If I use dput() to output the structure of a raster object created using the raster package, then assigning that structure back into a new object throws an error
Error in datanotation %in% c("LOG1S", "INT1S", "INT2S", "INT4S", "INT1U", :
error in evaluating the argument 'x' in selecting a method for function '%in%': Error: object 'datanotation' not found
Example output from dput to test this on:
rast <- new("RasterLayer", file = new(".RasterFile"
, name = ""
, datanotation = "FLT4S"
, byteorder = "little"
, nodatavalue = -Inf
, NAchanged = FALSE
, nbands = 1L
, bandorder = "BIL"
, offset = 0L
, toptobottom = TRUE
, blockrows = 0L
, blockcols = 0L
, driver = ""
, open = FALSE
)
, data = new(".SingleLayerData"
, values = c(NA, NA, NA, NA, 27.7696047300953, 25.8297302967319, 21.8282877533719,
18.2355885882618, 27.0557882676846, 27.2210269605054, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, 27.7812364734848, 27.405183119753,
24.2674419226904, 21.1096354803572, 19.7839120235376, 28.0337762198564,
30.3552042477317, 27.9129238649901, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, 27.8602581108286, 25.5695030720577, 19.308317452836,
20.2224030952562, 19.8943689815922, 26.0737945219631, 29.8730429910469,
30.0356550838097, NA, NA, NA, NA, NA, NA, NA, NA, NA, 27.9364248138976,
26.9457930700303, 23.0304323166943, 19.4650798632613, 19.0999036995668,
17.5193560841074, 27.7251998095169, 28.4496104452209, 28.9315408261731,
NA, NA, NA, NA, NA, NA, NA, NA, NA, 26.8544908125766, 25.0566493895284,
19.392461671792, 17.9138961574326, 18.457466509715, 16.2828861956587,
24.3601694045773, 28.1808209395655, 28.9282707782622, 26.6332021683416,
NA, NA, NA, NA, NA, NA, NA, 25.7558302469057, 25.8550702427802,
22.5693001232205, 19.6993922601795, 16.1425172340908, 18.5221217322922,
15.6749250516081, 23.7808882591915, 26.8347423074187, 27.2630654814702,
25.9184967686647, NA, NA, NA, NA, NA, NA, NA, 24.8123372469289,
21.9120014347897, 21.8593245154305, 18.7720082061109, 19.7574885247249,
18.4980326509342, 16.3585539605331, 24.9138993320561, 25.2434828477134,
24.163634092843, 21.0163621891882, 20.415437668758, NA, NA, NA,
NA, NA, NA, 24.1877819407117, 20.6452893546199, 20.1902008603325,
19.3002926063194, 16.8587312480956, 16.2594198755341, 19.2032612963314,
23.627249155838, 20.2610810034085, 20.512646252079, 21.2108132984962,
21.3929956864179, 22.5462104762584, NA, NA, NA, NA, 28.1377507911064,
26.6783600800768, 21.9226216069185, 18.7325546681671, 19.3040954243679,
18.9295032049331, 16.9754437056141, 18.4150075374079, 22.1472527043877,
23.0212426364059, 24.3613220176048, 23.8262550760194, 23.1817611577951,
23.5871416966677, 24.5249361302642, 24.8507563698565, 24.5380700828535,
24.6222669309606, 28.1310406991608, 26.6318516890262, 22.2093701933002,
18.5946021290531, 18.8365649393596, 19.1392679329481, 18.0261774155026,
15.4867865984622, 22.6594382919435, 24.0000969920539, 26.8590549383737,
25.3828920205212, 24.7396876533108, 24.2529425383968, 25.4417776029091,
25.4515553773556, 25.362837214521, 24.9104771169439, NA, 26.0466484214637,
22.5547365784066, 21.385068811716, 21.7011412999039, 21.5908931968994,
17.5042944634609, 16.1420136345859, 22.2389789351034, 24.9668657681713,
27.1669375893459, 26.7413589409561, 26.421134458086, 26.219636989708,
26.3182362528439, 26.4198369697735, 26.3436222765849, NA, NA,
