Remodelando una matriz en data.frame

Question

Tengo la siguiente estructura de datos (¿un vector atómico?) Salida desde daply en plyr, en la que tuve la función devolver tres medidas diferentes para cada sujeto, condición y artículo.

x = structure(c(-0.93, 0.39, 0.88, 0.63, 0.86, -0.69, 1.02, 0.29, 0.94, 
0.93, -0.01, 0.79, 0.32, 0.14, 0.13, -0.07, -0.63, 0.26, 0.07, 0.87, 
-0.36, 1.043, 0.33, -0.12, -0.055, 0.07, 0.67, 0.48, 0.002, 0.008, 
-0.19, -1.39, 0.98, 0.43, -0.02, -0.15,-0.08, 0.74, 0.96, 0.44, -0.005, 
1.09, 0.36, 0.04, 0.09, 0.17, 0.68, 0.51, 0.09, 0.12, -0.05, 0.11, 
0.99, 0.62, 0.13, 0.06, 0.27, 0.74, 0.96, 0.45), .Dim = c(5L, 
2L, 2L, 3L), .Dimnames = structure(list(Subject = c("s1", "s2", 
"s3", "s4", "s5"), Cond = c("A", "B"), Item = c("1", "2"), c("Measure1", 
"Measure2", "Measure3")), .Names = c("Subject", "Cond", 
"Item", ""))) 

quiero cambiarlo a parecerse a:

Subject Cond Item Measure1 Measure2 Measure3 
    s1 A 1 -0.93 -0.360 -0.005 
    s1 A 2 -0.01 -0.19 -0.05 
    s1 B 1 -0.69 0.070  0.17 
    s1 B 2 -0.07 -0.15  0.06 
    s2 A 1  0.39 1.043 1.090 
    s2 A 2  0.79 -1.39  0.11 
    s2 B 1  1.02 0.670  0.68 
    s2 B 2 -0.63 -0.08  0.27 

etc.

¿Hay una manera fácil de hacer esto?

Answer 1

Sí, utilice adply():

adply(x, c(1,2,3)) 
    Subject Cond Item Measure1 Measure2 Measure3 
1  s1 A 1 -0.93 -0.360 -0.005 
2  s2 A 1  0.39 1.043 1.090 
3  s3 A 1  0.88 0.330 0.360 
4  s4 A 1  0.63 -0.120 0.040 
5  s5 A 1  0.86 -0.055 0.090 
6  s1 B 1 -0.69 0.070 0.170 
7  s2 B 1  1.02 0.670 0.680 
8  s3 B 1  0.29 0.480 0.510 
9  s4 B 1  0.94 0.002 0.090 
10  s5 B 1  0.93 0.008 0.120 
11  s1 A 2 -0.01 -0.190 -0.050 
12  s2 A 2  0.79 -1.390 0.110 
13  s3 A 2  0.32 0.980 0.990 
14  s4 A 2  0.14 0.430 0.620 
15  s5 A 2  0.13 -0.020 0.130 
16  s1 B 2 -0.07 -0.150 0.060 
17  s2 B 2 -0.63 -0.080 0.270 
18  s3 B 2  0.26 0.740 0.740 
19  s4 B 2  0.07 0.960 0.960 
20  s5 B 2  0.87 0.440 0.450 

Answer 2

df = melt(x) le da algo muy similar a lo que desea. Entonces podrías calcular las diversas variables de medida de los diferentes niveles de medida.

Usando el paquete "reshape2", trate de:

dcast(melt(x), Subject + Cond + Item ~ Var4) 

Answer 3

ftable prácticamente te lleva a donde tiene que estar:

y <- ftable(x) 
y 
# 
#     Measure1 Measure2 Measure3 
# Subject Cond Item        
# s1  A 1  -0.930 -0.360 -0.005 
#    2  -0.010 -0.190 -0.050 
#   B 1  -0.690 0.070 0.170 
#    2  -0.070 -0.150 0.060 
# s2  A 1  0.390 1.043 1.090 
#    2  0.790 -1.390 0.110 
#   B 1  1.020 0.670 0.680 
#    2  -0.630 -0.080 0.270 
# s3  A 1  0.880 0.330 0.360 
#    2  0.320 0.980 0.990 
#   B 1  0.290 0.480 0.510 
#    2  0.260 0.740 0.740 
# s4  A 1  0.630 -0.120 0.040 
#    2  0.140 0.430 0.620 
#   B 1  0.940 0.002 0.090 
#    2  0.070 0.960 0.960 
# s5  A 1  0.860 -0.055 0.090 
#    2  0.130 -0.020 0.130 
#   B 1  0.930 0.008 0.120 
#    2  0.870 0.440 0.450 

