def bargraph_language(results):
r = robjects.r
for language in languages:
varis = []
probs = []
locs = []
for (lang, prob, var) in results.keys():
if lang == language:
loc = results[(lang, prob, var)]
varis.append(pretty_varis[var])
probs.append(prob)
locs.append(loc)
r.pdf('bargraph-loc-lang-' + language + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Variation': StrVector(varis),
'Problem': StrVector(probs),
'Lines': IntVector(locs),
})
#print (df)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Lines', fill='Variation') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Lines of Code")')
pp.plot()
r['dev.off']()
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 compare_sum_barplot(locus_table, interval_table, intervals, loci, names,
rows):
frame = get_r_data_by_top(locus_table, interval_table, intervals, names,
rows)
#pdb.set_trace()
frame2 = robjects.r('''agg_data <- aggregate(pi ~ interval + db, data = data, sum)''')
if len(intervals) > 1:
sort_string = '''agg_data$interval <- factor(agg_data$interval,{})'''.format(order_intervals(frame2[0]))
robjects.r(sort_string)
gg_frame = ggplot2.ggplot(robjects.r('''agg_data'''))
plot = gg_frame + \
ggplot2.aes_string(
x = 'interval',
y = 'pi',
fill='factor(db)'
) + \
ggplot2.geom_bar(**{
'position':'dodge',
'colour':'#767676',
'alpha':0.6
}
) + \
ggplot2.scale_y_continuous('net phylogenetic informativeness') + \
ggplot2.scale_x_discrete('interval (years ago)') + \
ggplot2.scale_fill_brewer("database", palette="Blues")
return plot
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 main():
usage = 'usage: %prog [options] arg'
parser = OptionParser(usage)
#parser.add_option()
(options,args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide BAM file')
else:
bam_file = args[0]
align_lengths = {}
for aligned_read in pysam.Samfile(bam_file, 'rb'):
align_lengths[aligned_read.qlen] = align_lengths.get(aligned_read.qlen,0) + 1
min_len = min(align_lengths.keys())
max_len = max(align_lengths.keys())
# construct data frame
len_r = ro.IntVector(range(min_len,max_len+1))
counts_r = ro.IntVector([align_lengths.get(l,0) for l in range(min_len,max_len+1)])
df = ro.DataFrame({'length':len_r, 'counts':counts_r})
# construct full plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='length', y='counts') + \
ggplot2.geom_bar(stat='identity') + \
ggplot2.scale_x_continuous('Alignment length') + \
ggplot2.scale_y_continuous('')
# plot to file
grdevices.pdf(file='align_lengths.pdf')
gp.plot()
grdevices.dev_off()
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 barPlot(self, dataframe, filename, x_parm, y_parm): grdevices.png(file=filename, width=512, height=512) data = ggplot2.ggplot(dataframe) aes = ggplot2.aes_string(x=x_parm,y=y_parm) geom = ggplot2.geom_bar(stat = "identity") gg = data + aes + geom gg.plot() grdevices.dev_off()
def barPlot(self, dataframe, filename, x_parm, y_parm):
grdevices.png(file=filename, width=512, height=512)
data = ggplot2.ggplot(dataframe)
aes = ggplot2.aes_string(x=x_parm, y=y_parm)
geom = ggplot2.geom_bar(stat="identity")
gg = data + aes + geom
gg.plot()
grdevices.dev_off()
def groupBar(fi_data):
dev_off = robjects.r('dev.off')
read_delim = robjects.r('read.delim')
#print(fi_data)
class_data = read_delim(fi_data, header=True, stringsAsFactors=False)
robjects.r.assign('class.data', class_data)
robjects.r.pdf(fi_data + ".Bar.pdf")
robjects.r('class_data <- class.data')
class_data = robjects.r('class_data')
ggplot2.theme = SignatureTranslatedFunction(ggplot2.theme, init_prm_translate={'axis_text_x': 'axis.text.x', 'axis_text_y': 'axis.text.y', 'axis_text_fill': 'axis.text.fill'})
bar = ggplot2.ggplot(class_data) + ggplot2.geom_bar(stat='identity', position='dodge') + ggplot2.aes_string(x='Class',y='Percent',fill='Group') + ggplot2.theme(axis_text_x=ggplot2.element_text(angle=90, hjust=1))
bar.plot()
dev_off()
def bargraph_variation_diff():
r = robjects.r
for (standard, expert) in [('seq', 'expertseq'), ('par', 'expertpar')]:
langs = []
probs = []
diffs = []
for lang in languages:
for prob in problems:
error = False
try:
time = result[lang][prob][standard]
except KeyError:
error = True
try:
time_expert = result[lang][prob][expert]
except KeyError:
error = True
if not error:
diff = (float(time_expert + time) / float(time) - 1)
else:
diff = 0
langs.append(pretty_langs[lang])