NA, 23.0141531354431, 25.0932401677589, 21.6662460243741, 20.5190520941524,
18.375683158989, 21.0476911567136, 24.5643254483451, 26.328155553503,
26.272891752264, 27.9174179692592, 27.8104921435185, 27.3675508861065,
27.0387799062499, 26.7967626268208, NA, NA, NA, NA, 23.9459211033352,
27.0411266756461, 24.5366020483741, 21.827679045105, 20.9547907819176,
22.0691273897516, 23.4745553057174, 26.3462307150211, 28.3701287602482,
27.3758861302374, 27.3750656061461, 27.962003557149, 27.5345722331493,
NA, NA, NA, NA, NA, NA, 28.2432491874035, 25.6912040459346, 23.8651528078732,
21.6046243626329, 22.9131480337219, 23.819129269607, 26.3568262380137,
28.9188481472128, 28.1497370861287, 27.7360100735352, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, 25.045874725646, 23.2493769507419,
23.1730515314323, 24.2038209656421, 28.3416254663092, 28.8959112067936,
NA, NA, NA, NA, NA, NA, NA)
, offset = 0
, gain = 1
, inmemory = TRUE
, fromdisk = FALSE
, isfactor = FALSE
, attributes = list()
, haveminmax = TRUE
, min = 15.4867865984622
, max = 30.3552042477317
, band = 1L
, unit = ""
, names = "MAT_eclp"
)
, legend = new(".RasterLegend"
, type = character(0)
, values = logical(0)
, color = logical(0)
, names = logical(0)
, colortable = logical(0)
)
, title = character(0)
, extent = new("Extent"
, xmin = 832565.530013465
, xmax = 2452565.53001346
, ymin = 383803.949813352
, ymax = 1733803.94981335
)
, rotated = FALSE
, rotation = new(".Rotation"
, geotrans = numeric(0)
, transfun = function ()
NULL
)
, ncols = 18L
, nrows = 15L
, crs = new("CRS"
, projargs = "+proj=aea +lat_1=20 +lat_2=-23 +lat_0=0 +lon_0=25 +x_0=0 +y_0=0 +datum=WGS84 +units=m +no_defs +ellps=WGS84 +towgs84=0,0,0"
)
, history = list()
, z = list()
)
Or, another minimal example to dput(), then try assigning output to another object:
library(raster)
r1 <- raster(nrow=10, ncol=10)
values(r1) <- runif(ncell(r1))
dput(r1)
How can I load a raster from the text version and avoid this error?
This is a bug, due to an error in the validity check of the .RasterFile object (part of the RasterLayer). Illustrated here:
x <- new(".RasterFile")
validObject(x)
#Error in datanotation %in% c("LOG1S", "INT1S", "INT2S", "INT4S", "INT1U", :
# object 'datanotation' not found
I fixed this in version 2.5-11 (available from R-Forge in an hour or so: install.packages("raster", repos="http://R-Forge.R-project.org") ).
P.S. why would you want to use dput/dget?
Related
I want to make a prediction at a finer spatial scale using XGBoost regression. I created a model at a coarse spatial scale and now I want to apply the model parameters at a finer scale. The issue is that at the finer spatial scale the xgb.DMatrix doesn't include the dependent variable so the predict function returns this error:
Error in predict.xgb.Booster(m, xgb_p, na.rm = TRUE): Feature names stored in `object` and `newdata` are different!
I have seen this post but I still get the same error. Also, I tried to create a data.frame with the independent variables and an extra empty column with the name of the dependent variable, but still the same error.
How can I use the XGB model parameters found in the coarse spatial scale to make predictions at a fine spatial scale?
I have checked the names of the variables in both the coarse and spatial scales and they are the same.
