def plot_squiggle(args, filename, start_times, mean_signals):
"""
Use rpy2 to create a squiggle plot of the read
"""
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]
total_time = start_times[-1] - start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([t - t_0 for t in start_times])
r_mean_signals = robjects.FloatVector(mean_signals)
# infer the appropriate number of events given the number of facets
num_events = len(r_mean_signals)
events_per_facet = (num_events / args.num_facets) + 1
# dummy variable to control faceting
facet_category = robjects.FloatVector([(i / events_per_facet) + 1 for i in range(len(start_times))])
# make a data frame of the start times and mean signals
d = {'start': r_start_times, 'mean': r_mean_signals, 'cat': facet_category}
df = robjects.DataFrame(d)
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)})
else:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)}) \
+ ggplot2.theme_bw()
if args.saveas is not None:
plot_file = os.path.basename(filename) + "." + args.saveas
if os.path.isfile(plot_file):
raise Exception('Cannot create plot for %s: plot file %s already exists' % (filename, plot_file))
if args.saveas == "pdf":
grdevices.pdf(plot_file, width = 8.5, height = 11)
elif args.saveas == "png":
grdevices.png(plot_file, width = 8.5, height = 11,
units = "in", res = 300)
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
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 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 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 plot_crawldb_status(self, data, row_filter, img_file, ratio=1.0):
if row_filter:
data = data[data['type'].isin(row_filter)]
categories = []
for value in row_filter:
if re.search('^crawldb:status:db_', value):
replacement = re.sub('^crawldb:status:db_', '', value)
categories.append(replacement)
data.replace(to_replace=value, value=replacement, inplace=True)
data['type'] = pandas.Categorical(data['type'],
ordered=True,
categories=categories.reverse())
data['size'] = data['size'].astype(float)
ratio = 0.1 + len(data['crawl'].unique()) * .03
print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='size', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='Pastel1', type='sequential',
guide=ggplot2.guide_legend(reverse=False)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='CrawlDb Size and Status Counts\n(before crawling)',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path, height=int(7 * ratio), width=7)
return p
def plot_fetch_status(self, data, row_filter, img_file, ratio=1.0):
if row_filter:
data = data[data['type'].isin(row_filter)]
data = data[['crawl', 'percentage', 'type']]
categories = []
for value in row_filter:
if re.search('^fetcher:(?:aggr:)?', value):
replacement = re.sub('^fetcher:(?:aggr:)?', '', value)
categories.append(replacement)
data.replace(to_replace=value, value=replacement, inplace=True)
data['type'] = pandas.Categorical(data['type'],
ordered=True,
categories=categories.reverse())
ratio = 0.1 + len(data['crawl'].unique()) * .03
# print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='percentage', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='RdYlGn', type='sequential',
guide=ggplot2.guide_legend(reverse=True)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='Percentage of Fetch Status',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path, height=int(7 * ratio), width=7)
return p
def plot(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 get_nogrid_theme():
"""
Get no grid theme for ggplot2.
"""
nogrid_x_theme = theme(**{'panel.grid.major.x': element_blank(),
'panel.grid.minor.x': element_blank(),
'panel.grid.major.y': element_blank(),
'panel.grid.minor.y': element_blank()})
return nogrid_x_theme
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 _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_coef(feat_mat_dir,
model_dir,
expt_names,
pref,
outfile=None,
height=120,
fsize=12):
for expt_idx, ex in enumerate(expt_names):
feat_mat_file = os.path.join(feat_mat_dir, ex + '_feat_mat.npz')
model_file = os.path.join(model_dir, pref + ex + '_model.pkl')
model = read_model(model_file)
(tmp_feat, tmp_y, tmp_feat_names,
tmp_gene_names) = read_feat_mat(feat_mat_file)
if expt_idx == 0:
feat_names = tmp_feat_names
clf_coef = model.clf_coef()
reg_coef = model.reg_coef()
else:
assert (all(f[0] == f[1] for f in zip(feat_names, tmp_feat_names)))
clf_coef = np.concatenate((clf_coef, model.clf_coef()), axis=1)
reg_coef = np.concatenate((reg_coef, model.reg_coef()), axis=1)
