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 line_plot(self, data, title, ylabel, img_file,
x='date', y='size', c='type', clabel=''):
if PLOTLIB == 'ggplot':
# date_label = "%Y\n%b"
date_label = "%Y\n%W" # year + week number
p = ggplot(data,
aes(x=x, y=y, color=c)) \
+ ggtitle(title) \
+ ylab(ylabel) \
+ xlab(' ') \
+ scale_x_date(breaks=date_breaks('3 months'),
labels=date_label) \
+ geom_line() + geom_point()
elif PLOTLIB == 'rpy2.ggplot2':
# convert y axis to float because R uses 32-bit signed integers,
# values > 2 bln. (2^31) will overflow
data[y] = data[y].astype(float)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x=x, y=y, color=c) \
+ ggplot2.geom_line() + ggplot2.geom_point() \
+ GGPLOT2_THEME \
+ ggplot2.labs(title=title, x='', y=ylabel, color=clabel)
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path)
# data.to_csv(img_path + '.csv')
return p
def render_plot(gp, args):
"""Render a plot using ggplot
:gp: A base ggplot2 object
:x: The x value expression
:y: The y value expression
:type: The type of plot to make
"""
args = util.Namespace(args)
import rpy2.robjects.lib.ggplot2 as ggplot2
pp = gp + ggplot2.aes_string(x=args.x,
y=args.y)
if args.type == 'points':
pp += ggplot2.geom_point()
elif args.type == 'lines':
pp += ggplot2.geom_line()
elif args.type == 'boxplot':
pp += ggplot2.geom_boxplot()
else:
raise Exception("{0} not implemented".format(args.type))
if args.facets is not None:
try:
pp += ggplot2.facet_grid(ro.Formula(args.facets))
except Exception:
pass
try:
pp.plot()
except Exception:
pass
def plot(data, x, y, ylabel, color, filename):
gp = ggplot2.ggplot(data=data)
gp = gp + \
ggplot2.geom_line(ggplot2.aes_string(x=x, y=y), color=color) + \
ggplot2.theme(**{'axis.text.x' : ggplot2.element_text(angle = 90, hjust = 1),
'strip.text.y' : ggplot2.element_text(size = 6, angle=90)}) + \
ggplot2.scale_y_continuous(ylabel)
ggplot2.ggplot2.ggsave(filename, gp)
def plot_ROC(self, path):
robjects.r['pdf'](path, width=14, height=8)
df = self.df
print(df)
gp = ggplot2.ggplot(convert_to_r_dataframe(df, strings_as_factors=True))
gp += ggplot2.aes_string(x='fpr', y='tpr')
gp += ggplot2.geom_line(color='blue')
gp += ggplot2.geom_point(size=2)
gp.plot()
def plot_ROC(self, path):
robjects.r["pdf"](path, width=14, height=8)
df = self.df
# print(df)
gp = ggplot2.ggplot(convert_to_r_dataframe(df, strings_as_factors=True))
gp += ggplot2.aes_string(x="fpr", y="tpr")
gp += ggplot2.geom_line(color="blue")
gp += ggplot2.geom_point(size=2)
gp.plot()
def plot_all_errors(self, path):
# print self.error_matrix[0]
robjects.r["pdf"](path, width=14, height=8)
df = pandas.melt(self.df, id_vars="iteration")
gp = ggplot2.ggplot(convert_to_r_dataframe(df, strings_as_factors=True))
x_col = "iteration"
gp += ggplot2.aes_string(x=x_col, y="value", color="variable")
gp += ggplot2.geom_point(size=2)
gp += ggplot2.geom_line()
gp.plot()
def generate_step3_5_lrr_acc20_line_chart(subgroups_to_lrrs_acc20mean,
prefix=''):
pandas2ri.activate()
subgroups_to_lrr_count = {}
columns_to_data = {'subgroup': [], 'pos': [], 'acc20': []}
for subgroup, (acc20means,
acc20_count) in subgroups_to_lrrs_acc20mean.items():
subgroups_to_lrr_count[subgroup] = acc20_count
for index, acc20mean in enumerate(acc20means):
columns_to_data['subgroup'].append(subgroup)
columns_to_data['pos'].append(index + 1)
columns_to_data['acc20'].append(acc20mean)
# Write the count of LRRs for each subgroup to file
with open(os.path.join(OUTPUT_PATH, prefix + "step3_5_lrr_count.txt"),
'w') as f:
for subgroup, lrr_count in subgroups_to_lrr_count.items():
f.write(str.format("{}: {}\n", subgroup, lrr_count))
# Generate the line chart file
r_columns_to_data = {
'subgroup': ro.StrVector(columns_to_data['subgroup']),
'pos': ro.IntVector(columns_to_data['pos']),
'acc20': ro.FloatVector(columns_to_data['acc20'])
