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 __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 render( self, work, path ):
# initiate output structure
results = ResultBlocks( title = path )
# iterate over all items at leaf
for key in work:
t = type(work[key])
try:
l = "%i" % len(work[key])
except AttributeError:
l = "na"
except TypeError:
l = "na"
# add a result block.
data = str(work[key])
if len(data) > 30: data=data[:30] + "..."
results.append( ResultBlock( "path= %s, type= %s, len= %s, data= %s" % \
( path2str(path + (key,)),
t, l, data),
title = "") )
return results
def render( self, work, path ):
"""render the data.
"""
results = ResultBlocks( title = path )
matrix, rows, columns = self.buildMatrix( work )
title = path2str(path)
if len(rows) == 0:
return ResultBlocks( ResultBlock( "", title = title) )
# do not output large matrices as rst files
if not self.force and (len(rows) > self.max_rows or len(columns) > self.max_cols):
return self.asFile( [ [ self.toString(x) for x in r ] for r in matrix ],
rows,
columns,
title )
lines = []
lines.append( ".. csv-table:: %s" % title )
lines.append( ' :header: "track","%s" ' % '","'.join( columns ) )
lines.append( '')
for x in range(len(rows)):
lines.append( ' "%s","%s"' % (rows[x], '","'.join( [ self.toString(x) for x in matrix[x,:] ] ) ) )
lines.append( "")
if not path: subtitle = ""
else: subtitle = path2str(path)
results.append( ResultBlock( "\n".join(lines), title = subtitle ) )
return results
def __call__(self, data, path ):
'''iterate over leaves/branches in data structure.
This method will call the :meth:`render` method for
each leaf/branch at level :attr:`nlevels`.
'''
if self.nlevels == None: raise NotImplementedError("incomplete implementation of %s" % str(self))
result = ResultBlocks( title = path2str(path) )
labels = DataTree.getPaths( data )
if len(labels) < self.nlevels:
self.warn( "at %s: expected at least %i levels - got %i: %s" %\
(str(path), self.nlevels, len(labels), str(labels)) )
result.append( EmptyResultBlock( title = path2str(path) ) )
return result
paths = list(itertools.product( *labels[:-self.nlevels] ))
for p in paths:
work = DataTree.getLeaf( data, p )
if not work: continue
try:
result.extend( self.render( work, path + p ) )
except:
self.warn("exeception raised in rendering for path: %s" % str(path+p))
raise
return result
def render( self, data, path ):
# initiate output structure
results = ResultBlocks( title = path )
try:
results.append( ResultBlock(json.dumps(data, indent=4), title=''))
except TypeError:
results.append( ResultBlock(str(data), title=''))
return results
def __call__(self, track, slice = None ):
blocks = ResultBlocks()
block = '''
.. figure:: %(image)s
:height: 300
'''
for image in glob.glob( os.path.join( IMAGEDIR, "*.png" )):
blocks.append( ResultBlock( text = block % locals(),
title = "image" ) )
return odict( (("rst", "\n".join( Utils.layoutBlocks( blocks, layout = "columns-2"))),))
def render( self, work, path ):
# initiate output structure
results = ResultBlocks( title = path2str(path) )
labels = DataTree.getPaths( work )
# iterate over all items at leaf
for path, branch in DataTree.getNodes( work, len(labels) - 2 ):
for key in Utils.TrackerKeywords:
if key in branch:
# add a result block
results.append( ResultBlock( branch[key],
title = path2str(path) ) )
return results
def render(self):
"""supply the :class:`Renderer.Renderer` with the data to render.
The data supplied will depend on the ``groupby`` option.
return resultblocks
"""
self.debug("%s: rendering data started for %i items" % (self, len(self.data)))
results = ResultBlocks(title="main")
# get number of levels required by renderer
try:
renderer_nlevels = self.renderer.nlevels
except AttributeError:
renderer_nlevels = 0
data_paths = DataTree.getPaths(self.data)
nlevels = len(data_paths)
group_level = self.group_level
self.debug(
"%s: rendering data started. levels=%i, required levels>=%i, group_level=%i, data_paths=%s"
% (self, nlevels, renderer_nlevels, group_level, str(data_paths)[:100])
)
if nlevels < renderer_nlevels:
# add some dummy levels if levels is not enough
d = self.data
for x in range(renderer_nlevels - nlevels):
d = odict((("all", d),))
results.append(self.renderer(d, path=("all",)))
elif group_level < 0 or renderer_nlevels < 0:
# no grouping
results.append(self.renderer(self.data, path=()))
else:
# group at level group_level
paths = list(itertools.product(*data_paths[: group_level + 1]))
for path in paths:
work = DataTree.getLeaf(self.data, path)
if not work:
continue
try:
results.append(self.renderer(work, path=path))
except:
results.append(ResultBlocks(Utils.buildException("rendering")))
if len(results) == 0:
self.warn("tracker returned no data.")
raise ValueError("tracker returned no data.")
self.debug("%s: rendering data finished with %i blocks" % (self.tracker, len(results)))
return results
def render( self, work, path ):
# initiate output structure
results = ResultBlocks( title = path )
# iterate over all items at leaf
#for key in work:
if "text" in work:
# add a result block
results.append( ResultBlock( work["text"],
title = "" ) )
elif "rst" in work:
# add a result block
results.append( ResultBlock( work["rst"],
title = "" ) )
return results
def render( self, work, path ):
"""render the data.
