问题
Please find My Data of w and w1 at the bottom of this page. I have a Predictor (w$test and w1$test) which is the quantity of positive lymph nodes per total lymph node yield, i.e. ranging between 0 and 1.
I have produced two models - each representing two different disease stages. I wish to plot them together but I all I get is this:
The plot is produced with this code:
library(ggplot2)
library(rms)
library(ggsci)
d <- datadist(w)
j <- options(datadist="d")
d1 <- datadist(w1)
j1 <- options(datadist="d1")
model <- cph(Surv(os.neck,mors)~rcs(test),data=w)
model1 <- cph(Surv(os.neck,mors)~rcs(test),data=w1)
ggplot(Predict(model1, fun=exp)) + scale_x_continuous(limits = c(0,0.80))
out <- bind_rows(fortify(Predict(model, fun=exp)), fortify(Predict(model1, fun=exp)), .id = "model")
ggplot(as.data.frame(out), aes(x = test)) +
geom_ribbon(aes(fill = model, ymin = lower, ymax = upper), alpha = .05) +
geom_line(aes(y = yhat, col = model)) +
scale_color_jco(name="", labels = c("A", "B")) +
scale_fill_jco(name="", labels = c("A", "B")) +
geom_segment(aes(x = 0, y = 1, xend = 0.55, yend = 1), lty="dashed", size=0.1, alpha=0.75)
As you can see, the plot is cut around 0.35 on the x-axis. I don't get why and I want the plot to continue as there are several w$test and w1$test values greater than 0.35. Please note that this code is produced from a dput() of 30 samples and not the entire cohort.
When I look at View(out), I realize that there is only 400 entities - 200 from each model and model1. It seem that each entity number 200 equal to the test-value-cut-off of 0.35. Please see here:
And
How can I make the plot complete according to all test-values?
My data w and w1
w1 <- structure(list(sex = c(1L, 1L, 1L, 0L, 1L, 1L, 0L, 0L, 1L, 1L,
0L, 1L, 1L, 0L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 0L,
1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L), mors = c(1L, 0L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L),
os = c(26.01, 138.68, 8.41, 29.63, 10, 19.59, 22.17, 63.52,
21.44, 27.87, 40.81, 64.15, 43.24, 8.14, 17.01, 23.16, 24.38,
25.61, 29.59, 29.9, 44.7, 44.52, 64.65, 93.06, 102.88, 140.79,
157.07, 34.1, 81.15, 133.42, 24.57, 2.35, 3.44, 3.98, 4.8
), os.beh = c(20.9, 138.68, NA, 20.24, 4.7, 13.01, 16.1,
45.17, 15.56, 20.24, NA, 45.47, 42.32, 2.49, 12.26, 19, 17.02,
18.6, NA, 20.83, 31.28, 39.86, 45.34, 67.02, 96.45, NA, NA,
32.99, 77.73, 131.98, 17.38, 0.79, 0.5, 2.23, 2.33), os.neck = c(18.2,
138.68, 5.42, 19.55, 6.6, 13.01, 16.1, 45.17, 14.29, 20.24,
28.85, 45.47, 42.32, 4.99, 11.73, 16.36, 17.02, 18.6, 20.53,
20.83, 31.28, 31.51, 45.31, 67.02, 73.07, 99.98, 112.03,
32.99, 80.46, 131.98, 17.38, 0.79, 2.04, 2.23, 2.3), rfs.neck = c(11.07,
10.32, 4.44, 17.25, 5.39, 5.49, 7.03, 33.61, 12.71, 5.49,
16.92, 14.52, 13.37, 4.14, 9.36, 11.53, 8.8, 9.59, 16.53,
8.34, 8.28, 18.17, 29.6, 10.32, 7.13, 22.51, 43.93, 24.74,
12.85, 28.94, NA, NA, NA, NA, NA), rfs.neck.tsite = c(11.07,
10.32, NA, NA, NA, NA, 7.03, 33.61, NA, NA, NA, NA, NA, 4.14,
