R语言数据重塑知识点总结

# Create vector objects.
city <- c("Tampa","Seattle","Hartford","Denver")
state <- c("FL","WA","CT","CO")
zipcode <- c(33602,98104,06161,80294)

# Combine above three vectors into one data frame.
addresses <- cbind(city,state,zipcode)

# Print a header.
cat("# # # # The First data frame
") 

# Print the data frame.
print(addresses)

# Create another data frame with similar columns
new.address <- data.frame(
  city = c("Lowry","Charlotte"),
  state = c("CO","FL"),
  zipcode = c("80230","33949"),
  stringsAsFactors = FALSE
)

# Print a header.
cat("# # # The Second data frame
") 

# Print the data frame.
print(new.address)

# Combine rows fORM both the data frames.
all.addresses <- rbind(addresses,new.address)

# Print a header.
cat("# # # The combined data frame
") 

# Print the result.
print(all.addresses)

# # # # The First data frame
   city    state zipcode
[1,] "Tampa"  "FL" "33602"
[2,] "Seattle" "WA" "98104"
[3,] "Hartford" "CT"  "6161" 
[4,] "Denver"  "CO" "80294"

# # # The Second data frame
    city    state  zipcode
1   Lowry   CO   80230
2   Charlotte FL   33949

# # # The combined data frame
    city   state zipcode
1   Tampa   FL  33602
2   Seattle  WA  98104
3   Hartford CT   6161
4   Denver  CO  80294
5   Lowry   CO  80230
6   Charlotte FL  33949

library(MASS)
merged.Pima <- merge(x = Pima.te, y = Pima.tr,
  by.x = c("bp", "bmi"),
  by.y = c("bp", "bmi")
)
print(merged.Pima)
nrow(merged.Pima)

  bp bmi npreg.x glu.x skin.x ped.x age.x type.x npreg.y glu.y skin.y ped.y
1 60 33.8    1  117   23 0.466  27   No    2  125   20 0.088
2 64 29.7    2  75   24 0.370  33   No    2  100   23 0.368
3 64 31.2    5  189   33 0.583  29  Yes    3  158   13 0.295
4 64 33.2    4  117   27 0.230  24   No    1  96   27 0.289
5 66 38.1    3  115   39 0.150  28   No    1  114   36 0.289
6 68 38.5    2  100   25 0.324  26   No    7  129   49 0.439
7 70 27.4    1  116   28 0.204  21   No    0  124   20 0.254
8 70 33.1    4  91   32 0.446  22   No    9  123   44 0.374
9 70 35.4    9  124   33 0.282  34   No    6  134   23 0.542
10 72 25.6    1  157   21 0.123  24   No    4  99   17 0.294
11 72 37.7    5  95   33 0.370  27   No    6  103   32 0.324
12 74 25.9    9  134   33 0.460  81   No    8  126   38 0.162
13 74 25.9    1  95   21 0.673  36   No    8  126   38 0.162
14 78 27.6    5  88   30 0.258  37   No    6  125   31 0.565
15 78 27.6   10  122   31 0.512  45   No    6  125   31 0.565
16 78 39.4    2  112   50 0.175  24   No    4  112   40 0.236
17 88 34.5    1  117   24 0.403  40  Yes    4  127   11 0.598
  age.y type.y
1   31   No
2   21   No
3   24   No
4   21   No
5   21   No
6   43  Yes
7   36  Yes
8   40   No
9   29  Yes
10  28   No
11  55   No
12  39   No
13  39   No
14  49  Yes
15  49  Yes
16  38   No
17  28   No
[1] 17

 Status  Age  V1   V2   V3  V4
   P 23646 45190 50333 55166 56271
   CC 26174 35535 38227 37911 41184
   CC 27723 25691 25712 26144 26398
   CC 27193 30949 29693 29754 30772
   CC 24370 50542 51966 54341 54273
   CC 28359 58591 58803 59435 61292
   CC 25136 45801 45389 47197 47126

zz <- read.csv("mr.csv", strip.white = TRUE)
zzz <- cbind(zz[gl(nrow(zz), 1, 4*nrow(zz)), 1:2], stack(zz[, 3:6]))

   Status  Age values ind
X1     P 23646 45190 V1
X2    CC 26174 35535 V1
X3    CC 27723 25691 V1
X4    CC 27193 30949 V1
X5    CC 24370 50542 V1
X6    CC 28359 58591 V1
X7    CC 25136 45801 V1
X11    P 23646 50333 V2
...

> reshape(zz, idvar="id",timevar="var",
 varying=list(c("V1","V2","V3","V4")),direction="long")
  Status  Age var  V1 id
1.1   P 23646  1 45190 1
2.1   CC 26174  1 35535 2
3.1   CC 27723  1 25691 3
4.1   CC 27193  1 30949 4
5.1   CC 24370  1 50542 5
6.1   CC 28359  1 58591 6
7.1   CC 25136  1 45801 7
1.2   P 23646  2 50333 1
2.2   CC 26174  2 38227 2
...