}
df = ro.DataFrame(r_columns_to_data)
line_chart_file_path = os.path.join(OUTPUT_PATH,
prefix + "step3_5_lrr_acc20_line.png")
logging.debug(
str.format("The Data Frame for file {}: \n{}", line_chart_file_path,
df))
grdevices.png(file=line_chart_file_path, width=1024, height=512)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.theme_bw() + \
ggplot2.theme_classic() + \
ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=35)}) + \
ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=35)}) + \
ggplot2.aes_string(x='pos', y='acc20', group='subgroup', colour='subgroup') + \
ggplot2.geom_point(size=4, shape=20) + \
ggplot2.geom_line(size=3) + \
ggplot2.theme(**{'legend.title': ggplot2.element_blank()}) + \
ggplot2.theme(**{'legend.text': ggplot2.element_text(size=20)}) + \
ggplot2.scale_x_continuous(breaks=ro.IntVector(range(1, 25)), labels=ro.StrVector(list('LxxLxLxxNxLsGxIPxxLxxLxx')))
pp.plot()
logging.info(str.format("Output step3 file {}", line_chart_file_path))
grdevices.dev_off()
def _generate_step3_5_ss_acc20_line_chart(ts_to_acc20s, tname,
line_chart_file_path):
logging.debug(
str.format("Begin to generate {}, data {}", line_chart_file_path,
ts_to_acc20s))
ts_to_acc20mean = calc_acc20mean_by_types(ts_to_acc20s)
columns_to_data = {tname: [], 'site': [], 'acc20': []}
for ss, acc20means in ts_to_acc20mean.items():
for index, acc20mean in enumerate(acc20means):
columns_to_data[tname].append(ss)
columns_to_data['site'].append(index - 5)
columns_to_data['acc20'].append(acc20mean)
# Generate the line chart file
r_columns_to_data = {
tname: ro.StrVector(columns_to_data[tname]),
'site': ro.IntVector(columns_to_data['site']),
'acc20': ro.FloatVector(columns_to_data['acc20'])
}
df = ro.DataFrame(r_columns_to_data)
logging.debug(
str.format("The Data Frame for file {}: \n{}", line_chart_file_path,
df))
grdevices.png(file=line_chart_file_path, width=1024, height=512)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.theme_bw() + \
ggplot2.theme_classic() + \
ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=35)}) + \
ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=35)}) + \
ggplot2.aes_string(x='site', y='acc20', group=tname, colour=tname) + \
ggplot2.geom_point(size=4, shape=20) + \
ggplot2.geom_line(size=3) + \
ggplot2.theme(**{'legend.title': ggplot2.element_blank()}) + \
ggplot2.theme(**{'legend.text': ggplot2.element_text(size=20)}) + \
ggplot2.scale_x_continuous(breaks=ro.IntVector(list(range(-5, 6))),
labels=ro.StrVector(['-5', '-4', '-3', '-2', '-1', 'N', '1', '2', '3', '4', '5']))
pp.plot()
logging.info(str.format("Output step3 file {}", line_chart_file_path))
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
'axis.title.x':
element_text(size=12, color=robjects.r.color_axis_title, vjust=0),
#'panel.grid.major':element_line(color=robjects.r.color_grid_major,size=.25),
'axis.title.y':
element_text(size=12, color=robjects.r.color_axis_title, angle=90)
})
pandas2ri.activate()
#set up basic, repetitive plot features
base_plot = ggplot2.aes_string(x='mos_since_start',
y='value',
group='variable',
colour='variable',
shape='variable',
linetype='variable')
line = ggplot2.geom_line()
point = ggplot2.geom_point()
vert_line_onset = ggplot2.geom_vline(xintercept=-1.5,
linetype=2,
colour="#999999")
vert_line_exhaust = ggplot2.geom_vline(xintercept=5.5,
linetype=2,
colour="#999999")
vert_line_exhaust_FL = ggplot2.geom_vline(xintercept=3.5,
linetype=2,
colour="#999999")
colors = ggplot2.scale_colour_manual(values=robjects.r.palette_lines)
hollow = ggplot2.scale_shape_manual(
values=robjects.r('c(16,17,15,18,6,7,9,3)'))
xlab = ggplot2.labs(x="Months Since First UI Check")
loc_default = robjects.r('c(1,0)')
xmin = np.min(x)
xmax = np.max(x)
xs = np.linspace(xmin, xmax, num=100).reshape(100, 1)
lm = LinearRegression()
