ggplot2 - geom_ribbon bug?

This code throws an error and I can't figure out why...

library( plyr )
library( ggplot2 )
library( grid )
library( proto )

# the master dataframe
myDF = structure(list(Agg52WkPrceRange = c(2L, 2L, 2L, 2L, 2L, 2L, 3L, 
5L, 3L, 5L, 3L, 5L, 3L, 2L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 2L, 2L, 
3L, 3L, 3L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 4L, 3L, 4L, 3L, 4L, 4L, 4L, 4L), OfResidualPntReturn52CWk = c(0.201477324, 
0.22350293, 0.248388728, 0.173871456, 0.201090654, 0.170666183, 
0.18681883, 0.178840521, 0.159744891, 0.129811042, 0.13209741, 
0.114989407, 0.128347625, 0.100945992, 0.057017002, 0.081123718, 
0.018900252, 0.021784814, 0.081931816, 0.059067844, 0.095879746, 
0.038977508, 0.078895248, 0.051344317, 0.077515295, 0.011776214, 
0.099216033, 0.054714439, 0.022879951, -0.079558277, -0.050889584, 
-0.006934821, -0.003407085, 0.032545474, -0.003387139, 0.030418511, 
0.053942523, 0.051398537, 0.073482355, 0.087963039, 0.079555591, 
-0.040490418, -0.130754663, -0.125826649, -0.141766316, -0.150708718, 
-0.171906882, -0.174623614, -0.212945405, -0.174480554), IndependentVariableBinned = structure(c(1L, 
1L, 1L, 1L, 1L, 2L, 3L, 10L, 3L, 10开发者_运维知识库L, 4L, 10L, 4L, 2L, 4L, 4L, 
4L, 5L, 2L, 2L, 2L, 3L, 3L, 5L, 5L, 5L, 5L, 6L, 3L, 6L, 6L, 6L, 
6L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 9L, 8L, 9L, 9L, 9L, 9L, 
10L, 10L), .Label = c("1", "2", "3", "4", "5", "6", "7", "8", 
"9", "10"), class = "factor")), .Names = c("Agg52WkPrceRange", 
"OfResidualPntReturn52CWk", "IndependentVariableBinned"), row.names = 28653:28702, class = "data.frame")

# secondary data frame
meansByIndependentVariableBin = ddply( myDF , .( IndependentVariableBinned ) , function( df ) mean( df[[ "OfResidualPntReturn52CWk" ]] ) )

# construct the plot
thePlot = ggplot( myDF , aes_string( x = "IndependentVariableBinned" , y = "OfResidualPntReturn52CWk" ) )
thePlot = thePlot + geom_point( data = meansByIndependentVariableBin , aes( x = IndependentVariableBinned , y = V1 ) )
thePlot = thePlot + geom_line( data = meansByIndependentVariableBin , aes( x = IndependentVariableBinned , y = V1 , group = 1 )  )
thePlot = thePlot + geom_ribbon( data = meansByIndependentVariableBin , aes( group = 1 ,  x = IndependentVariableBinned , ymin = V1 - 1 , ymax = V1 + 1 ) )

# print - error!
print( thePlot )

I've tried with/without group=1. The error is:

Error in eval(expr, envir, enclos) : 
  object 'OfRelStrength52CWk' not found

but not sure how that is relevant?? I must be missing something obvious. Take away the last geom (ribbon) and it plots just fine!

There is no bug in geom_ribbon. Your error is because you are defining y = OfResidualPntReturn52CWk in your ggplot call as a result of which geom_ribbon is looking for it. Since you are passing a different data frame to geom_ribbon, there is confusion and hence an error. From your plotting call, although you are using y = OfResidualPntReturn52CWk in your ggplot call, there is no layer where you are calling it, and hence it is immaterial to the plot.

Here is how to do it correctly (if I am understanding what you intend to do in this plot)

MIVB    = meansByIndependentVariableBin
thePlot = ggplot(myDF , aes(x = IndependentVariableBinned)) +
  geom_point(aes(y = OfResidualPntReturn52CWk)) +
  geom_point(data = MIVB, aes(y = V1), colour = 'red') + 
  geom_line(data = MIVB , aes(y = V1, group = 1), colour = 'red') +
  geom_ribbon(data = MIVB, aes(group = 1, ymin = V1 - 1 , ymax = V1 + 1), 
     alpha = 0.2)

Here is the output it produces

Here is another way to do it, without computing the means in advance. Also I have used mean +- standard errors in the ribbon as I find the choice of +- 1 to be arbitrary

myDF$IndependentVariableBinned = as.numeric(myDF$IndependentVariableBinned)
thePlot = ggplot(myDF , aes(x = IndependentVariableBinned, y = 
   OfResidualPntReturn52CWk)) +
   geom_point() +
   geom_point(stat = 'summary', fun.y = 'mean', colour = 'red') + 
   geom_line(stat = 'summary', fun.y = 'mean', colour = 'red') +
   geom_ribbon(stat = 'summary', fun.data = 'mean_se', alpha = 0.2)

This produces

@Ramnath is spot on. Your initial call to ggplot is not needed as all of the layers you are plotting come from the summarized data.frame made by ddply(). You can also simplify your call to ddply() by using the summarize function:

meansByIndependentVariableBin2 = ddply( myDF , .( IndependentVariableBinned ) 
, summarize, means = mean(OfResidualPntReturn52CWk) )

I would then plot your graph as such:

ggplot(meansByIndependentVariableBin2, aes(x = as.numeric(IndependentVariableBinned), y = means)) +
  geom_ribbon(aes(ymin = (means - 1), ymax = (means + 1)), alpha = .4) + 
  geom_point() + 
  geom_line()

Is that what you had in mind? I added an alpha to the ribbon layer so we can see the lines and points clearly.