def rank_abundance_plot(counter, name):
grdevices.png('analytics_out/{0}_rank_abundance.png'.format(name))
ranks, fracs = rank_abundance_data(counter)
df = robjects.DataFrame({'rank': ranks, 'f': fracs})
pp = ggplot.ggplot(df) + \
ggplot.aes_string(x = 'rank', y = 'f') + \
ggplot.geom_point() + \
ggplot.scale_y_log10(name = 'fraction of hits')
pp.plot()
grdevices.dev_off()
def plot_host_domain_tld(self):
# -- pages/URLs per host / domain / tld
data = self.histogr
data = data[data['type'].isin(['host', 'domain', 'tld'])]
data = data[data['type_counted'].isin(['url'])]
img_path = os.path.join(PLOTDIR, 'crawler/histogr_host_domain_tld.png')
# data.to_csv(img_path + '.csv')
title = 'URLs per Host / Domain / TLD'
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='count', weight='frequency', color='type') \
+ ggplot2.geom_freqpoly(bins=20) \
+ ggplot2.facet_wrap('crawl', ncol=4) \
+ ggplot2.labs(title='', x=title,
y='Frequency') \
+ ggplot2.scale_y_log10() \
+ ggplot2.scale_x_log10()
p.save(img_path)
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 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_host_domain_tld(self):
# -- pages/URLs per host / domain / tld
data = self.histogr
data = data[data['type'].isin(['host', 'domain', 'tld'])]
data = data[data['type_counted'].isin(['url'])]
img_path = os.path.join(PLOTDIR,
'crawler/histogr_host_domain_tld.png')
# data.to_csv(img_path + '.csv')
title = 'URLs per Host / Domain / TLD'
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='count', weight='frequency', color='type') \
+ ggplot2.geom_freqpoly(bins=20) \
+ ggplot2.facet_wrap('crawl', ncol=4) \
+ ggplot2.labs(title='', x=title,
y='Frequency') \
+ ggplot2.scale_y_log10() \
+ ggplot2.scale_x_log10()
p.save(img_path)
return p
def scatter(self, dataframe, filename, parm1, parm2, units1, units2, group,logx,logy): grdevices.png(file=filename, width=512, height=512) data = ggplot2.ggplot(dataframe) aes = ggplot2.aes_string(x=parm1, y=parm2,colour=group) geom = ggplot2.geom_point(alpha = 0.7) labs = ggplot2.labs(x=parm1+ " " + units1, y=parm2 + " " + units2) xlogscale = ggplot2.scale_x_log10() ylogscale = ggplot2.scale_y_log10() if logx == True and logy == True: gg = data + aes + geom + labs + xlogscale + ylogscale elif logx == True: gg = data + aes + geom + labs + xlogscale elif logy == True: gg = data + aes + geom + labs + ylogscale else: gg = data + aes + geom + labs gg.plot() grdevices.dev_off()
def scatter(self, dataframe, filename, parm1, parm2, units1, units2, group,
logx, logy):
grdevices.png(file=filename, width=512, height=512)
data = ggplot2.ggplot(dataframe)
aes = ggplot2.aes_string(x=parm1, y=parm2, colour=group)
geom = ggplot2.geom_point(alpha=0.7)
labs = ggplot2.labs(x=parm1 + " " + units1, y=parm2 + " " + units2)
xlogscale = ggplot2.scale_x_log10()
ylogscale = ggplot2.scale_y_log10()
if logx == True and logy == True:
gg = data + aes + geom + labs + xlogscale + ylogscale
elif logx == True:
gg = data + aes + geom + labs + xlogscale
elif logy == True:
gg = data + aes + geom + labs + ylogscale
else:
gg = data + aes + geom + labs
gg.plot()
grdevices.dev_off()
def plot_domain_cumul(self, crawl):
# -- coverage (cumulative pages) per domain
data = self.histogr
data = data[data['type'].isin(['domain'])]
data = data[data['crawl'] == crawl]
data = data[data['type_counted'].isin(['url'])]
data['urls'] = data['count']*data['frequency']
print(data)
data = data[['urls', 'count', 'frequency']]
data = data.sort_values(['count'], ascending=0)
data['cum_domains'] = data['frequency'].cumsum()
data['cum_urls'] = data['urls'].cumsum()
data_perc = data.apply(lambda x: round(100.0*x/float(x.sum()), 1))
data['%domains'] = data_perc['frequency']
data['%urls'] = data_perc['urls']
data['%cum_domains'] = data['cum_domains'].apply(
lambda x: round(100.0*x/float(data['frequency'].sum()), 1))
data['%cum_urls'] = data['cum_urls'].apply(
lambda x: round(100.0*x/float(data['urls'].sum()), 1))
with pandas.option_context('display.max_rows', None,
'display.max_columns', None,
'display.width', 200):
print(data)
img_path = os.path.join(PLOTDIR,
'crawler/histogr_domain_cumul.png')
# data.to_csv(img_path + '.csv')
title = 'Cumulative URLs for Top Domains'
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='cum_domains', y='cum_urls') \