Here is the code:
library(xgboost)
library(raster)
# the dependent and independent variables at the coarse scale
xgb_m <- xgb.DMatrix(data = data.matrix(block.data), label = block.data$ntl)
# that's the model
m = xgb.train(data = xgb_m,
max.depth = 2,
nrounds = 1000,
min_child_weight = 1,
subsample = 0.75,
eta = 0.015,
gamma = 0.5,
colsample_bytree = 1,
objective = "reg:squarederror")
# these are the independent variables at the fine spatial scale
pop = raster(paste0(wd, "pop.tif"))
tirs = raster(paste0(wd, "tirs.tif"))
agbh = raster(paste0(wd, "agbh.tif"))
vars = stack(pop, tirs, agbh)
# the xgb.DMatrix with the independent variables
xgb_p <- xgb.DMatrix(data = data.matrix(vars))
xgb_pred <- predict(m, xgb_p, na.rm = TRUE) # the error
The data.frame (block.data):
block.data = structure(list(x = c(11880750L, 11879250L, 11879750L, 11880250L,
11880750L, 11881250L, 11879250L, 11879750L, 11880250L, 11880750L,
11881250L, 11878750L, 11879250L, 11879750L, 11880250L, 11880750L,
11881250L, 11879250L, 11879750L, 11880250L, 11880750L, 11881250L,
11881750L, 11882250L, 11879250L, 11879750L, 11880250L, 11880750L,
11881250L, 11881750L, 11882250L, 11882750L, 11879250L, 11879750L
), y = c(1802250L, 1801750L, 1801750L, 1801750L, 1801750L, 1801750L,
1801250L, 1801250L, 1801250L, 1801250L, 1801250L, 1800750L, 1800750L,
1800750L, 1800750L, 1800750L, 1800750L, 1800250L, 1800250L, 1800250L,
1800250L, 1800250L, 1800250L, 1800250L, 1799750L, 1799750L, 1799750L,
1799750L, 1799750L, 1799750L, 1799750L, 1799750L, 1799250L, 1799250L
), ntl = c(18.7969169616699, 25.7222957611084, 23.4188251495361,
25.4322757720947, 16.4593601226807, 12.7868213653564, 30.9337253570557,
29.865758895874, 30.4080600738525, 29.5479888916016, 24.3493347167969,
35.2427635192871, 38.989933013916, 34.6536979675293, 29.4607238769531,
30.7469024658203, 34.3946380615234, 42.8660278320312, 34.7930717468262,
30.9516315460205, 32.20654296875, 39.999755859375, 46.6002235412598,
38.6480979919434, 60.5214920043945, 33.1799964904785, 31.8498134613037,
30.9209423065186, 32.2269744873047, 53.7062034606934, 45.5225944519043,
38.3570976257324, 123.040382385254, 73.0528182983398), pop = c(19.6407718658447,
610.009216308594, 654.812622070312, 426.475830078125, 66.3839492797852,
10.6471328735352, 443.848846435547, 602.677429199219, 488.478454589844,
387.470947265625, 58.2341117858887, 413.888488769531, 315.057678222656,
354.082946777344, 602.827758789062, 463.518829345703, 296.713928222656,
923.920593261719, 434.436645507812, 799.562927246094, 404.709564208984,
265.043304443359, 366.697235107422, 399.851684570312, 952.2314453125,
870.356994628906, 673.406616210938, 493.521606445312, 273.841888427734,
371.428619384766, 383.057830810547, 320.986755371094, 991.131225585938,
1148.87768554688), tirs = c(39.7242431640625, 44.9583969116211,
41.4048385620117, 42.6056709289551, 40.0976028442383, 38.7490005493164,
44.2747650146484, 43.5645370483398, 41.6180191040039, 40.3799781799316,
38.8664817810059, 44.9089202880859, 44.414306640625, 44.560977935791,
43.1288986206055, 40.9315185546875, 38.8918418884277, 46.3063850402832,
45.5805702209473, 44.9196586608887, 42.2495613098145, 39.3051452636719,
38.7914810180664, 38.6069412231445, 44.6782455444336, 46.4024772644043,
44.4720573425293, 41.7361183166504, 42.3378067016602, 41.0018348693848,
39.3579216003418, 41.6303863525391, 43.8207550048828, 46.0460357666016
), agbh = c(3.32185006141663, 4.98925733566284, 4.35699367523193,
4.94798421859741, 3.14325952529907, 2.93211793899536, 4.52736520767212,
4.99723243713379, 5.13944292068481, 3.92965626716614, 3.43465113639832,
3.55617475509644, 3.4659411907196, 5.24469566345215, 5.36995029449463,
4.61549234390259, 4.82002925872803, 4.20452928543091, 4.71502685546875,
5.20452785491943, 5.05676746368408, 5.9952244758606, 6.16778612136841,
4.69053316116333, 2.62325501441956, 4.74775457382202, 4.93133020401001,
5.02366256713867, 5.74016952514648, 6.28353786468506, 4.67424774169922,
4.56812858581543, 1.88153350353241, 4.31531000137329)), class = "data.frame", row.names = c(NA,
-34L))
The fine resolution data
vars = new("RasterBrick", file = new(".RasterFile", name = "", datanotation = "FLT4S",
byteorder = "little", nodatavalue = -Inf, NAchanged = FALSE,
