使用循环处理和格式化多个.csv文件

问题描述 投票：0回答：1

我有一堆csv文件，我正在读入R.

以下是帮助此查询的示例数据。

ABC_H <- structure(list(Name = c("Jim Smith", "John Doe"), user_id = c(23L, 25L), sales = c(300L, 140L), shape = c(6L, 200L), size = c(402L, 305L)),row.names= c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list(cols = list(Name = structure(list(), class = c("collector_character", "collector")), user_id = structure(list(), class = c("collector_integer", "collector")), sales = structure(list(), class = c("collector_integer", "collector")), shape = structure(list(), class = c("collector_integer", "collector")), size = structure(list(), class = c("collector_integer", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
BCD_H <- structure(list(Name = c("Jim Smith", "John Doe"), user_id = c(23L, 25L), sales = c(190L, 120L), shape = c(10L, 5L), size = c(500L, 200L)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"), spec =structure(list(cols = list(Name = structure(list(), class = c("collector_character", "collector")), user_id = structure(list(), class = c("collector_integer", "collector")), sales = structure(list(), class = c("collector_integer", "collector")), shape = structure(list(), class = c("collector_integer", "collector")), size = structure(list(), class = c("collector_integer", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
XYZ_H <- structure(list(Name = c("Jim Smith", "John Doe"), user_id = c(23L, 25L), sales = c(190L, 120L), shape = c(10L, 5L), size = c(500L, 200L)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"), spec =structure(list(cols = list(Name = structure(list(), class = c("collector_character", "collector")), user_id = structure(list(), class = c("collector_integer", "collector")), sales = structure(list(), class = c("collector_integer", "collector")), shape = structure(list(), class = c("collector_integer", "collector")), size = structure(list(), class = c("collector_integer", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))

ABC_P <- structure(list(Name = c("Alex Smith", "John Curry"), user_id = c(102L, 433L), color = c(164L, 153L), number = c(20L, 3L), scale = c(6L, 1L)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list(cols = list(Name = structure(list(), class = c("collector_character", "collector")), user_id = structure(list(), class = c("collector_integer", "collector")), color = structure(list(), class = c("collector_integer", "collector")), number = structure(list(), class = c("collector_integer", "collector")), scale = structure(list(), class = c("collector_integer", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
BCD_P <- structure(list(Name = c("Alex Smith", "John Curry"), user_id = c(102L, 433L), color = c(300L, 200L), number = c(100L, 4L), scale = c(2L, 5L)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list(cols = list(Name = structure(list(), class = c("collector_character", "collector")), user_id = structure(list(), class = c("collector_integer", "collector")), color = structure(list(), class = c("collector_integer", "collector")), number = structure(list(), class = c("collector_integer", "collector")), scale = structure(list(), class = c("collector_integer", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))
XYZ_P <- structure(list(Name = c("Alex Smith", "John Curry"), user_id = c(102L, 433L), color = c(300L, 200L), number = c(100L, 4L), scale = c(2L, 5L)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"), spec = structure(list(cols = list(Name = structure(list(), class = c("collector_character", "collector")), user_id = structure(list(), class = c("collector_integer", "collector")), color = structure(list(), class = c("collector_integer", "collector")), number = structure(list(), class = c("collector_integer", "collector")), scale = structure(list(), class = c("collector_integer", "collector"))), default = structure(list(), class = c("collector_guess", "collector"))), class = "col_spec"))

我使用的命名约定基于文件名。

这是我目前用于加载.csv文件的手动代码的示例。还有其他几个csv文件。工作目录加载在脚本的顶部。

ABC_H <- read_csv(file.path(getwd(), "input_data","ABC_H_2018.csv"))
ABC_P <- read_csv(file.path(getwd(), "input_data","ABC_P_2018.csv"))
BCD_H <- read_csv(file.path(getwd(), "input_data","BCD_H_2018.csv"))
BCD_P <- read_csv(file.path(getwd(), "input_data","BCD_P_2018.csv"))
XYZ_H <- read_csv(file.path(getwd(), "input_data","XYZ_H_2018.csv"))
XYZ_P <- read_csv(file.path(getwd(), "input_data","XYZ_P_2018.csv"))

然后我使用dplyr单独格式化每个文件。包含后缀“H”的所有文件将使用相同的列进行格式化，并且包含“P”的所有文件将使用相同的列进行格式化。这是我前两个带有后缀“H”的dplyr代码示例。

ABC_H_formatted <- ABC_H %>%
mutate(data_source = "ABC")%>%
rename(user_id = user)%>%
select(user_id, Name, data_source, size, shape, sales)

BCD_H_formatted <- BCD_H %>%
mutate(data_source = "BCD")%>%
rename(user_id = user)%>%
select(user_id, Name, data_source, size, shape, sales)


XYZ_H_formatted <- BCD_H %>%
mutate(data_source = "BCD")%>%
rename(user_id = user)%>%
select(user_id, Name, data_source, size, shape, sales)

ABC_P_formatted <- ABC_P %>%
mutate(data_source = "ABC")%>%
rename(user_id = user)%>%
select(user_id, Name, data_source, color, number, scale)

BCD_P_formatted <- BCD_P %>%
mutate(data_source = "BCD")%>%
rename(user_id = user)%>%
select(user_id, Name, data_source, color, number, scale)

XYZ_P_formatted <- XYZ_P %>%
mutate(data_source = "XYZ")%>%
rename(user_id = user)%>%
select(user_id, Name, data_source, color, number, scale)

这就是我想做的事情。

  1. 创建2个循环，一个用于带有_H后缀的所有文件，一个用于带有_P后缀的所有文件
  2. 根据文件名创建data_source列（如上所示）
  3. 为每个文件选择上面列出的列
  4. 为所有_H创建一个data.frame，为_P创建一个

提前致谢！

r loops dplyr lapply
1个回答
1
投票

这是您真正想到编写自定义函数以执行所需操作然后将该函数应用于对象列表的想法。这是迭代通常在R中接近的方式。

由于你已经在使用dplyr，我将展示一种tidyverse方法（但这也很容易在基础R中完成）。创建一个执行所需处理步骤的函数，并分配后缀和data_source列（从文件名中提取一些正则表达式和stringr）。

然后，您将需要从目录中获取文件列表，使用匹配模式获取所有文件，而不是手动输入每个文件。

最后，我们使用来自map_df的purrr将read_data函数“映射”到列表中的每个文件，然后将所有结果绑定到一个数据框中。这不会产生您希望的两个数据框，但是使用suffix列，您可​​以轻松地将每个数据分组。

您可能会遇到一些错误，因为我没有您的数据来测试它。将来，最好能够制作一个可重复的问题示例，以便我们更好地帮助您！

library(tidyverse) #dplyr, purrr, stringr, readr

read_data <- function(file) {

  name <- basename(file)

  suffix <- str_extract(name, "(?<=_)[HP]")

  data_source <- str_extact(name, "[A-Z]+(?=_)")

  if (suffix == "P") {
    cols <- c("suffix", "user_id", "Name", "data_source", "color", "number", "scale")
  } 

  if (suffix == "H") {
    cols <- c("suffix", "user_id", "Name", "data_source", "size", "shape", "sales")
  }

  read_csv(file) %>% 
    rename(user_id = user) %>% 
    mutate(datar_source = data_source,
           suffix = suffix) %>% 
    select(one_of(cols))

}
files <- dir(file.path(getwd(), "input_data"), pattern = "ABC|BCD", full.names = TRUE)

result <- map_df(files, read_data)
最新问题
© www.soinside.com 2019 - 2024. All rights reserved.