def endPlot(self, layout, legend, path):
title = path2str(path)
r = ResultBlock(
text="#$hv {}$#".format(title),
title=title)
r.hv = layout
return ResultBlocks(r)
def endPlot(self, plts, legends, path):
"""close plots.
"""
title = path2str(path)
figid = 10
lines = []
figid = self.bokeh_figure._id
lines.append("")
lines.append("#$bkh %s$#" % figid)
lines.append("")
r = ResultBlock("\n".join(lines), title=title)
r.bokeh = self.bokeh_figure
return ResultBlocks(r)
def __call__(self, track, slice=None):
# note there are spaces behind the %(image)s directive to accomodate
# for path substitution
block = '''
.. figure:: %(image)s
:height: 300
'''
blocks = ResultBlocks()
tracks = sorted([x.asFile() for x in TRACKS])
for track in tracks:
files = glob.glob(
os.path.join(EXPORTDIR, "fastqc", "%s*_fastqc" % track))
for x, fn in enumerate(sorted(files)):
y = x + 1
image = os.path.abspath(
os.path.join(fn, "Images", "%s.png" % slice))
if not os.path.exists(image):
continue
blocks.append(
ResultBlock(text=block % locals(),
title=os.path.basename(fn)))
return odict(
(("rst", "\n".join(Utils.layoutBlocks(blocks,
layout="columns-2"))), ))
def __call__(self, track, slice=None):
edir = EXPORTDIR
method = "utr_extension"
blocks = ResultBlocks()
filepath = "%(edir)s/%(method)s/%(track)s.readextension_%(region)s_%(direction)s.%(slice)s.png"
block = \
'''
.. figure:: %(filename)s
:height: 300
'''
# append spaces for file extension
block = "\n".join([x + " " * 200 for x in block.split("\n")])
for region, direction in itertools.product(
("downstream", "upstream"), ("sense", "antisense", "anysense")):
filename = filepath % locals()
if os.path.exists(filename):
blocks.append(
ResultBlock(text=block % locals(),
title="%(track)s %(region)s %(direction)s" %
locals()))
# else:
# blocks.append( ResultBlock( "",
# title = "%(track)s %(region)s %(direction)s" % locals() ) )
return odict(
(("rst", "\n".join(Utils.layoutBlocks(blocks,
layout="columns-3"))), ))
def endPlot(self, plots, legends, path):
"""close plots.
"""
result = ResultBlocks()
title = path2str(path)
for plot in plots:
figid = plot._id
lines = []
lines.append("")
lines.append("#$bkh %s$#" % figid)
lines.append("")
r = ResultBlock("\n".join(lines), title=title)
r.bokeh = plot
result.append(r)
return result
def render(self, dataframe, path):
R.library('ggplot2')
# add all indices as columns
dataframe.reset_index(inplace=True)
rframe = pandas.rpy.common.convert_to_r_dataframe(dataframe)
# for the issue below, see:
# http://stackoverflow.com/questions/12865218/getting-rid-of-asis-class-attribute
unAsIs = R('''function (x) {
if(typeof(x) %in% c("integer","double")) {
class(x) <- "numeric"
return (x)}
else if (typeof(x) == "character") {
class(x) <- "character"
return (x) }
else {
return(x) } }''')
rframe = R["as.data.frame"](R.lapply(rframe, unAsIs))
R.assign("rframe", rframe)
# start plot
R('''gp = ggplot(rframe)''')
# add aesthetics and geometries
try:
pp = R('''gp + %s ''' % self.statement)
except ValueError as msg:
raise ValueError(
"could not interprete R statement: "
"gp + %s; msg=%s" % (self.statement, msg))
figname = re.sub('/', '_', path2str(path))
r = ResultBlock('#$ggplot %s$#' % figname,
title=path2str(path))
r.rggplot = pp
r.figname = figname
return ResultBlocks(r)
def asFile(self, dataframe, row_headers, col_headers, title):
'''save the table as HTML file.
Multiple files of the same Renderer/Tracker combination are
distinguished by the title.