probs.append(prob)
diffs.append(diff)
r.pdf('bargraph-codingtime-diff-' + standard + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Difference': FloatVector(diffs),
})
#print (df)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Difference', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('ylab("Coding time difference (in percent)")') +\
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('scale_y_continuous(labels = percent_format())')
pp.plot()
r['dev.off']()
def generate_histogram(subgroups_to_sses_to_n_count, tname, file_name):
columns_to_data = {'subgroup': [], tname: [], 'count': []}
max_count = 0
for subgroup, sses_to_n_count in subgroups_to_sses_to_n_count.items():
for ss, n_count in sses_to_n_count.items():
columns_to_data['subgroup'].append(subgroup)
columns_to_data[tname].append(ss)
columns_to_data['count'].append(n_count)
if n_count > max_count:
max_count = n_count
r_columns_to_data = {
'subgroup':
ro.FactorVector(columns_to_data['subgroup'],
levels=ro.StrVector(
_sort_subgroup(set(columns_to_data['subgroup'])))),
tname:
ro.StrVector(columns_to_data[tname]),
'count':
ro.IntVector(columns_to_data['count'])
}
df = ro.DataFrame(r_columns_to_data)
max_count = int(max_count / 1000 * 1000 + 1000)
histogram_file_path = os.path.join(OUTPUT_PATH, file_name)
logging.debug(
str.format("The Data Frame for file {}: \n{}", histogram_file_path,
df))
grdevices.png(file=histogram_file_path, width=1200, height=800)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string(x='subgroup', y='count', fill=tname) + \
ggplot2.geom_bar(position="dodge",width=0.8, stat="identity") + \
ggplot2.theme_bw() + \
ggplot2.theme_classic() + \
ggplot2.theme(**{'legend.title': ggplot2.element_blank()}) + \
ggplot2.theme(**{'legend.text': ggplot2.element_text(size=40)}) + \
ggplot2.theme(**{'axis.text.x': ggplot2.element_text(size=40,angle=45)}) + \
ggplot2.theme(**{'axis.text.y': ggplot2.element_text(size=40)}) + \
ggplot2.scale_y_continuous(expand=ro.IntVector([0, 0]),
limits=ro.IntVector([0, max_count])) + \
ggplot2.geom_text(ggplot2.aes_string(label='count'), size=6, angle=35, hjust=-0.1,
position=ggplot2.position_dodge(width=0.8),
vjust=-0.2)
pp.plot()
logging.info(str.format("Output step3 file {}", histogram_file_path))
grdevices.dev_off()
def bargraph_language(cfg, values):
r = robjects.r
for lang in cfg.languages:
times = []
varss = []
probs = []
ses = []
for prob in cfg.problems:
for var in cfg.variations:
# we use the pretty names to make the
varss.append(pretty_varis[var])
probs.append(prob)
data = FloatVector(values[prob][var][lang][0])
times.append(r['mean'](data)[0])
t_result = r['t.test'](data, **{
" conf.level": 0.999
}).rx('conf.int')[0]
ses.append((t_result[1] - t_result[0]) / 2)
r.pdf('bargraph-executiontime-lang-' + lang + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Variation': StrVector(varss),
'Problem': StrVector(probs),
'Time': FloatVector(times),
'SE': FloatVector(ses)
})
limits = ggplot2.aes(ymax='Time + SE', ymin='Time - SE')
dodge = ggplot2.position_dodge(width=0.9)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Time', fill='Variation') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time (in seconds)")')
pp.plot()
r['dev.off']()
def bargraph_language (cfg, values):
r = robjects.r
for lang in cfg.languages:
times = []
varss = []
probs = []
ses = []
for prob in cfg.problems:
for var in cfg.variations:
# we use the pretty names to make the
varss.append (pretty_varis [var])
probs.append (prob)
data = FloatVector (values[prob][var][lang][0])
times.append (r['mean'] (data)[0])
t_result = r['t.test'] (data,
**{" conf.level": 0.999}).rx ('conf.int')[0]
ses.append ((t_result[1] - t_result[0])/2)
r.pdf ('bargraph-executiontime-lang-' + lang + '.pdf',
height=pdf_height (), width=pdf_width ())
df = robjects.DataFrame({'Variation': StrVector (varss),
'Problem': StrVector (probs),
'Time' : FloatVector (times),
'SE' : FloatVector (ses)
})
limits = ggplot2.aes (ymax = 'Time + SE', ymin = 'Time - SE')
dodge = ggplot2.position_dodge (width=0.9)
gp = ggplot2.ggplot (df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Time', fill='Variation') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time (in seconds)")')
pp.plot ()
r['dev.off']()
def bargraph_language():
r = robjects.r
for language in languages:
varis = []
probs = []
times = []
