我需要对一个非常大的csv文件(c.8.5GB)进行一些相对简单的更改。我最初尝试使用各种读取器函数:read.csv,readr :: read.csv,data.table :: fread。但是:它们都耗尽了内存。
我想我需要使用流处理方法;读取一个块,更新它,写入,重复。我发现this answer位于右侧;但是我不知道如何终止循环(我对R来说比较新)。
所以我有两个问题:
目前的代码如下:
src_fname <- "testdata/model_input.csv"
tgt_fname <- "testdata/model_output.csv"
#Changes needed in file: rebase identifiers, set another col to constant value
rebase_data <- function(data, offset) {
data$'Unique Member ID' <- data$'Unique Member ID' - offset
data$'Client Name' <- "TestClient2"
return(data)
}
CHUNK_SIZE <- 1000
src_conn = file(src_fname, "r")
data <- read.csv(src_conn, nrows = CHUNK_SIZE, check.names=FALSE)
cols <- colnames(data)
offset <- data$'Unique Member ID'[1] - 1
data <- rebase_data(data, offset)
#1st time through, write the headers
tgt_conn = file(tgt_fname, "w")
write.csv(data,tgt_conn, row.names=FALSE)
#loop over remaining data
end = FALSE
while(end == FALSE) {
data <- read.csv(src_conn, nrows = CHUNK_SIZE, check.names=FALSE, col.names = cols)
data <- rebase_data(data, offset)
#write.csv doesn't support col.names=FALSE; so use write.table which does
write.table(data, tgt_conn, row.names=FALSE, col.names=FALSE, sep=",")
# ??? How to test for EOF and set end = TRUE if so ???
# This doesn't work, presumably because nrow() != CHUNK_SIZE on final loop?
if (nrow(data) < CHUNK_SIZE) {
end <- TRUE
}
}
close(src_conn)
close(tgt_conn)
感谢您的任何指示。
答案 0 :(得分:1)
试试这个:
library("chunked")
read_chunkwise(src_fname, chunk_size=CHUNK_SIZE) %>%
rebase_data(offset) %>%
write_chunkwise(tgt_fname)
您可能需要对字母进行一些调整以获得您想要的内容。
(免责声明:没有尝试过代码)
请注意,包中没有插图但标准用法在github上有描述:https://github.com/edwindj/chunked/
答案 1 :(得分:0)
好的,我找到了一个解决方案,如下:
# src_fname <- "testdata/model_input.csv"
# tgt_fname <- "testdata/model_output.csv"
CHUNK_SIZE <- 20000
#Changes needed in file: rebase identifiers, set another col to constant value
rebase_data <- function(data, offset) {
data$'Unique Member ID' <- data$'Unique Member ID' - offset
data$'Client Name' <- "TestClient2"
return(data)
}
#--------------------------------------------------------
# Get the structure first to speed things up
#--------------------------------------------------------
structure <- read.csv(src_fname, nrows = 2, check.names = FALSE)
cols <- colnames(structure)
offset <- structure$'Unique Member ID'[1] - 1
#Open the input & output files for reading & writing
src_conn = file(src_fname, "r")
tgt_conn = file(tgt_fname, "w")
lines_read <- 0
end <- FALSE
read_header <- TRUE
write_header <- TRUE
while(end == FALSE) {
data <- read.csv(src_conn, nrows = CHUNK_SIZE, check.names=FALSE, col.names = cols, header = read_header)
if (nrow(data) > 0) {
lines_read <- lines_read + nrow(data)
print(paste0("lines read this chunk: ", nrow(data), ", lines read so far: ", lines_read))
data <- rebase_data(data, offset)
#write.csv doesn't support col.names=FALSE; so use write.table which does
write.table(data, tgt_conn, row.names=FALSE, col.names=write_header, sep = ",")
}
if (nrow(data) < CHUNK_SIZE) {
end <- TRUE
}
read_header <- FALSE
write_header <- FALSE
}
close(src_conn)
close(tgt_conn)
答案 2 :(得分:0)
很抱歉戳了2年的线程,但是现在在setHasOptionsMenu(true);
内,我们还可以这样做:
tidyverse
这里最棘手的部分是根据参数require(tidyverse)
src_fname = "testdata/model_input.csv"
tgt_fname = "testdata/model_output.csv"
CHUNK_SIZE = 1000
offset = read_csv(src_fname, n_max=1)$comm_code %>% as.numeric() - 1
rebase.chunk = function(df, pos) {
df$comm_code = df$comm_code %>% as.numeric() - offset
df$'Client Name' = "TestClient2"
is.append = ifelse(pos > 1, T, F)
df %>% write_csv(
tgt_fname,
append=is.append
)
}
read_csv_chunked(
src_fname,
callback=SideEffectChunkCallback$new(rebase.chunk),
chunk_size = chunck.size,
progress = T # optional, show progress bar
)
设置is.append
,该参数表示原始文件中数据帧pos
的起始行号。在readr::write_csv
中,当df
时,标头(列名)将被写入文件,否则不会被写入。