# The training data for scikit models must be in matrix
# form, i.e. columns == features, rows == observations.
# For this we need to reshape the 1-dimensional arrays.
X = corr_nci60.reshape(len(x), 1)
y = corr_sec
lm.fit(X, y)
y_pred = lm.predict(xs)
# Plot the data using the R-bridge rpy and ggplot
p = gg.ggplot(pd.DataFrame())
p += gg.geom_point(
gg.aes_string(x='r_nci60', y='r_sec'),
data=pd.DataFrame({
'r_nci60': corr_nci60,
'r_sec': corr_sec
})
)
p += gg.geom_line(
gg.aes_string(x='x', y='y'),
data=pd.DataFrame({
'x': xs.reshape(-1),
'y': y_pred
}),
color='red'
)
p.plot()
for col_i, yscale in enumerate(['log', 'linear']):
vp = grid.viewport(**{'layout.pos.col':col_i+1, 'layout.pos.row': 1})
pp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='Date', y='Performance', color='color',
shape='PerfType', linetype='PerfType') + \
ggplot2.opts(**{'title' :
'Performance vs. Color',
'legend.key.size' : ro.r.unit(1.4, "lines") } ) + \
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()
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()
# Create animated .gif of pickups by hour
import imageio
file_names = sorted((fn for fn in os.listdir('./plots') if fn.startswith('taxi_pickups')))
file_names = ['plots/' + s for s in file_names]
images = []
for filename in file_names:
images.append(imageio.imread(filename))
imageio.mimsave('./plots/pickups_movie.gif', images, duration=0.4)
# total pickups by date, color
p1 = ggplot2.ggplot(pandas2ri.py2ri(date_avgs)) + \
ggplot2.aes_string(x='date', y='total_pickups', color='type') + \
ggplot2.scale_colour_manual(values = robjects.StrVector(['green', 'yellow'])) + \
ggplot2.geom_line() + \
ggplot2.theme(legend_position='bottom') + \
ggplot2.labs(y='Total Pickups', x='Date', title='Total Pickups by Date')
p1.save('./plots/pickups_by_date.png', width=6, height=5)
# average fare and tip by date, color
p2 = ggplot2.ggplot(pandas2ri.py2ri(date_avgs)) + \
ggplot2.aes_string(x='date', y='fare_amount', color='type') + \
ggplot2.scale_colour_manual(values = robjects.StrVector(['green', 'yellow'])) + \
ggplot2.geom_line() + \
ggplot2.theme(legend_position='bottom') + \
ggplot2.labs(y='Average Fare ($)', x='Date', title='Average Fare by Date')
p2.save('./plots/fares_by_date.png', width=6, height=5)
p3 = ggplot2.ggplot(pandas2ri.py2ri(date_avgs)) + \
ggplot2.aes_string(x='date', y='tip_amount', color='type') + \
d['code'] = StrVector([x[0]
for x in combos]) + StrVector([x[0] for x in combos_r])
d['sequence'] = StrVector([x[-2] for x in combos]) + StrVector(
[x[0] for x in combos_r])
d['time'] = FloatVector([x for x in times]) + FloatVector(
[x[0] for x in combos_r])
d['n_loop'] = IntVector([x[-1] for x in combos]) + IntVector(
[x[1] for x in combos_r])
d['group'] = StrVector(
[d['code'][x] + ':' + d['sequence'][x] for x in xrange(len(d['n_loop']))])
dataf = DataFrame(d)
from rpy2.robjects.lib import ggplot2
p = ggplot2.ggplot(dataf) + \
ggplot2.geom_line(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.geom_point(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.facet_wrap(Formula('~sequence')) + \
ggplot2.scale_y_continuous('running time') + \
ggplot2.scale_x_continuous('repeated n times', ) + \
ggplot2.xlim(0, max(n_loops)) + \
ggplot2.opts(title = "Benchmark (running time)")
from rpy2.robjects.packages import importr
grdevices = importr('grDevices')
grdevices.png('../../_static/benchmark_sum.png', width=712, height=512)
p.plot()
grdevices.dev_off()
intercept = ests[0]
slope = ests[1]
gs = [ests[j + 2] for j in range(len(x))]
print gs
cut = min(0.5, np.percentile(gs, 15))
typical = [g >= cut for g in gs]
pdf = ro.DataFrame(
{
"x": ro.FloatVector(x),
"y": ro.FloatVector(y),
"e": ro.FloatVector(e),
"ymin": ro.FloatVector(y - e),
"ymax": ro.FloatVector(y + e),
"yest": ro.FloatVector(slope * x + intercept),
"typical": ro.BoolVector(typical),
}
)
rprint(pdf)
gpf = ggplot2.ggplot(pdf)
ppf = (
gpf
+ ggplot2.geom_point(ggplot2.aes_string(x="x", y="y", color="typical", shape="typical"), size=5)
+ ggplot2.geom_errorbar(ggplot2.aes_string(x="x", ymin="ymin", ymax="ymax"))
+ ggplot2.geom_line(ggplot2.aes_string(x="x", y="yest"))
)
grdevices.png(file="fit.png", width=512, height=512)
print (ppf)
grdevices.dev_off()
'axis.text.x':element_text(size=size,color=robjects.r.color_axis_text),
'axis.text.y':element_text(size=size,color=robjects.r.color_axis_text),
'axis.title.x':element_text(size=size,color=robjects.r.color_axis_title, vjust=0),