for prob in problems:
for var in variations:
try:
time = result[language][prob][var]
except KeyError:
time = 0
# for the expert times, add expert and non-expert times together
if var.startswith('expert'):
try:
time = time + result[language][prob][var.replace(
'expert', '')]
except KeyError:
pass
varis.append(pretty_varis[var])
probs.append(prob)
times.append(time)
r.pdf('bargraph-codingtime-lang-' + language + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Variation': StrVector(varis),
'Problem': StrVector(probs),
'Time': IntVector(times),
})
#print (df)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Time', fill='Variation') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Coding time (in minutes)")')
pp.plot()
r['dev.off']()
def generate_step3_9_n_count_histogram(place_type_pos_type_to_count,
file_name):
columns_to_data = {'place': [], 'pos': [], 'count': []}
max_count = 0
for place_pos_type, n_count in place_type_pos_type_to_count.items():
place_type, pos_type = place_pos_type.split('_')
columns_to_data['place'].append(place_type)
columns_to_data['pos'].append(pos_type)
columns_to_data['count'].append(n_count)
if n_count > max_count:
max_count = n_count
r_columns_to_data = {
'place': ro.StrVector(columns_to_data['place']),
'pos': ro.StrVector(columns_to_data['pos']),
'count': ro.IntVector(columns_to_data['count'])
}
df = ro.DataFrame(r_columns_to_data)
if max_count > 1000:
max_count = int(max_count / 1000 * 1000 + 1000)
else:
max_count = int(max_count / 100 * 100 + 100)
histogram_file_path = os.path.join(OUTPUT_PATH, file_name)
logging.debug(
str.format("The Data Frame for file {}: \n{}", histogram_file_path,
df))
grdevices.png(file=histogram_file_path, width=1024, height=512)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string(x='pos', y='count', fill='place') + \
ggplot2.geom_bar(position="dodge", stat="identity") + \
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.scale_y_continuous(expand=ro.IntVector([0, 0]),
limits=ro.IntVector([0, max_count])) + \
ggplot2.geom_text(ggplot2.aes_string(label='count'),
position=ggplot2.position_dodge(width=0.8), size=10, angle=35, hjust=-0.2,
vjust=-0.5)
pp.plot()
logging.info(str.format("Output step3 file {}", histogram_file_path))
grdevices.dev_off()
def bargraph_variation_diff(cfg, values):
r = robjects.r
for (standard, expert) in [('seq', 'expertseq'), ('par', 'expertpar')]:
langs = []
probs = []
diffs = []
for lang in cfg.languages:
for prob in cfg.problems:
data = FloatVector(values[prob][standard][lang][0])
data_expert = FloatVector(values[prob][expert][lang][0])
mean = r['mean'](data)[0]
mean_expert = r['mean'](data_expert)[0]
diff = (float(mean_expert) / float(mean) - 1)
langs.append(pretty_langs[lang])
probs.append(prob)
diffs.append(diff)
r.pdf('bargraph-executiontime-diff-' + standard + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Difference': FloatVector(diffs),
})
#print (df)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Difference', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time difference (in percent)")') +\
robjects.r('scale_y_continuous(labels = percent_format())')
pp.plot()
r['dev.off']()
def bargraph_variation_norm(results):
r = robjects.r
for variation in variations:
langs = []
probs = []
locs = []
for problem in problems:
results_filtered = {
key: results[key]
for key in [(lang, problem, variation) for lang in languages]
}
loc_min = min(results_filtered.values())
for (lang, prob, var) in results_filtered.keys():
loc_norm = (float(
results_filtered[(lang, prob, var)])) / float(loc_min)
langs.append(pretty_langs[lang])
probs.append(prob)
locs.append(loc_norm)
r.pdf('bargraph-loc-var-norm-' + variation + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Lines': FloatVector(locs),
})
#print (df)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Lines', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Lines of Code (normalized to smallest)")')
pp.plot()
r['dev.off']()
def mem_usage_graph(cfg):
r = robjects.r
varis = []
langs = []
probs = []
mems = []
for var in cfg.variations:
for lang in cfg.languages:
for prob in cfg.problems:
mem_filename = get_mem_output(lang, prob, var)
with open(mem_filename, 'r') as mem_file:
mem = mem_file.readline()
mems.append(float(mem))
varis.append(pretty_varis[var])
langs.append(pretty_langs[lang])
probs.append(prob)