nbands = 1L, bandorder = "BIL", offset = 0L, toptobottom = TRUE,
blockrows = 0L, blockcols = 0L, driver = "", open = FALSE),
data = new(".MultipleRasterData", values = structure(c(NA,
NA, NA, NA, 18.7969169616699, NA, NA, NA, NA, NA, 25.7222957611084,
23.4188251495361, 25.4322757720947, 16.4593601226807, 12.7868213653564,
NA, NA, NA, NA, 30.9337253570557, 29.865758895874, 30.4080600738525,
29.5479888916016, 24.3493347167969, NA, NA, NA, 35.2427635192871,
38.989933013916, 34.6536979675293, 29.4607238769531, 30.7469024658203,
34.3946380615234, NA, NA, NA, NA, 42.8660278320312, 34.7930717468262,
30.9516315460205, 32.20654296875, 39.999755859375, 46.6002235412598,
38.6480979919434, NA, NA, 60.5214920043945, 33.1799964904785,
31.8498134613037, 30.9209423065186, 32.2269744873047, 53.7062034606934,
45.5225944519043, 38.3570976257324, NA, 123.040382385254,
73.0528182983398, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
19.6407718658447, NA, NA, NA, NA, NA, 610.009216308594, 654.812622070312,
426.475830078125, 66.3839492797852, 10.6471328735352, NA,
NA, NA, NA, 443.848846435547, 602.677429199219, 488.478454589844,
387.470947265625, 58.2341117858887, NA, NA, NA, 413.888488769531,
315.057678222656, 354.082946777344, 602.827758789062, 463.518829345703,
296.713928222656, NA, NA, NA, NA, 923.920593261719, 434.436645507812,
799.562927246094, 404.709564208984, 265.043304443359, 366.697235107422,
399.851684570312, NA, NA, 952.2314453125, 870.356994628906,
673.406616210938, 493.521606445312, 273.841888427734, 371.428619384766,
383.057830810547, 320.986755371094, NA, 991.131225585938,
1148.87768554688, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
39.7242431640625, NA, NA, NA, NA, NA, 44.9583969116211, 41.4048385620117,
42.6056709289551, 40.0976028442383, 38.7490005493164, NA,
NA, NA, NA, 44.2747650146484, 43.5645370483398, 41.6180191040039,
40.3799781799316, 38.8664817810059, NA, NA, NA, 44.9089202880859,
44.414306640625, 44.560977935791, 43.1288986206055, 40.9315185546875,
38.8918418884277, NA, NA, NA, NA, 46.3063850402832, 45.5805702209473,
44.9196586608887, 42.2495613098145, 39.3051452636719, 38.7914810180664,
38.6069412231445, NA, NA, 44.6782455444336, 46.4024772644043,
44.4720573425293, 41.7361183166504, 42.3378067016602, 41.0018348693848,
39.3579216003418, 41.6303863525391, NA, 43.8207550048828,
46.0460357666016, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
3.32185006141663, NA, NA, NA, NA, NA, 4.98925733566284, 4.35699367523193,
4.94798421859741, 3.14325952529907, 2.93211793899536, NA,
NA, NA, NA, 4.52736520767212, 4.99723243713379, 5.13944292068481,
3.92965626716614, 3.43465113639832, NA, NA, NA, 3.55617475509644,
3.4659411907196, 5.24469566345215, 5.36995029449463, 4.61549234390259,
4.82002925872803, NA, NA, NA, NA, 4.20452928543091, 4.71502685546875,
5.20452785491943, 5.05676746368408, 5.9952244758606, 6.16778612136841,
4.69053316116333, NA, NA, 2.62325501441956, 4.74775457382202,
4.93133020401001, 5.02366256713867, 5.74016952514648, 6.28353786468506,
4.67424774169922, 4.56812858581543, NA, 1.88153350353241,
4.31531000137329, NA, NA, NA, NA, NA, NA), .Dim = c(63L,
4L)), offset = 0, gain = 1, inmemory = TRUE, fromdisk = FALSE,
nlayers = 4L, dropped = NULL, isfactor = c(FALSE, FALSE,
FALSE, FALSE), attributes = list(), haveminmax = TRUE,
min = c(12.7868213653564, 10.6471328735352, 38.6069412231445,
1.88153350353241), max = c(123.040382385254, 1148.87768554688,
46.4024772644043, 6.28353786468506), unit = "", names = c("ntl",
"pop", "tirs", "agbh")), legend = new(".RasterLegend",
type = character(0), values = logical(0), color = logical(0),
names = logical(0), colortable = logical(0)), title = character(0),
extent = new("Extent", xmin = 11878500, xmax = 11883000,
ymin = 1799000, ymax = 1802500), rotated = FALSE, rotation = new(".Rotation",
geotrans = numeric(0), transfun = function ()
NULL), ncols = 9L, nrows = 7L, crs = new("CRS", projargs = NA_character_),
srs = character(0), history = list(), z = list())
The issue you have is that the model is trained on all columns present in block.data, so also on x, y and ntl itself. In your later rasterstack, those variables are not present and thus you get an error.