#'panel.grid.major':element_line(color=robjects.r.color_grid_major,size=.25),
'axis.title.y':element_text(size=size,color=robjects.r.color_axis_title,angle=90)})
#??? efficiently change legend titles
#right now it takes two legend calls to make this work
#alternatives that tried and failed
#base_plot = lambda gr_name = 'variable': ggplot2.aes_string(x='x', y='value',group=gr_name,colour=gr_name, shape = gr_name)
#colors = ggplot2.scale_colour_manual(values=robjects.r.palette_lines, name = ltitle)
pandas2ri.activate()
#set up basic, repetitive plot features
base_plot = ggplot2.aes_string(x='x', y='value',group='variable',colour='variable', shape = 'variable')
line = ggplot2.geom_line()
point = ggplot2.geom_point()
bar = ggplot2.geom_bar(stat="identity")
vert_line_onset = ggplot2.geom_vline(xintercept=-1, linetype=2, colour="red", alpha=0.25)
vert_line_exhaust = ggplot2.geom_vline(xintercept=5, linetype=2, colour="red", alpha=0.25)
ltitle = "crazy"
ltitle_default = 'Variable'
#colors = lambda ltitle = ltitle_default: ggplot2.scale_colour_manual(values=robjects.r.palette_lines, name = ltitle)
colors = ggplot2.scale_colour_manual(values=robjects.r.palette_lines)
legend_t_c = lambda ltitle = ltitle_default: ggplot2.scale_color_discrete(name = ltitle)
legend_t_s = lambda ltitle = ltitle_default: ggplot2.scale_shape_discrete(name = ltitle)
loc_default = robjects.r('c(1,0)')
legend_f = lambda loc = loc_default: ggplot2.theme(**{'legend.position':loc, 'legend.justification':loc})
ggsave = lambda filename, plot: robjects.r.ggsave(filename=out_path + filename + ".pdf", plot=plot, width = 6, height = 4)
colors_alt = ggplot2.scale_colour_manual(values=robjects.r.palette_lines[1])
def as_dataframe(cfg, results, basis):
r = robjects.r
varis = []
langs = []
probs = []
times = []
threads = []
# speedups, with upper and lower bounds below
speedups = []
speedup_lowers = []
speedup_uppers = []
ses = [] # standard errors
mems = [] # memory usage
langs_ideal = list(cfg.languages)
langs_ideal.append('ideal')
probs_ideal = list(cfg.problems)
probs_ideal.append('ideal')
for var in cfg.variations:
for lang in langs_ideal: # cfg.languages:
for prob in probs_ideal: # cfg.problems:
for thread in cfg.threads:
if lang == 'ideal' and prob == 'ideal':
continue
elif lang == 'ideal' or prob == 'ideal':
varis.append(var)
langs.append(pretty_langs[lang])
probs.append(prob)
threads.append(thread)
speedups.append(thread)
speedup_lowers.append(thread)
speedup_uppers.append(thread)
times.append(0)
ses.append(0)
mems.append(0)
continue
varis.append(var) # pretty_varis [var])
langs.append(pretty_langs[lang])
probs.append(prob)
threads.append(thread)
if var.find('seq') >= 0:
thread = cfg.threads[-1]
vals = FloatVector(results[thread][prob][var][lang][0])
time = mean(vals)
times.append(time)
#
# time confidence interval
#
t_result = r['t.test'](FloatVector(vals), **{
" conf.level": 0.999
}).rx('conf.int')[0]
ses.append((t_result[1] - t_result[0]) / 2)
#
# memory usage
#
mem_filename = get_mem_output(lang, prob, var)
with open(mem_filename, 'r') as mem_file:
mem = mem_file.readline()
mems.append(float(mem))
# we include dummy data for the sequential case to avoid the
# speedup calculation below
if var.find('seq') >= 0:
speedups.append(1)
speedup_lowers.append(1)
speedup_uppers.append(1)
continue
#
# speedup values and confidence intervals
#
seq_vals = results[cfg.threads[-1]][prob][var.replace(
'par', 'seq')][lang][0]
# sequential base
base = FloatVector(seq_vals)
# base with p = 1
base_p1 = FloatVector(results[1][prob][var][lang][0])
# use fastest sequential program
if basis == 'fastest' and mean(base_p1) < mean(base):
base = base_p1
elif basis == 'seq':
pass
elif basis == 'p1':
base = base_p1
labels = ['Base'
] * r.length(base)[0] + ['N'] * r.length(vals)[0]
df = DataFrame({
'Times': base + vals,
'Type': StrVector(labels)
})
ratio_test = r['pairwiseCI'](r('Times ~ Type'),
data=df,
control='N',
method='Param.ratio',
**{
'var.equal': False
})[0][0]
speedups.append(mean(base) / time)
speedup_lowers.append(ratio_test[1][0])
speedup_uppers.append(ratio_test[2][0])
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Variation': StrVector(varis),
'Threads': IntVector(threads),
'Time': FloatVector(times),
'SE': FloatVector(ses),
'Speedup': FloatVector(speedups),
'SpeedupLower': FloatVector(speedup_lowers),
'SpeedupUpper': FloatVector(speedup_uppers),
'Mem': FloatVector(mems)
})
r.assign('df', df)
r('save (df, file="performance.Rda")')
