ggplot2.ggplotGrob(p1)
g2 = ggplot2.ggplot2.ggplotGrob(p2)
g3 = ggplot2.ggplot2.ggplotGrob(p3)
robjects.globalenv["g"] = base.rbind(g1, g2, g3, size='first')
robjects.r("grid::grid.draw(g)")
grid.newpage()
logger.debug('Plotted region ' + str(region.bin))
grdevices.dev_off()
def plot_collectors_curve(args, start_times, read_lengths):
"""
Use rpy2 to create a collectors curve of the run
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([float(t - t_0) / float(3600) \
for t in start_times])
r_read_lengths = robjects.IntVector(read_lengths)
# compute the cumulative based on reads or total base pairs
if args.plot_type == 'reads':
y_label = "Total reads"
cumulative = \
r.cumsum(robjects.IntVector([1] * len(start_times)))
elif args.plot_type == 'basepairs':
y_label = "Total base pairs"
cumulative = r.cumsum(r_read_lengths)
# make a data frame of the lists
d = {'start': r_start_times,
'lengths': r_read_lengths,
'cumul': cumulative}
df = robjects.DataFrame(d)
# title
total_reads = len(read_lengths)
total_bp = sum(read_lengths)
plot_title = "Yield: " \
+ str(total_reads) + " reads and " \
+ str(total_bp) + " base pairs."
# plot
gp = ggplot2.ggplot(df)
pp = gp + ggplot2.aes_string(x='start', y='cumul') \
+ ggplot2.geom_point() \
+ ggplot2.geom_line() \
+ ggplot2.scale_x_continuous('Time (hours)') \
+ ggplot2.scale_y_continuous(y_label) \
+ ggplot2.ggtitle(plot_title)
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width = 8.5, height = 8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width = 8.5, height = 8.5,
units = "in", res = 300)
else:
print >>sys.stderr, "Unrecognized extension for %s!" % (plot_file)
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
#text_log+="sum: "+str(rsum(test23)[0])+end
roughbin= round(ma[0]/100)
bins=round(roughbin/100)*100
#ma2=rmax(ed)
#dataf_subset = dataf.rx(dataf.rx2("contig").ro >= 18, true)
scales = importr('scales')
gp = ggplot2.ggplot(dataf)
#geom_histogram(aes(y = ..density..))
# ggplot2.geom_density()+\
# pp = gp + ggplot2.aes_string(x='%s(contrrr)') + ggplot2.geom_histogram()+ggplot2.scale_y_sqrt()
#bins=10
theme=robjects.r('theme(axis.text.x=element_text(angle=90))')
pp = gp + \
ggplot2.aes_string(x='Length') + \
ggplot2.geom_histogram()+\
ggplot2.ggtitle("Found IS fragment lengths")+ \
ggplot2.scale_x_continuous(name="fragment lengths, bin="+str(bins),breaks=scales.pretty_breaks(20)) +\
ggplot2.scale_y_continuous(labels=scales.comma,name="Count",breaks=scales.pretty_breaks(10))+ \
ggplot2.ggtitle(args.title)+\
theme
pp.plot()
robjects.r.ggsave(args.out)
def show4():
open4()
r.source('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/R/end.R',encoding="utf-8")
data = DataFrame.from_csvfile('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/temp/project2.csv')
pp = ggplot2.ggplot(data)+ggplot2.aes_string(x='day', y='time',fill = 'factor(project)')+ggplot2.geom_bar(stat ='identity',position = 'dodge')+ggplot2.ggtitle("两项目时间对比图")+ggplot2.labs(x='日期',y='时间 (min)')+ggplot2.theme(**{'axis.text.x': ggplot2.element_text(angle = 45)})
pp.plot()
def _plt_percountr(dat, independentpdf=False, fname='xpercount.pdf'):
def _filt_dat(dat, item, getlabel=True):
df = pd.DataFrame(dat[item].value_counts())
df.columns = ['count']
if getlabel:
df['label'] = [
list(dat[dat[item] == i]['label'])[0] for i in df.index
]
n = len(df)
mx = max(df['count'])
return df, n, mx
dat = dat[dat['label'] != 'NA']
## NUMBER OF MIRNA PER TSS
df, n, mx = _filt_dat(dat, 'tss', False)
df = {'count': robjects.IntVector(df['count'])}
df = robjects.DataFrame(df)
pt = ggplot2.ggplot(df) + \
ggplot2.geom_histogram(binwidth=1, origin=-.5, alpha=.5, position="identity") + \
ggplot2.xlim(-.5, mx+1) + \
ggplot2.aes_string(x='count') + \
ggplot2.ggtitle('TSS [Total = %s]' % n) + \