# memory usage is a simple histogram with all information in one graph.
r.pdf('bargraph-memusage.pdf', height=pdf_height(), width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Variation': StrVector(varis),
'Mem': FloatVector(mems)
})
gp = ggplot2.ggplot(df)
# we rotate the x labels to make sure they don't overlap
pp = gp +\
ggplot2.opts (**{'axis.text.x': ggplot2.theme_text (angle = 90, hjust=1)}) + \
ggplot2.aes_string (x='Problem', y='Mem', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.facet_wrap ('Variation') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Memory usage (in bytes)")')# + \
pp.plot()
r['dev.off']()
def mem_usage_graph (cfg):
r = robjects.r
varis = []
langs = []
probs = []
mems = []
for var in cfg.variations:
for lang in cfg.languages:
for prob in cfg.problems:
mem_filename = get_mem_output (lang, prob, var)
with open (mem_filename, 'r') as mem_file:
mem = mem_file.readline()
mems.append (float (mem))
varis.append (pretty_varis [var])
langs.append (pretty_langs [lang])
probs.append (prob)
# memory usage is a simple histogram with all information in one graph.
r.pdf ('bargraph-memusage.pdf', height=pdf_height (), width=pdf_width ())
df = robjects.DataFrame({'Language': StrVector (langs),
'Problem': StrVector (probs),
'Variation' : StrVector (varis),
'Mem' : FloatVector (mems)
})
gp = ggplot2.ggplot (df)
# we rotate the x labels to make sure they don't overlap
pp = gp +\
ggplot2.opts (**{'axis.text.x': ggplot2.theme_text (angle = 90, hjust=1)}) + \
ggplot2.aes_string (x='Problem', y='Mem', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.facet_wrap ('Variation') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Memory usage (in bytes)")')# + \
pp.plot ()
r['dev.off']()
def singleTablePlot_gg(parser, args):
''' kmerdict is a defaultdict(int)
It can take both empty and non-empty kmerdicts
returns update of the input kmerdict given the input string and k'''
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
kmerdict = kmercount_in_table(args.table1)
data = defaultdict(list)
numKmers = len(kmerdict)
for k in sorted(kmerdict.keys()):
data['kmers'].append(k)
data['counts'].append(kmerdict[k])
df = robjects.DataFrame(data)
gp = ggplot2.ggplot(df)
## pp = gp + ggplot2.geom_bar(stat="identity")
pp = gp + ggplot2.aes_string(x=range(1,numKmers+1),y=data['counts']) \
+ ggplot2.geom_bar(stat="identity") \
+ ggplot2.scale_x_continuous(name="kmer", breaks=0.5+(range(1,numKmers+1)), labels=kmers)
pp.plot()
print('Type enter to exit.')
raw_input()
def bargraph_variation_diff(results):
r = robjects.r
for (standard, expert) in [('seq', 'expertseq'), ('par', 'expertpar')]:
langs = []
probs = []
diffs = []
for lang in languages:
for prob in problems:
loc = results[(lang, prob, standard)]
loc_expert = results[(lang, prob, expert)]
diff = (float(loc_expert) / float(loc) - 1)
langs.append(pretty_langs[lang])
probs.append(prob)
diffs.append(diff)
r.pdf('bargraph-loc-diff-' + standard + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Difference': FloatVector(diffs),
})
#print (df)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Difference', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('ylab("Lines of code difference (in percent)")') +\
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('scale_y_continuous(labels = percent_format())')
pp.plot()
r['dev.off']()
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 singleTablePlot_gg(parser, args):
''' kmerdict is a defaultdict(int)
It can take both empty and non-empty kmerdicts
returns update of the input kmerdict given the input string and k'''
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
kmerdict = kmercount_in_table(args.table1)
data = defaultdict(list)
numKmers = len(kmerdict)
for k in sorted(kmerdict.keys()):
data['kmers'].append(k)
data['counts'].append(kmerdict[k])
df = robjects.DataFrame(data)
gp = ggplot2.ggplot(df)
## pp = gp + ggplot2.geom_bar(stat="identity")
pp = gp + ggplot2.aes_string(x=range(1,numKmers+1),y=data['counts']) \
+ ggplot2.geom_bar(stat="identity") \
+ ggplot2.scale_x_continuous(name="kmer", breaks=0.5+(range(1,numKmers+1)), labels=kmers)
pp.plot()
print('Type enter to exit.')