nexpt = expt_idx + 1
# Now clf_coef has one row per coefficient and one column per experiment.
# The reshape below will read the data row-first.
df = pd.DataFrame({
'feature': np.repeat(feat_names, nexpt),
'Classification': np.reshape(clf_coef, (clf_coef.size, )),
'Regression': np.reshape(reg_coef, (reg_coef.size, ))
})
df2 = pd.melt(df, id_vars='feature', var_name='fun')
r_df = com.convert_to_r_dataframe(df2)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(feature)', y = 'value') + \
ggplot2.facet_wrap('fun', scales = 'free_y') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Importance') + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
w = max(22 * nexpt, 80)
if outfile is None:
gp.plot()
else:
ro.r.ggsave(filename=outfile,
plot=gp,
width=w,
height=height,
unit='mm')
return df
def plot_similarity_matrix(self, item_type, image_file, title):
'''Plot similarities of crawls (overlap of unique items)
as heat map matrix'''
data = defaultdict(dict)
n = 1
for crawl1 in self.similarity[item_type]:
for crawl2 in self.similarity[item_type][crawl1]:
similarity = self.similarity[item_type][crawl1][crawl2]
data['crawl1'][n] = MonthlyCrawl.short_name(crawl1)
data['crawl2'][n] = MonthlyCrawl.short_name(crawl2)
data['similarity'][n] = similarity
data['sim_rounded'][n] = similarity # to be rounded
n += 1
data = pandas.DataFrame(data)
print(data)
# select median of similarity values as midpoint of similarity scale
midpoint = data['similarity'].median()
decimals = 3
textsize = 2
minshown = .0005
if (data['similarity'].max()-data['similarity'].min()) > .2:
decimals = 2
textsize = 2.8
minshown = .005
data['sim_rounded'] = data['sim_rounded'].apply(
lambda x: ('{0:.'+str(decimals)+'f}').format(x).lstrip('0')
if x >= minshown else '0')
print('Median of similarities for', item_type, '=', midpoint)
matrix_size = len(self.similarity[item_type])
if matrix_size > self.MAX_MATRIX_SIZE:
n = 0
for crawl1 in sorted(self.similarity[item_type], reverse=True):
short_name = MonthlyCrawl.short_name(crawl1)
if n > self.MAX_MATRIX_SIZE:
data = data[data['crawl1'] != short_name]
data = data[data['crawl2'] != short_name]
n += 1
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl2', y='crawl1',
fill='similarity', label='sim_rounded') \
+ ggplot2.geom_tile(color="white") \
+ ggplot2.scale_fill_gradient2(low="red", high="blue", mid="white",
midpoint=midpoint, space="Lab") \
+ GGPLOT2_THEME \
+ ggplot2.coord_fixed() \
+ ggplot2.theme(**{'axis.text.x':
ggplot2.element_text(angle=45,
vjust=1, hjust=1)}) \
+ ggplot2.labs(title=title, x='', y='') \
+ ggplot2.geom_text(color='black', size=textsize)
img_path = os.path.join(PLOTDIR, image_file)
p.save(img_path)
return p
def plot_cv_r2(pandas_df, outfile, fsize = 10, height = 120, max_width = 50, xlab = 'Parameters'):
"""Makes boxplots of cross-validation results for different parameter settings"""
ncv = len(set(list(pandas_df['title'])))
r_df = com.convert_to_r_dataframe(pandas_df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(title)', y = 'r2') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('R-squared') + \
ggplot2.scale_x_discrete(xlab) + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize)})
w = max(5 * ncv, max_width)
ro.r.ggsave(filename = outfile, plot = gp, width = w, height = height, unit = 'mm')
def makeDistanceBox( alldata, figurename, feature="distance") :
alldata["distance"] = alldata.het + alldata.hom
r_dataframe = com.convert_to_r_dataframe(alldata)
p = ggplot2.ggplot(r_dataframe) + \
ggplot2.aes_string(x="factor(continent)", y=feature) + \
ggplot2.geom_boxplot() + \
ggplot2.ggtitle("Distance from Reference by Continent") + \
ggplot2.theme(**mytheme) #+ \
#ggplot2.theme(**{'axis.text.x': ggplot2.element_text(angle = 45)}) + \
#ggplot2.facet_grid( robjects.Formula('RVIS_type ~ .') )
grdevices.png(figurename)
p.plot()
grdevices.dev_off()
def plot_cels(expr, expt_names, expt_name_idx, cel_names, outdir = None):
"""Makes correlation plots between CEL files for the same cell type"""
fsize = 10
names_1 = []
names_2 = []
cors = []
titles = []
for ex_idx, ex in enumerate(expt_names):
