Question

我有一系列步骤要转换为函数，因此我只需通过调用它就可以将它应用于数据框。以下是带有一些注释的代码：

library("textreadr")
library("pdftools")   
library("tidyverse")
library("tidytext")    
library("textreadr")
library("tm")

# Create Data frame
Off_let_data <- data.frame(page_id = c(3,3,3,3,3), element_id = c(19, 22, 26, 31, 31), 
                                 text = c("The Protected Percentage of your property value thats has been chosen is 0%", 
                                          "The Arrangement Fee payable at complettion: £50.00", 
                                          "The Fixed Interest Rate that is applied for the life of the period is: 5.40%", 
                                          "The Benchmark rate that will be used to calculate any early repayment 2.08%", 
                                          "The property value used in this scenario is 275,000.00"))

# read in the first element of a list of pdf file from a folder
files <- list.files(pattern = "pdf$")[1]

# extract the account number from the first pdf file
acc_num <- str_extract(files, "^\\d+")

# The RegEx's used to extract the relevant information
protec_per_reg <- "Protected\\sP\\w+\\sof"
Arr_Fee_reg <- "^The\\sArrangement\\sF\\w+"
Fix_inter_reg <- "Fixed\\sI\\w+\\sR\\w+"
Bench_rate_reg <- "Benchmark\\sR\\w+\\sthat"

# create a df that only includes the rows which match the above RegEx
Off_let <- Off_let_data %>% filter(page_id == 3, str_detect(Off_let_data$text, protec_per_reg)|
                                     str_detect(Off_let_data$text, Arr_Fee_reg) | str_detect(Off_let_data$text, Fix_inter_reg) | 
                                     str_detect(Off_let_data$text, Bench_rate_reg))

# Now only extract the numbers from the above DF
off_let_num <- str_extract(Off_let$text, "\\d+\\.?\\d+")

# The first element is always a NA value - based on the structure of these PDF files
# replace the first element of this character vector with the below
off_let_num[is.na(off_let_num)] <- str_extract(Off_let$text, "\\d+%")[[1]] 
off_let_num

有人可以帮助我把它变成一个功能。感谢

Answer 1

这样的东西？

该功能的输入/输出应该是什么？目前，该函数仅将data.frame作为参数，但您可以对其进行扩展，因此您可以传递不同的正则表达式，或者例如定义page_id。

library("textreadr")
library("pdftools")   
library("tidyverse")
library("tidytext")    
library("textreadr")
library("tm")

# Create Data frame
Off_let_data <- data.frame(page_id = c(3,3,3,3,3), element_id = c(19, 22, 26, 31, 31), 
                           text = c("The Protected Percentage of your property value thats has been chosen is 0%", 
                                    "The Arrangement Fee payable at complettion: £50.00", 
                                    "The Fixed Interest Rate that is applied for the life of the period is: 5.40%", 
                                    "The Benchmark rate that will be used to calculate any early repayment 2.08%", 
                                    "The property value used in this scenario is 275,000.00"))

dummyFunc <- function(df) {
  # read in the first element of a list of pdf file from a folder
  files <- list.files(pattern = "pdf$")[1]

  # extract the account number from the first pdf file
  acc_num <- str_extract(files, "^\\d+")

  # The RegEx's used to extract the relevant information
  protec_per_reg <- "Protected\\sP\\w+\\sof"
  Arr_Fee_reg <- "^The\\sArrangement\\sF\\w+"
  Fix_inter_reg <- "Fixed\\sI\\w+\\sR\\w+"
  Bench_rate_reg <- "Benchmark\\sR\\w+\\sthat"

  # create a df that only includes the rows which match the above RegEx
  Off_let <- df %>% filter(page_id == 3, str_detect(df$text, protec_per_reg)|
                                       str_detect(df$text, Arr_Fee_reg) | str_detect(df$text, Fix_inter_reg) | 
                                       str_detect(df$text, Bench_rate_reg))

  # Now only extract the numbers from the above DF
  off_let_num <- str_extract(Off_let$text, "\\d+\\.?\\d+")

  # The first element is always a NA value - based on the structure of these PDF files
  # replace the first element of this character vector with the below
  off_let_num[is.na(off_let_num)] <- str_extract(Off_let$text, "\\d+%")[[1]] 
  return(off_let_num)
}

dummyFunc(Off_let_data)

对于该功能的更广泛版本：

# The RegEx's used to extract the relevant information
protec_per_reg <- "Protected\\sP\\w+\\sof"
Arr_Fee_reg <- "^The\\sArrangement\\sF\\w+"
Fix_inter_reg <- "Fixed\\sI\\w+\\sR\\w+"
Bench_rate_reg <- "Benchmark\\sR\\w+\\sthat"

regexprlist <- list(protec_per_reg, Arr_Fee_reg,
                    Fix_inter_reg, Bench_rate_reg)

dummyFuncExt <- function(df, regexp, page_id) {
  # read in the first element of a list of pdf file from a folder
  files <- list.files(pattern = "pdf$")[1]

  # extract the account number from the first pdf file
  acc_num <- str_extract(files, "^\\d+")

  # create a df that only includes the rows which match the above RegEx
  Off_let <- df %>% filter(page_id == page_id, str_detect(df$text, regexprlist[[1]])|
                             str_detect(df$text, regexprlist[[2]]) | str_detect(df$text, regexprlist[[3]]) | 
                             str_detect(df$text, regexprlist[[4]]))

  # Now only extract the numbers from the above DF
  off_let_num <- str_extract(Off_let$text, "\\d+\\.?\\d+")

  # The first element is always a NA value - based on the structure of these PDF files
  # replace the first element of this character vector with the below
  off_let_num[is.na(off_let_num)] <- str_extract(Off_let$text, "\\d+%")[[1]] 
  return(off_let_num)
}

dummyFuncExt(df = Off_let_data, regexp = regexprlist, page_id = 3)

将代码转换为R中的函数

1 个答案: