def plot_crawldb_status(self, data, row_filter, img_file, ratio=1.0):
if row_filter:
data = data[data['type'].isin(row_filter)]
categories = []
for value in row_filter:
if re.search('^crawldb:status:db_', value):
replacement = re.sub('^crawldb:status:db_', '', value)
categories.append(replacement)
data.replace(to_replace=value, value=replacement, inplace=True)
data['type'] = pandas.Categorical(data['type'],
ordered=True,
categories=categories.reverse())
data['size'] = data['size'].astype(float)
ratio = 0.1 + len(data['crawl'].unique()) * .03
print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='size', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='Pastel1', type='sequential',
guide=ggplot2.guide_legend(reverse=False)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='CrawlDb Size and Status Counts\n(before crawling)',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path, height=int(7 * ratio), width=7)
return p
def plot_fetch_status(self, data, row_filter, img_file, ratio=1.0):
if row_filter:
data = data[data['type'].isin(row_filter)]
data = data[['crawl', 'percentage', 'type']]
categories = []
for value in row_filter:
if re.search('^fetcher:(?:aggr:)?', value):
replacement = re.sub('^fetcher:(?:aggr:)?', '', value)
categories.append(replacement)
data.replace(to_replace=value, value=replacement, inplace=True)
data['type'] = pandas.Categorical(data['type'],
ordered=True,
categories=categories.reverse())
ratio = 0.1 + len(data['crawl'].unique()) * .03
# print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='percentage', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='RdYlGn', type='sequential',
guide=ggplot2.guide_legend(reverse=True)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='Percentage of Fetch Status',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path, height=int(7 * ratio), width=7)
return p
def plot_thresh_distr(motif_names, thresh, out_dir, width = 350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif':motif_names, 'thresh':thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep = '\t', index = False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename = os.path.join(out_dir, 'count_thresh_bar' + ext),
plot = gp, width = width, height = 300, unit = 'mm')
def plot_thresh_distr(motif_names, thresh, out_dir, width=350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif': motif_names, 'thresh': thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep='\t', index=False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename=os.path.join(out_dir, 'count_thresh_bar' + ext),
plot=gp,
width=width,
height=300,
unit='mm')
def plot_stacked_bar(self, data, row_filter, img_file, ratio=1.0):
if len(row_filter) > 0:
data = data[data['type'].isin(row_filter)]
for value in row_filter:
if re.search('^fetcher:(?:aggr:)?', value):
replacement = re.sub('^fetcher:(?:aggr:)?', '', value)
data.replace(to_replace=value, value=replacement, inplace=True)
# print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='percentage', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='RdYlGn', type='sequential',
guide=ggplot2.guide_legend(reverse=True)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='Percentage of Fetch Status',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path)
return p
def plot_fetch_status(self, data, row_filter, img_file, ratio=1.0):
if len(row_filter) > 0:
data = data[data['type'].isin(row_filter)]
for value in row_filter:
if re.search('^fetcher:(?:aggr:)?', value):
replacement = re.sub('^fetcher:(?:aggr:)?', '', value)
data.replace(to_replace=value, value=replacement, inplace=True)
# print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='percentage', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='RdYlGn', type='sequential',
guide=ggplot2.guide_legend(reverse=True)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='Percentage of Fetch Status',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path)
return p
def plot_crawldb_status(self, data, row_filter, img_file, ratio=1.0):
if len(row_filter) > 0:
data = data[data['type'].isin(row_filter)]
for value in row_filter:
if re.search('^crawldb:status:db_', value):
replacement = re.sub('^crawldb:status:db_', '', value)
data.replace(to_replace=value, value=replacement, inplace=True)
data['size'] = data['size'].astype(float)
