My script and one of the first 3 csv files are can be found in my Github folder
I have split a list of NDVI and climate data into small csv. files with 34 years of data each.
Every 34 years should then be split into two parts depending on a conflict year, saved in the same table and a certain time range. But this part of the code works already.
Now I want to control the second part of the list with the climate data of the first part, by using multiple linear regression, which is also done.
I basically need to make a loop to store all the coefficients from every round of the lm function of one csv. file in a new list.
I know that I can use lapply to loop and get the output as a list. But there are some missing parts to actually loop through the csv. files.
#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
}}
Since you have code working for a single CSV, consider separating process and loop. Specifically:
Create a function that receives a single csv path as input parameter and does everything you need for a single file.
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))
})
}
Loop through csv paths, passing each file into your function, building a list of results which you can handle with lapply
for list return or sapply
(or vapply
that specifies length and type) for simplified return such as vector, matrix/array if applicable.
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))