def makePlot(grdevices, plotName, samp_set1_vals, samp_set2_vals,
image_file_type):
samp_vector = ["set1" for i in range(len(samp_set1_vals))]
samp_vector.extend(["set2" for i in range(len(samp_set2_vals))])
dframe = robjects.DataFrame({
"sample":
robjects.StrVector(samp_vector),
"value":
robjects.FloatVector(samp_set1_vals + samp_set2_vals)
})
gp = ggplot2.ggplot(dframe)
pp = gp + \
ggplot2.aes_string(x="sample", y='value') + \
ggplot2.geom_boxplot() +\
ggplot2.geom_jitter() +\
ggplot2.theme_bw()
if image_file_type == "pdf":
grdevices.pdf(file=plotName)
else:
grdevices.png(file=plotName, width=512, height=512)
pp.plot()
grdevices.dev_off()
def interval(locus_table, interval_table, intervals, loci, boxplot = True):
qry = get_interval_query(intervals, loci, locus_table, interval_table)
frame = robjects.r('''data <- dbGetQuery(con, {})'''.format(qry))
# because we're sorting by interval, which is a factor, we need to
# explicitly re-sort the data by the first integer value
# of the interval. This is a bit cumbersome, because sorting
# in R is less than pleasant.
sort_string = '''data$interval <- factor(data$interval, {})'''.format(order_intervals(frame[1]))
robjects.r(sort_string)
gg_frame = ggplot2.ggplot(robjects.r('''data'''))
if boxplot:
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi') + \
ggplot2.geom_boxplot(**{
'outlier.size':0,
'alpha':0.3
}
) + \
ggplot2.geom_jitter(ggplot2.aes_string(color = 'locus'), size = 3, \
alpha = 0.6, position=ggplot2.position_jitter(width=0.25)) + \
ggplot2.scale_y_continuous('phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)')
else:
plot = gg_frame + ggplot2.aes_string(x = 'interval', y = 'pi',
fill='locus') + ggplot2.geom_bar() + \
ggplot2.facet_wrap(robjects.Formula('~ locus')) + \
ggplot2.opts(**{
'axis.text.x':ggplot2.theme_text(angle = -90, hjust = 0),
'legend.position':'none'
}) + \
ggplot2.scale_y_continuous('phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)')
return plot
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_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 plot_dupl_url(self):
# -- pages per URL (URL-level duplicates)
row_filter = ['url']
data = self.histogr
data = data[data['type'].isin(row_filter)]
title = 'Pages per URL (URL-level duplicates)'
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='count', y='frequency') \
+ ggplot2.geom_jitter() \
+ ggplot2.facet_wrap('crawl', ncol=5) \
+ ggplot2.labs(title=title, x='(duplicate) pages per URL',
y='log(frequency)') \
+ ggplot2.scale_y_log10()
# + ggplot2.scale_x_log10() # could use log-log scale
img_path = os.path.join(PLOTDIR, 'crawler/histogr_url_dupl.png')
p.save(img_path)
# data.to_csv(img_path + '.csv')
return p
def plot_dupl_url(self):
# -- pages per URL (URL-level duplicates)
row_filter = ['url']
data = self.histogr
data = data[data['type'].isin(row_filter)]
title = 'Pages per URL (URL-level duplicates)'
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='count', y='frequency') \
+ ggplot2.geom_jitter() \
+ ggplot2.facet_wrap('crawl', ncol=5) \
+ ggplot2.labs(title=title, x='(duplicate) pages per URL',
y='log(frequency)') \
+ ggplot2.scale_y_log10()
# + ggplot2.scale_x_log10() # could use log-log scale
img_path = os.path.join(PLOTDIR, 'crawler/histogr_url_dupl.png')
p.save(img_path)
# data.to_csv(img_path + '.csv')
return p
def makePlot(grdevices, plotName, samp_set1_vals, samp_set2_vals,
image_file_type):
samp_vector = ["set1" for i in range(len(samp_set1_vals))]
samp_vector.extend(["set2" for i in range(len(samp_set2_vals))])
dframe = robjects.DataFrame({"sample":robjects.StrVector(samp_vector),
"value":robjects.FloatVector(samp_set1_vals + samp_set2_vals)})
gp = ggplot2.ggplot(dframe)
pp = gp + \
ggplot2.aes_string(x="sample", y='value') + \
ggplot2.geom_boxplot() +\
ggplot2.geom_jitter() +\
ggplot2.theme_bw()
if image_file_type == "pdf":
grdevices.pdf(file=plotName)
else:
grdevices.png(file=plotName, width=512, height=512)
pp.plot()
grdevices.dev_off()
