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 asFile( self, matrix, 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), title = title)
# create an html table
data = ["<table>"]
data.append( "<tr><th></th><th>%s</th></tr>" % "</th><th>".join( map(str,col_headers)) )
for h, row in zip( row_headers, matrix):
data.append( "<tr><th>%s</th><td>%s</td></tr>" % (h, "</td><td>".join(map(str,row)) ))
data.append( "</table>\n" )
r.html = "\n".join( data )
return ResultBlocks( r )
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 __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 render(self, dataframe, path ):
R.library( 'ggplot2' )
rframe = pandas.rpy.common.convert_to_r_dataframe(dataframe)
# sometimes the row/column mapping did not work
# rframe.colnames = dataframe.columns
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 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)))
quick = len(dataframe) > 10000
if quick:
# quick writing, only append method works
wb = openpyxl.Workbook( optimized_write = True)
def addWorksheet( wb, dataframe, title ):
ws = wb.create_sheet()
ws.append( [""] + list(col_headers) )
for x,row in enumerate( dataframe.iterrows() ):
ws.append( [path2str(row_headers[x])] + list(row) )
# 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 addWorksheet( wb, dataframe, title ):
ws = wb.create_sheet()
# regex to detect rst hypelinks
regex_link = re.compile( '`(.*) <(.*)>`_')
for column, column_name in enumerate( dataframe.columns ):
c = ws.cell( row=0, column=column)
c.value = column_name
dataseries = dataframe[column_name]
if dataseries.dtype == object:
for row, value in enumerate( dataseries ):
c = ws.cell( row=row+1, column=column)
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+1, column=column)
c.value = value
# patch: maximum title length seems to be 31
ws.title = title[:30]
is_hierarchical = isinstance( dataframe.index, pandas.core.index.MultiIndex )
split = is_hierarchical and len(dataframe.index.levels) > 1
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( [dataframe.index.labels[: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 )[:30]
ws.append( list(path) + [title, len(work)] )
c = ws.cell( row = row+1, column = nlevels )
c.hyperlink = "#%s" % title
addWorksheet( wb, work, title = title )
else:
writeWorksheet( wb, 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