We get can around this by creating the xgb.DMatrix differently:
#create matrix
xgb_m <- xgb.DMatrix(data = data.matrix(block.data[, c("pop", "tirs", "agbh")]), label = block.data$ntl)
#your model
m = xgb.train(data = xgb_m,
max.depth = 2,
nrounds = 1000,
min_child_weight = 1,
subsample = 0.75,
eta = 0.015,
gamma = 0.5,
colsample_bytree = 1,
objective = "reg:squarederror")
#load rasterstack
library(terra)
pop = rast("pop.tif")
tirs = rast("tirs.tif")
agbh = rast("agbh.tif")
vars <- c(pop, tirs, agbh)
#predict
xgb_p <- xgb.DMatrix(data.matrix(vars))
predict(m, xgb_p)
This question already has answers here:
Error in if/while (condition) {: missing Value where TRUE/FALSE needed
(4 answers)
Closed 4 years ago.
I am trying to define a new matrix z based on another matrix x. This is what I did :
x = structure(
.Data = c(5012, 3257,2638,-898,1734,2642,1828,599,-54,172,
-106,4179,-1111,5270,3116,1817,-103,0,535,NA,
3410,5582,4881,2268,2594,3479,0,603,NA, NA,
5655,5900,4211,5500,2159,2658,984, NA, NA, NA,
1092,8473,6271,6333,3786,-225, NA, NA, NA, NA,
1513,4932,5257,1233,2917, NA , NA, NA, NA, NA,
-557,3463,6926,1368, NA, NA, NA, NA, NA, NA,
1351,5596,6165, NA, NA, NA, NA, NA, NA, NA,
3133,2262, NA, NA, NA , NA , NA , NA, NA , NA,
2063, NA, NA, NA , NA , NA , NA, NA , NA, NA),
.Dim = c(10,10))
x = t(x)
r=ncol(x)
z = matrix(ncol = r, nrow = r)
for(i in 1:r){
for(j in 1:r){
if(x[i,j]>0){
z[i,j] = 1
}
else if(x[i,j]<0){
z[i,j] = -1
}
else {
z[i,j]=0
}
}
}
but I got error :
Error in if (x[i, j] > 0) { : missing value where TRUE/FALSE needed
How can I fix it ?
The problem happened when if hit NA
for(i in 1:r){
for(j in 1:r){
if(!is.na(x[i,j]) & x[i,j]>0){
z[i,j] = 1
}
else if(!is.na(x[i,j]) & x[i,j]<0){
z[i,j] = -1
}
else {
z[i,j]=0
}
}
}
I want to run Pearson correlations of each row of a matrix (dat) vs a vector (v1), as part of a loop, and output the correlation coefficients and associated p-values in a table. Here is an example for random data (data pasted at the end):
result_table <- data.frame(matrix(ncol = 2, nrow = nrow(dat)))
colnames(result_table) <- c("correlation_coefficient", "pvalue")
for(i in 1:nrow(dat)){
print(i)
corr <- cor.test(as.numeric(dat[i,]), v1, na.action = "na.omit")
result_table[i,1] <- corr$estimate
result_table[i,2] <- corr$p.value
}
When cor.test() removes missing data, sometimes there are not enough observations remaining and the loop stops with an error (for example at row 11). I would like the loop to continue running, just leaving the values in the result table as NAs. I think the result table should then look like this:
> result_table
correlation_coefficient pvalue
1 0.68422642 0.04206591
2 -0.15895586 0.70694013
3 -0.37005028 0.53982309
4 0.08448970 0.89255250
5 0.86860091 0.05603661
6 0.19544883 0.75274040
7 -0.94695380 0.01454887
8 -0.03817885 0.94275955
9 -0.15214122 0.77354897
10 -0.22997890 0.70978386
11 NA NA
12 NA NA
13 -0.27769887 0.59415930
14 -0.09768153 0.81800885
15 -0.20986632 0.61790214
16 -0.40474976 0.31990456
17 -0.00605937 0.98863896
18 0.02176976 0.95919460
19 -0.14755097 0.72733118
