只读取选定的列

Question

谁能告诉我如何只读取以下数据中每年的前 6 个月（7 列），例如使用read.table()？

Year   Jan  Feb  Mar  Apr  May  Jun  Jul  Aug  Sep  Oct  Nov  Dec   
2009   -41  -27  -25  -31  -31  -39  -25  -15  -30  -27  -21  -25
2010   -41  -27  -25  -31  -31  -39  -25  -15  -30  -27  -21  -25 
2011   -21  -27   -2   -6  -10  -32  -13  -12  -27  -30  -38  -29

Answer 1

假设数据在文件data.txt 中，您可以使用read.table() 的colClasses 参数来跳过列。这里前7列的数据是"integer"，我们将剩下的6列设置为"NULL"，表示应该跳过它们

> read.table("data.txt", colClasses = c(rep("integer", 7), rep("NULL", 6)), 
+            header = TRUE)
  Year Jan Feb Mar Apr May Jun
1 2009 -41 -27 -25 -31 -31 -39
2 2010 -41 -27 -25 -31 -31 -39
3 2011 -21 -27  -2  -6 -10 -32

根据实际数据类型，将"integer" 更改为?read.table 中详述的可接受类型之一。

data.txt 看起来像这样：

$ cat data.txt 
"Year" "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"
2009 -41 -27 -25 -31 -31 -39 -25 -15 -30 -27 -21 -25
2010 -41 -27 -25 -31 -31 -39 -25 -15 -30 -27 -21 -25
2011 -21 -27 -2 -6 -10 -32 -13 -12 -27 -30 -38 -29

并且是通过使用创建的

write.table(dat, file = "data.txt", row.names = FALSE)

dat 在哪里

dat <- structure(list(Year = 2009:2011, Jan = c(-41L, -41L, -21L), Feb = c(-27L, 
-27L, -27L), Mar = c(-25L, -25L, -2L), Apr = c(-31L, -31L, -6L
), May = c(-31L, -31L, -10L), Jun = c(-39L, -39L, -32L), Jul = c(-25L, 
-25L, -13L), Aug = c(-15L, -15L, -12L), Sep = c(-30L, -30L, -27L
), Oct = c(-27L, -27L, -30L), Nov = c(-21L, -21L, -38L), Dec = c(-25L, 
-25L, -29L)), .Names = c("Year", "Jan", "Feb", "Mar", "Apr", 
"May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"), class = "data.frame",
row.names = c(NA, -3L))

如果事先不知道列数，实用函数count.fields 将读取文件并计算每行中的字段数。

## returns a vector equal to the number of lines in the file
count.fields("data.txt", sep = "\t")
## returns the maximum to set colClasses
max(count.fields("data.txt", sep = "\t"))

Answer 2

您也可以使用 JDBC 来实现这一点。让我们创建一个示例 csv 文件。

write.table(x=mtcars, file="mtcars.csv", sep=",", row.names=F, col.names=T) # create example csv file

从此链接下载并保存 CSV JDBC 驱动程序：http://sourceforge.net/projects/csvjdbc/files/latest/download

> library(RJDBC)

> path.to.jdbc.driver <- "jdbc//csvjdbc-1.0-18.jar"
> drv <- JDBC("org.relique.jdbc.csv.CsvDriver", path.to.jdbc.driver)
> conn <- dbConnect(drv, sprintf("jdbc:relique:csv:%s", getwd()))

> head(dbGetQuery(conn, "select * from mtcars"), 3)
   mpg cyl disp  hp drat    wt  qsec vs am gear carb
1   21   6  160 110  3.9  2.62 16.46  0  1    4    4
2   21   6  160 110  3.9 2.875 17.02  0  1    4    4
3 22.8   4  108  93 3.85  2.32 18.61  1  1    4    1

> head(dbGetQuery(conn, "select mpg, gear from mtcars"), 3)
   MPG GEAR
1   21    4
2   21    4
3 22.8    4

Answer 3

要从数据集中读取一组特定的列，还有其他几个选项：

1) 使用fread来自data.table-package：

您可以使用来自data.table 包的fread 中的select 参数指定所需的列。您可以使用包含列名或列号的向量来指定列。

对于示例数据集：

library(data.table)
dat <- fread("data.txt", select = c("Year","Jan","Feb","Mar","Apr","May","Jun"))
dat <- fread("data.txt", select = c(1:7))

或者，您可以使用drop 参数来指示不应读取哪些列：

dat <- fread("data.txt", drop = c("Jul","Aug","Sep","Oct","Nov","Dec"))
dat <- fread("data.txt", drop = c(8:13))

所有结果：

> data
  Year Jan Feb Mar Apr May Jun
1 2009 -41 -27 -25 -31 -31 -39
2 2010 -41 -27 -25 -31 -31 -39
3 2011 -21 -27  -2  -6 -10 -32

