def plot_total_bp(parser, args, tot_bp_per_pore):
"""
Plot the pore performance
"""
import math
r = robjects.r
r.library("ggplot2")
grdevices = importr("grDevices")
flowcell_layout = minion_flowcell_layout()
pore_values = []
for pore in flowcell_layout:
if pore in tot_bp_per_pore:
pore_values.append(math.log10(tot_bp_per_pore[pore]))
else:
pore_values.append(0)
# make a data frame of the lists
d = {
"rownum": robjects.IntVector(range(1, 17) * 32),
"colnum": robjects.IntVector(sorted(range(1, 33) * 16)),
"log10_tot_bp": robjects.IntVector(pore_values),
"labels": robjects.IntVector(flowcell_layout),
}
df = robjects.DataFrame(d)
gp = gg.ggplot(df)
pp = (
gp
+ gg.aes_string(y="factor(rownum, rev(rownum))", x="factor(colnum)")
+ gg.geom_point(gg.aes_string(color="log10_tot_bp"), size=7)
+ gg.geom_text(gg.aes_string(label="labels"), colour="white", size=2)
+ gg.scale_colour_gradient2(low="black", mid="black", high="red")
+ gg.coord_fixed(ratio=1.4)
+ gg.labs(x=gg.NULL, y=gg.NULL)
)
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width=11, height=8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width=11, height=8.5, units="in", res=300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print ("Type enter to exit.")
raw_input()
def plot_total_bp(parser, args, tot_bp_per_pore):
"""
Plot the pore performance
"""
import math
r = robjects.r
r.library("ggplot2")
grdevices = importr('grDevices')
flowcell_layout = minion_flowcell_layout()
pore_values = []
for pore in flowcell_layout:
if pore in tot_bp_per_pore:
pore_values.append(math.log10(tot_bp_per_pore[pore]))
else:
pore_values.append(0)
# make a data frame of the lists
d = {'rownum': robjects.IntVector(range(1,17)*32),
'colnum': robjects.IntVector(sorted(range(1,33)*16)),
'log10_tot_bp': robjects.IntVector(pore_values),
'labels': robjects.IntVector(flowcell_layout)
}
df = robjects.DataFrame(d)
gp = gg.ggplot(df)
pp = gp + gg.aes_string(y = 'factor(rownum, rev(rownum))', \
x = 'factor(colnum)') \
+ gg.geom_point(gg.aes_string(color='log10_tot_bp'), size = 7) \
+ gg.geom_text(gg.aes_string(label ='labels'), colour="white", size = 2) \
+ gg.scale_colour_gradient2(low = "black", mid= "black", high="red") \
+ gg.coord_fixed(ratio=1.4) \
+ gg.labs(x=gg.NULL, y=gg.NULL)
if args.saveas is not None:
plot_file = args.saveas
if plot_file.endswith(".pdf"):
grdevices.pdf(plot_file, width = 11, height = 8.5)
elif plot_file.endswith(".png"):
grdevices.png(plot_file, width = 11, height = 8.5,
units = "in", res = 300)
else:
logger.error("Unrecognized extension for %s!" % (plot_file))
sys.exit()
pp.plot()
grdevices.dev_off()
else:
pp.plot()
# keep the plot open until user hits enter
print('Type enter to exit.')
raw_input()
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 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_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()
onlysurf=robjects.r('onlysurface<-onlyfilt[ which("Sampledepth" =="0.30487806"),]')
#print "onlysurf"
#print onlysurf
#colours2 = grdevices.topo_colors(10)
colours2 = grdevices.cm_colors(10)
#colours2 = grdevices.rainbow(20)
#print colours2
#colours = ggplot2.rainbow(54)
#bins=10
gp = ggplot2.ggplot(onlysurf)
#gp = ggplot2.ggplot(onlyfilts)
gp=gp+ggplot2.aes_string(x="Lon", y="Lat", col="Temp",label="Station")
gp=gp+ggplot2.scale_colour_gradientn(colours=colours2)
gp=gp+ggplot2.geom_text(col="black",offset = 10)
gp=gp+ggplot2.geom_point(position="jitter")
gp=gp+ggplot2.ggtitle(graphtitle)
robjects.r('library(ggmap)')
robjects.r('library(mapproj)')
robjects.r('map <- get_map(location = "Europe", zoom = 4)')
robjects.r('ggmap(map)')
#robjects.r('library(maps)')
#robjects.r('map("world", interior = FALSE)')
#robjects.r('map("state", boundary = FALSE, col="gray", add = TRUE)')
#gp.plot()
iris_py = pandas.read_csv("/home/yarden/iris.csv")
iris_py = iris_py.rename(columns={"Name": "Species"})
corrs = []
from scipy.stats import spearmanr
for species in set(iris_py.Species):
entries = iris_py[iris_py["Species"] == species]
c = spearmanr(entries["SepalLength"], entries["SepalWidth"])
print "c: ", c
# compute r.cor(x, y) and divide up by Species
# Assume we get a vector of length Species saying what the
# correlation is for each Species' Petal Length/Width
p = ggplot2.ggplot(iris) + \
ggplot2.geom_point(ggplot2.aes_string(x="Sepal.Length", y="Sepal.Width")) + \
ggplot2.facet_wrap(Formula("~Species"))
p.plot()
r["dev.off"]()
sys.exit(1)
grdevices = importr('grDevices')
ggplot2.theme_set(ggplot2.theme_bw(12))
p = ggplot2.ggplot(iris) + \
ggplot2.geom_point(ggplot2.aes_string(x="Sepal.Length", y="Sepal.Width")) + \
ggplot2.facet_wrap(Formula('~ Species'), ncol=2, nrow = 2) + \
ggplot2.geom_text(aes_string(x="Sepal.Length", y="Sepal.Width"), label="t") + \
ggplot2.GBaseObject(r('ggplot2::coord_fixed')()) # aspect ratio
p.plot()