# Indices of CEL files (columns of expr) corresponding to that cell type
tmp_idx = expt_name_idx[ex]
plot_idx = 0
for i in range(len(tmp_idx)):
name1 = re.sub('_', '.', cel_names[tmp_idx[i]])
for j in range(i + 1, len(tmp_idx)):
name2 = re.sub('_', '.', cel_names[tmp_idx[j]])
plot_idx += 1
cor = np.corrcoef(expr[:, tmp_idx[i]], expr[:, tmp_idx[j]])[0, 1]
names_1.append(name1)
names_2.append(name2)
cors.append(cor)
titles.append(ex + '-' + str(plot_idx))
df = ro.DataFrame({'x':ro.FloatVector(expr[:, tmp_idx[i]]),
'y':ro.FloatVector(expr[:, tmp_idx[j]])})
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x = 'x', y = 'y') + \
ggplot2.geom_point(size = 1) + \
ggplot2.scale_x_continuous(name1) + ggplot2.scale_y_continuous(name2) + \
ggplot2.theme_bw() + ggplot2.ggtitle('{:s}-{:d} ({:.4f})'.format(ex, plot_idx, cor)) + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.title.x':ggplot2.element_text(size = 8),
'axis.text.y':ggplot2.element_text(size = fsize),
'axis.title.y':ggplot2.element_text(size = 8, angle = 90),
'plot.title':ggplot2.element_text(size = fsize)})
if outdir is None:
gp.plot()
else:
if not os.path.isdir(outdir):
os.makedirs(outdir)
outfile = os.path.join(outdir, ex + '-' + str(plot_idx) + '.png')
ro.r.ggsave(filename = outfile, plot = gp, width = 85, height = 85, unit = 'mm')
df = pd.DataFrame({'name1':names_1, 'name2':names_2, 'cor':cors}, index = titles)
if not outdir is None:
df.to_csv(os.path.join(outdir, 'cor_summary.txt'), sep = '\t')
return df
def plot_cv_r2(pandas_df,
outfile,
fsize=10,
height=120,
max_width=50,
xlab='Parameters'):
"""Makes boxplots of cross-validation results for different parameter settings"""
ncv = len(set(list(pandas_df['title'])))
r_df = com.convert_to_r_dataframe(pandas_df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(title)', y = 'r2') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('R-squared') + \
ggplot2.scale_x_discrete(xlab) + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize)})
w = max(5 * ncv, max_width)
ro.r.ggsave(filename=outfile, plot=gp, width=w, height=height, unit='mm')
def plot_thresh_distr(motif_names, thresh, out_dir, width = 350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif':motif_names, 'thresh':thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep = '\t', index = False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename = os.path.join(out_dir, 'count_thresh_bar' + ext),
plot = gp, width = width, height = 300, unit = 'mm')
def plot_thresh_distr(motif_names, thresh, out_dir, width=350):
"""Creates boxplots of the thresholds used with each feature."""
df = pd.DataFrame({'motif': motif_names, 'thresh': thresh})
df = df[df['thresh'] > 1]
df.to_csv(os.path.join(out_dir, 'count_thresh.txt'), sep='\t', index=False)
fsize = 10
r_df = com.convert_to_r_dataframe(df)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(motif)', y = 'thresh') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Threshold counts', limits = ro.IntVector([0, 70])) + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + ggplot2.coord_flip() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.text.y':ggplot2.element_text(size = fsize, hjust = 1),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
for ext in ['.pdf', '.png']:
ro.r.ggsave(filename=os.path.join(out_dir, 'count_thresh_bar' + ext),
plot=gp,
width=width,
height=300,
unit='mm')
def plot_coef(feat_mat_dir, model_dir, expt_names, pref, outfile = None, height = 120, fsize = 12):
for expt_idx, ex in enumerate(expt_names):
feat_mat_file = os.path.join(feat_mat_dir, ex + '_feat_mat.npz')
model_file = os.path.join(model_dir, pref + ex + '_model.pkl')
model = read_model(model_file)
(tmp_feat, tmp_y, tmp_feat_names, tmp_gene_names) = read_feat_mat(feat_mat_file)
if expt_idx == 0:
feat_names = tmp_feat_names
clf_coef = model.clf_coef()
reg_coef = model.reg_coef()
else:
assert(all(f[0] == f[1] for f in zip(feat_names, tmp_feat_names)))
clf_coef = np.concatenate((clf_coef, model.clf_coef()), axis = 1)
reg_coef = np.concatenate((reg_coef, model.reg_coef()), axis = 1)