+ ggplot2.geom_line() + ggplot2.geom_point() \
+ GGPLOT2_THEME \
+ ggplot2.labs(title=title, x='domains cumulative',
y='URLs cumulative') \
+ ggplot2.scale_y_log10() \
+ ggplot2.scale_x_log10()
p.save(img_path)
return p
def plot_domain_cumul(self, crawl):
# -- coverage (cumulative pages) per domain
data = self.histogr
data = data[data['type'].isin(['domain'])]
data = data[data['crawl'] == crawl]
data = data[data['type_counted'].isin(['url'])]
data['urls'] = data['count'] * data['frequency']
print(data)
data = data[['urls', 'count', 'frequency']]
data = data.sort_values(['count'], ascending=0)
data['cum_domains'] = data['frequency'].cumsum()
data['cum_urls'] = data['urls'].cumsum()
data_perc = data.apply(lambda x: round(100.0 * x / float(x.sum()), 1))
data['%domains'] = data_perc['frequency']
data['%urls'] = data_perc['urls']
data['%cum_domains'] = data['cum_domains'].apply(
lambda x: round(100.0 * x / float(data['frequency'].sum()), 1))
data['%cum_urls'] = data['cum_urls'].apply(
lambda x: round(100.0 * x / float(data['urls'].sum()), 1))
with pandas.option_context('display.max_rows', None,
'display.max_columns', None,
'display.width', 200):
print(data)
img_path = os.path.join(PLOTDIR, 'crawler/histogr_domain_cumul.png')
# data.to_csv(img_path + '.csv')
title = 'Cumulative URLs for Top Domains'
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='cum_domains', y='cum_urls') \
+ ggplot2.geom_line() + ggplot2.geom_point() \
+ GGPLOT2_THEME \
+ ggplot2.labs(title=title, x='domains cumulative',
y='URLs cumulative') \
+ ggplot2.scale_y_log10() \
+ ggplot2.scale_x_log10()
p.save(img_path)
return p
ggplot2.scale_colour_manual("Color",
values=colormap,
breaks=colormap.names,
labels=[elt[1] for elt in
colormap_labels]) + \
ggplot2.geom_point(size=3) + \
ggplot2.scale_linetype_manual(values=linemap) + \
ggplot2.geom_line(size=1.5)
# custom y-axis lines: major lines ("breaks") are every 10^n; 9
# minor lines ("minor_breaks") between major lines
if (yscale == 'log'):
pp = pp + \
ggplot2.scale_y_log10(breaks = ro.r("10^(%d:%d)" % (gflops_range[0],
gflops_range[1])),
minor_breaks =
ro.r("rep(10^(%d:%d), each=9) * rep(1:9, %d)" %
(gflops_range[0] - 1, gflops_range[1],
gflops_range[1] - gflops_range[0])))
#pp.plot(vp = vp)
#-- ggplot2perfcolor-end
grdevices.dev_off()
# grdevices.png('../../_static/graphics_ggplot2coordtranssqrt.png',
# width = 612, height = 612)
# #-- ggplot2coordtranssqrt-begin
# pp = gp + \
# ggplot2.aes_string(x='wt', y='mpg') + \
# ggplot2.scale_y_sqrt() + \
# ggplot2.geom_point()
ggplot2.scale_colour_manual("Color",
values=colormap,
breaks=colormap.names,
labels=[elt[1] for elt in
colormap_labels]) + \
ggplot2.geom_point(size=3) + \
ggplot2.scale_linetype_manual(values=linemap) + \
ggplot2.geom_line(size=1.5)
# custom y-axis lines: major lines ("breaks") are every 10^n; 9
# minor lines ("minor_breaks") between major lines
if (yscale == 'log'):
pp = pp + \
ggplot2.scale_y_log10(breaks = ro.r("10^(%d:%d)" % (gflops_range[0],
gflops_range[1])),
minor_breaks =
ro.r("rep(10^(%d:%d), each=9) * rep(1:9, %d)" %
(gflops_range[0] - 1, gflops_range[1],
gflops_range[1] - gflops_range[0])))
pp.plot(vp = vp)
#-- ggplot2perfcolor-end
grdevices.dev_off()
# grdevices.png('../../_static/graphics_ggplot2coordtranssqrt.png',
# width = 612, height = 612)
# #-- ggplot2coordtranssqrt-begin
# pp = gp + \
# ggplot2.aes_string(x='wt', y='mpg') + \
# ggplot2.scale_y_sqrt() + \
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 = importr('grDevices')
grdevices.pdf(file="area_qs.pdf")
pp.plot()
#!/usr/bin/env python2
import cPickle
import numpy
from rpy2.robjects import FloatVector, DataFrame
from rpy2.robjects.lib import ggplot2
from rpy2.robjects.packages import importr
pscores = cPickle.load(open('bootstrap.pickle'))
pscores.sort()
proportion = numpy.linspace(1, len(pscores), len(pscores)) / len(pscores)
dataf = DataFrame({
'pscore': FloatVector(pscores),
'proportion': FloatVector(proportion),
})
grdevices = importr('grDevices')
#grdevices.postscript(file="pscores.eps", width=512, height=512)
grdevices.postscript(file='pscores.eps')
(
ggplot2.ggplot(dataf)
+ ggplot2.aes_string(y='pscore', x='proportion')
+ ggplot2.geom_point()
+ ggplot2.scale_x_log10()
+ ggplot2.scale_y_log10()
+ ggplot2.stat_smooth(method='lm')
).plot()
grdevices.dev_off()