20 -0.25830856 0.50216600
I would also like the errors to keep being printed
Here is the data:
> dput(v1)
c(-0.840396, 0.4746047, -1.101857, 0.5164767, 1.2203134, -0.9758888,
-0.3657913, -0.6272523, -0.5853803, 1.7367901)
> dput(dat)
structure(list(s1 = c(-0.52411895, 0.14709633, 0.05433954, 0.7504406,
-0.59971988, -0.59679685, -0.12571854, 0.73289705, -0.71668771,
-0.04813957, -0.67849896, -0.11947141, -0.26371884, -1.34137162,
2.60928064, -1.23397547, 0.51811222, -4.10759883, -0.70127093,
7.51914575), s2 = c(0.21446623, -0.27281487, NA, NA, NA, NA,
NA, NA, -0.62468391, NA, NA, NA, -3.84387999, 0.64010069, NA,
NA, NA, NA, NA, NA), s3 = c(0.3461212, 0.279062, NA, NA, NA,
-0.4737744, 0.6313365, -2.8472641, 1.2647846, 2.2524449, -0.7913039,
-0.752590307, -3.535815266, 1.692385187, 3.55789764, -1.694910854,
-3.624517121, -4.963855198, 2.395998161, 5.35680032), s4 = c(0.3579742,
0.3522745, -1.1720907, 0.4223402, 0.146605, -0.3175295, -1.383926807,
-0.688551166, NA, NA, NA, NA, NA, 0.703612974, 1.79890268, -2.625404608,
-3.235884921, -2.845474098, 0.058650461, 1.83900702), s5 = c(1.698104376,
NA, NA, NA, NA, NA, -1.488000007, -0.739488766, 0.276012387,
0.49344994, NA, NA, -1.417434166, -0.644962513, 0.04010434, -3.388182254,
2.900252493, -1.493417096, -2.852256003, -0.98871696), s6 = c(0.3419271,
0.2482013, -1.2230283, 0.270752, -0.6653978, -1.1357202, NA,
NA, NA, NA, NA, NA, NA, NA, -1.0288213, -1.17817328, 6.1682455,
1.02759131, -3.80372867, -2.6249692), s7 = c(0.3957243, 0.8758406,
NA, NA, NA, NA, NA, 0.60196247, -1.28631859, -0.5754757, NA,
NA, NA, NA, NA, NA, NA, NA, NA, -2.6303001), s8 = c(-0.26409595,
1.2643281, 0.05687957, -0.09459169, -0.7875279, NA, NA, NA, NA,
NA, NA, NA, 2.42442997, -0.00445559, -1.0341522, 2.47315322,
0.1190265, 5.82533417, 0.82239131, -0.8279679), s9 = c(0.237123,
-0.5004619, 0.4447322, -0.2155249, -0.2331443, 1.3438071, -0.3817672,
1.9228182, 0.305661, -0.01348, NA, NA, 3.4009042, 0.8268469,
0.2061843, -1.1228663, -0.1443778, 4.8789902, 1.3480328, 0.4258486
), s10 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
0.5211859, 0.2196643, -1.2333367, 0.1186947, 1.478086, 0.5211859,
0.2196643)), .Names = c("s1", "s2", "s3", "s4", "s5", "s6", "s7",
"s8", "s9", "s10"), class = "data.frame", row.names = c(NA, -20L
))
A solution with tryCatch could be
for(i in 1:nrow(dat)){
print(i)
corr <- tryCatch(cor.test(as.numeric(dat[i,]), v1, na.action = "na.omit"), error = function(e) return(NA))
if(length(corr) == 1){
result_table[i,1] <- NA
result_table[i,2] <- NA
}else{
result_table[i,1] <- corr$estimate
result_table[i,2] <- corr$p.value
}
}
Here is a solution with tryCatch():
Replacing the for loop with:
for(i in 1:nrow(dat)){
tryCatch({
print(i)
corr <- cor.test(as.numeric(dat[i,]), v1, na.action = "na.omit") # Correlation miRNA activity vs CNVs for that gene
result_table[i,1] <- corr$estimate
result_table[i,2] <- corr$p.value
}, error=function(e){cat("ERROR :",conditionMessage(e), "\n")})
}
I can see that there are a lot of questions similar to this, but I cant find solution for my particular problem.