'''
self.debug("%s: saving %i x %i table as file'" %
(id(self),
len(row_headers),
len(col_headers)))
lines = []
lines.append("`%i x %i table <#$html %s$#>`__" %
(len(row_headers), len(col_headers),
title))
r = ResultBlock("\n".join(lines) + "\n", title=title)
out = StringIO.StringIO()
dataframe.to_csv(out)
lines = out.getvalue().split("\n")
# create an html table
data = ["<table>"]
data.append("<tr><th></th><th>%s</th></tr>" %
"</th><th>".join(map(str, lines[0].split(","))))
data.extend(["<tr><td>%s</td></tr>" %
("</td><td>".join(x.split(","))) for x in lines[1:]])
data.append("</table>\n")
# substitute links
data = [re.sub(
"`(.*?(?:\".+\"|\'.+\')?.*?)\s<(.*?(?:\".+\"|\'.+\')?.*?)>`_",
r'<a href="\2">\1</a>',
x)
for x in data]
r.html = "\n".join(data)
return r
def render(self, dataframe, path):
R.library('ggplot2')
# add all indices as columns
dataframe.reset_index(inplace=True)
rframe = rpy2.robjects.pandas2ri.py2ri(dataframe)
# for the issue below, see:
# http://stackoverflow.com/questions/12865218/getting-rid-of-asis-class-attribute
unAsIs = R('''function (x) {
if("AsIs" %in% class(x)) {
class(x) <- class(x)[-match("AsIs", class(x))]
}
return (x) } ''')
rframe = R["as.data.frame"](R.lapply(rframe, unAsIs))
R.assign("rframe", rframe)
# start plot
R('''gp = ggplot(rframe)''')
# add aesthetics and geometries
try:
pp = R('''gp + %s ''' % self.statement)
except ValueError as msg:
raise ValueError(
"could not interprete R statement: "
"gp + %s; msg=%s" % (self.statement, msg))
figname = re.sub('/', '_', path2str(path))
r = ResultBlock('#$ggplot %s$#' % figname,
title=path2str(path))
r.rggplot = pp
r.figname = figname
return ResultBlocks(r)
def __call__(self, data, path):
colorbar, factors, unique, xkcd = self.getColorBar(data)
n_samples = data.shape[0]
data = data.iloc[:, :n_samples]
col_dict = dict(list(zip(unique, xkcd)))
print(data.head())
seaborn.set(font_scale=.5)
ax = seaborn.clustermap(data,
row_colors=colorbar, col_colors=colorbar)
plt.setp(ax.ax_heatmap.yaxis.set_visible(False))
for label in unique:
ax.ax_col_dendrogram.bar(
0, 0, color=seaborn.xkcd_rgb[col_dict[label]],
label=label, linewidth=0)
ax.ax_col_dendrogram.legend(loc="center", ncol=len(unique))
return ResultBlocks(ResultBlock(
'''#$mpl %i$#\n''' % ax.cax.figure.number,
title='ClusterMapPlot'))
def asSpreadSheet(self, dataframe, row_headers, col_headers, title):
'''save the table as an xls file.
Multiple files of the same Renderer/Tracker combination are
distinguished by the title.
'''
self.debug("%s: saving %i x %i table as spread-sheet'" %
(id(self),
len(row_headers),
len(col_headers)))
is_hierarchical = isinstance(dataframe.index,
pandas.core.index.MultiIndex)
split = is_hierarchical and len(dataframe.index.levels) > 1
quick = len(dataframe) > 10000
if quick and not split:
# quick writing, only append method works
wb = openpyxl.Workbook(optimized_write=True)
def fillWorksheet(ws, dataframe, title):
ws.append([""] + list(col_headers))
for x, row in enumerate(dataframe.iterrows()):
ws.append([path2str(row[0])] + list(row[1]))
# patch: maximum title length seems to be 31
ws.title = title[:30]
else:
# do it cell-by-cell, this might be slow
wb = openpyxl.Workbook(optimized_write=False)
def fillWorksheet(ws, dataframe, title):
# regex to detect rst hypelinks
regex_link = re.compile('`(.*) <(.*)>`_')
# write row names
for row, row_name in enumerate(dataframe.index):
# rows and columns start at 1
c = ws.cell(row=row + 2, column=1)
c.value = row_name
# write columns
for column, column_name in enumerate(dataframe.columns):
# set column title
# rows and columns start at 1
c = ws.cell(row=1, column=column + 2)
c.value = column_name
# set column values
dataseries = dataframe[column_name]
if dataseries.dtype == object:
for row, value in enumerate(dataseries):
c = ws.cell(row=row + 2,
column=column + 2)
value = str(value)
if value.startswith('`'):
c.value, c.hyperlink =\
regex_link.match(value).groups()
else:
c.value = value
else:
for row, value in enumerate(dataseries):
c = ws.cell(row=row + 2,
column=column + 2)
c.value = value
# patch: maximum title length seems to be 31
ws.title = re.sub("/", "_", title)[:30]
if len(wb.worksheets) == 0:
wb.create_sheet()
if split:
# create separate worksheets for nested indices
nlevels = len(dataframe.index.levels)
paths = map(tuple, DataTree.unique(
[x[:nlevels - 1]
for x in dataframe.index.unique()]))
ws = wb.worksheets[0]
ws.title = 'Summary'
ws.append(
[""] * (nlevels - 1) + ["Worksheet", "Rows"])
for row, path in enumerate(paths):
# select data frame as cross-section
work = dataframe.xs(path, axis=0)
title = path2str(path)
if len(title) > 30:
title = "sheet%i" % row
ws.append(list(path) + [title, len(work)])
c = ws.cell(row=row + 1,
column=nlevels)
# this does not work in oocalc
c.hyperlink = "#%s!A1" % title
fillWorksheet(wb.create_sheet(),
work,
title=title)
else:
fillWorksheet(wb.worksheets[0], dataframe,
title=title)
# write result block
lines = []
lines.append("`%i x %i table <#$xls %s$#>`__" %
(len(row_headers), len(col_headers),
title))
lines.append("")
r = ResultBlock("\n".join(lines), title=title)
r.xls = wb
self.debug("%s: saved %i x %i table as spread-sheet'" %
(id(self),
len(row_headers),
len(col_headers)))
return r
