在 R 中，如何遍历 csv 文件并将线性回归的输出保存在新的数据框中？

Question

我的脚本和前 3 个 csv 文件之一可以在我的 Github 文件夹中找到

我已将 NDVI 和气候数据列表拆分为小 csv。每个文件都有 34 年的数据。

然后应根据冲突年份将每 34 年分为两部分，保存在同一张表和特定时间范围内。但是这部分代码已经可以了。

现在我想用第一部分的气候数据来控制列表的第二部分，通过使用多元线性回归，这也是这样做的。

我基本上需要做一个循环来存储一个csv的lm函数每一轮的所有系数。新列表中的文件。

我知道我可以使用 lapply 循环并将输出作为列表获取。但是有一些缺失的部分实际上循环通过 csv。文件。

#load libraries
library(ggplot2)
library(readr)
library(tidyr)
library(dplyr)
library(ggpubr)
library(plyr)
library(tidyverse)
library(fs)


file_paths <- fs::dir_ls("E:\\PYTHON_ST\\breakCSV_PYTHON\\AIM_2_regions\\Afghanistan")
file_paths

#create empty list and fill with file paths and loop through them
file_contents <- list()
for (i in seq_along(file_paths)) { #seq_along for vectors (list of file paths is a vector)
  file_contents[[i]] <- read_csv(file = file_paths[[i]])
                  
                for (i in seq_len(file_contents[[i]])){ # redundant?
                  
                 # do all the following steps in every file                                        
                 
                 # Step 1) 
                 # Define years to divide table
                 
                 #select conflict year in df 
                 ConflictYear = file_contents[[i]][1,9]
                 ConflictYear
                 
                 # select Start year of regression in df
                 SlopeYears = file_contents[[i]][1,7] #to get slope years (e.g.17)
                 BCStartYear = ConflictYear-SlopeYears #to get start year for regression
                 BCStartYear
                 
                 #End year of regression
                 ACEndYear = ConflictYear+(SlopeYears-1) # -1 because the conflict year is included
                 ACEndYear
                 
                 
                 # Step 2
                 
                 #select needed rows from df
                 #no headers but row numbers. NDVI.Year = [r1-r34,c2]
                 NDVI.Year <- file_contents[[i]][1:34,2]
                 NDVI <- file_contents[[i]][1:34,21]
                 T.annual.max <- file_contents[[i]][1:34,19]
                 Prec.annual.max <- file_contents[[i]][1:34,20]
                 soilM.annual.max <- file_contents[[i]][1:34,18]
                 
                 #Define BeforeConf and AfterConf depending on Slope Year number and Conflict Years
                 #Go through NDVI.Year till Conflict.Year (-1 year) since the conflict year is not included in bc
                 BeforeConf1 <- file_contents[[i]][ which(file_contents[[i]]$NDVI.Year >= BCStartYear & file_contents[[i]]$NDVI.Year < ConflictYear),] #eg. 1982 to 1999
                 BeforeConf2 <-  c(NDVI.Year, NDVI, T.annual.max, Prec.annual.max, soilM.annual.max) #which columns to include
                 BeforeConf <- BeforeConf1[BeforeConf2] #create table
                 
                 AfterConf1 <- myFiles[ which(file_contents[[i]]$NDVI.Year >= ConflictYear & file_contents[[i]]$NDVI.Year <= ACEndYear),] #eg. 1999 to 2015
                 AfterConf2 <-  c(NDVI.Year, NDVI, T.annual.max, Prec.annual.max, soilM.annual.max)
                 AfterConf <- AfterConf1[AfterConf2]
                 
                 #Step 3)a)
                 #create empty list, to fill with coefficient results from each model results for each csv file and safe in new list
                 
                 #Create an empty df for the output coefficients
                 names <- c("(Intercept)","BeforeConf$T.annual.max","BeforeConf$Prec.annual.max","BeforeConf$soilM.annual.max")
                 coef_df <- data.frame()
                 for (k in names) coef_df[[k]] <- as.character() 
                 
                 #Apply Multiple Linear Regression
                 plyrFunc <- function(x){
                   model <- lm(NDVI ~ T.annual.max + Prec.annual.max + soilM.annual.max, data = BeforeConf)
                   return(summary(model)$coefficients[1,1:4])
                 }
                 
                 coef_df <- ddply(BeforeConf, .(), x)
                 coef_DF
    }}

Answer 1

由于您的代码适用于单个 CSV，因此请考虑分离进程和循环。具体来说：

1. 创建一个接收单个 csv 路径作为输入参数的函数，并为 单个 文件执行您需要的所有操作。

   get_coeffs <- function(csv_path) {
     df <- read.csv(csv_path)
   
     ### Step 1
     # select conflict year, start year, and end year in df 
     ConflictYear <- df[1,9]
     SlopeYears <- df[1,7]                       # to get slope years (e.g.17)
     BCStartYear <- ConflictYear - SlopeYears    # to get start year for regression
     ACEndYear <- ConflictYear + (SlopeYears-1)  # -1 because the conflict year is included
   
     ### Step 2
     # select needed rows from df
     #no headers but row numbers. NDVI.Year = [r1-r34,c2]
     NDVI.Year <- df[1:34, 2]
     NDVI <- df[1:34, 21]
     T.annual.max <- df[1:34, 19]
     Prec.annual.max <- df[1:34, 20]
     soilM.annual.max <- df[1:34, 18]
   
     # Define BeforeConf and AfterConf depending on Slope Year number and Conflict Years
     # Go through NDVI.Year till Conflict.Year (-1 year) since the conflict year is not included in bc
     BeforeConf1 <- df[ which(df$NDVI.Year >= BCStartYear & df$NDVI.Year < ConflictYear),]
     BeforeConf2 <- c(NDVI.Year, NDVI, T.annual.max, Prec.annual.max, soilM.annual.max)
     BeforeConf  <- BeforeConf1[BeforeConf2] #create table
   
     AfterConf1 <- myFiles[ which(df$NDVI.Year >= ConflictYear & df$NDVI.Year <= ACEndYear),]
     AfterConf2 <- c(NDVI.Year, NDVI, T.annual.max, Prec.annual.max, soilM.annual.max)
     AfterConf  <- AfterConf1[AfterConf2]
   
     ### Step 3
     tryCatch({
         # Run model and return coefficients
         model <- lm(NDVI ~ T.annual.max + Prec.annual.max + soilM.annual.max, data = BeforeConf) 
         return(summary(model)$coefficients[1,1:4])
     }, error = function(e) {
         print(e)
         return(rep(NA, 4))
     })
   }
   

2. 遍历 csv 路径，将每个文件传递到您的函数中，构建一个结果列表，您可以使用lapply 处理列表返回或sapply（或指定长度和类型的vapply）以简化返回，例如作为向量，矩阵/数组（如果适用）。

   mypath <- "E:\\PYTHON_ST\\breakCSV_PYTHON\\AIM_2_regions\\Afghanistan"
   file_paths <- list.files(pattern=".csv", path=mypath)
   
   # LIST RETURN
   result_list <- lapply(file_paths, get_coeffs)
   
   # MATRIX RETURN
   results_matrix <- sapply(file_paths, get_coeffs)
   results_matrix <- vapply(file_paths, get_coeffs, numeric(4))