Code from the first session of dPrep 2024 (https://dprep.hannesdatta.com)

script.R

# use cases

# as a calculator
x + 1

# to assign variables
x = 5

# calculation w/ variables
x + 5

# assign new values
y = x + 5

# assign new values w/ <- 
y <- x + 7

# compare two objects
x == y
x
y

5 == (25/5)

# functions
x = c(1,2,3)

sum(x)

mean(x)

avg_x = mean(x)

round(8.42,1)

# getting help
?round

# assign character strings to a vector
cities = c('Amsterdam','Tilburg', 'Den Bosch')
# this doesn't run due to lack of quotation marks:
# cities = c(Amsterdam)

x = c('Hannes','Max','Lisa','Thijs')

x[1]
x[3]

x[x=='Lisa']


#### A BIT OF PRACTICE

# 1. 
rooms = c(1,2,1,8)

# or:
rooms <- c(1,2,1,8)

# 2. the max function
max(rooms)

# 3. 
rooms <- c(1,2,1,8,NA)

rooms <- c(rooms, NA)

# 4.
max(rooms)
?max

max_value <- max(rooms, na.rm = TRUE)

# 5.
rooms[3]

# 6.
rooms
rooms >= 2
which(rooms >= 2)
rooms[which(rooms >= 2)]


########

download.file("https://raw.githubusercontent.com/hannesdatta/course-dprep/master/content/docs/modules/week4/regional-global-daily-latest.csv", "streams.csv")

library(tidyverse)
streams <- read_csv('streams.csv', skip=1)

streams
head(streams)
view(streams)
nrow(streams)
summary(streams)


install.packages('tidyverse')

# 

streams$Streams

mean(streams$Streams)

# '' for characters
# "" same, for characters
# `` for variable names containing spaces

streams %>% select(`Track Name`) # more modern way of coding in R
streams$`Track Name` # totally legacy and slow way of coding

streams %>% filter(`Track Name`=='Pepas')


streams %>% mutate(weekly_streams = `Streams` * 7)


###

streams %>% select(`Artist`,`Track Name`)


select(streams, `Artist`, `Track Name`)

### 2.
streams %>% filter(`Artist`=='Lil Nas X') %>% summarize(sum(`Streams`))