raw_input()
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 bargraph_variation_diff (cfg, values):
r = robjects.r
for (standard, expert) in [('seq', 'expertseq'), ('par', 'expertpar')]:
langs = []
probs = []
diffs = []
for lang in cfg.languages:
for prob in cfg.problems:
data = FloatVector (values[prob][standard][lang][0])
data_expert = FloatVector (values[prob][expert][lang][0])
mean = r['mean'] (data)[0]
mean_expert = r['mean'] (data_expert)[0]
diff = (float(mean_expert) / float(mean) - 1)
langs.append (pretty_langs [lang])
probs.append (prob)
diffs.append (diff)
r.pdf ('bargraph-executiontime-diff-' + standard + '.pdf', height=pdf_height (), width=pdf_width ())
df = robjects.DataFrame({'Language': StrVector (langs),
'Problem': StrVector (probs),
'Difference' : FloatVector (diffs),
})
#print (df)
gp = ggplot2.ggplot (df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Difference', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time difference (in percent)")') +\
robjects.r('scale_y_continuous(labels = percent_format())')
pp.plot ()
r['dev.off']()
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 main():
usage = 'usage: %prog [options] arg'
parser = OptionParser(usage)
#parser.add_option()
(options, args) = parser.parse_args()
if len(args) != 1:
parser.error('Must provide BAM file')
else:
bam_file = args[0]
align_lengths = {}
for aligned_read in pysam.Samfile(bam_file, 'rb'):
align_lengths[aligned_read.qlen] = align_lengths.get(
aligned_read.qlen, 0) + 1
min_len = min(align_lengths.keys())
max_len = max(align_lengths.keys())
# construct data frame
len_r = ro.IntVector(range(min_len, max_len + 1))
counts_r = ro.IntVector(
[align_lengths.get(l, 0) for l in range(min_len, max_len + 1)])
df = ro.DataFrame({'length': len_r, 'counts': counts_r})
# construct full plot
gp = ggplot2.ggplot(df) + \
ggplot2.aes_string(x='length', y='counts') + \
ggplot2.geom_bar(stat='identity') + \
ggplot2.scale_x_continuous('Alignment length') + \
ggplot2.scale_y_continuous('')
# plot to file
grdevices.pdf(file='align_lengths.pdf')
gp.plot()
grdevices.dev_off()
# Restructure hour data
hour_arr = []
hits_arr = []
for hour in hour_hits:
hour_arr.append(datetime.min + timedelta(hours=int(hour[0:2])))
hits_arr.append(hour_hits[hour])
hour = POSIXct(hour_arr)
hits = IntVector(hits_arr)
grdevices.png('analytics_out/hits_by_time.png')
df = robjects.DataFrame({'hour': POSIXct(hour), 'hits': IntVector(hits)})
pp = ggplot.ggplot(df) + \
ggplot.aes_string(x = 'hour', y = 'hits') + \
ggplot.scale_x_datetime(labels = scales.date_format('%H:%M UTC')) + \
ggplot.geom_bar(stat = 'identity')
pp.plot()
grdevices.dev_off()
# Restructure circular hit time datax
time_hits_vec = FloatVector(time_hits)
hits_circ = circular.circular(time_hits_vec, units='hours', template='clock24')
hits_density = circular.density_circular(hits_circ, bw=100)
print('Von Mises fit for hits by time (hours past 00:00 UTC)')
hits_mle = circular.mle_vonmises(hits_circ)
mu = base.cbind(hits_mle.rx('mu'))[0][0]
mu_se = hits_mle.rx('se.mu')[0][0]
kappa = hits_mle.rx('kappa')[0][0]
kappa_se = hits_mle.rx('se.kappa')[0][0]
print('MLE: mu = %0.2f (%0.2f) kappa = %0.2f (%0.2f)' %
'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])
shape_alt = ggplot2.scale_shape_manual(values=17)
def bargraph_variation():
r = robjects.r
for var in variations:
# each variation gets plot
values = []
# normalized values
nvalues = []
langs = []
probs = []
for prob in problems:
# aggregate by problems
lvalues = []
for lang in languages:
# each problem displays a list of language times for that problem
langs.append(pretty_langs[lang])
probs.append(prob)