# reshape the data to make variation not a column itself, but a part of
# the other columns describe ie, time, speedup, etc.
#
# also, remove the 'ideal' problem as we don't want it in this plot.
df = r('''
redf = reshape (df,
timevar="Variation",
idvar = c("Language","Problem","Threads"),
direction="wide")
redf$Problem <- factor(redf$Problem, levels = c("randmat","thresh","winnow","outer","product","chain"))
redf[which(redf$Problem != "ideal"),]
''')
r.pdf('speedup-expertpar-all.pdf', height=6.5, width=10)
change_name = 'Language'
legendVec = IntVector(range(len(langs_ideal)))
legendVec.names = StrVector(langs_ideal)
gg = ggplot2.ggplot(df)
limits = ggplot2.aes(ymax='SpeedupUpper.expertpar',
ymin='SpeedupLower.expertpar')
dodge = ggplot2.position_dodge(width=0.9)
pp = gg + \
ggplot2.geom_line() + ggplot2.geom_point(size=2.5) +\
robjects.r('scale_color_manual(values = c("#ffcb7e", "#1da06b", "#b94646", "#00368a", "#CCCCCC"))') +\
ggplot2.aes_string(x='Threads', y='Speedup.expertpar',
group=change_name, color=change_name,
shape=change_name) + \
ggplot2.geom_errorbar (limits, width=0.25) + \
ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, vjust=-0.2),
'axis.title.y' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, angle=90, vjust=0.2),
'axis.text.x' : ggplot2.theme_text(family = 'serif', size = 10),
'axis.text.y' : ggplot2.theme_text(family = 'serif', size = 10),
'legend.title' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10),
'legend.text' : ggplot2.theme_text(family = 'serif', size = 10),
'strip.text.x' : ggplot2.theme_text(family = 'serif', size = 10),
'aspect.ratio' : 1,
}) + \
robjects.r('ylab("Speedup")') + \
robjects.r('xlab("Number of cores")') + \
ggplot2.facet_wrap ('Problem', nrow = 2)
pp.plot()
r['dev.off']()
from rpy2.robjects.vectors import DataFrame, FloatVector, StrVector, IntVector
d = {}
d['code'] = StrVector([x[0] for x in combos]) + StrVector([x[0] for x in combos_r])
d['sequence'] = StrVector([x[-2] for x in combos]) + StrVector([x[0] for x in combos_r])
d['time'] = FloatVector([x for x in times]) + FloatVector(times_r)
d['n_loop'] = IntVector([x[-1] for x in combos]) + IntVector([x[3] for x in combos_r])
d['group'] = StrVector([d['code'][x] + ':' + d['sequence'][x] for x in range(len(d['n_loop']))])
dataf = DataFrame(d)
from rpy2.robjects.lib import ggplot2
p = ggplot2.ggplot(dataf) + \
ggplot2.geom_line(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.geom_point(ggplot2.aes_string(x="n_loop",
y="time",
colour="code")) + \
ggplot2.facet_wrap(Formula('~sequence')) + \
ggplot2.scale_y_continuous('running time') + \
ggplot2.scale_x_continuous('repeated n times', ) + \
ggplot2.xlim(0, max(n_loops)) + \
ggplot2.labs(title = "Benchmark (running time)")
from rpy2.robjects.packages import importr
grdevices = importr('grDevices')
grdevices.png('../../_static/benchmark_sum.png',
width = 712, height = 512)
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 as_dataframe (cfg, results, basis):
r = robjects.r
varis = []
langs = []
probs = []
times = []
threads = []
# speedups, with upper and lower bounds below
speedups = []
speedup_lowers = []
speedup_uppers = []
ses = [] # standard errors
mems = [] # memory usage
langs_ideal = list (cfg.languages)
langs_ideal.append ('ideal')
probs_ideal = list (cfg.problems)
probs_ideal.append ('ideal')
for var in cfg.variations:
for lang in langs_ideal: # cfg.languages:
for prob in probs_ideal: # cfg.problems:
for thread in cfg.threads:
if lang == 'ideal' and prob == 'ideal':
continue
elif lang == 'ideal' or prob == 'ideal':
varis.append (var)
langs.append (pretty_langs[lang])
probs.append (prob)
threads.append (thread)
speedups.append (thread)
speedup_lowers.append (thread)
speedup_uppers.append (thread)
times.append (0)
ses.append(0)
mems.append (0)
continue
varis.append (var) # pretty_varis [var])
langs.append (pretty_langs [lang])
probs.append (prob)
threads.append (thread)
if var.find('seq') >= 0:
thread = cfg.threads[-1]
vals = FloatVector (results[thread][prob][var][lang][0])
time = mean (vals)
times.append (time)
#
# time confidence interval
#
t_result = r['t.test'] (FloatVector(vals),
**{" conf.level": 0.999}).rx ('conf.int')[0]
ses.append ((t_result[1] - t_result[0])/2)
#
# memory usage
#
mem_filename = get_mem_output (lang, prob, var)
with open (mem_filename, 'r') as mem_file:
mem = mem_file.readline()
mems.append (float (mem))
# we include dummy data for the sequential case to avoid the
# speedup calculation below
if var.find('seq') >= 0:
speedups.append (1)
speedup_lowers.append (1)
speedup_uppers.append (1)
continue
#
# speedup values and confidence intervals
#
seq_vals = results[cfg.threads[-1]][prob][var.replace ('par', 'seq')][lang][0]
# sequential base
base = FloatVector (seq_vals)
# base with p = 1
base_p1 = FloatVector (results[1][prob][var][lang][0])
# use fastest sequential program
if basis == 'fastest' and mean (base_p1) < mean(base):
base = base_p1
elif basis == 'seq':
pass
elif basis == 'p1':
base = base_p1
labels = ['Base'] * r.length(base)[0] + ['N']*r.length (vals)[0]
df = DataFrame ({'Times': base + vals,
'Type': StrVector(labels)})
ratio_test = r['pairwiseCI'] (r('Times ~ Type'), data=df,
control='N',
method='Param.ratio',
**{'var.equal': False})[0][0]
speedups.append (mean(base) / time)
speedup_lowers.append (ratio_test[1][0])
speedup_uppers.append (ratio_test[2][0])
df = robjects.DataFrame({'Language': StrVector (langs),
'Problem': StrVector (probs),
'Variation' : StrVector (varis),
'Threads': IntVector (threads),
'Time': FloatVector (times),
'SE': FloatVector (ses),
'Speedup': FloatVector (speedups),
'SpeedupLower': FloatVector (speedup_lowers),
'SpeedupUpper': FloatVector (speedup_uppers),
'Mem' : FloatVector (mems)
})
r.assign ('df', df)
r ('save (df, file="performance.Rda")')