nexpt = expt_idx + 1
# Now clf_coef has one row per coefficient and one column per experiment.
# The reshape below will read the data row-first.
df = pd.DataFrame({'feature':np.repeat(feat_names, nexpt),
'Classification':np.reshape(clf_coef, (clf_coef.size,)),
'Regression':np.reshape(reg_coef, (reg_coef.size,))})
df2 = pd.melt(df, id_vars = 'feature', var_name = 'fun')
r_df = com.convert_to_r_dataframe(df2)
gp = ggplot2.ggplot(r_df) + ggplot2.aes_string(x = 'factor(feature)', y = 'value') + \
ggplot2.facet_wrap('fun', scales = 'free_y') + \
ggplot2.geom_boxplot() + ggplot2.scale_y_continuous('Importance') + \
ggplot2.scale_x_discrete('') + ggplot2.theme_bw() + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize, angle = 65, vjust = 1, hjust = 1),
'axis.text.y':ggplot2.element_text(size = fsize),
'strip.text.x':ggplot2.element_text(size = fsize + 1)})
w = max(22 * nexpt, 80)
if outfile is None:
gp.plot()
else:
ro.r.ggsave(filename = outfile, plot = gp, width = w, height = height, unit = 'mm')
return df
def plot_stacked_bar(self, data, row_filter, img_file, ratio=1.0):
if len(row_filter) > 0:
data = data[data['type'].isin(row_filter)]
for value in row_filter:
if re.search('^fetcher:(?:aggr:)?', value):
replacement = re.sub('^fetcher:(?:aggr:)?', '', value)
data.replace(to_replace=value, value=replacement, inplace=True)
# print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='percentage', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='RdYlGn', type='sequential',
guide=ggplot2.guide_legend(reverse=True)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='Percentage of Fetch Status',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path)
return p
def plot_fetch_status(self, data, row_filter, img_file, ratio=1.0):
if len(row_filter) > 0:
data = data[data['type'].isin(row_filter)]
for value in row_filter:
if re.search('^fetcher:(?:aggr:)?', value):
replacement = re.sub('^fetcher:(?:aggr:)?', '', value)
data.replace(to_replace=value, value=replacement, inplace=True)
# print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='percentage', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='RdYlGn', type='sequential',
guide=ggplot2.guide_legend(reverse=True)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='Percentage of Fetch Status',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path)
return p
def plot_crawldb_status(self, data, row_filter, img_file, ratio=1.0):
if len(row_filter) > 0:
data = data[data['type'].isin(row_filter)]
for value in row_filter:
if re.search('^crawldb:status:db_', value):
replacement = re.sub('^crawldb:status:db_', '', value)
data.replace(to_replace=value, value=replacement, inplace=True)
data['size'] = data['size'].astype(float)
print(data)
p = ggplot2.ggplot(data) \
+ ggplot2.aes_string(x='crawl', y='size', fill='type') \
+ ggplot2.geom_bar(stat='identity', position='stack', width=.9) \
+ ggplot2.coord_flip() \
+ ggplot2.scale_fill_brewer(palette='Pastel1', type='sequential',
guide=ggplot2.guide_legend(reverse=False)) \
+ GGPLOT2_THEME \
+ ggplot2.theme(**{'legend.position': 'bottom',
'aspect.ratio': ratio}) \
+ ggplot2.labs(title='CrawlDb Size and Status Counts (before crawling)',
x='', y='', fill='')
img_path = os.path.join(PLOTDIR, img_file)
p.save(img_path)
return p
def 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()
def rest():
df = q1_median_q3_rep_wide
pops = ["pdc", "dc-cd11b", "dc-cd8a"]
stats_l = []
for stat, (popa, popb) in product(["Q1", "median", "Q3"],
product(pops, pops)):
print(stat, popa, popb)
popa = "hsc"
popb = "pdc"
stat = "median"
mw_u, pvalue = scipy.stats.mannwhitneyu(
[0.8, 0.81, 0.79],