Data:
risk_accum <- structure(list(date = structure(c(1465948800, 1465952400, 1465956000,
1465959600, 1465963200, 1465966800, 1465970400, 1465974000, 1465977600,
1465981200, 1465984800, 1465988400, 1465992000, 1465995600, 1465999200,
1466002800, 1466006400, 1466010000, 1466013600, 1466017200, 1466020800,
1466024400, 1466028000, 1466031600, 1466035200, 1466038800, 1466042400,
1466046000, 1466049600, 1466053200, 1466056800, 1466060400, 1466064000,
1466067600, 1466071200, 1466074800, 1466078400, 1466082000, 1466085600,
1466089200, 1466092800, 1466096400, 1466100000, 1466103600, 1466107200,
1466110800, 1466114400, 1466118000, 1466121600, 1466125200, 1466128800,
1466132400, 1466136000, 1466139600, 1466143200, 1466146800, 1466150400,
1466154000, 1466157600, 1466161200, 1466164800, 1466168400, 1466172000,
1466175600, 1466179200, 1466182800, 1466186400, 1466190000, 1466193600,
1466197200, 1466200800, 1466204400, 1466208000, 1466211600, 1466215200,
1466218800, 1466222400, 1466226000, 1466229600, 1466233200, 1466236800,
1466240400, 1466244000, 1466247600, 1466251200, 1466254800, 1466258400,
1466262000, 1466265600, 1466269200, 1466272800, 1466276400, 1466280000,
1466283600, 1466287200, 1466290800, 1466294400, 1466298000, 1466301600,
1466305200, 1466308800, 1466312400, 1466316000, 1466319600, 1466323200,
1466326800, 1466330400, 1466334000, 1466337600, 1466341200, 1466344800,
1466348400, 1466352000, 1466355600, 1466359200, 1466362800, 1466366400,
1466370000, 1466373600, 1466377200), class = c("POSIXct", "POSIXt"
), tzone = "UTC"), risk = c(NA, NA, NA, 1, 2, 3, 4, 5, 6, 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, 1, 2, 3, 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, 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, NA, NA, NA, NA, NA, NA, 1, 2, 3,
4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, NA, NA)), .Names = c("date",
"risk"), row.names = c(NA, -120L), class = c("tbl_df", "tbl",
"data.frame"))
And code to generate graph:
#color variable
color_var <- vector(mode = "double",length = length(risk_accum$risk))
color_var[color_var== '0']<-NA
color_var[risk_accum$risk<6] <- "green4"
color_var[risk_accum$risk>=6 & risk_accum$risk<12] <- "yellow2"
color_var[risk_accum$risk>=12] <- "red"
#plot of Effective Blight Hours accumulation
ggplot(risk_accum)+
geom_line(aes(x = date, y = risk), color = color_var)+
scale_y_continuous(name = "EBH accumulation")+
scale_colour_manual(values=c("green", "yellow", "red"))+
geom_line(aes(date, y= 12), linetype= "dotted", size = 0.1)+
theme(axis.title.x = element_blank())
I need to get a legend which would explain the traffic light system (red is danger, etc) and manually added threshold risk line.
Add your color variable to the dataset, map to that variable inside aes, and use scale_*_identity to directly use the colors.
risk_accum$color_var <- NA
risk_accum$color_var[risk_accum$risk<6] <- "green4"
risk_accum$color_var[risk_accum$risk>=6 & risk_accum$risk<12] <- "yellow2"
risk_accum$color_var[risk_accum$risk>=12] <- "red"
ggplot(risk_accum)+
geom_line(aes(x = date, y = risk, color = color_var)) +
scale_y_continuous(name = "EBH accumulation")+
scale_color_identity(guide = 'legend') +
geom_line(aes(date, y= 12), linetype= "dotted", size = 0.1)+
theme(axis.title.x = element_blank())
You can also add your threshold to the legend:
ggplot(risk_accum)+
geom_line(aes(x = date, y = risk, color = color_var)) +
geom_line(aes(date, y= 12, linetype = "threshold"), size = 0.1)+
scale_y_continuous(name = "EBH accumulation")+
scale_color_identity(guide = 'legend') +
scale_linetype_manual(values = 2) +
theme(axis.title.x = element_blank())
I am trying to move the position of x-ticks and x-labels from the bottom of the figure to its top.
In addition, my data has a bunch of NAs. Currently, levelplot just remove them and leave them as white space in the plot. I wondering if it is possible to add this NAs to the legend as well.
Any suggestions? Thanks!