"""
results = ResultBlocks( title = path )
matrix, rows, columns = self.buildMatrix( work )
title = path2str(path)
if len(rows) == 0:
return ResultBlocks( ResultBlock( "", title = title) )
# do not output large matrices as rst files
# separate and force need to be mixed in.
if self.separate or (not self.force and (len(rows) > self.max_rows or len(columns) > self.max_cols)):
return ResultBlocks( self.asFile( pandas.DataFrame( matrix,
index = rows,
columns = columns),
rows,
columns,
title ),
title = path )
lines = []
lines.append( ".. csv-table:: %s" % title )
lines.append( " :class: sortable" )
lines.append( ' :header: "track","%s" ' % '","'.join( columns ) )
lines.append( '')
for x in range(len(rows)):
lines.append( ' "%s","%s"' % (rows[x], '","'.join( [ self.toString(x) for x in matrix[x,:] ] ) ) )
lines.append( "")
if path is None: subtitle = ""
else: subtitle = path2str(path)
results.append( ResultBlock( "\n".join(lines), title = subtitle ) )
return results
def __call__(self, dataframe, path):
# modify table (adding/removing columns) according to user options
# matrix, row_headers, col_headers = self.modifyTable( matrix, row_headers, col_headers )
dataframe = self.modifyTable( dataframe )
title = path2str(path)
results = ResultBlocks()
row_headers = dataframe.index
col_headers = dataframe.columns
# do not output large matrices as rst files
if self.separate or (not self.force and
(len(row_headers) > self.max_rows or
len(col_headers) > self.max_cols)):
if self.large == "xls":
results.append( self.asSpreadSheet( dataframe, row_headers, col_headers, title ) )
else:
results.append( self.asFile( dataframe, row_headers, col_headers, title ) )
if self.preview:
row_headers = row_headers[:self.max_rows]
col_headers = col_headers[:self.max_cols]
matrix = [ x[:self.max_cols] for x in matrix[:self.max_rows] ]
else:
return results
out = StringIO.StringIO()
dataframe.to_csv( out )
lines = []
lines.append( ".. csv-table:: %s" % title )
lines.append( " :class: sortable" )
if self.add_rowindex:
lines.append( ' :header: "row", "", "%s" ' % '","'.join( map(str, col_headers) ) )
lines.append( '' )
x = 0
for header, line in zip( row_headers, matrix ):
x += 1
lines.append( ' %i,"%s","%s"' % (x, str(header), '","'.join( map(str, line) ) ) )
else:
l = out.getvalue().split("\n")
lines.append( ' :header: %s' % l[0] )
lines.append( '' )
lines.extend( [' %s' % x for x in l[1:] ] )
lines.append( "")
results.append( ResultBlock( "\n".join(lines), title = title) )
return results
def layoutBlocks( blocks, layout = "column"):
"""layout blocks of rst text.
layout can be one of "column", "row", or "grid".
The layout uses an rst table to arrange elements.
"""
lines = []
if len(blocks) == 0: return lines
# flatten blocks
x = ResultBlocks()
for b in blocks:
if b.title: b.updateTitle( b.title, "prefix" )
try:
x.extend( b )
except TypeError:
x.append( b )
blocks = x
if layout == "column":
for block in blocks:
if block.title:
lines.extend( block.title.split("\n") )
lines.append( "" )
else:
logging.warn( "report_directive.layoutBlocks: missing title" )
lines.extend(block.text.split("\n"))
lines.extend( [ "", ] )
return lines
elif layout in ("row", "grid"):
if layout == "row": ncols = len(blocks)
elif layout == "grid": ncols = int(math.ceil(math.sqrt( len(blocks) )))
elif layout.startswith("column"):
ncols = min( len(blocks), int(layout.split("-")[1]))
# TODO: think about appropriate fix for empty data
if ncols == 0:
ncols = 1
return lines
else:
raise ValueError( "unknown layout %s " % layout )
# compute column widths
widths = [ x.getWidth() for x in blocks ]
text_heights = [ x.getTextHeight() for x in blocks ]
title_heights = [ x.getTitleHeight() for x in blocks ]
columnwidths = []
for x in range(ncols):
columnwidths.append( max( [widths[y] for y in range( x, len(blocks), ncols ) ] ) )
separator = "+%s+" % "+".join( ["-" * x for x in columnwidths ] )
## add empty blocks
if len(blocks) % ncols:
blocks.extend( [ ResultBlock( "", "" )] * (ncols - len(blocks) % ncols) )
for nblock in range(0, len(blocks), ncols ):
## add text
lines.append( separator )
max_height = max( text_heights[nblock:nblock+ncols] )
new_blocks = ResultBlocks()
for xx in range(nblock, min(nblock+ncols,len(blocks))):
txt, col = blocks[xx].text.split("\n"), xx % ncols
max_width = columnwidths[col]
# add missig lines
txt.extend( [""] * (max_height - len(txt)) )
# extend lines
txt = [ x + " " * (max_width - len(x)) for x in txt ]
new_blocks.append( txt )
for l in zip( *new_blocks ):
lines.append( "|%s|" % "|".join( l ) )
## add subtitles
max_height = max( title_heights[nblock:nblock+ncols] )
if max_height > 0:
new_blocks = ResultBlocks()
lines.append( separator )
for xx in range(nblock, min(nblock+ncols,len(blocks))):
txt, col = blocks[xx].title.split("\n"), xx % ncols
max_width = columnwidths[col]
# add missig lines
txt.extend( [""] * (max_height - len(txt) ) )
# extend lines
txt = [ x + " " * (max_width - len(x)) for x in txt ]
new_blocks.append( txt )
for l in zip( *new_blocks ):
lines.append( "|%s|" % "|".join( l ) )
lines.append( separator )
lines.append( "" )
return lines
def __call__(self, *args, **kwargs ):
#self.debug( "%s: heap at start\n%s" % (self, str(HP.heap()) ))
try: self.parseArguments( *args, **kwargs )
except:
self.error( "%s: exception in parsing" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "parsing" ) ))
# collect no data if tracker is the empty tracker
# and go straight to rendering
try:
if self.tracker.getTracks() == ["empty"]:
# is instance does not work because of module mapping
# type(Tracker.Empty) == SphinxReport.Tracker.Empty
# type(self.tracker) == Tracker.Empty
# if isinstance( self.tracker, Tracker.Empty):
result =self.renderer()
return ResultBlocks( result )
except AttributeError:
# for function trackers
pass
self.debug( "profile: started: tracker: %s" % (self.tracker))
# collecting data
try: self.collect()
except:
self.error( "%s: exception in collection" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "collection" ) ))
finally:
self.debug( "profile: finished: tracker: %s" % (self.tracker))
if len(self.data) == 0:
self.info( "%s: no data - processing complete" % self.tracker )
return None
data_paths = DataTree.getPaths( self.data )
self.debug( "%s: after collection: %i data_paths: %s" % (self,len(data_paths), str(data_paths)))
# self.debug( "%s: heap after collection\n%s" % (self, str(HP.heap()) ))
# transform data
try: self.transform()
except:
self.error( "%s: exception in transformation" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "transformation" ) ))
data_paths = DataTree.getPaths( self.data )
self.debug( "%s: after transformation: %i data_paths: %s" % (self,len(data_paths), str(data_paths)))
# special Renderers - do not proceed
# Special renderers
if isinstance( self.renderer, Renderer.User):
results = ResultBlocks( title="main" )
results.append( self.renderer( self.data, ('') ) )
return results
elif isinstance( self.renderer, Renderer.Debug):
results = ResultBlocks( title="main" )
results.append( self.renderer( self.data, ('') ) )
return results
# self.debug( "%s: heap after transformation\n%s" % (self, str(HP.heap()) ))
# restrict
try: self.restrict()
except:
self.error( "%s: exception in restrict" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "restrict" ) ))
data_paths = DataTree.getPaths( self.data )
self.debug( "%s: after restrict: %i data_paths: %s" % (self,len(data_paths), str(data_paths)))
# exclude
try: self.exclude()
except:
self.error( "%s: exception in exclude" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "exclude" ) ))
data_paths = DataTree.getPaths( self.data )
self.debug( "%s: after exclude: %i data_paths: %s" % (self,len(data_paths), str(data_paths)))
# remove superfluous levels
try: self.prune()
except:
self.error( "%s: exception in pruning" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "pruning" ) ))
data_paths = DataTree.getPaths( self.data )
self.debug( "%s: after pruning: %i data_paths: %s" % (self,len(data_paths), str(data_paths)))
# remove group plots
try: self.group()
except:
self.error( "%s: exception in grouping" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "grouping" ) ))
data_paths = DataTree.getPaths( self.data )
self.debug( "%s: after grouping: %i data_paths: %s" % (self,len(data_paths), str(data_paths)))
self.debug( "profile: started: renderer: %s" % (self.renderer))
try: result = self.render()
except:
self.error( "%s: exception in rendering" % self )
return ResultBlocks(ResultBlocks( Utils.buildException( "rendering" ) ))
finally:
self.debug( "profile: finished: renderer: %s" % (self.renderer))
#self.debug( "%s: heap at end\n%s" % (self, str(HP.heap()) ))
return result
def render( self ):
'''supply the :class:`Renderer.Renderer` with the data to render.