print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='size', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='Pastel1', type='sequential',
guide=ggplot2.guide_legend(reverse=False)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='CrawlDb Size and Status Counts (before crawling)',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path)
return p
def plot(self,
fn,
x='x',
y='y',
col=None,
group=None,
w=1100,
h=800,
size=2,
smooth=True,
point=True,
jitter=False,
boxplot=False,
boxplot2=False,
title=False,
flip=False,
se=False,
density=False,
line=False):
df = self.df
#import math, datetime
grdevices = importr('grDevices')
if not title:
title = fn.split("/")[-1]
grdevices.png(file=fn, width=w, height=h)
gp = ggplot2.ggplot(df)
pp = gp
if col and group:
pp += ggplot2.aes_string(x=x, y=y, col=col, group=group)
elif col:
pp += ggplot2.aes_string(x=x, y=y, col=col)
elif group:
pp += ggplot2.aes_string(x=x, y=y, group=group)
else:
pp += ggplot2.aes_string(x=x, y=y)
if boxplot:
if col:
pp += ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),
color='blue')
else:
pp += ggplot2.geom_boxplot(color='blue')
if point:
if jitter:
if col:
pp += ggplot2.geom_point(ggplot2.aes_string(fill=col,
col=col),
size=size,
position='jitter')
else:
pp += ggplot2.geom_point(size=size, position='jitter')
else:
if col:
pp += ggplot2.geom_point(ggplot2.aes_string(fill=col,
col=col),
size=size)
else:
pp += ggplot2.geom_point(size=size)
if boxplot2:
if col:
pp += ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),
color='blue',
outlier_colour="NA")
else:
pp += ggplot2.geom_boxplot(color='blue')
if smooth:
if smooth == 'lm':
if col:
pp += ggplot2.stat_smooth(ggplot2.aes_string(col=col),
size=1,
method='lm',
se=se)
else:
pp += ggplot2.stat_smooth(col='blue',
size=1,
method='lm',
se=se)
else:
if col:
pp += ggplot2.stat_smooth(ggplot2.aes_string(col=col),
size=1,
se=se)
else:
pp += ggplot2.stat_smooth(col='blue', size=1, se=se)
if density:
pp += ggplot2.geom_density(ggplot2.aes_string(x=x, y='..count..'))
if line:
pp += ggplot2.geom_line(position='jitter')
pp += ggplot2.opts(
**{
'title': title,
'axis.text.x': ggplot2.theme_text(size=24),
'axis.text.y': ggplot2.theme_text(size=24, hjust=1)
})
#pp+=ggplot2.scale_colour_brewer(palette="Set1")
pp += ggplot2.scale_colour_hue()
if flip:
pp += ggplot2.coord_flip()
pp.plot()
grdevices.dev_off()
print ">> saved: " + fn
def plot(self, fn, x='x', y='y', col=None, group=None, w=1100, h=800, size=2, smooth=True, point=True, jitter=False, boxplot=False, boxplot2=False, title=False, flip=False, se=False, density=False, line=False):
df=self.df
#import math, datetime
grdevices = importr('grDevices')
if not title:
title=fn.split("/")[-1]
grdevices.png(file=fn, width=w, height=h)
gp = ggplot2.ggplot(df)
pp = gp
if col and group:
pp+=ggplot2.aes_string(x=x, y=y,col=col,group=group)
elif col:
pp+=ggplot2.aes_string(x=x, y=y,col=col)
elif group:
pp+=ggplot2.aes_string(x=x, y=y,group=group)
else:
pp+=ggplot2.aes_string(x=x, y=y)
if boxplot:
if col:
pp+=ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),color='blue')
else:
pp+=ggplot2.geom_boxplot(color='blue')
if point:
if jitter:
if col:
pp+=ggplot2.geom_point(ggplot2.aes_string(fill=col,col=col),size=size,position='jitter')
else:
pp+=ggplot2.geom_point(size=size,position='jitter')
else:
if col:
pp+=ggplot2.geom_point(ggplot2.aes_string(fill=col,col=col),size=size)
else:
pp+=ggplot2.geom_point(size=size)
if boxplot2:
if col:
pp+=ggplot2.geom_boxplot(ggplot2.aes_string(fill=col),color='blue',outlier_colour="NA")
else:
pp+=ggplot2.geom_boxplot(color='blue')
if smooth:
if smooth=='lm':
if col:
pp+=ggplot2.stat_smooth(ggplot2.aes_string(col=col),size=1,method='lm',se=se)
else:
pp+=ggplot2.stat_smooth(col='blue',size=1,method='lm',se=se)
else:
if col:
pp+=ggplot2.stat_smooth(ggplot2.aes_string(col=col),size=1,se=se)
else:
pp+=ggplot2.stat_smooth(col='blue',size=1,se=se)
if density:
pp+=ggplot2.geom_density(ggplot2.aes_string(x=x,y='..count..'))
if line:
pp+=ggplot2.geom_line(position='jitter')
pp+=ggplot2.opts(**{'title' : title, 'axis.text.x': ggplot2.theme_text(size=24), 'axis.text.y': ggplot2.theme_text(size=24,hjust=1)} )
#pp+=ggplot2.scale_colour_brewer(palette="Set1")
pp+=ggplot2.scale_colour_hue()
if flip:
pp+=ggplot2.coord_flip()
pp.plot()
grdevices.dev_off()
print ">> saved: "+fn
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)