[0.4, 0.39, 0.41],
# df.query("Population == @popa")[stat].to_numpy(),
# df.query("Population == @popb")[stat].to_numpy(),
use_continuity=True,
alternative="two-sided",
)
pvalue
stats_l.append([stat, popa, popb, mw_u, pvalue])
stats_df = pd.DataFrame(stats_l).set_axis(
["stat", "popA", "popB", "U", "pvalue"], axis=1)
kruskal_format_means = pd.pivot(
q1_median_q3_rep_wide.query("Population in @pops"),
index="Population",
columns="Replicate",
values="mean",
)
import scikit_posthocs
stat, p_value = scipy.stats.kruskal(
*[kruskal_format_means.loc[pop].to_numpy() for pop in pops], )
dunn_res_df = scikit_posthocs.posthoc_dunn(
kruskal_format_means.to_numpy(),
p_adjust='fdr_bh',
sort=True,
)
stat, pvalue = scipy.stats.f_oneway(
*[kruskal_format_means.loc[pop].to_numpy() for pop in pops], )
import statsmodels
df = kruskal_format_means.stack().reset_index()
kruskal_format_means
res = statsmodels.stats.multicomp.pairwise_tukeyhsd(
df[0], df['Population'].to_numpy(), alpha=0.05)
res.pvalues
res.summary()
# wilcox.test(c(0.8, 0.79, 0.81), c(0.4, 0.39, 0.41), paired=F, exact=F)
plot_pops = ["pdc", "dc-cd8a", "dc-cd11b"]
results_dir = "/icgc/dkfzlsdf/analysis/hs_ontogeny/notebook-data/gNs4xcMJscaLLwlt"
point_plot_quartiles_png = results_dir + "/point-plot-quartiles.png"
q1_median_q3_rep_wide
ggplot_data = (
q1_median_q3_rep_long.query("Population in @plot_pops").sort_values(
"value",
ascending=False,
).groupby(["Population", "stat"]).apply(
lambda df: df.assign(group_order=np.arange(1, df.shape[0] + 1))))
g = (gg.ggplot(ggplot_data) + gg.aes_string(
x="Population", y="value", group="group_order", color="stat") +
gg.geom_point(position=gg.position_dodge(width=0.5), size=1) +
mh_rpy2_styling.gg_paper_theme + gg.labs(y='Methylation (%)', x=''))
a = 3
rpy2_utils.image_png2(g, (ut.cm(6), ut.cm(6)))
ut.save_and_display(
g,
png_path=point_plot_quartiles_png,
# additional_formats=tuple(),
height=ut.cm(6),
width=ut.cm(6),
)
q1_median_q3_rep_wide
g = (
gg.ggplot(
q1_median_q3_rep_wide.query("Population in @plot_pops").assign(
sample=lambda df: df["Population"].astype(str) + df[
"Replicate"].astype(str))) + gg.geom_boxplot(
gg.aes_string(
x="Population",
fill="Population",
group="sample",
lower="Q1",
upper="Q3",
middle="median",
ymin="min1",
ymax="max99",
# position=gg.position_dodge(width=0.5),
),
stat="identity",
)
# + mh_rpy2_styling.gg_paper_theme
+ gg.theme(axis_text_x=gg.element_text(angle=90, hjust=1)) +
gg.scale_fill_brewer(guide=False))
a = 3
ut.save_and_display(
g,
png_path=point_plot_quartiles_png,
additional_formats=tuple(),
height=ut.cm(6),
width=ut.cm(7),
)
# image_png2(g, (ut.cm(12), ut.cm(12)))
beta_values.loc[:, ("hsc", "1")]
# lines
# plot with both log and linear y scales
# aes_string: set the axis labels and what we're plotting
# opts: sets thickness of the lines
# note the use of **{} to allow setting "legend.key.size" as a keyword
# scale_colour_manual: associate color datasets with actual colors and names
# geom_point and geom_line: thicker points and lines
# 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])),
# 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') + \
ggplot2.scale_colour_manual(values = robjects.StrVector(['green', 'yellow'])) + \
fte_theme = theme(
**{
'axis.ticks':
element_blank(),
'panel.background':
element_rect(fill=robjects.r.color_background,
color=robjects.r.color_background),
'plot.background':
element_rect(fill=robjects.r.color_background,
color=robjects.r.color_background),
'panel.border':
element_rect(
color=robjects.r.color_background
), #'panel.grid.major':element_line(color=robjects.r.color_grid_major, size = 0.25),
'panel.grid.minor':
element_blank(),