# reshape the data to make variation not a column itself, but a part of
# the other columns describe ie, time, speedup, etc.
#
# also, remove the 'ideal' problem as we don't want it in this plot.
df = r('''
redf = reshape (df,
timevar="Variation",
idvar = c("Language","Problem","Threads"),
direction="wide")
redf$Problem <- factor(redf$Problem, levels = c("randmat","thresh","winnow","outer","product","chain"))
redf[which(redf$Problem != "ideal"),]
''')
r.pdf ('speedup-expertpar-all.pdf',
height=6.5, width=10)
change_name = 'Language'
legendVec = IntVector (range (len (langs_ideal)))
legendVec.names = StrVector (langs_ideal)
gg = ggplot2.ggplot (df)
limits = ggplot2.aes (ymax = 'SpeedupUpper.expertpar', ymin = 'SpeedupLower.expertpar')
dodge = ggplot2.position_dodge (width=0.9)
pp = gg + \
ggplot2.geom_line() + ggplot2.geom_point(size=2.5) +\
robjects.r('scale_color_manual(values = c("#ffcb7e", "#1da06b", "#b94646", "#00368a", "#CCCCCC"))') +\
ggplot2.aes_string(x='Threads', y='Speedup.expertpar',
group=change_name, color=change_name,
shape=change_name) + \
ggplot2.geom_errorbar (limits, width=0.25) + \
ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, vjust=-0.2),
'axis.title.y' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10, angle=90, vjust=0.2),
'axis.text.x' : ggplot2.theme_text(family = 'serif', size = 10),
'axis.text.y' : ggplot2.theme_text(family = 'serif', size = 10),
'legend.title' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 10),
'legend.text' : ggplot2.theme_text(family = 'serif', size = 10),
'strip.text.x' : ggplot2.theme_text(family = 'serif', size = 10),
'aspect.ratio' : 1,
}) + \
robjects.r('ylab("Speedup")') + \
robjects.r('xlab("Number of cores")') + \
ggplot2.facet_wrap ('Problem', nrow = 2)
pp.plot()
r['dev.off']()
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 line_plot(cfg, var, control, change_name, changing, selector,
base_selector, basis):
speedups = []
thrds = []
changes = []
lowers = []
uppers = []
for n in cfg.threads:
probs.append('ideal')
langs.append('ideal')
speedups.append(n)
thrds.append(n)
changes.append('ideal')
lowers.append(n)
uppers.append(n)
for c in changing:
sel = selector(c)
# sequential base
base = FloatVector(base_selector(c))
# base with p = 1
base_p1 = FloatVector(sel(1))
# use fastest sequential program
if basis == 'fastest' and mean(base_p1) < mean(base):
base = base_p1
elif basis == 'seq':
pass
elif basis == 'p1':
base = base_p1
for n in cfg.threads:
ntimes = FloatVector(sel(n))
# ratio confidence interval
labels = ['Base'] * r.length(base)[0] + ['N'] * r.length(ntimes)[0]
df = DataFrame({'Times': base + ntimes, 'Type': StrVector(labels)})
ratio_test = r['pairwiseCI'](r('Times ~ Type'),
data=df,
control='N',
method='Param.ratio',
**{
'var.equal': False,
'conf.level': 0.999
})[0][0]
lowers.append(ratio_test[1][0])
uppers.append(ratio_test[2][0])
mn = mean(ntimes)
speedups.append(mean(base) / mn)
# plot slowdowns
#speedups.append (-mn/base)#(base / mn)
thrds.append(n)
if change_name == 'Language':
changes.append(pretty_langs[c])
else:
changes.append(c)
df = DataFrame({
'Speedup': FloatVector(speedups),
'Threads': IntVector(thrds),
change_name: StrVector(changes),
'Lower': FloatVector(lowers),
'Upper': FloatVector(uppers)
})
ideal_changing = ['ideal']
if change_name == 'Language':
ideal_changing.extend([pretty_langs[c] for c in changing])
else:
ideal_changing.extend(changing)
legendVec = IntVector(range(len(ideal_changing)))
legendVec.names = StrVector(ideal_changing)
gg = ggplot2.ggplot(df)
limits = ggplot2.aes(ymax='Upper', ymin='Lower')
dodge = ggplot2.position_dodge(width=0.9)
pp = gg + \
ggplot2.geom_line() + ggplot2.geom_point(size=3) +\
ggplot2.aes_string(x='Threads', y='Speedup',
group=change_name, color=change_name,
shape=change_name) + \
ggplot2.scale_shape_manual(values=legendVec) + \
ggplot2.geom_errorbar (limits, width=0.25) + \
ggplot2_options () + \
ggplot2_colors () + \
ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 15, vjust=-0.2)}) + \