9.36, 11.53, 8.8, 9.59, 16.53, 8.34, 8.28, 18.17, 29.6, 10.32,
7.13, 22.51, 43.93, 24.74, 12.85, 28.94, NA, NA, NA, NA,
NA), rfs.neck.nsite = c(11.07, 10.32, 4.44, 17.25, NA, NA,
7.03, 33.61, 12.71, 5.49, 16.92, 14.52, 13.37, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA), rfs.neck.msite = c(11.07, 10.32, 4.44, 17.25,
5.39, 5.49, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA), recidiv.tsite = c(1L, 1L, 0L, 0L, 0L, 0L, 1L, 1L,
0L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), recidiv.nsite = c(1L,
1L, 1L, 1L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L), n.fjernet = c(19L, 7L, 28L, 2L, 15L, 12L,
19L, 17L, 9L, 5L, 6L, 33L, 10L, 27L, 34L, 28L, 14L, NA, 8L,
11L, 14L, 19L, 5L, 38L, 5L, 8L, 10L, 55L, 22L, 8L, 16L, 18L,
6L, 23L, 5L), n.sygdom = c(2L, 0L, 2L, 0L, 9L, 1L, 1L, 1L,
0L, 1L, 0L, 4L, 0L, 4L, 0L, 0L, 0L, NA, 2L, 1L, 0L, 0L, 0L,
0L, 2L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 2L, 2L, 1L), stadie = c(1L,
2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 1L,
2L, 2L, 1L, 1L), test = c(0.105263157894737, 0, 0.0714285714285714,
0, 0.6, 0.0833333333333333, 0.0526315789473684, 0.0588235294117647,
0, 0.2, 0, 0.121212121212121, 0, 0.148148148148148, 0, 0,
0, NA, 0.25, 0.0909090909090909, 0, 0, 0, 0, 0.4, 0, 0, 0,
0, 0, 0, 0, 0.333333333333333, 0.0869565217391304, 0.2)), .Names = c("sex",
"mors", "os", "os.beh", "os.neck", "rfs.neck", "rfs.neck.tsite",
"rfs.neck.nsite", "rfs.neck.msite", "recidiv.tsite", "recidiv.nsite",
"n.fjernet", "n.sygdom", "stadie", "test"), row.names = c(3L,
4L, 5L, 12L, 29L, 40L, 59L, 61L, 69L, 74L, 78L, 82L, 86L, 95L,
101L, 108L, 109L, 113L, 115L, 116L, 120L, 121L, 128L, 130L, 134L,
139L, 141L, 144L, 150L, 153L, 156L, 159L, 164L, 165L, 166L), class = "data.frame")
w <- structure(list(sex = c(1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 1L, 1L,
0L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 0L, 0L, 1L, 1L, 1L, 1L,
0L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 1L), mors = c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
os = c(16.56, 12.03, 12.08, 18.28, 17.28, 20.86, 23.48, 38.27,
58.63, 96.18, 47.84, 25.7, 27.01, 45.38, 50.04, 70.21, 7.69,
13.26, 15.2, 15.79, 15.74, 15.29, 18.59, 17.24, 22.35, 26.6,
31.85, 31.94, 31.62, 33.52, 34.2, 55.92, 55.92, 67.27, 80.17
), os.beh = c(NA, 7.28, NA, 11.17, 4.93, 64.33, 15.77, 26.94,
40.77, 69.09, 31.7, 17.05, 15.16, 32.3, 34.46, 49.81, 4.9,
5.47, 8.73, 9.92, 10.05, 10.77, 12.48, 12.52, 14.82, 18.19,
21.45, 27.05, NA, 27.01, 24.28, 40.11, 51.39, 62.11, 76.28
), os.neck = c(10.97, 8.02, 8.77, 11.66, 12.55, 13.8, 15.77,
26.94, 40.77, 69.06, 46.82, 17.05, 18.76, 32.3, 34.46, 49.81,
4.9, 8.61, 9.92, 9.92, 10.05, 10.51, 12.48, 12.52, 14.82,
15.87, 21.45, 22.14, 22.97, 23.26, 24.28, 40.11, 40.11, 47.08,
52.14), rfs.neck = c(8.21, 6.7, 5.36, 7.72, 3.71, 5.39, 8.61,
18.46, 9.56, 19.29, 12.42, 11.01, 18.14, 26.05, 15.87, 9.46,
3.81, 7.79, 8.34, 8.61, 8.28, 9.79, 6.21, 5.36, 7.49, 9.56,
16.07, 4.63, 13.31, 12.68, 20.67, 21.59, 30.16, 22.21, 0),