'axis.ticks':
element_blank(),
'legend.position':
"right",
'legend.background':
element_rect(fill=robjects.r.color_background),
'legend.text':
element_text(size=10, color=robjects.r.color_axis_title),
'legend.title':
element_blank(),
'plot.title':
element_text(
size=12, color=robjects.r.color_title, vjust=1.25, hjust=0),
'axis.text.x':
element_text(size=10, color=robjects.r.color_axis_text),
'axis.text.y':
element_text(size=10, color=robjects.r.color_axis_text),
'axis.title.x':
element_text(size=10, 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=10, color=robjects.r.color_axis_title, angle=90)
})
def plot_squiggle(args, filename, start_times, mean_signals):
"""
Use rpy2 to create a squiggle plot of the read
"""
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]
total_time = start_times[-1] - start_times[0]
# adjust times to be relative to t_0
r_start_times = robjects.FloatVector([t - t_0 for t in start_times])
r_mean_signals = robjects.FloatVector(mean_signals)
# infer the appropriate number of events given the number of facets
num_events = len(r_mean_signals)
events_per_facet = (num_events / args.num_facets) + 1
# dummy variable to control faceting
facet_category = robjects.FloatVector([(i / events_per_facet) + 1
for i in range(len(start_times))])
# make a data frame of the start times and mean signals
d = {'start': r_start_times, 'mean': r_mean_signals, 'cat': facet_category}
df = robjects.DataFrame(d)
gp = ggplot2.ggplot(df)
if not args.theme_bw:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)})
else:
pp = gp + ggplot2.aes_string(x='start', y='mean') \
+ ggplot2.geom_step(size=0.25) \
+ ggplot2.facet_wrap(robjects.Formula('~cat'), ncol=1, scales="free_x") \
+ ggplot2.scale_x_continuous('Time (seconds)') \
+ ggplot2.scale_y_continuous('Mean signal (picoamps)') \
+ ggplot2.ggtitle('Squiggle plot for read: ' + filename + "\nTotal time (sec): " + str(total_time)) \
+ ggplot2.theme(**{'plot.title': ggplot2.element_text(size=11)}) \
+ ggplot2.theme_bw()
if args.saveas is not None:
plot_file = os.path.basename(filename) + "." + args.saveas
if os.path.isfile(plot_file):
raise Exception(
'Cannot create plot for %s: plot file %s already exists' %
(filename, plot_file))
if args.saveas == "pdf":
grdevices.pdf(plot_file, width=8.5, height=11)
elif args.saveas == "png":
grdevices.png(plot_file, width=8.5, height=11, units="in", res=300)
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
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.theme(**{ 'legend.position': 'left', \
'legend.key.size': R.r.unit(2, 'lines'), \
'legend.title' : ggplot2.element_text(size = 14, hjust=0), \
'legend.text': ggplot2.element_text(size = 12), \
'title' : ggplot2.element_text('Obama Vote Share and Distance to Railroads in IL'), \
'plot.title': ggplot2.element_text(size = 24),
'plot.margin': R.r.unit(R.r.rep(0,4),'lines'), \
'panel.background': ggplot2.element_blank(), \
'panel.grid.minor': ggplot2.element_blank(), \
'panel.grid.major': ggplot2.element_blank(), \
'axis.ticks': ggplot2.element_blank(), \
'axis.title.x': ggplot2.element_blank(), \
'axis.title.y': ggplot2.element_blank(), \
'axis.title.x': ggplot2.element_blank(), \
'axis.title.x': ggplot2.element_blank(), \
'axis.text.x': ggplot2.element_blank(), \
'axis.text.y': ggplot2.element_blank()} ) + \
ggplot2.geom_line(ggplot2.aes(x='long',
y='lat',
group='group'),
data=IL_railroads,
color='grey',
size=0.2) + \
ggplot2.coord_equal()
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()
def plot_cels(expr, expt_names, expt_name_idx, cel_names, outdir=None):
"""Makes correlation plots between CEL files for the same cell type"""
