def plot_qc_percents(qc_df):
"""
Plot percentage parts of pipeline QC file.
"""
# Record NA values as 0
qc_df = qc_df.fillna(0).set_index("sample")
r.par(mfrow=np.array([1,2]))
num_samples = len(qc_df.num_reads)
r_opts = r.options(scipen=10)
r.options(r_opts)
r.par(bty="n", lwd=1.7, lty=2)
r.dotchart(convert_to_r_matrix(qc_df[["percent_mapped",
"percent_unique",
"percent_ribo"]]),
xlab="Percent reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)
r.par(bty="n")
r.dotchart(convert_to_r_matrix(qc_df[["percent_exons",
"percent_cds",
"percent_3p_utr",
"percent_5p_utr",
"percent_introns"]]),
xlab="Percent reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)
def RWarnings(level):
"""
There are two levels: 'error' and 'ignore'. With 'error', R warnings are
treated as R errors and can be caught as RRuntimeError. With 'ignore', they
are ignored and not even printed. Beware that all Python warning filters
will be reset after using this context manager.
"""
new = {"error": 2, "ignore": -1}[level]
old = r.getOption("warn")
warnings.filterwarnings("ignore", category=RRuntimeWarning)
r.options(warn=new)
yield
r.options(warn=old)
warnings.resetwarnings()
def plot_qc_reads(qc_df):
"""
Plot number of reads part of a pipeline QC file.
"""
# Record NA values as 0
qc_df = qc_df.fillna(0)#.set_index("sample")
cols = ["sample",
"num_reads",
"num_mapped",
"num_unique_mapped",
"num_junctions"]
qc_df = qc_df[cols]
melted_qc = pandas.melt(qc_df, id_vars=["sample"])
qc_r = conversion_pydataframe(melted_qc)
labels = tuple(["num_reads",
"num_mapped",
"num_unique_mapped",
"num_junctions"])
labels = robj.StrVector(labels)
variable_i = qc_r.names.index('variable')
qc_r[variable_i] = robj.FactorVector(qc_r[variable_i],
levels = labels)
ggplot2.theme_set(ggplot2.theme_bw(12))
scales = importr("scales")
r_opts = r.options(scipen=4)
p = ggplot2.ggplot(qc_r) + \
ggplot2.geom_point(aes_string(x="sample", y="value")) + \
ggplot2.scale_y_continuous(trans=scales.log10_trans(),
breaks=scales.trans_breaks("log10",
robj.r('function(x) 10^x')),
labels=scales.trans_format("log10",
robj.r('math_format(10^.x)'))) + \
r.xlab("CLIP-Seq samples") + \
r.ylab("No. reads") + \
ggplot2.coord_flip() + \
ggplot2.facet_wrap(Formula("~ variable"), ncol=1) + \
theme(**{"panel.grid.major.x": element_blank(),
"panel.grid.minor.x": element_blank(),
"panel.grid.major.y": theme_line(size=0.5,colour="grey66",linetype=3)})
p.plot()
return
r.par(mfrow=np.array([1,2]))
num_samples = len(qc_df.num_reads)
r.par(bty="n", lwd=1.7, lty=2)
r_opts = r.options(scipen=4)
r.options(r_opts)
r.dotchart(convert_to_r_matrix(qc_df[["num_reads",
"num_mapped",
"num_unique_mapped"]]),
xlab="No. reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)
r.par(bty="n")
r.dotchart(convert_to_r_matrix(qc_df[["num_ribosub_mapped",
"num_ribo",
"num_junctions"]]),
xlab="No. reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)