ggplot2.labs(x='Number of miRNA per TSS (max = %s)' % mx)
pt_den = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='count', y='..density..') + \
ggplot2.geom_density(binwidth=1, alpha=.5, origin=-.5) + \
ggplot2.geom_histogram(binwidth=1, alpha=.33, position='identity', origin=-.5) + \
ggplot2.ggtitle('TSS [Total = %s]' % n) + \
ggplot2.labs(x='Number of miRNA per TSS (max = %s)' % mx)
## NUMBER OF TSS PER MIRNA
df, n, mx = _filt_dat(dat, 'mirna')
df = {
'count': robjects.IntVector(df['count']),
'label': robjects.StrVector(df['label'])
}
df = robjects.DataFrame(df)
_pm = ggplot2.ggplot(df) + \
ggplot2.geom_histogram(binwidth=1, origin=-.5, alpha=.5, position="identity") + \
ggplot2.xlim(-.5, mx+1) + \
ggplot2.ggtitle('miRNA [Total = %s]' % n)
_pm_den = ggplot2.ggplot(df) + \
ggplot2.geom_density(binwidth=1, alpha=.5, origin=-.5) + \
ggplot2.geom_histogram(binwidth=1, alpha=.33, position='identity', origin=-.5) + \
ggplot2.ggtitle('miRNA [Total = %s]' % n)
## not split by label
pm = _pm + ggplot2.aes_string(x='count')
pm_den = _pm_den + ggplot2.aes_string(x='count', y='..density..')
## split by label
pms = _pm + ggplot2.aes_string(x='count', fill='label')
pm_dens = _pm_den + ggplot2.aes_string(
x='count', fill='label', y='..density..')
## add xlabelling (need to be added after aes_string)
_xlab = ggplot2.labs(x='Number of TSS per miRNA (max = %s)' % mx)
pm += _xlab
pm_den += _xlab
pms += _xlab
pm_dens += _xlab
if independentpdf:
grdevices = importr('grDevices')
grdevices.pdf(fname)
pt.plot()
pt_den.plot()
pm.plot()
pm_den.plot()
pms.plot()
pm_dens.plot()
grdevices.dev_off()
else:
pt.plot()
pt_den.plot()
pm.plot()
pm_den.plot()
pms.plot()
pm_dens.plot()
return
#-- ggplot2mtcars-end
grdevices.dev_off()
grdevices.png('../../_static/graphics_ggplot2geombin2d.png',
width = 1000, height = 350, antialias="subpixel", type="cairo")
grid.newpage()
grid.viewport(layout=grid.layout(1, 3)).push()
vp = grid.viewport(**{'layout.pos.col':1, 'layout.pos.row': 1})
#-- ggplot2geombin2d-begin
gp = ggplot2.ggplot(dataf_rnorm)
pp = gp + \
ggplot2.aes_string(x='value', y='other_value') + \
ggplot2.geom_bin2d() + \
ggplot2.ggtitle('geom_bin2d')
pp.plot(vp = vp)
#-- ggplot2geombin2d-end
vp = grid.viewport(**{'layout.pos.col':2, 'layout.pos.row': 1})
#-- ggplot2geomdensity2d-begin
gp = ggplot2.ggplot(dataf_rnorm)
pp = gp + \
ggplot2.aes_string(x='value', y='other_value') + \
ggplot2.geom_density2d() + \
ggplot2.ggtitle('geom_density2d')
pp.plot(vp = vp)
#-- ggplot2geomdensity2d-end
vp = grid.viewport(**{'layout.pos.col':3, 'layout.pos.row': 1})
def plot_collectors_curve(args, start_times, read_lengths):
"""
Use rpy2 to create a collectors curve of the run
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([float(t - t_0) / float(3600) + 0.00000001 \
for t in start_times])
r_read_lengths = robjects.IntVector(read_lengths)
# compute the cumulative based on reads or total base pairs
if args.plot_type == 'reads':
y_label = "Total reads"
cumulative = \
r.cumsum(robjects.IntVector([1] * len(start_times)))
elif args.plot_type == 'basepairs':
y_label = "Total base pairs"
cumulative = r.cumsum(r_read_lengths)
step = args.skip
# make a data frame of the lists
d = {
'start':
robjects.FloatVector(
[r_start_times[n] for n in xrange(0, len(r_start_times), step)]),
'lengths':
robjects.IntVector(
[r_read_lengths[n] for n in xrange(0, len(r_read_lengths), step)]),
'cumul':
robjects.IntVector(
[cumulative[n] for n in xrange(0, len(cumulative), step)])
}
df = robjects.DataFrame(d)
if args.savedf:
robjects.r("write.table")(df, file=args.savedf, sep="\t")
# title
total_reads = len(read_lengths)
total_bp = sum(read_lengths)
plot_title = "Yield: " \
+ str(total_reads) + " reads and " \
+ str(total_bp) + " base pairs."