fsize = 10
names_1 = []
names_2 = []
cors = []
titles = []
for ex_idx, ex in enumerate(expt_names):
# Indices of CEL files (columns of expr) corresponding to that cell type
tmp_idx = expt_name_idx[ex]
plot_idx = 0
for i in range(len(tmp_idx)):
name1 = re.sub('_', '.', cel_names[tmp_idx[i]])
for j in range(i + 1, len(tmp_idx)):
name2 = re.sub('_', '.', cel_names[tmp_idx[j]])
plot_idx += 1
cor = np.corrcoef(expr[:, tmp_idx[i]], expr[:, tmp_idx[j]])[0,
1]
names_1.append(name1)
names_2.append(name2)
cors.append(cor)
titles.append(ex + '-' + str(plot_idx))
df = ro.DataFrame({
'x': ro.FloatVector(expr[:, tmp_idx[i]]),
'y': ro.FloatVector(expr[:, tmp_idx[j]])
})
gp = ggplot2.ggplot(df) + ggplot2.aes_string(x = 'x', y = 'y') + \
ggplot2.geom_point(size = 1) + \
ggplot2.scale_x_continuous(name1) + ggplot2.scale_y_continuous(name2) + \
ggplot2.theme_bw() + ggplot2.ggtitle('{:s}-{:d} ({:.4f})'.format(ex, plot_idx, cor)) + \
ggplot2.theme(**{'axis.text.x':ggplot2.element_text(size = fsize),
'axis.title.x':ggplot2.element_text(size = 8),
'axis.text.y':ggplot2.element_text(size = fsize),
'axis.title.y':ggplot2.element_text(size = 8, angle = 90),
'plot.title':ggplot2.element_text(size = fsize)})
if outdir is None:
gp.plot()
else:
if not os.path.isdir(outdir):
os.makedirs(outdir)
outfile = os.path.join(outdir,
ex + '-' + str(plot_idx) + '.png')
ro.r.ggsave(filename=outfile,
plot=gp,
width=85,
height=85,
unit='mm')
df = pd.DataFrame({
'name1': names_1,
'name2': names_2,
'cor': cors
},
index=titles)
if not outdir is None:
df.to_csv(os.path.join(outdir, 'cor_summary.txt'), sep='\t')
return df
color_grid_major = palette[3]
color_axis_text = palette[6]
color_axis_title = palette[7]
color_title = palette[9]
palette_lines <- brewer.pal("Set2", n=8)
''')
size = 9
fte_theme = theme(**{'axis.ticks':element_blank(),
'panel.background':element_rect(fill=robjects.r.color_background, color=robjects.r.color_background),
'plot.background':element_rect(fill=robjects.r.color_background, color=robjects.r.color_background),
'panel.border':element_rect(color=robjects.r.color_background),
'panel.grid.minor':element_blank(),
'axis.ticks':element_blank(),
'legend.position':"right",
'legend.background': element_rect(fill="transparent"),
'legend.text': element_text(size=size,color=robjects.r.color_axis_title),
'legend.title': element_text(size=size,color=robjects.r.color_axis_title),
'plot.title':element_text(color=robjects.r.color_title, size=10, vjust=1.25),
'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()
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()
# lines
# plot with both log and linear y scales
# aes_string: set the axis labels and what we're plotting
# opts: sets thickness of the lines
# note the use of **{} to allow setting "legend.key.size" as a keyword
# scale_colour_manual: associate color datasets with actual colors and names
# geom_point and geom_line: thicker points and lines
# 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])),
def plot_volcano_with_r(
data,
xlabel='Estimated effect (change in H/L ratio)',
title='',
max_labels=20,
color_background='#737373',
color_significant='#252525',
color_significant_muted='#252525',
label_only_large_fc=False,
special_labels=None,
special_palette=None,
base_size=12,
label_size=3,
x='logFC',
y='neg_log10_p_adjust',
special_labels_mode='all',
xlim=None,
skip_labels=None,
nudges=None,
):
r_data, r_like_data = transform_data_for_ggplot(
data,
label_only_large_fc=label_only_large_fc,
special_labels=special_labels,
max_labels=max_labels,
special_labels_mode=special_labels_mode,
skip_labels=skip_labels,
nudges=nudges)
plot = r_ggplot2.ggplot(r_data)