rfs.neck.tsite = c(8.21, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, 11.01, 18.14, 26.05, 15.87, 9.46, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA
), rfs.neck.nsite = c(8.21, 6.7, 5.36, 7.72, 3.71, 5.39,
8.61, 18.46, 9.56, 19.29, 12.42, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA), rfs.neck.msite = c(8.21, 6.7, 5.36, 7.72, 3.71,
5.39, 8.61, 18.47, 9.56, 19.29, 12.42, 11.01, 18.14, 26.06,
15.87, 9.46, 3.81, 7.79, 8.35, 8.61, 8.28, 9.79, 6.21, 5.36,
7.49, 9.56, 16.07, 4.63, 13.31, 12.68, 20.67, 21.59, 30.16,
22.21, 0), recidiv.tsite = c(1L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), recidiv.nsite = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L), n.fjernet = c(15L, 7L, 12L, 57L, 6L, 27L,
18L, 11L, 24L, 9L, 25L, 9L, 13L, 19L, 8L, 10L, 33L, 23L,
10L, 3L, 15L, 15L, 3L, 6L, 16L, 9L, 9L, 13L, 10L, 12L, 20L,
30L, 16L, 16L, NA), n.sygdom = c(2L, 1L, 6L, 6L, 0L, 0L,
9L, 0L, 0L, 0L, 0L, 2L, 3L, 0L, 0L, 0L, 2L, 1L, 0L, 2L, 1L,
4L, 1L, 2L, 4L, 3L, 2L, 0L, 0L, 2L, 0L, 0L, 1L, 0L, NA),
stadie = c(4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 4L,
3L, 4L, 4L, 3L, 4L, 3L, 3L, 3L, 4L, 3L, 4L, 4L, 4L, 4L, 4L,
3L, 5L, 3L, 3L, 4L, 4L, 4L, 4L), test = c(0.133333333333333,
0.142857142857143, 0.5, 0.105263157894737, 0, 0, 0.5, 0,
0, 0, 0, 0.222222222222222, 0.230769230769231, 0, 0, 0, 0.0606060606060606,
0.0434782608695652, 0, 0.666666666666667, 0.0666666666666667,
0.266666666666667, 0.333333333333333, 0.333333333333333,
0.25, 0.333333333333333, 0.222222222222222, 0, 0, 0.166666666666667,
0, 0, 0.0625, 0, NA)), .Names = c("sex", "mors", "os", "os.beh",
"os.neck", "rfs.neck", "rfs.neck.tsite", "rfs.neck.nsite", "rfs.neck.msite",
"recidiv.tsite", "recidiv.nsite", "n.fjernet", "n.sygdom", "stadie",
"test"), row.names = c(2L, 6L, 7L, 8L, 9L, 10L, 11L, 14L, 15L,
17L, 18L, 22L, 23L, 24L, 25L, 26L, 28L, 31L, 34L, 35L, 36L, 37L,
38L, 39L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 51L
), class = "data.frame")
回答1:
Markus is right, and the way to overcome that is to define your own range values:
Predict(model1,test=seq(0,0.6,by=0.1))
test yhat lower upper
1 0.0 -0.4295911 -0.754044179 -0.1051379
2 0.1 0.6336235 0.027948982 1.2392981
3 0.2 0.7307858 0.175765821 1.2858057
4 0.3 0.6062680 -0.001284515 1.2138206
5 0.4 0.4817503 -0.453891190 1.4173919
6 0.5 0.3572326 -0.994418951 1.7088842
7 0.6 0.2327149 -1.562760195 2.0281900
So:
out <- bind_rows(fortify(Predict(model,test=seq(0,0.6,by=0.01), fun=exp)), fortify(Predict(model1,test=seq(0,0.6,by=0.01), fun=exp)), .id = "model")
ggplot(as.data.frame(out), aes(x = test)) +
geom_ribbon(aes(fill = model, ymin = lower, ymax = upper), alpha = .05) +
geom_line(aes(y = yhat, col = model)) +
scale_color_jco(name="", labels = c("A", "B")) +
scale_fill_jco(name="", labels = c("A", "B")) +
geom_segment(aes(x = 0, y = 1, xend = 0.55, yend = 1), lty="dashed", size=0.1, alpha=0.75)
gives
来源：https://stackoverflow.com/questions/54416953/why-does-ggplot-predict-not-plot-in-r-rms-package