robjects.r('ylab("Speedup")') + \
robjects.r('xlab("Cores")')
# ggplot2.xlim (min(threads), max(threads)) + ggplot2.ylim(min(threads), max(threads)) +\
pp.plot()
r['dev.off']()
def line_plot (cfg, var, control, change_name, changing, selector, base_selector, basis):
speedups = []
thrds = []
changes = []
lowers = []
uppers = []
for n in cfg.threads:
probs.append ('ideal')
langs.append ('ideal')
speedups.append (n)
thrds.append (n)
changes.append ('ideal')
lowers.append (n)
uppers.append (n)
for c in changing:
sel = selector (c)
# sequential base
base = FloatVector (base_selector(c))
# base with p = 1
base_p1 = FloatVector (sel(1))
# use fastest sequential program
if basis == 'fastest' and mean (base_p1) < mean(base):
base = base_p1
elif basis == 'seq':
pass
elif basis == 'p1':
base = base_p1
for n in cfg.threads:
ntimes = FloatVector (sel(n))
# ratio confidence interval
labels = ['Base'] * r.length(base)[0] + ['N']*r.length (ntimes)[0]
df = DataFrame ({'Times': base + ntimes,
'Type': StrVector(labels)})
ratio_test = r['pairwiseCI'] (r('Times ~ Type'), data=df,
control='N',
method='Param.ratio',
**{'var.equal': False,
'conf.level': 0.999})[0][0]
lowers.append (ratio_test[1][0])
uppers.append (ratio_test[2][0])
mn = mean (ntimes)
speedups.append (mean(base) / mn)
# plot slowdowns
#speedups.append (-mn/base)#(base / mn)
thrds.append (n)
if change_name == 'Language':
changes.append (pretty_langs [c])
else:
changes.append (c)
df = DataFrame ({'Speedup': FloatVector (speedups),
'Threads': IntVector (thrds),
change_name: StrVector (changes),
'Lower': FloatVector (lowers),
'Upper': FloatVector (uppers)
})
ideal_changing = ['ideal']
if change_name == 'Language':
ideal_changing.extend ([pretty_langs [c] for c in changing])
else:
ideal_changing.extend (changing)
legendVec = IntVector (range (len (ideal_changing)))
legendVec.names = StrVector (ideal_changing)
gg = ggplot2.ggplot (df)
limits = ggplot2.aes (ymax = 'Upper', ymin = 'Lower')
dodge = ggplot2.position_dodge (width=0.9)
pp = gg + \
ggplot2.geom_line() + ggplot2.geom_point(size=3) +\
ggplot2.aes_string(x='Threads', y='Speedup',
group=change_name, color=change_name,
shape=change_name) + \
ggplot2.scale_shape_manual(values=legendVec) + \
ggplot2.geom_errorbar (limits, width=0.25) + \
ggplot2_options () + \
ggplot2_colors () + \
ggplot2.opts (**{'axis.title.x' : ggplot2.theme_text(family = 'serif', face = 'bold', size = 15, vjust=-0.2)}) + \
robjects.r('ylab("Speedup")') + \
robjects.r('xlab("Cores")')
# ggplot2.xlim (min(threads), max(threads)) + ggplot2.ylim(min(threads), max(threads)) +\
pp.plot()
r['dev.off']()
## note that the order matters when we add another layer in ggplot (here IL_railroads): first aes, then data, that's different from R
## (see http://permalink.gmane.org/gmane.comp.python.rpy/2349)
## note that we use dictionary to set the opts to be able to set options as keywords, for example legend.key.size
p_map = ggplot2.ggplot(IL_final) + \
ggplot2.geom_polygon(ggplot2.aes(x = 'long', y = 'lat', group = 'group', color = 'ObamaShare', fill = 'ObamaShare')) + \
ggplot2.scale_fill_gradient(high = 'blue', low = 'red') + \
ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \
ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \
ggplot2.opts(**{'legend.position': 'left', 'legend.key.size': robjects.r.unit(2, 'lines'), 'legend.title' : ggplot2.theme_text(size = 14, hjust=0), \
'legend.text': ggplot2.theme_text(size = 12), 'title' : "Obama Vote Share and Distance to Railroads in IL", \
'plot.title': ggplot2.theme_text(size = 24), 'plot.margin': robjects.r.unit(robjects.r.rep(0,4),'lines'), \
'panel.background': ggplot2.theme_blank(), 'panel.grid.minor': ggplot2.theme_blank(), 'panel.grid.major': ggplot2.theme_blank(), \
'axis.ticks': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.title.y': ggplot2.theme_blank(), \
'axis.title.x': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.text.x': ggplot2.theme_blank(), \
'axis.text.y': ggplot2.theme_blank()} ) + \