plot += r_ggplot2.theme_minimal(base_size=base_size)
plot += r_ggplot2.theme(
**{
'panel.grid.major':
r_ggplot2.element_blank(),
'panel.grid.minor':
r_ggplot2.element_blank(),
'panel.border':
r_ggplot2.element_rect(fill=robjects.rinterface.NA, color="black")
})
plot += r_ggplot2.theme(
text=r_ggplot2.element_text(family='Helvetica', face='plain'))
plot += r_ggplot2.theme(
**{
'plot.title': r_ggplot2.element_text(hjust=0.5),
# 'axis.title.y': r_ggplot2.element_text((t = 0, r = 20, b = 0, l = 0)),
})
aes_points = r_ggplot2.aes_string(x=x, y=y, color='group')
scale_points = r_ggplot2.scale_colour_manual(
aes_points,
values=r_label_palette(
r_like_data,
special_palette,
color_background=color_background,
color_significant=color_significant,
color_significant_muted=color_significant_muted))
plot += aes_points
plot += scale_points
if xlim is not None:
plot += r_ggplot2.scale_x_continuous(
labels=r_custom.formatterFunTwoDigits, limits=robjects.r.c(*xlim))
else:
plot += r_ggplot2.scale_x_continuous(
labels=r_custom.formatterFunTwoDigits)
plot += r_ggplot2.scale_y_continuous(labels=r_custom.formatterFunOneDigit)
plot += r_ggplot2.geom_hline(
yintercept=float(-np.log10(FDR_THRESHOLD_RESPONSE)),
color='#BDBDBD',
alpha=.3)
plot += r_ggplot2.geom_vline(xintercept=float(FC_THRESHOLD_RESPONSE),
color='#BDBDBD',
alpha=.3)
plot += r_ggplot2.geom_vline(xintercept=-float(FC_THRESHOLD_RESPONSE),
color='#BDBDBD',
alpha=.3)
plot += r_ggplot2.geom_point(**{'show.legend': False})
aes_text = r_ggplot2.aes_string(label='label')
plot += aes_text
plot += r_ggrepel.geom_text_repel(
aes_text,
nudge_x=r_dollar(r_data, 'nudgex'),
nudge_y=r_dollar(r_data, 'nudgey'),
size=label_size,
family='Helvetica',
**{
'show.legend': False,
'point.padding': 0.25,
'min.segment.length': 0,
#'max.iter':0,
'segment.color': '#BDBDBD'
},
)
plot += r_ggplot2.labs(x=xlabel,
y='Adjusted p value (-log10)',
title=title)
plot.plot()
def plot_qc_reads(qc_df):
"""
Plot number of reads part of a pipeline QC file.
"""
# Record NA values as 0
qc_df = qc_df.fillna(0)#.set_index("sample")
cols = ["sample",
"num_reads",
"num_mapped",
"num_unique_mapped",
"num_junctions"]
qc_df = qc_df[cols]
melted_qc = pandas.melt(qc_df, id_vars=["sample"])
qc_r = conversion_pydataframe(melted_qc)
labels = tuple(["num_reads",
"num_mapped",
"num_unique_mapped",
"num_junctions"])
labels = robj.StrVector(labels)
variable_i = qc_r.names.index('variable')
qc_r[variable_i] = robj.FactorVector(qc_r[variable_i],
levels = labels)
ggplot2.theme_set(ggplot2.theme_bw(12))
scales = importr("scales")
r_opts = r.options(scipen=4)
p = ggplot2.ggplot(qc_r) + \
ggplot2.geom_point(aes_string(x="sample", y="value")) + \
ggplot2.scale_y_continuous(trans=scales.log10_trans(),
breaks=scales.trans_breaks("log10",
robj.r('function(x) 10^x')),
labels=scales.trans_format("log10",
robj.r('math_format(10^.x)'))) + \
r.xlab("CLIP-Seq samples") + \
r.ylab("No. reads") + \
ggplot2.coord_flip() + \
ggplot2.facet_wrap(Formula("~ variable"), ncol=1) + \
theme(**{"panel.grid.major.x": element_blank(),
"panel.grid.minor.x": element_blank(),
"panel.grid.major.y": theme_line(size=0.5,colour="grey66",linetype=3)})
p.plot()
return
r.par(mfrow=np.array([1,2]))
num_samples = len(qc_df.num_reads)
r.par(bty="n", lwd=1.7, lty=2)
r_opts = r.options(scipen=4)
r.options(r_opts)
r.dotchart(convert_to_r_matrix(qc_df[["num_reads",
"num_mapped",
"num_unique_mapped"]]),
xlab="No. reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)
r.par(bty="n")
r.dotchart(convert_to_r_matrix(qc_df[["num_ribosub_mapped",
"num_ribo",
"num_junctions"]]),
xlab="No. reads",
lcolor="black",
pch=19,
gcolor="darkblue",
cex=0.8)