# plot
gp = ggplot2.ggplot(df)
pp = gp + ggplot2.aes_string(x='start', y='cumul') \
+ ggplot2.geom_step(size=2) \
+ ggplot2.scale_x_continuous('Time (hours)') \
+ ggplot2.scale_y_continuous(y_label) \
+ ggplot2.ggtitle(plot_title)
# extrapolation
if args.extrapolate:
start = robjects.ListVector({'a': 1, 'b': 1})
pp = pp + ggplot2.stat_smooth(fullrange='TRUE', method='nls',
formula='y~a*I((x*3600)^b)',
se='FALSE', start=start) \
+ ggplot2.xlim(0, float(args.extrapolate))
if args.theme_bw:
pp = pp + ggplot2.theme_bw()
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width=8.5, height=8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file,
width=8.5,
height=8.5,
units="in",
res=300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
def plot_cels(expr, expt_names, expt_name_idx, cel_names, outdir=None):
"""Makes correlation plots between CEL files for the same cell type"""
fsize = 10
names_1 = []
names_2 = []
cors = []
titles = []
for ex_idx, ex in enumerate(expt_names):
# Indices of CEL files (columns of expr) corresponding to that cell type
tmp_idx = expt_name_idx[ex]
plot_idx = 0
for i in range(len(tmp_idx)):
name1 = re.sub('_', '.', cel_names[tmp_idx[i]])
for j in range(i + 1, len(tmp_idx)):
name2 = re.sub('_', '.', cel_names[tmp_idx[j]])
plot_idx += 1
cor = np.corrcoef(expr[:, tmp_idx[i]], expr[:, tmp_idx[j]])[0,
1]
names_1.append(name1)
names_2.append(name2)
cors.append(cor)
titles.append(ex + '-' + str(plot_idx))
df = ro.DataFrame({
'x': ro.FloatVector(expr[:, tmp_idx[i]]),
'y': ro.FloatVector(expr[:, tmp_idx[j]])
})
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x = 'x', y = 'y') + \
ggplot2.geom_point(size = 1) + \
ggplot2.scale_x_continuous(name1) + ggplot2.scale_y_continuous(name2) + \
ggplot2.theme_bw() + ggplot2.ggtitle('{:s}-{:d} ({:.4f})'.format(ex, plot_idx, cor)) + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.title.x':ggplot2.element_text(size = 8),
'axis.text.y':ggplot2.element_text(size = fsize),
'axis.title.y':ggplot2.element_text(size = 8, angle = 90),
'plot.title':ggplot2.element_text(size = fsize)})
if outdir is None:
gp.plot()
else:
if not os.path.isdir(outdir):
os.makedirs(outdir)
outfile = os.path.join(outdir,
ex + '-' + str(plot_idx) + '.png')
ro.r.ggsave(filename=outfile,
plot=gp,
width=85,
height=85,
unit='mm')
df = pd.DataFrame({
'name1': names_1,
'name2': names_2,
'cor': cors
},
index=titles)
if not outdir is None:
df.to_csv(os.path.join(outdir, 'cor_summary.txt'), sep='\t')
return df
#print onlysurf
#colours2 = grdevices.topo_colors(10)
colours2 = grdevices.cm_colors(10)
#colours2 = grdevices.rainbow(20)
#print colours2
#colours = ggplot2.rainbow(54)
#bins=10
gp = ggplot2.ggplot(onlysurf)
#gp = ggplot2.ggplot(onlyfilts)
gp=gp+ggplot2.aes_string(x="Lon", y="Lat", col="Temp",label="Station")
gp=gp+ggplot2.scale_colour_gradientn(colours=colours2)
gp=gp+ggplot2.geom_text(col="black",offset = 10)
gp=gp+ggplot2.geom_point(position="jitter")
gp=gp+ggplot2.ggtitle(graphtitle)
robjects.r('library(ggmap)')
robjects.r('library(mapproj)')
robjects.r('map <- get_map(location = "Europe", zoom = 4)')
robjects.r('ggmap(map)')
#robjects.r('library(maps)')
#robjects.r('map("world", interior = FALSE)')
#robjects.r('map("state", boundary = FALSE, col="gray", add = TRUE)')
#gp.plot()
'''
pp = gp + \
r_sq_lab = "R^{2}~"+r_sq
y_lab = r("expression(Discharge (m^{3}/s))")
x_lab = r("expression(Area (km^{2}))")
annotate1 = r('annotate("text", x = '+str(max(areas)-30)+', y = 0.5, color = "red", label = "Mean Annual", parse=FALSE)')
