Base R functions vs. Tidyverse

3 + 5 #maths! including - , *, /

weight_kg <- 55 #assignment operator! for objects/variables. shortcut: alt + - 

weight_lb <- 2.2 * weight_kg #can assign output to an object. can use objects to do calculations

ten <- sqrt(weight_kg) #contain calculations wrapped into one command to type. 
                       #functions take "arguments": you have to tell them what to run their script against

round(3.14159) #don't have to assign

args(round) #the args() function will show you the required arguments of another function

?round #will show you the full help page for a function, so you can see what it does, 
       #what argument it takes etc.

round(3.14159, 2) #the round function's second argument is the number of digits you want in the result
round(3.14159, digits = 2) #same as above
round(digits = 2, x = 3.14159) #when reordered you need to specify

weight_g <- c(21, 34, 39, 54, 55) #use the combine function to join values into a vector object

length(weight_g) #explore vector
class(weight_g) #a vector can only contain one data type
str(weight_g) #find the structure of your object.
              #our vector is numeric. 
              #other options include: character (words), logical (TRUE or FALSE), integer etc.

animals <- c("mouse", "rat", "dog") #to create a character vector, use quotes

#R will convert (force) all values in a vector to the same data type.
#for this reason: try to keep one data type in each vector
#a data table / data frame is just multiple vectors (columns)

animals #calling your object will print it out
animals[2] #square brackets = indexing. selects the 2nd value in your vector

weight_g > 50 #conditional indexing: selects based on criteria
weight_g[weight_g <=30 | weight_g == 55] #many new operators here!  
                                         #<= less than or equal to, | "or", == equal to
weight_g[weight_g >= 30 & weight_g == 21] #  >=  greater than or equal to, & "and" 
                                          # this particular example give 0 results - why?

heights <- c(2, 4, 4, NA, 6)
mean(heights) #some functions cant handle NAs
mean(heights, na.rm = TRUE) #remove the NAs before calculating

#other ways to get a dataset without NAs:
heights[!is.na(heights)] #indexes for values where its NOT NA 
                         #! is an operator that reverses the function
na.omit(heights) #omit the NAs
heights[complete.cases(heights)] #select only complete cases

# Tidyverse - provides dplyr, ggplot2, and many other packages that simplify data.frame manipulation in R
library(tidyverse)

# Thanks for the data Dr. Lennox!
load("seaTrout.rda")  # load 1.5m sea trout detections from a dataset in the Norwegian fjords.

# Base R way:
str(seaTrout)
# Tidyverse option:
glimpse(seaTrout)

# Base R way:
head(seaTrout)
# alternate way of calling the same head() function using Tidyverse
seaTrout %>% head

# %>% is a "pipe" which allows you to join functions together in sequence. 
#it can be read as "and then". shortcut: ctrl + shift + m

#recall base R indexing
seaTrout[,c(7)] #selects column 7. need an x and y coordinate
seaTrout %>% dplyr::select(7) 

# dplyr::select this syntax is to specify that we want the select function from the dplyr package. 
#often functions are named the same but do diff things

seaTrout[c(1:5),] #selects rows 1 to 5
seaTrout %>% slice(1:5) #dplyr way

seaTrout_full = seaTrout #make a copy of full dataset
seaTrout <- seaTrout %>% slice(1:100000) #make dataframe smaller, so that it will be easier to work with later

nrow(data.frame(unique(seaTrout$Species))) #number of species, in base R
seaTrout %>% distinct(Species) %>% nrow #number of species in dplyr!

seaTrout[which(seaTrout$Species=="Trout"),] #filtering a subset of data (only species = AB)
seaTrout %>% filter(Species=="Trout") #filtering in dplyr!

tapply(seaTrout$lon, seaTrout$tag.ID, mean) #get the mean value across a column, in base R
seaTrout %>%
  group_by(tag.ID) %>%
  summarise(mean=mean(lon)) #uses pipes and dplyr functions to do this!

as.POSIXct(seaTrout$DateTime) #Tells R to treat this column as a date, not numbers

library(lubridate) #can use tidyverse package lubridate to work with dates easier
seaTrout %>% mutate(DateTime=ymd_hms(DateTime)) #ta-da!

#lubridate is amazing if you have a dataset with multiple datetime formats / timezones
#the function parse_date_time() can be used to specify multiple date formats
#the function with_tz() can change timezone. accounting for daylight savings too!

plot(seaTrout$lon, seaTrout$lat)  #base R

library(ggplot2) #tidyverse-style plotting, a very customizable plotting package
seaTrout %>%  
  ggplot(aes(lon, lat)) + #aes = the aesthetic. x and y etc.
  geom_point() #geom = the type of plot