ggplot2.geom_line(ggplot2.aes(x='long', y='lat', group='group'), data=IL_railroads, color='grey', size=0.2) + \
ggplot2.coord_equal()
p_map.plot()
## add the scatterplot
## define layout of subplot with viewports
vp_sub = grid.viewport(x=0.19, y=0.2, width=0.32, height=0.4)
p_sub = ggplot2.ggplot(RR_distance) + \
ggplot2.aes_string(x = 'OBAMA_SHAR', y= 'NEAR_DIST') + \
ggplot2.geom_point(ggplot2.aes(color='OBAMA_SHAR')) + \
ggplot2.stat_smooth(color="black") + \
ggplot2.opts(**{'legend.position': 'none'}) + \
ggplot2.scale_x_continuous("Obama Vote Share") + \
## note that the order matters when we add another layer in ggplot (here IL_railroads): first aes, then data, that's different from R
## (see http://permalink.gmane.org/gmane.comp.python.rpy/2349)
## note that we use dictionary to set the opts to be able to set options as keywords, for example legend.key.size
p_map = ggplot2.ggplot(IL_final) + \
ggplot2.geom_polygon(ggplot2.aes(x = 'long', y = 'lat', group = 'group', color = 'ObamaShare', fill = 'ObamaShare')) + \
ggplot2.scale_fill_gradient(high = 'blue', low = 'red') + \
ggplot2.scale_fill_continuous(name = "Obama Vote Share") + \
ggplot2.scale_colour_continuous(name = "Obama Vote Share") + \
ggplot2.opts(**{'legend.position': 'left', 'legend.key.size': robjects.r.unit(2, 'lines'), 'legend.title' : ggplot2.theme_text(size = 14, hjust=0), \
'legend.text': ggplot2.theme_text(size = 12), 'title' : "Obama Vote Share and Distance to Railroads in IL", \
'plot.title': ggplot2.theme_text(size = 24), 'plot.margin': robjects.r.unit(robjects.r.rep(0,4),'lines'), \
'panel.background': ggplot2.theme_blank(), 'panel.grid.minor': ggplot2.theme_blank(), 'panel.grid.major': ggplot2.theme_blank(), \
'axis.ticks': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.title.y': ggplot2.theme_blank(), \
'axis.title.x': ggplot2.theme_blank(), 'axis.title.x': ggplot2.theme_blank(), 'axis.text.x': ggplot2.theme_blank(), \
'axis.text.y': ggplot2.theme_blank()} ) + \
ggplot2.geom_line(ggplot2.aes(x='long', y='lat', group='group'), data=IL_railroads, color='grey', size=0.2) + \
ggplot2.coord_equal()
p_map.plot()
## add the scatterplot
## define layout of subplot with viewports
vp_sub = grid.viewport(x = 0.19, y = 0.2, width = 0.32, height = 0.4)
p_sub = ggplot2.ggplot(RR_distance) + \
ggplot2.aes_string(x = 'OBAMA_SHAR', y= 'NEAR_DIST') + \
ggplot2.geom_point(ggplot2.aes(color='OBAMA_SHAR')) + \
ggplot2.stat_smooth(color="black") + \
ggplot2.opts(**{'legend.position': 'none'}) + \
ggplot2.scale_x_continuous("Obama Vote Share") + \
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
# scale_linetype_manual: associate perf types with linetypes
for col_i, yscale in enumerate(['log', 'linear']):
vp = grid.viewport(**{'layout.pos.col': col_i + 1, 'layout.pos.row': 1})
pp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='variable', y='Performance', color='color',
shape='PerfType', linetype='PerfType') + \
ggplot2.ggtitle('Performance vs. Color') + \
ggplot2.theme(**{'legend.key.size' : ro.r.unit(1.4, "lines") } ) + \
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()
sampler.run_mcmc(starting_guesses, nsteps)
sample = sampler.chain # shape = (nwalkers, nsteps, ndim)
ests = [np.mean(sample[:, :, j]) for j in range(ndim)]
intercept = ests[0]
slope = ests[1]
gs = [ests[j + 2] for j in range(len(x))]
print gs
cut = min(0.5, np.percentile(gs, 15))
typical = [g >= cut for g in gs]
pdf = ro.DataFrame({'x': ro.FloatVector(x), \
'y': ro.FloatVector(y), \
'e': ro.FloatVector(e), \
'ymin': ro.FloatVector(y-e), \
'ymax': ro.FloatVector(y+e), \
'yest': ro.FloatVector(slope*x+intercept), \
'typical': ro.BoolVector(typical)})
rprint(pdf)
gpf = ggplot2.ggplot(pdf)
ppf = gpf + \
ggplot2.geom_point(ggplot2.aes_string(x='x', y='y',\
color='typical',shape='typical'),size=5) + \
ggplot2.geom_errorbar(ggplot2.aes_string(x='x', ymin='ymin', ymax='ymax')) +\
ggplot2.geom_line(ggplot2.aes_string(x='x', y='yest'))
grdevices.png(file="fit.png", width=512, height=512)
print(ppf)
grdevices.dev_off()
