R 将数据转换为不精确分析的正确格式

我计划使用iNEXT函数（来自iNEXT包）分析两种池塘类型之间的潜在差异。这些数据是存在/不存在的，并且是按物种矩阵划分的站点中的数据，例如

Pond.type <- c("A", "A", "A", "B", "B", "B")
Sample.no <- c(1,2,3,1,2,3)
Species1 <- c(0,1,1,1,0,0)
Species2 <- c(0,1,1,0,1,0)
Species3 <- c(1,1,1,1,0,1)
Species4 <- c(0,1,0,1,0,0)
Species5 <- c(1,1,1,0,0,0)

mydata <- cbind.data.frame(Pond.type, Sample.no, Species1, Species2, Species3, Species4, Species5)

---

Pond.type如果您有这样的2.csv结构

A型池塘：

Species, Sample1, Sample2, Sample3
Species1, 0,1,1
Species2, 0,1,1
Species3, 1,1,1
Species4, 0,1,0
Species5, 1,1,1

B类池塘：

Species, Sample1, Sample2, Sample3
Species1, 1,0,0
Species2, 0,1,0
Species3, 1,0,1
Species4, 1,0,0
Species5, 0,0,0

然后假设您调用“读取csv”的pondA和pondB，您可以执行以下操作：

library(iNEXT)
library(ggplot2)

# make a matrix from pondA as type "integer"
mPondA <- as.matrix(apply(pondA[,-1],2,as.integer))

# use your species names as row names
row.names(mPondA) <- pondA[,1]

# do the same for pondB
mPondB <- as.matrix(apply(pondB[,-1],2,as.integer))
row.names(mPondB) <- pondB[,1]

# create a list of your matrices (named so the output looks nice)
pondABM = list(A = mPondA, B = mPondB)

# have a look at the raw data
out.raw <- iNEXT(pondABM, datatype="incidence_raw", endpoint=20)
ggiNEXT(out.raw)

如果你有这样的2.csv结构

A型池塘：

Species, Sample1, Sample2, Sample3
Species1, 0,1,1
Species2, 0,1,1
Species3, 1,1,1
Species4, 0,1,0
Species5, 1,1,1

B类池塘：

Species, Sample1, Sample2, Sample3
Species1, 1,0,0
Species2, 0,1,0
Species3, 1,0,1
Species4, 1,0,0
Species5, 0,0,0

然后假设您调用“读取csv”的pondA和pondB，您可以执行以下操作：

library(iNEXT)
library(ggplot2)

# make a matrix from pondA as type "integer"
mPondA <- as.matrix(apply(pondA[,-1],2,as.integer))

# use your species names as row names
row.names(mPondA) <- pondA[,1]

# do the same for pondB
mPondB <- as.matrix(apply(pondB[,-1],2,as.integer))
row.names(mPondB) <- pondB[,1]

# create a list of your matrices (named so the output looks nice)
pondABM = list(A = mPondA, B = mPondB)

# have a look at the raw data
out.raw <- iNEXT(pondABM, datatype="incidence_raw", endpoint=20)
ggiNEXT(out.raw)

我找到了一个解决方案，可能比它需要的更冗长，但它是有效的

# I've altered the dataset as I usually type these data in long format
Pond.type <- c(rep("A", 15), rep("B", 15)) 
Site.no <- rep(seq(1,6, by=1), 5)
Species <- c(rep("Spp1", 6), rep("Spp2", 6), rep("Spp3", 6), rep("Spp4", 6), rep("Spp5", 6))
Presence <- rep(1, 30)

# join the vectors together into a dataframe
mydata.long <- cbind.data.frame(Pond.type, Site.no, Species, Presence)

# I then cast the data into a species x site matrix (dcast is from the reshape2 library)
mydata.cast <- dcast(mydata.long, Species + Pond.type ~ Site.no)

# Changes the NAs to zeros. 
mydata.cast[is.na(mydata.cast)] <- 0

# Separate the dataframe into each pond tyoe
pondA <- mydata.cast[grep("A", mydata.cast$Pond.type),]
pondB <- mydata.cast[grep("B", mydata.cast$Pond.type),]

# Calculate the frequency counts using the  function from the iNEXT library
pondA.freq <- as.incfreq(pondA[,3:ncol(pondA)])
pondB.freq <- as.incfreq(pondB[,3:ncol(pondB)])

# join them as a list
pond.list = list(A = pondA.freq, B = pondB.freq)

# ready for comparison
pond.out <- iNEXT(pond.list, datatype = "incidence_freq", q=0)
pond.out

#我更改了数据集，因为我通常以长格式键入这些数据
Pond.type我找到了一个解决方案，可能比它需要的更冗长，但它是有效的

# I've altered the dataset as I usually type these data in long format
Pond.type <- c(rep("A", 15), rep("B", 15)) 
Site.no <- rep(seq(1,6, by=1), 5)
Species <- c(rep("Spp1", 6), rep("Spp2", 6), rep("Spp3", 6), rep("Spp4", 6), rep("Spp5", 6))
Presence <- rep(1, 30)

# join the vectors together into a dataframe
mydata.long <- cbind.data.frame(Pond.type, Site.no, Species, Presence)

# I then cast the data into a species x site matrix (dcast is from the reshape2 library)
mydata.cast <- dcast(mydata.long, Species + Pond.type ~ Site.no)

# Changes the NAs to zeros. 
mydata.cast[is.na(mydata.cast)] <- 0

# Separate the dataframe into each pond tyoe
pondA <- mydata.cast[grep("A", mydata.cast$Pond.type),]
pondB <- mydata.cast[grep("B", mydata.cast$Pond.type),]

# Calculate the frequency counts using the  function from the iNEXT library
pondA.freq <- as.incfreq(pondA[,3:ncol(pondA)])
pondB.freq <- as.incfreq(pondB[,3:ncol(pondB)])

# join them as a list
pond.list = list(A = pondA.freq, B = pondB.freq)

# ready for comparison
pond.out <- iNEXT(pond.list, datatype = "incidence_freq", q=0)
pond.out

#我更改了数据集，因为我通常以长格式键入这些数据
Pond.type我试过Oliver Burdekin的答案，效果很好-谢谢

如果使用大量数据，则需要添加一个函数-在运行iNEXT函数之前，将as.abucount函数应用于矩阵列表

# create a list of your matrices (named so the output looks nice)
pondABM = list(A = mPondA, B = mPondB)

# apply as.abucount to the list of matrices
pondABM2 = lapply(pondABM, as.abucount)

# run the iNEXT function
iNEXT(pondABM2, datatype="abundance")

我尝试了奥利弗·伯德金的答案，效果很好——谢谢

如果使用大量数据，则需要添加一个函数-在运行iNEXT函数之前，将as.abucount函数应用于矩阵列表

# create a list of your matrices (named so the output looks nice)
pondABM = list(A = mPondA, B = mPondB)

# apply as.abucount to the list of matrices
pondABM2 = lapply(pondABM, as.abucount)

# run the iNEXT function
iNEXT(pondABM2, datatype="abundance")

你能把它们分成两个矩阵吗？一个用于A型池塘（sampleNo 1、2、3），一个用于B型池塘（sampleNo 1、2、3）。然后你可以比较A型和B型。你能把它们分成两个矩阵吗？一个用于A型池塘（sampleNo 1、2、3），一个用于B型池塘（sampleNo 1、2、3）。然后你就可以比较A型和B型了。我找到了一个非常相似的解决方案，我会发布，谢谢！我找到了一个非常类似的解决方案，我会发布，谢谢！