value = 0
try:
value = result[lang][prob][var]
except KeyError:
print "Warning: no value for:"
print(lang, prob, var)
value = 0 # FIXME to account for missing seq-version of Erlang
# for the expert times, add expert and non-expert times together
if var.startswith('expert'):
try:
value = value + result[lang][prob][var.replace(
'expert', '')]
except KeyError:
pass
lvalues.append(value)
values.extend(lvalues)
lmin = min([x for x in lvalues if x != 0])
nvalues.extend([(lambda x: x / lmin)(la) for la in lvalues])
# plot histogram of actual times
r.pdf('bargraph-codingtime-var-' + var + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Time': FloatVector(values),
})
dodge = ggplot2.position_dodge(width=0.9)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Time', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Coding time (in minutes)")')
pp.plot()
# plot histogram of times normalized with respect to fastest time for a problem
r.pdf('bargraph-codingtime-var-norm-' + var + '.pdf',
height=pdf_height(),
width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Time': FloatVector(nvalues),
})
dodge = ggplot2.position_dodge(width=0.9)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Time', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Coding time (normalized to fastest)")')
pp.plot()
r['dev.off']()
def speedup_diffs (values, basis):
r = robjects.r
speedups = {}
for var in ['par', 'expertpar']:
speedups[var] = {}
for lang in languages:
speedups[var][lang] = {}
i = 0
p1 = 0
print lang
for prob in problems:
i = i + 1
speedups[var][lang][prob] = []
base = r.mean (FloatVector (values [cfg.threads[-1]][prob][var.replace ('par','seq')][lang][0]))[0]
# base with p = 1
base_p1 = r.mean (FloatVector (values [1][prob][var][lang][0]))[0]
# use fastest sequential program
if basis == 'fastest' and base_p1 < base:
base = base_p1
p1 = p1 + 1
elif basis == 'seq':
pass
elif basis == 'p1':
base = base_p1
mn = (r.mean (FloatVector (values[32][prob][var][lang][0])))[0]
speedups[var][lang][prob].append (float (base) / float (mn))
print i
print p1
langs = []
probs = []
diffs = []
for lang in languages:
for prob in problems:
sp = speedups['par'][lang][prob][0]
sp_expert = speedups['expertpar'][lang][prob][0]
diff = (float(sp_expert) / float(sp))
langs.append (pretty_langs [lang])
probs.append (prob)
diffs.append (diff)
r.pdf ('bargraph-speedup-diff.pdf', height=pdf_height (), width=pdf_width ())
df = robjects.DataFrame({'Language': StrVector (langs),
'Problem': StrVector (probs),
'Difference' : FloatVector (diffs),
})
#print (df)
gp = ggplot2.ggplot (df)
scale = r('''
xformatter <- function(x) {
sprintf("%d x", x)
}
scale_y_continuous(labels = xformatter)
''')
pp = gp + \
ggplot2.aes_string (x='Problem', y='Difference', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
ggplot2_options () + \
ggplot2_colors () + \
r('ylab("Change in speedup")') +\
scale
# r('scale_y_continuous(labels = percent_format())')
pp.plot ()
r['dev.off']()
def bargraph_variation (cfg, values):
r = robjects.r
for var in cfg.variations:
# each variation gets plot
avgs = []
ses = []
# normalized values
navgs = []
nses = []
langs = []
probs = []
for prob in cfg.problems:
# aggregate by problems
lavgs = []
lses = []
for lang in cfg.languages:
# each problem displays a list of language times for that problem
data = FloatVector (values[prob][var][lang][0])
langs.append (pretty_langs [lang])
probs.append (prob)
mean = r['mean'] (data)[0]
lavgs.append (mean)
t_result = r['t.test'] (data, **{"conf.level": 0.999}).rx ('conf.int')[0]
lses.append ((t_result[1] - t_result[0])/2)
avgs.extend (lavgs)
ses.extend (lses)
lmin = min (lavgs)
