[R] grey colored lines and overwriting labels i qqplot2
Brian Diggs
diggsb at ohsu.edu
Fri Jul 29 00:44:47 CEST 2011
On 7/25/2011 8:27 PM, Sigrid wrote:
> Thank you Brian.
>
> Sorry for being such a noob. I am not a programmer and just learning R by
> myself. This is was I typed, but ended up with a couple error messages.
>
>> df<-structure(list(year = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
> + 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
> + 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
> + 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
> + 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
> + 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L,
> + 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> + 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
> + 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
> + 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
> + 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), treatment =
> structure(c(1L,
> + 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L,
> + 6L, 7L, 7L, 7L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L,
> + 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 1L, 1L, 1L, 2L, 2L, 2L, 3L,
> + 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 1L, 1L,
> + 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L,
> + 7L, 7L, 7L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L,
> + 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L,
> + 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 1L, 1L, 2L,
> + 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L,
> + 7L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L,
> + 6L, 6L, 6L, 7L, 7L, 7L), .Label = c("A", "B", "C", "D", "E",
> + "F", "G"), class = "factor"), total = c(135L, 118L, 121L, 64L,
> + 53L, 49L, 178L, 123L, 128L, 127L, 62L, 129L, 126L, 99L, 183L,
> + 45L, 57L, 45L, 72L, 30L, 71L, 123L, 89L, 102L, 60L, 44L, 59L,
> + 124L, 145L, 126L, 103L, 67L, 97L, 66L, 76L, 108L, 36L, 48L, 41L,
> + 69L, 47L, 57L, 167L, 136L, 176L, 85L, 36L, 82L, 222L, 149L, 171L,
> + 145L, 122L, 192L, 136L, 164L, 154L, 46L, 57L, 57L, 70L, 55L,
> + 102L, 111L, 152L, 204L, 41L, 46L, 103L, 156L, 148L, 155L, 103L,
> + 124L, 176L, 111L, 142L, 187L, 43L, 52L, 75L, 64L, 91L, 78L, 196L,
> + 314L, 265L, 44L, 39L, 98L, 197L, 273L, 274L, 89L, 91L, 74L, 91L,
> + 112L, 98L, 140L, 90L, 121L, 120L, 161L, 83L, 230L, 266L, 282L,
> + 35L, 53L, 57L, 315L, 332L, 202L, 90L, 79L, 89L, 67L, 116L, 109L,
> + 44L, 68L, 75L, 29L, 52L, 52L, 253L, 203L, 87L, 105L, 234L, 152L,
> + 247L, 243L, 144L, 167L, 165L, 95L, 300L, 128L, 125L, 84L, 183L,
> + 88L, 153L, 185L, 175L, 226L, 216L, 118L, 118L, 94L, 224L, 259L,
> + 176L, 175L, 147L, 197L, 141L, 176L, 187L, 87L, 92L, 148L, 86L,
> + 139L, 122L), country = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L,
> + 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
> + 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
> + 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
> + 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
> + 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
> + 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
> + 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
> + 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
> + 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L,
> + 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L
> + ), .Label = c("high", "low"), class = "factor")), .Names = c("year",
> + "treatment", "total", "country"), class = "data.frame", row.names = c(NA,
> + -167L))
OK, here you have created a data.frame named "df". It has four columns:
year, treatment, total, and country. year is 1, 2, 3, or 4. treatment is
a factor with values "A", "B", "C", "D", "E", "F", or "G". total is a
number (integer). country is a factor with values "high" or "low".
>>> dput(lines)
> Error: unexpected '>' in ">"
The ">" at the beginning of this line represented the prompt; it was not
supposed to be typed in.
>> structure(list(`Line #` = 1:6, country = structure(c(2L, 2L,
> + 2L, 1L, 1L, 1L), .Label = c("High", "Low"), class = "factor"),
> + treatment = structure(c(1L, 2L, 3L, 1L, 2L, 3L), .Label = c("A",
> + "B", "C"), class = "factor"), Intercept = c(81.47, 31.809,
> + 69.892, 67.024, 17.357, 105.107), Slope = c(47.267, 20.234,
> + 33.717, 47.267, 20.234, 33.717)), .Names = c("Line #", "country",
> + "treatment", "Intercept", "Slope"), class = "data.frame", row.names =
> c(NA,
> + -6L))
And this was the output of the dput command. If you want to recreate
lines, you need:
lines <-
structure(list(`Line #` = 1:6, country = structure(c(2L, 2L,
2L, 1L, 1L, 1L), .Label = c("High", "Low"), class = "factor"),
treatment = structure(c(1L, 2L, 3L, 1L, 2L, 3L), .Label = c("A",
"B", "C"), class = "factor"), Intercept = c(81.47, 31.809,
69.892, 67.024, 17.357, 105.107), Slope = c(47.267, 20.234,
33.717, 47.267, 20.234, 33.717)), .Names = c("Line #", "country",
"treatment", "Intercept", "Slope"), class = "data.frame", row.names = c(NA,
-6L))
This creates a data frame named "lines". it has 5 columns: "Line #",
"country", "treatment", "Intercept", and "Slope". You indicated that
this was just a few of the lines you wanted. I didn't know what the
other slopes and intercepts were, so I couldn't create a working example
using those. However they are determined, if you get them into a
data.frame that has this same structure (just more rows), then the
example will work.
> Line # country treatment Intercept Slope
> 1 1 Low A 81.470 47.267
> 2 2 Low B 31.809 20.234
> 3 3 Low C 69.892 33.717
> 4 4 High A 67.024 47.267
> 5 5 High B 17.357 20.234
> 6 6 High C 105.107 33.717
>> p=ggplot(data = test, aes(x = year, y = total, colour = treatment)) +
> + geom_point(aes(shape = treatment)) +
> + facet_wrap(~country) +
> + scale_colour_grey(breaks=c('A','B','C','D','E','F','G'),
> + labels=c('label A','label B','label C','label D',
> + 'label E','label F','label G')) +
> + scale_shape_manual(breaks=c('A','B','C','D','E','F','G'),
> + labels=c('label A','label B','label C','label D',
> + 'label E','label F','label G'),
> + values = c(0, 1, 2, 3, 4, 5, 6)) +
> + scale_y_continuous("number of votes") +
> + scale_x_continuous("Years", breaks=1:4) +
> + theme_bw()+
> + geom_abline(aes(intercept = Intercept, slope = Slope, colour =
> + treatment), data = lines)
> Error in ggplot(data = test, aes(x = year, y = total, colour = treatment)) :
> object 'test' not found
In your original examples, the name of the data frame with your data was
"test"; now it appears to be "df". Since you changed the name of the
data frame, you need to change it in the ggplot call. There you have
"data = test", but there is no object called "test" (that is what the
error says). It should be "data = df".
> Thank you for all help.
>
> --
> View this message in context: http://r.789695.n4.nabble.com/grey-colored-lines-and-overwriting-labels-i-qqplot2-tp3657119p3694796.html
> Sent from the R help mailing list archive at Nabble.com.
>
--
Brian S. Diggs, PhD
Senior Research Associate, Department of Surgery
Oregon Health & Science University
More information about the R-help
mailing list