根据特定变量的存在/不存在创建 TRUE/FALSE 数据框

Question

我有一个数据框，其中包含从不同季节采集的样本。我想总结一下哪些站点有不同年份的春季（3-5 月）和秋季（9-11 月）的样本。例如，如果站点 A 有 2007 年春季的样本，则单元格显示为“真”。这是一个示例数据集：

Dates <- data.frame(c(as.Date("2007-9-1"),
                  rep(as.Date("2008-3-1"), times = 3) , 
                  rep(as.Date("2008-9-1"), times = 3)))
Sites <- as.data.frame(as.factor(c("SiteA",rep(c("SiteA","SiteB","SiteC"), 2))))
Values <- data.frame(matrix(sample(0:50, 3.5*2, replace=TRUE), ncol=1))
Dataframe <- cbind(Dates,Sites,Values)
colnames(Dataframe) <- c("date","site","value")

我已经设法根据这些函数在这个数据框中创建了因子“季节”。

Dataframe$Months <- as.numeric(format(Dataframe$date, '%m'))
Dataframe$Season <- cut(Dataframe$Months, 
                    breaks = c(1, 2, 5, 8, 11, 12), 
                    labels = c("Winter", "Spring", "Summer", "Autumn", "Winter"), 
                    right = FALSE)

但我不确定从这里去哪里。这是输出的样子。

A <- rep("TRUE",times = 3)
B <- c("FALSE",rep("TRUE",times = 2))
C <- c("FALSE",rep("TRUE",times = 2))

Output <- as.data.frame(rbind(A,B,C))
colnames(Output) <- c("Autumn.07","Spring.07","Autumn.08") 

Answer 1

这是一个命题：

Dataframe$Samplings <- interaction(Dataframe$Season, unlist(lapply(strsplit(as.character(Dataframe$date), '-'), function(x) x[[1]]) ))

u1 <- unique(Dataframe$site)
u2 <- unique(Dataframe$Samplings)

output <- matrix(
  matrix(levels(interaction(u1, u2)), nrow=length(unique(Dataframe$site))) %in% 
    interaction(Dataframe$site,Dataframe$Samplings), 
  nrow=length(unique(Dataframe$site))
)

colnames(output) <- levels(Dataframe$Samplings)
rownames(output) <- unique(Dataframe$site)
output # with all time interactions
# you can clear it with 
output[, apply(output, 2, sum) != 0]

Answer 2

使用 reshape2::dcast

Dataframe$site <- gsub("Site","",Dataframe$site)
Dataframe$year <- format(Dataframe$date, "%y")
temp <- reshape2::dcast(Dataframe, site ~ Season + year, length)
(ans <- apply(data.frame(temp[,2:ncol(temp)], row.names=temp[,1]), 1:2, as.logical))

由于标签重复，您的 Dataframe$Season 会出现警告。你可能想解决这个问题。

Answer 3

我认为这就是您要寻找的。时间标签与问题中的不完全一样，但我希望它仍然可以理解。

library(reshape2)

# prepare the input, to have a handy label for the columns
Dataframe$Year <- as.numeric(format(Dataframe$date, '%Y'))
Dataframe$TimeLabel <- paste0(Dataframe$Season, '.', Dataframe$Year)

# This is in stages, to make it clear what's happening.

# create a data frame with the right structure, but cells holding NA / numbers
df1 <- dcast(Dataframe, site ~ TimeLabel)

# turn NA / number into false/true, while ignoring the site column
df2 <- !is.na(df1[, -1])

# add back the site labels for rows
df3 <- cbind(as.data.frame(df1$site), df2)