navgs.extend ([la/lmin for la in lavgs])
nses.extend ([ls/lmin for ls in lses])
df = robjects.DataFrame({'Language': StrVector (langs),
'Problem': StrVector (probs),
'Time' : FloatVector (avgs),
'SE' : FloatVector (ses),
'NormTime' : FloatVector (navgs),
'NormSE' : FloatVector (nses),
'TimeLabel' : StrVector ([str(round(time, 1)) + "s" for time in avgs])
})
# plot histogram of actual times
r.pdf ('bargraph-executiontime-var-' + var + '.pdf', height=pdf_height (), width=pdf_width ())
limits = ggplot2.aes (ymax = 'Time + SE', ymin = 'Time - SE')
dodge = ggplot2.position_dodge (width=0.9)
gp = ggplot2.ggplot (df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Time', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time (in seconds)")')
pp.plot ()
# plot histogram of times normalized with respect to fastest time for a problem
r.pdf ('bargraph-executiontime-var-norm-' + var + '.pdf', height=pdf_height (), width=pdf_width ())
limits = ggplot2.aes (ymax = 'NormTime + NormSE', ymin = 'NormTime - NormSE')
dodge = ggplot2.position_dodge (width=0.9)
gp = ggplot2.ggplot (df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='NormTime', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.geom_errorbar (limits, position=dodge, width=0.25) +\
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time (normalized to fastest)")')
#ggplot2.geom_text(data=df,
# mapping = ggplot2.aes_string (x='Problem',
# y='NormTime + NormSE + 0.1',
# label='TimeLabel')
pp.plot ()
r['dev.off']()
def speedup_diffs(values, basis):
r = robjects.r
speedups = {}
for var in ['par', 'expertpar']:
speedups[var] = {}
for lang in languages:
speedups[var][lang] = {}
i = 0
p1 = 0
print lang
for prob in problems:
i = i + 1
speedups[var][lang][prob] = []
base = r.mean(
FloatVector(values[cfg.threads[-1]][prob][var.replace(
'par', 'seq')][lang][0]))[0]
# base with p = 1
base_p1 = r.mean(FloatVector(values[1][prob][var][lang][0]))[0]
# use fastest sequential program
if basis == 'fastest' and base_p1 < base:
base = base_p1
p1 = p1 + 1
elif basis == 'seq':
pass
elif basis == 'p1':
base = base_p1
mn = (r.mean(FloatVector(values[32][prob][var][lang][0])))[0]
speedups[var][lang][prob].append(float(base) / float(mn))
print i
print p1
langs = []
probs = []
diffs = []
for lang in languages:
for prob in problems:
sp = speedups['par'][lang][prob][0]
sp_expert = speedups['expertpar'][lang][prob][0]
diff = (float(sp_expert) / float(sp))
langs.append(pretty_langs[lang])
probs.append(prob)
diffs.append(diff)
r.pdf('bargraph-speedup-diff.pdf', height=pdf_height(), width=pdf_width())
df = robjects.DataFrame({
'Language': StrVector(langs),
'Problem': StrVector(probs),
'Difference': FloatVector(diffs),
})
#print (df)
gp = ggplot2.ggplot(df)
scale = r('''
xformatter <- function(x) {
sprintf("%d x", x)
}
scale_y_continuous(labels = xformatter)
''')
pp = gp + \
ggplot2.aes_string (x='Problem', y='Difference', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
ggplot2_options () + \
ggplot2_colors () + \
r('ylab("Change in speedup")') +\
scale
# r('scale_y_continuous(labels = percent_format())')
pp.plot()
r['dev.off']()
def show4():
open4()
r.source('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/R/end.R',encoding="utf-8")
data = DataFrame.from_csvfile('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/temp/project2.csv')
pp = ggplot2.ggplot(data)+ggplot2.aes_string(x='day', y='time',fill = 'factor(project)')+ggplot2.geom_bar(stat ='identity',position = 'dodge')+ggplot2.ggtitle("两项目时间对比图")+ggplot2.labs(x='日期',y='时间 (min)')+ggplot2.theme(**{'axis.text.x': ggplot2.element_text(angle = 45)})
pp.plot()
print("Start plotting...")