The data supplied will depend on the ``groupby`` option.
returns a ResultBlocks data structure.
'''
self.debug( "%s: rendering data started for %i items" % (self,
len(self.data)))
# get number of levels required by renderer
try:
renderer_nlevels = self.renderer.nlevels
except AttributeError:
# set to -1 to avoid any grouping
# important for user renderers that are functions
# and have no level attribute.
renderer_nlevels = -1
# initiate output structure
results = ResultBlocks( title = "")
# convert to data series
# The data is melted, i.e,
# BMW price 10000
# BMW speed 100
# Golf price 5000
# Golf speed 50
dataframe = DataTree.asDataFrame( self.data )
# dataframe.write_csv( "test.csv" )
if dataframe is None:
self.warn( "%s: no data after conversion" % self )
raise ValueError( "no data for renderer" )
# special patch: set column names to pruned levels
# if there are no column names
if len(dataframe.columns) == len(self.pruned):
if list(dataframe.columns) == list(range( len(dataframe.columns))):
dataframe.columns = [x[1] for x in self.pruned]
index = dataframe.index
def getIndexLevels( index ):
try:
# hierarchical index
nlevels = len(index.levels)
except AttributeError:
nlevels = 1
index = [ (x,) for x in index]
#raise ValueError('data frame without MultiIndex' )
return nlevels
nlevels = getIndexLevels( index )
self.debug( "%s: rendering data started. levels=%i, required levels>=%i, group_level=%s" %\
(self, nlevels,
renderer_nlevels,
str(self.group_level) ) )
if renderer_nlevels < 0 and self.group_level <= 0:
# no grouping for renderers that will accept
# a dataframe with any level of indices and no explicit
# grouping has been asked for.
results.append( self.renderer( dataframe, path = () ) )
else:
# user specified group level by default
group_level = self.group_level
# set group level to maximum allowed by renderer
if renderer_nlevels >= 0:
group_level = max(nlevels - renderer_nlevels, group_level)
# add additional level if necessary
if nlevels < group_level:
prefix = tuple(["level%i" % x for x in range( group_level - nlevels)])
dataframe.index = pandas.MultiIndex.from_tuples( [ prefix + x for x in dataframe.index ] )
# used to be: group_level + 1
# hierarchical index
# numpy.unique converts everything to a string
# which is not consistent with selecting later
paths = map( tuple, DataTree.unique( [ x[:group_level] for x in dataframe.index.unique() ] ))
pathlength = len(paths[0]) - 1
is_hierarchical = isinstance( dataframe.index, pandas.core.index.MultiIndex )
if is_hierarchical:
# Note: can only sort hierarchical indices
dataframe = dataframe.sortlevel()
if dataframe.index.lexsort_depth < pathlength:
raise ValueError('could not sort data frame: sort depth=%i < pathlength=%i, dataframe=%s' \
% (dataframe.index.lexsort_depth,
pathlength,
dataframe))
for path in paths:
if path:
if len(path) == nlevels:
# extract with loc in order to obtain dataframe
work = dataframe.loc[[path]]
else:
# select data frame as cross-section
work = dataframe.xs(path, axis=0 )
else:
# empty tuple - use full data set
work = dataframe
# remove columns and rows in work that are all Na
work = work.dropna( axis=1, how='all').dropna( axis=0, how='all')
if is_hierarchical and renderer_nlevels >= 0:
work_levels = getIndexLevels( work.index )
# reduce levels of indices required to that required
# for Renderer. This occurs if groupby=none.
if work_levels > renderer_nlevels:
sep = work_levels - (renderer_nlevels - 1)
tuples = [ ( DataTree.path2str( x[:sep] ), ) + x[sep:] \
for x in work.index ]
work.index = pandas.MultiIndex.from_tuples( tuples )
try:
results.append( self.renderer( work,
path = path ))
except:
self.error( "%s: exception in rendering" % self )
results.append( ResultBlocks( Utils.buildException( "rendering" ) ) )
if len(results) == 0:
self.warn("renderer returned no data.")
raise ValueError( "renderer returned no data." )
self.debug( "%s: rendering data finished with %i blocks" % (self.tracker, len(results)))
return results