更新：当您不希望 fread 返回 data.table 时，请使用 data.table = FALSE 参数，例如：fread("data.txt", select = c(1:7), data.table = FALSE)

2) 使用来自sqldf-package 的read.csv.sql：

另一种选择是sqldf 包中的read.csv.sql 函数：

library(sqldf)
dat <- read.csv.sql("data.txt",
                    sql = "select Year,Jan,Feb,Mar,Apr,May,Jun from file",
                    sep = "\t")

3) 使用 readr-package 中的 read_*-functions：

library(readr)
dat <- read_table("data.txt",
                  col_types = cols_only(Year = 'i', Jan = 'i', Feb = 'i', Mar = 'i',
                                        Apr = 'i', May = 'i', Jun = 'i'))
dat <- read_table("data.txt",
                  col_types = list(Jul = col_skip(), Aug = col_skip(), Sep = col_skip(),
                                   Oct = col_skip(), Nov = col_skip(), Dec = col_skip()))
dat <- read_table("data.txt", col_types = 'iiiiiii______')

从文档中对col_types中使用的字符的解释：

每个字符代表一列：c = 字符，i = 整数，n = 数字，d = 双精度，l = 逻辑，D = 日期，T = 日期时间，t = 时间，？ = 猜测，或 _/- 跳过该列

Answer 4

你这样做：

df = read.table("file.txt", nrows=1, header=TRUE, sep="\t", stringsAsFactors=FALSE)
colClasses = as.list(apply(df, 2, class))
needCols = c("Year", "Jan", "Feb", "Mar", "Apr", "May", "Jun")
colClasses[!names(colClasses) %in% needCols] = list(NULL)
df = read.table("file.txt", header=TRUE, colClasses=colClasses, sep="\t", stringsAsFactors=FALSE)

Answer 5

vroom package 提供了一种在导入期间按名称选择/删除列的“整洁”方法。文档：https://www.tidyverse.org/blog/2019/05/vroom-1-0-0/#column-selection

列选择（col_select）

vroom 参数“col_select”使选择要保留（或省略）的列更加直接。 col_select 的接口与 dplyr::select() 相同。

按名称选择列

data <- vroom("flights.tsv", col_select = c(year, flight, tailnum))
#> Observations: 336,776
#> Variables: 3
#> chr [1]: tailnum
#> dbl [2]: year, flight
#> 
#> Call `spec()` for a copy-pastable column specification
#> Specify the column types with `col_types` to quiet this message

按名称删除列

data <- vroom("flights.tsv", col_select = c(-dep_time, -air_time:-time_hour))
#> Observations: 336,776
#> Variables: 13
#> chr [4]: carrier, tailnum, origin, dest
#> dbl [9]: year, month, day, sched_dep_time, dep_delay, arr_time, sched_arr_time, arr...
#> 
#> Call `spec()` for a copy-pastable column specification
#> Specify the column types with `col_types` to quiet this message
Use the selection helpers
data <- vroom("flights.tsv", col_select = ends_with("time"))
#> Observations: 336,776
#> Variables: 5
#> dbl [5]: dep_time, sched_dep_time, arr_time, sched_arr_time, air_time
#> 
#> Call `spec()` for a copy-pastable column specification
#> Specify the column types with `col_types` to quiet this message

或按名称重命名列

data <- vroom("flights.tsv", col_select = list(plane = tailnum, everything()))
#> Observations: 336,776
#> Variables: 19
#> chr  [ 4]: carrier, tailnum, origin, dest
#> dbl  [14]: year, month, day, dep_time, sched_dep_time, dep_delay, arr_time, sched_arr...
#> dttm [ 1]: time_hour
#> 
#> Call `spec()` for a copy-pastable column specification
#> Specify the column types with `col_types` to quiet this message
data
#> # A tibble: 336,776 x 19
#>    plane  year month   day dep_time sched_dep_time dep_delay arr_time
#>    <chr> <dbl> <dbl> <dbl>    <dbl>          <dbl>     <dbl>    <dbl>
#>  1 N142…  2013     1     1      517            515         2      830
#>  2 N242…  2013     1     1      533            529         4      850
#>  3 N619…  2013     1     1      542            540         2      923
#>  4 N804…  2013     1     1      544            545        -1     1004
#>  5 N668…  2013     1     1      554            600        -6      812
#>  6 N394…  2013     1     1      554            558        -4      740
#>  7 N516…  2013     1     1      555            600        -5      913
#>  8 N829…  2013     1     1      557            600        -3      709
#>  9 N593…  2013     1     1      557            600        -3      838
#> 10 N3AL…  2013     1     1      558            600        -2      753
#> # … with 336,766 more rows, and 11 more variables: sched_arr_time <dbl>,
#> #   arr_delay <dbl>, carrier <chr>, flight <dbl>, origin <chr>,
#> #   dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
#> #   time_hour <dttm>