library(terra)
library(geospaar)
# data(dem)
topo <- lapply(c("TRI", "flowdir"), function(x) terrain(rast(dem), x))
png(here::here("docs/figures/zambia_topo.png"), 
       width = 7, height = 2.5, res = 300, units = "in", bg = "grey")
par(mfrow = c(1, 2))#, mar = c(0, 1, 2, 4), oma = c(0, 1, 0, 2))
plot(topo[[1]], mar = c(0.5, 1, 1, 4), main = "TRI", axes = FALSE)
plot(topo[[2]], mar = c(0.5, 1, 1, 4), main = "Flow Direction", axes = FALSE)
dev.off()

Data generation

Create the following:

  • dat, a data.frame built from V1, V2, V3, and V4, where:
    • V1 = 1:20
    • V2 is a random sample between 1:100
    • V3 is drawn from a random uniform distribution between 0 and 50
    • V4 is a random selection of the letters A-E
    • Use set.seed(50)
  • Do this all at once (i.e. wrap the creation of V1-V4 in the data.frame call, precede it with set.seed())

Exercises

  • Use a for to iterate over each row of dat and calculate it’s sum
  • Do the same with lapply and sapply
  • Do the same using rowSums
  • Select rows from dat containing the letter “E” in V4, and take the mean of values from the result in column V3

Spot the bug

for(i in 1:dat) {
  print(sum(dat[i]))
}

lapply(i in 1:nrow(dat) function(x) sum(dat[i, ]))

sapply(1:nrow(dat) function(x) sum(dat[, x]))

rowSums(dat)

mean(dat[dat`V4` == "E", "V3"])

In-class

  • Using an lapply, create an output list of 3 data.frames in which the first data.frame has it’s V2 column multiplied by 5, the second data.frame has V2 multiplied by 10, and the third has V2 multipled by 20. Use dat as the starting data.frame.
  • Make a data.frame called dat2 that is a copy of dat. Update dat2 so that its V3 is set to 40 in the places where values > 40

Reading and writing data

File paths

Let’s read in a csv a few different ways.

Full path - clear for you, bad for code sharing.

