def render(self, work, path ):
self.startPlot()
nplotted = 0
xlabels, ylabels = [], []
if len(work) < 2:
raise ValueError( "requiring two coordinates, only got %s" % str(work.keys()))
xlabel, ylabel = work.keys()[:2]
xvals, yvals = Stats.filterNone( work.values()[:2])
if len(xvals) == 0 or len(yvals) == 0:
raise ValueError("no data" )
# apply log transformation on data not on plot
if self.logscale:
if "x" in self.logscale:
xvals = R.log10(xvals)
if "y" in self.logscale:
yvals = R.log10(yvals)
R.smoothScatter( xvals, yvals,
xlab=xlabel, ylab=ylabel,
nbin = self.nbins )
return self.endPlot( work, path )
def render(self, dataframe, path ):
if len(dataframe.columns) < 2:
raise ValueError( "requiring two coordinates, only got %s" % str(dataframe.columns))
plts, legend = [], []
blocks = ResultBlocks()
for xcolumn, ycolumn in itertools.combinations( dataframe.columns, 2 ):
# remove missing data points
xvalues, yvalues = Stats.filterMissing( (dataframe[xcolumn], dataframe[ycolumn]) )
# remove columns with all NaN
if len(xvalues) == 0 or len(yvalues) == 0:
continue
# apply log transformation on data not on plot
if self.logscale:
if "x" in self.logscale:
xvalues = R.log10(xvalues)
if "y" in self.logscale:
yvalues = R.log10(yvalues)
self.startPlot()
# wrap, as pandas series can not
# passed through rpy2.
R.smoothScatter( numpy.array( xvalues, dtype=numpy.float),
numpy.array( yvalues, dtype=numpy.float),
xlab=xcolumn,
ylab=ycolumn,
nbin = self.nbins )
blocks.extend( self.endPlot( dataframe, path ) )
return blocks
def apply( self, xvals, yvals ):
xx = numpy.array( [ x for x in xvals if x != None ] )
yy = numpy.array( [ y for y in yvals if y != None ] )
return Stats.doMannWhitneyUTest( xx, yy )
def apply( self, xvals, yvals ):
return Stats.doCorrelationTest( xvals, yvals, method = self.method )