循环文件，NetCDF 操作

Question

我正在尝试为数百个 NetCDF 文件执行以下代码，并将每个文件的此代码的结果组合在一起。

  library(raster)
  b <- brick('CA.195001.nc')
  be <- crop(b, extent(-177.0170, -117.2690, 32.7191, 32.9753)) 
  a <- aggregate(be, dim(be)[2:1], na.rm=TRUE)
  v <- values(a)

  #get date
  date <- getZ(be)

  df <- data.frame(date=date, prec=t(v)) 
  rownames(df) <- c()
  df


  df$date<- as.Date(df$date, "%m/%d/%Y") #Add dates
  df$year <- as.numeric(format(df$date, format = "%Y"))
  df$month <- as.numeric(format(df$date, format = "%m"))
  df$day <- as.numeric(format(df$date, format = "%d"))

我对循环比较陌生，并没有找到太多有用的指导。以下有助于识别文件，但我不太确定如何循环执行上述操作：

files <- list.files(path="mypath", pattern="*.nc", full.names=T, 
recursive=FALSE)
lapply(files, function(x) { 
}

谢谢！

Answer 1

您可以将代码放入一个函数中，然后使用 lapply 或 purrr:map_df 将该函数应用于所有 NetCDF 文件

library(raster)

read_ncdf <- function(input_NetCDF_file) {
  b  <- brick(input_NetCDF_file)
  be <- crop(b, extent(-177.0170, -117.2690, 32.7191, 32.9753)) 
  a  <- aggregate(be, dim(be)[2:1], na.rm=TRUE)
  v  <- values(a)

  #get date
  date <- getZ(be)

  df <- data.frame(date=date, prec=t(v)) 
  rownames(df) <- c()

  df$date<- as.Date(df$date, "%m/%d/%Y") #Add dates
  df$year <- as.numeric(format(df$date, format = "%Y"))
  df$month <- as.numeric(format(df$date, format = "%m"))
  df$day <- as.numeric(format(df$date, format = "%d"))

  return(df)
}

列出mypath中的所有NetCDF文件

files <- list.files(path = "mypath", pattern = "\\.nc$", full.names = TRUE, 
                recursive = FALSE)

使用lapply

result <- lapply(files, function(x) { read_ncdf(x) })
# rbind all together 
result_df <- do.call("rbind", result) 

使用purrr::map_df

library(tidyverse)
# Loop through all the files using map_df, read data 
# and create a FileName column to store filenames
# Then clean up filename: remove file path and extension
result_purrr <- files %>%
  purrr::set_names(nm = (basename(.) %>% tools::file_path_sans_ext())) %>%
  purrr::map_df(read_ncdf, .id = "FileName")