Here is my code and its output:
require(lattice)
# see data from dput() below
rownames(data)=data[,1]
data_matrix=as.matrix(data[,2:11])
color = colorRampPalette(rev(c("#D73027", "#FC8D59", "#FEE090", "#FFFFBF", "#E0F3F8", "#91BFDB", "#4575B4")))(100)
levelplot(data_matrix, scale=list(x=list(rot=45)), ylab="Days", xlab="Strains", col.regions = color)
Data
data <-
structure(list(X = structure(1:17, .Label = c("Arcobacter", "Bacillus",
"Bordetella", "Campylobacter", "Chlamydia", "Clostridium ", "Corynebacterium",
"Enterococcus", "Escherichia", "Francisella", "Legionella", "Mycobacterium",
"Pseudomonas", "Rickettsia", "Staphylococcus", "Streptococcus",
"Treponema"), class = "factor"), day.0 = c(NA, -3.823301154,
NA, NA, NA, -3.518606107, NA, NA, NA, NA, NA, -4.859479387, NA,
NA, NA, -2.588402346, -2.668136603), day.2 = c(-4.006281239,
-3.024823788, NA, -5.202804501, NA, -3.237622321, NA, NA, -5.296138823,
-5.105469059, NA, NA, -4.901775198, NA, NA, -2.979144202, -3.050083791
), day.4 = c(-2.880770182, -3.210165554, -4.749097175, -5.209064234,
NA, -2.946480184, NA, -5.264113795, -5.341881713, -4.435780293,
NA, -4.810650076, -4.152531609, NA, NA, -3.106172794, -3.543161966
), day.6 = c(-2.869833226, -3.293283924, -3.831346387, NA, NA,
-3.323947791, NA, NA, NA, NA, NA, -4.397581863, -4.068855504,
NA, NA, -3.27028378, -3.662618619), day.8 = c(-3.873589331, -3.446192193,
-3.616207965, NA, NA, -3.13869325, NA, -5.010807453, NA, NA,
NA, -4.091502649, -4.412399025, -4.681675749, NA, -3.404738625,
-3.955464159), day.15 = c(-5.176583159, -2.512963066, -3.392832457,
NA, NA, -3.194662968, NA, -3.60440455, NA, NA, -4.875554468,
-2.507376205, -4.727255906, -5.27116754, -3.200499549, -3.361296145,
-4.320554841), day.22 = c(-4.550052847, -3.654013004, -3.486879661,
NA, NA, -3.614890858, NA, NA, NA, NA, -4.706690492, -2.200533317,
-4.836957953, NA, -4.390423731, NA, NA), day.29 = c(-4.730006329,
-3.46707372, -3.594457287, NA, NA, -3.800757834, NA, NA, NA,
NA, -4.285154089, -2.121152491, -4.816807055, -5.064577888, -2.945243736,
-4.479177287, -5.226435146), day.43 = c(-4.398680025, -3.144603215,
-3.642065153, NA, NA, -3.8268662, NA, NA, NA, NA, -4.762539208,
-2.156862316, -4.118608495, NA, -4.030291084, -4.678213147, NA
), day.57 = c(-4.689982547, -2.713502214, -3.51279797, NA, -5.069579266,
-3.495580794, NA, NA, NA, NA, -4.515973639, -1.90591075, -4.134826117,
-4.479351427, -3.482134037, -4.538534489, NA)), .Names = c("X",
"day.0", "day.2", "day.4", "day.6", "day.8", "day.15", "day.22",
"day.29", "day.43", "day.57"), class = "data.frame", row.names = c("Arcobacter",
"Bacillus", "Bordetella", "Campylobacter", "Chlamydia", "Clostridium ",
"Corynebacterium", "Enterococcus", "Escherichia", "Francisella",
"Legionella", "Mycobacterium", "Pseudomonas", "Rickettsia", "Staphylococcus",
"Streptococcus", "Treponema"))
Figure
The request to move the labels to the top is pretty easy (after looking at the ?xyplot under the scales section):
levelplot(data_matrix, scale=list(x=list(rot=45,alternating=2)),
ylab="Days", xlab="Strains", col.regions = color)
Trying to get the NA values into the color legend may take a bit more thinking, but it seems as though sensible values for the colorkey arguments for at and col might suffice.
levelplot(data_matrix, scale=list(x=list(rot=45,alternating=2)),
ylab="Days", xlab="Strains", col.regions = color,
colorkey=list(at=as.numeric( factor( c( seq(-5.5, -2, by=0.5),
"NA"))),
labels=as.character( c( seq(-5.5, -2, by=0.5),
"NA")),
col=c(color, "#FFFFFF") ) )