Re-run ellis full data

can't use kable_styling() with pdf build as produces html

Rmd/cleaningFeederData.Rmd

@@ -27,7 +27,6 @@ output:
     toc: yes
     toc_depth: 2
     fig_width: 5
-always_allow_html: yes
 bibliography: '`r paste0(here::here(), "/bibliography.bib")`'
 ---
 
@@ -64,7 +63,7 @@ We have some electricity substation feeder data that has been cleaned to give me
 
 There seem to be some NA kW values and a lot of missing time stamps. We want to select the 'best' (i.e most complete) days within a day-of-the-week/season/year sampling frame. If we can't do that we may have to resort to seasonal mean kW profiles by hour & day of the week...
 
-Code used to generate this report: https://git.soton.ac.uk/ba1e12/spatialec/-/blob/master/isleOfWight/cleaningFeederData.Rmd
+The code used to generate this report is in: https://git.soton.ac.uk/ba1e12/dataCleaning/Rmd/
 
 # Data prep
 
@@ -78,8 +77,7 @@ origDataDT <- drake::readd(origData) # readd the drake object
 uniqDataDT <- drake::readd(uniqData) # readd the drake object
 
 kableExtra::kable(head(origDataDT), digits = 2,
-                  caption = "Counts per feeder (long table)") %>%
-  kable_styling()
+                  caption = "First 6 rows of data")
 ```
 
 Do a duplicate check by feeder_ID, dateTime & kW. In theory there should not be any.
@@ -89,16 +87,19 @@ message("Original data nrows: ", tidyNum(nrow(origDataDT)))
 
 message("Unique data nrows: ", tidyNum(nrow(uniqDataDT)))
 
-message("So we have ", tidyNum(nrow(origDataDT) - nrow(uniqDataDT)), " duplicates...")
+nDups <- tidyNum(nrow(origDataDT) - nrow(uniqDataDT))
+
+message("So we have ", tidyNum(nDups), " duplicates...")
 
 pc <- 100*((nrow(origDataDT) - nrow(uniqDataDT))/nrow(origDataDT))
 message("That's ", round(pc,2), "%")
 
 feederDT <- uniqDataDT[!is.na(rDateTime)] # use dt with no duplicates
 origDataDT <- NULL # save memory
+
 ```
 
-There were `r tidyNum(nrow(origDataDT) - nrow(uniqDataDT))` duplicates - that's `r round(pc,2)` % of the observations loaded.
+There were `r tidyNum(nDups)` duplicates - that's ~ `r round(pc,2)` % of the observations loaded.
 
 So we remove the duplicates...
 
@@ -321,23 +322,19 @@ ggplot2::ggplot(aggDT, aes(x = rDate, colour = season,
 aggDT[, rDoW := lubridate::wday(rDate, lab = TRUE)]
 h <- head(aggDT[season == "Spring"][order(-propExpected)])
 kableExtra::kable(h, caption = "Best Spring days overall", 
-                  digits = 3) %>%
-  kable_styling()
+                  digits = 3)
 
 h <- head(aggDT[season == "Summer"][order(-propExpected)])
 kableExtra::kable(h, caption = "Best Summer days overall", 
-                  digits = 3) %>%
-  kable_styling()
+                  digits = 3)
 
 h <- head(aggDT[season == "Autumn"][order(-propExpected)])
 kableExtra::kable(h, caption = "Best Autumn days overall",
-                  digits = 3) %>%
-  kable_styling()
+                  digits = 3) 
 
 h <- head(aggDT[season == "Winter"][order(-propExpected)])
 kableExtra::kable(h, caption = "Best Winter days overall", 
-                  digits = 3) %>%
-  kable_styling()
+                  digits = 3)
 ```
 
 # Summary