data_tib <- read.csv(
  "/Users/lestes/Dropbox/teaching/geog246346/geospaar/inst/extdata/cdf_corn.csv"
)
str(data_tib)
'data.frame':   5999 obs. of  20 variables:
 $ tenant      : chr  "planet" "planet" "planet" "planet" ...
 $ site_id     : chr  "UNLEN_CSP1_IMZ1" "UNLEN_CSP1_IMZ1" "UNLEN_CSP1_IMZ1" "UNLEN_CSP1_IMZ1" ...
 $ local       : chr  "2020-06-05 10:00:00-05:00" "2020-06-06 10:00:00-05:00" "2020-06-07 10:00:00-05:00" "2020-06-08 10:00:00-05:00" ...
 $ lat         : num  41.2 41.2 41.2 41.2 41.2 ...
 $ long        : num  -96.5 -96.5 -96.5 -96.5 -96.5 ...
 $ site_group  : chr  "Lincoln" "Lincoln" "Lincoln" "Lincoln" ...
 $ Tair        : num  27.4 25.5 29.6 27.7 26.7 ...
 $ Tabove      : num  27.93 17.43 9.18 8.58 18.71 ...
 $ Tbelow      : num  28 24.3 27 25.9 26.6 ...
 $ CGDD        : int  345 363 381 393 402 414 425 439 455 471 ...
 $ b1r         : num  0.098 0.052 0.0493 0.0484 0.0452 ...
 $ b2r         : num  0.0822 0.0762 0.0739 0.0722 0.0676 ...
 $ b3r         : num  0.2013 0.0911 0.0863 0.0848 0.0803 ...
 $ b4r         : num  0.1447 0.1001 0.0991 0.0958 0.0899 ...
 $ b5r         : num  0.0946 0.225 0.2378 0.246 0.2434 ...
 $ b6r         : num  0.139 0.282 0.332 0.348 0.334 ...
 $ b7r         : num  0.123 0.233 0.259 0.265 0.259 ...
 $ NDVI        : num  -0.0209 0.4754 0.54 0.5686 0.5755 ...
 $ CropType    : chr  "Corn" "Corn" "Corn" "Corn" ...
 $ PlantingDate: chr  "04/20/2020" "04/20/2020" "04/20/2020" "04/20/2020" ...
data_tib <- readr::read_csv(
  "/Users/lestes/Dropbox/teaching/geog246346/geospaar/inst/extdata/cdf_corn.csv"
)
str(data_tib)
spc_tbl_ [5,999 × 20] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ tenant      : chr [1:5999] "planet" "planet" "planet" "planet" ...
 $ site_id     : chr [1:5999] "UNLEN_CSP1_IMZ1" "UNLEN_CSP1_IMZ1" "UNLEN_CSP1_IMZ1" "UNLEN_CSP1_IMZ1" ...
 $ local       : POSIXct[1:5999], format: "2020-06-05 15:00:00" "2020-06-06 15:00:00" ...
 $ lat         : num [1:5999] 41.2 41.2 41.2 41.2 41.2 ...
 $ long        : num [1:5999] -96.5 -96.5 -96.5 -96.5 -96.5 ...
 $ site_group  : chr [1:5999] "Lincoln" "Lincoln" "Lincoln" "Lincoln" ...
 $ Tair        : num [1:5999] 27.4 25.5 29.6 27.7 26.7 ...
 $ Tabove      : num [1:5999] 27.93 17.43 9.18 8.58 18.71 ...
 $ Tbelow      : num [1:5999] 28 24.3 27 25.9 26.6 ...
 $ CGDD        : num [1:5999] 345 363 381 393 402 414 425 439 455 471 ...
 $ b1r         : num [1:5999] 0.098 0.052 0.0493 0.0484 0.0452 ...
 $ b2r         : num [1:5999] 0.0822 0.0762 0.0739 0.0722 0.0676 ...
 $ b3r         : num [1:5999] 0.2013 0.0911 0.0863 0.0848 0.0803 ...
 $ b4r         : num [1:5999] 0.1447 0.1001 0.0991 0.0958 0.0899 ...
 $ b5r         : num [1:5999] 0.0946 0.225 0.2378 0.246 0.2434 ...
 $ b6r         : num [1:5999] 0.139 0.282 0.332 0.348 0.334 ...
 $ b7r         : num [1:5999] 0.123 0.233 0.259 0.265 0.259 ...
 $ NDVI        : num [1:5999] -0.0209 0.4754 0.54 0.5686 0.5755 ...
 $ CropType    : chr [1:5999] "Corn" "Corn" "Corn" "Corn" ...
 $ PlantingDate: chr [1:5999] "04/20/2020" "04/20/2020" "04/20/2020" "04/20/2020" ...
 - attr(*, "spec")=
  .. cols(
  ..   tenant = col_character(),
  ..   site_id = col_character(),
  ..   local = col_datetime(format = ""),
  ..   lat = col_double(),
  ..   long = col_double(),
  ..   site_group = col_character(),
  ..   Tair = col_double(),
  ..   Tabove = col_double(),
  ..   Tbelow = col_double(),
  ..   CGDD = col_double(),
  ..   b1r = col_double(),
  ..   b2r = col_double(),
  ..   b3r = col_double(),
  ..   b4r = col_double(),
  ..   b5r = col_double(),
  ..   b6r = col_double(),
  ..   b7r = col_double(),
  ..   NDVI = col_double(),
  ..   CropType = col_character(),
  ..   PlantingDate = col_character()
  .. )
 - attr(*, "problems")=<externalptr>

Working directory "."

  • Working directory. Use getwd() (from console)
  • Usually set to project folder.
getwd() ## if in an RMD, this will show the folder of the RMD
[1] "/Users/LEstes/Dropbox/teaching/geog246346/devel/geospaar/docs"

Use . to start a file path from the working directory

list.files(".") ## 
data_tib <- readr::read_csv("./inst/extdata/cdf_corn.csv")
  • Use “..” to go up one folder level
list.files(".") ## files in working directory
list.files("..") ## files in folder one level up

User directory "~"

  • Set by environment variable
  • Use command below to see value
path.expand("~")
[1] "/Users/LEstes"
data_tib <- readr::read_csv(
  "~/Dropbox/teaching/geog246346/geospaar/inst/extdata/cdf_corn.csv"
)

Writing files

  • Use write.csv or readr::write_csv to write
readr::write_csv(data_tib, file = "temp.csv") ## by default writes to wd()

Saving/loading files

  • If you want to save an R object, like a data.frame, tibble etc.
  • Use save, and .rda extension
save(data_tib, file = "temp.rda") ## by default writes to wd()
data_tib <- NULL
load(file = "temp.rda") ## loads file back to environment

Dates with lubridate

  • The main function you want to use is as_date, which can convert a character to date format.
library(lubridate)
date1 <- as_date("2022-03-01") ## date in standard YYYY-MM-DD format
print(date1)
[1] "2022-03-01"

Dates with lubridate

  • More challenging with unclear date formats.
date2 <- as_date("3/1/22") ## is month or date first?
date2
[1] NA

Include format as shown below. See formats in this link

date2 <- as_date("3/1/22", format = "%m/%d/%y" )
date2
[1] "2022-03-01"

We can also write dates in desired format

date2_char <- as.character(date2, format = "%A %B %d, %Y")
date2_char
[1] "2022-03-01"

Date formats

How can we read in this date?

date3 <- as_date("Apr 3, 1999", format = "...")
date3
[1] NA