annotate2 = r('annotate("text", x = '+str(max(areas)-30)+', y = 0.42, label = "'+r_sq_lab+'", color = "red", parse=TRUE)')
annotate3 = r('annotate("text", x = '+str(max(areas)-30)+', y = 0.34, label = "slope~'+sl+'", color = "red", parse=TRUE)')
annotate4 = r('annotate("text", x = '+str(max(areas)-150)+', y = 0.7, color = "blue", label = "LGM", parse=FALSE)')
annotate5 = r('annotate("text", x = '+str(max(areas)-150)+', y = 0.6, color = "blue", label = "'+r_sq_lab_lgm+'", parse=TRUE)')
annotate6 = r('annotate("text", x = '+str(max(areas)-150)+', y = 0.5, color = "blue", label = "slope~'+sl_lgm+'", parse=TRUE)')
pp = ggplot2.ggplot(dat_frame) + \
ggplot2.aes_string(y='discharge', x='areas') + \
ggplot2.ggtitle('Area vs. Sediment Flux') + \
ggplot2.scale_x_log10(x_lab) + \
ggplot2.theme_bw() + \
ggplot2.stat_smooth(method = "lm", formula = 'y ~ x') + \
ggplot2.scale_y_log10(y_lab) + \
annotate1 + \
annotate2 + \
annotate3 + \
annotate4 + \
annotate5 + \
annotate6 + \
ggplot2.geom_point(color='blue') + \
ggplot2.geom_errorbar(ggplot2.aes_string(ymin='min',ymax='max'), data=dat_frame, width=.02, alpha=.3) + \
ggplot2.geom_point(data=dat_frame2,color='red',show_guide='FALSE' ) + \
ggplot2.stat_smooth(data=dat_frame2, method = "lm", formula = 'y ~ x', color='red')
grdevices.png('../../_static/graphics_ggplot2geombin2d.png',
width=1000,
height=350,
antialias="subpixel",
type="cairo")
grid.newpage()
grid.viewport(layout=grid.layout(1, 3)).push()
vp = grid.viewport(**{'layout.pos.col': 1, 'layout.pos.row': 1})
#-- ggplot2geombin2d-begin
gp = ggplot2.ggplot(dataf_rnorm)
pp = gp + \
ggplot2.aes_string(x='value', y='other_value') + \
ggplot2.geom_bin2d() + \
ggplot2.ggtitle('geom_bin2d')
pp.plot(vp=vp)
#-- ggplot2geombin2d-end
vp = grid.viewport(**{'layout.pos.col': 2, 'layout.pos.row': 1})
#-- ggplot2geomdensity2d-begin
gp = ggplot2.ggplot(dataf_rnorm)
pp = gp + \
ggplot2.aes_string(x='value', y='other_value') + \
ggplot2.geom_density2d() + \
ggplot2.ggtitle('geom_density2d')
pp.plot(vp=vp)
#-- ggplot2geomdensity2d-end
vp = grid.viewport(**{'layout.pos.col': 3, 'layout.pos.row': 1})
def plot_squiggle(args, filename, start_times, mean_signals):
"""
Use rpy2 to create a squiggle plot of the read
"""
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
# set t_0 as the first measured time for the read.
t_0 = start_times[0]
total_time = start_times[-1] - start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([t - t_0 for t in start_times])
r_mean_signals = robjects.FloatVector(mean_signals)
# infer the appropriate number of events given the number of facets
num_events = len(r_mean_signals)
events_per_facet = (num_events / args.num_facets) + 1
# dummy variable to control faceting
facet_category = robjects.FloatVector([(i / events_per_facet) + 1
for i in range(len(start_times))])
# make a data frame of the start times and mean signals
d = {'start': r_start_times, 'mean': r_mean_signals, 'cat': facet_category}
df = robjects.DataFrame(d)
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)})
else:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)}) \
+ ggplot2.theme_bw()
if args.saveas is not None:
plot_file = os.path.basename(filename) + "." + args.saveas
if os.path.isfile(plot_file):
raise Exception(
'Cannot create plot for %s: plot file %s already exists' %
(filename, plot_file))
if args.saveas == "pdf":
grdevices.pdf(plot_file, width=8.5, height=11)
elif args.saveas == "png":
grdevices.png(plot_file, width=8.5, height=11, units="in", res=300)
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