grdevices = importr('grDevices')
ro.r('''change_name=function(pop_size, generations,freq){
name=sprintf("../results/mcm_%sNe_%sfreq_%sgen.png", pop_size,freq,generations)
return(name)}
''')
name = ro.r['change_name']
name = name(args.ps, args.gen, args.freq)
print("Output figure in:", name)
grdevices.png(file=name, width=700, height=700)
gp = ggplot2.ggplot(res2)
pp = gp + ggplot2.aes_string(
x='Counts', y='Proportion') + ggplot2.geom_bar(
stat="identity", color="darkgoldenrod3") + ggplot2.theme_bw()
pp.plot()
grdevices.dev_off()
print("Plot done!")
elif (
args.diff
): ###references:doi: 10.1093/molbev/msx254 && https://doi.org/10.1111/j.1365-294X.2010.04997.x
p = args.freq
N = args.ps
t = args.gen
newx = []
x = np.arange(0, 1.001, 0.001001001)
res = [0] * len(x)
print("Estimating allele counts")
for i in range(1, 101):
def bargraph_variation(cfg, values):
r = robjects.r
for var in cfg.variations:
# each variation gets plot
avgs = []
ses = []
# normalized values
navgs = []
nses = []
langs = []
probs = []
for prob in cfg.problems:
# aggregate by problems
lavgs = []
lses = []
for lang in cfg.languages:
# each problem displays a list of language times for that problem
data = FloatVector(values[prob][var][lang][0])
langs.append(pretty_langs[lang])
probs.append(prob)
mean = r['mean'](data)[0]
lavgs.append(mean)
t_result = r['t.test'](data, **{
"conf.level": 0.999
}).rx('conf.int')[0]
lses.append((t_result[1] - t_result[0]) / 2)
avgs.extend(lavgs)
ses.extend(lses)
lmin = min(lavgs)
navgs.extend([la / lmin for la in lavgs])
nses.extend([ls / lmin for ls in lses])
df = robjects.DataFrame({
'Language':
StrVector(langs),
'Problem':
StrVector(probs),
'Time':
FloatVector(avgs),
'SE':
FloatVector(ses),
'NormTime':
FloatVector(navgs),
'NormSE':
FloatVector(nses),
'TimeLabel':
StrVector([str(round(time, 1)) + "s" for time in avgs])
})
# plot histogram of actual times
r.pdf('bargraph-executiontime-var-' + var + '.pdf',
height=pdf_height(),
width=pdf_width())
limits = ggplot2.aes(ymax='Time + SE', ymin='Time - SE')
dodge = ggplot2.position_dodge(width=0.9)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='Time', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.geom_errorbar (limits, position=dodge, width=0.25) + \
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time (in seconds)")')
pp.plot()
# plot histogram of times normalized with respect to fastest time for a problem
r.pdf('bargraph-executiontime-var-norm-' + var + '.pdf',
height=pdf_height(),
width=pdf_width())
limits = ggplot2.aes(ymax='NormTime + NormSE',
ymin='NormTime - NormSE')
dodge = ggplot2.position_dodge(width=0.9)
gp = ggplot2.ggplot(df)
pp = gp + \
ggplot2.aes_string (x='Problem', y='NormTime', fill='Language') + \
ggplot2.geom_bar (position='dodge', stat='identity') + \
ggplot2.geom_errorbar (limits, position=dodge, width=0.25) +\
ggplot2_options () + \
ggplot2_colors () + \
robjects.r('scale_x_discrete(limits=c("randmat", "thresh", "winnow", "outer", "product", "chain"))') +\
robjects.r('ylab("Execution time (normalized to fastest)")')
#ggplot2.geom_text(data=df,
# mapping = ggplot2.aes_string (x='Problem',
# y='NormTime + NormSE + 0.1',
# label='TimeLabel')
pp.plot()
r['dev.off']()
def show1():
open1()
r.source('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/R/head1.r',encoding="utf-8")
data = DataFrame.from_csvfile('D:/Postgraduate/Course/2-semester/R-language/TimeAnalyze/Programe/temp/day1.csv')
pp = ggplot2.ggplot(data)+ggplot2.aes_string(x='project', y='time',fill = 'project')+ggplot2.geom_bar(stat ='identity')+ggplot2.ggtitle("今日项目时间分布图")+ggplot2.labs(x='项目',y='时间 (min)')+ggplot2.theme(**{'axis.text.x': ggplot2.element_text(angle = 45)})
pp.plot()