---

embargo, la mayoría de la gente probablemente preferiría sus datos en un data.frame. El uso de as.data.frame.matrix extrae los valores, pero no los nombres de fila y columna. ftable almacena esa información en los atributos row.vars y col.vars.

attributes(y)$row.vars 
# $Subject 
# [1] "s1" "s2" "s3" "s4" "s5" 
# 
# $Cond 
# [1] "A" "B" 
# 
# $Item 
# [1] "1" "2" 

attributes(y)$col.vars 
# [[1]] 
# [1] "Measure1" "Measure2" "Measure3" 

Podemos utilizar esta información para escribir una función que convierte una ftable a un data.frame:

ftable2df <- function(mydata) { 
    ifelse(class(mydata) == "ftable", 
     mydata <- mydata, mydata <- ftable(mydata)) 
    dfrows <- rev(expand.grid(rev(attr(mydata, "row.vars")))) 
    dfcols <- as.data.frame.matrix(mydata) 
    names(dfcols) <- do.call(
    paste, c(rev(expand.grid(rev(attr(mydata, "col.vars")))), sep = "_")) 
    cbind(dfrows, dfcols) 
} 

Aquí está en uso directamente en la "x" original:

ftable2df(x) 
# Subject Cond Item Measure1 Measure2 Measure3 
# 1  s1 A 1 -0.93 -0.360 -0.005 
# 2  s1 A 2 -0.01 -0.190 -0.050 
# 3  s1 B 1 -0.69 0.070 0.170 
# 4  s1 B 2 -0.07 -0.150 0.060 
# 5  s2 A 1  0.39 1.043 1.090 
# 6  s2 A 2  0.79 -1.390 0.110 
# 7  s2 B 1  1.02 0.670 0.680 
# 8  s2 B 2 -0.63 -0.080 0.270 
# 9  s3 A 1  0.88 0.330 0.360 
# 10  s3 A 2  0.32 0.980 0.990 
# 11  s3 B 1  0.29 0.480 0.510 
# 12  s3 B 2  0.26 0.740 0.740 
# 13  s4 A 1  0.63 -0.120 0.040 
# 14  s4 A 2  0.14 0.430 0.620 
# 15  s4 B 1  0.94 0.002 0.090 
# 16  s4 B 2  0.07 0.960 0.960 
# 17  s5 A 1  0.86 -0.055 0.090 
# 18  s5 A 2  0.13 -0.020 0.130 
# 19  s5 B 1  0.93 0.008 0.120 
# 20  s5 B 2  0.87 0.440 0.450 

Answer 4

Use as.data.frame.table. A continuación, puede evitar la carga plyr - desanexar plyr cuando desee utilizar dplyr - cycle.

df0 <- as.data.frame.table(x) 
head(df0) 

# Subject Cond Item  Var4 Freq 
# 1  s1 A 1 Measure1 -0.93 
# 2  s2 A 1 Measure1 0.39 
# 3  s3 A 1 Measure1 0.88 
# 4  s4 A 1 Measure1 0.63 
# 5  s5 A 1 Measure1 0.86 
# 6  s1 B 1 Measure1 -0.69 

library(tidyr) 
df1 <- spread(data = df0, key = Var4, value = Freq) 
head(df1) 

# Subject Cond Item Measure1 Measure2 Measure3 
# 1  s1 A 1 -0.93 -0.360 -0.005 
# 2  s1 A 2 -0.01 -0.190 -0.050 
# 3  s1 B 1 -0.69 0.070 0.170 
# 4  s1 B 2 -0.07 -0.150 0.060 
# 5  s2 A 1  0.39 1.043 1.090 
# 6  s2 A 2  0.79 -1.390 0.110