- load the summarySE function
- and cut the year variable to create reasonable categories
library(ggplot2)
data(movies)
source("helpers.r")
movies$years <- cut(movies$year,breaks=15)
table(movies$years)
(1893,1900] (1900,1908] (1908,1915] (1915,1923] (1923,1930] (1930,1938]
65 162 276 327 935 3093
(1938,1945] (1945,1953] (1953,1960] (1960,1968] (1968,1975] (1975,1983]
3725 3357 4116 3702 5023 4554
(1983,1990] (1990,1998] (1998,2005]
6775 8257 14421
moviesSE <- summarySE(movies,measurevar="budget",groupvars="years",na.rm=T)
- a warning message because the one class without non-missing values in budget
Warnmeldung:
In qt(p, df, lower.tail, log.p) : NaNs wurden erzeugt
- a look at the new created data frame containing the means, se, sd and ci of the budget variable according to the years classes
head(moviesSE)
years N budget sd se ci
1 (1893,1900] 0 NaN NA NA NA
2 (1900,1908] 2 1125.00 1590.99 1125.00 14294.48
3 (1908,1915] 11 44023.73 63415.40 19120.46 42603.05
4 (1915,1923] 25 314215.76 298129.12 59625.82 123061.65
5 (1923,1930] 76 703895.24 761287.07 87325.62 173961.55
6 (1930,1938] 205 588688.42 553872.30 38684.12 76271.96
- build the plot using this new data frame
p <- ggplot(moviesSE,aes(x=years,y=budget,colour=years))
p +
geom_bar() + ## add bars
geom_errorbar(aes(ymin=budget-se,ymax=budget+se),width=0.5) + ## add errorbars
opts(axis.text.x = theme_text(angle=315,hjust=0,vjust=1)) ## customize tick labels
0 comments:
Post a Comment