R Essential

Views: 190
Wrote on June 29, 2020, 11:29 p.m.

Entering data

# Title:    Entering data
#           Wrangling and Visualizing Data

# BASIC COMMANDS ###########################################

2+2  # Basic math; press cmd/ctrl enter

1:100  # Prints numbers 1 to 100 across several lines

print("Hello, World!")  # Prints "Hello, World" in console

# ASSIGNING VALUES #########################################

# Individual values
a <- 1            # Use <- and not =
2 -> b            # Can go other way, but silly
c <- d <- e <- 3  # Multiple assignments

# Multiple values
x <- c(1, 2, 5, 9)  # c = Combine/collect/concatenate
x                   # Print contents of x in Console

# SEQUENCES ################################################

# Create sequential data
0:10     # 0 through 10
10:0     # 10 through 0
seq(10)  # 1 to 10
seq(30, 0, by = -3)  # Count down by 3

# MATH ################################################

# Surround command with parentheses to also print
(y <- c(5, 1, 0, 10)) 
x           # Take another look at x
x + y       # Adds corresponding elements in x and y
x * 2       # Multiplies each element in x by 2
2^6         # Powers/exponents
sqrt(64)    # Square root
log(100)    # Natural log: base e (2.71828...); NOT "ln"
log10(100)  # Base 10 log

# CLEAN UP #################################################

# Clear environment
rm(list = ls()) 

# Clear console
cat("\014")  # ctrl+L

# Clear mind :)

Data Type

# Title:    Data types and structures
#           Wrangling and Visualizing Data

# DATA TYPES ###############################################

## Numeric =================================================

n1 <- 15  # Double precision by default
n1
typeof(n1)

n2 <- 1.5
n2
typeof(n2)

## Character ===============================================

c1 <- "c"
c1
typeof(c1)

c2 <- "a string of text"
c2
typeof(c2)

## Logical =================================================

l1 <- TRUE
l1
typeof(l1)

l2 <- F
l2
typeof(l2)

# DATA STRUCTURES ##########################################

## Vector ==================================================

v1 <- c(1, 2, 3, 4, 5)
v1
is.vector(v1)

v2 <- c("a", "b", "c")
v2
is.vector(v2)

v3 <- c(TRUE, TRUE, FALSE, FALSE, TRUE)
v3
is.vector(v3)

## Matrix ==================================================

m1 <- matrix(c(T, T, F, F, T, F), nrow = 2)
m1

m2 <- matrix(c("a", "b", 
               "c", "d"), 
               nrow = 2,
               byrow = T)
m2

## Array ===================================================

# Give data, then dimensions (rows, columns, tables)
a1 <- array(c( 1:24), c(4, 3, 2))
a1

## Data Frame ==============================================

# Can combine vectors of the same length

vNumeric   <- c(1, 2, 3)
vCharacter <- c("a", "b", "c")
vLogical   <- c(T, F, T)

df1 <- cbind(vNumeric, vCharacter, vLogical)
df1  # Coerces all values to most basic data type

df2 <- as.data.frame(cbind(vNumeric, vCharacter, vLogical))
df2  # Makes a data frame with three different data types

## List ====================================================

o1 <- c(1, 2, 3)
o2 <- c("a", "b", "c", "d")
o3 <- c(T, F, T, T, F)

list1 <- list(o1, o2, o3)
list1

list2 <- list(o1, o2, o3, list1)  # Lists within lists!
list2

# COERCING TYPES ###########################################

## Automatic Coercion ======================================

# Goes to "least restrictive" data type

(coerce1 <- c(1, "b", TRUE))
typeof(coerce1)

## Coerce Numeric to Integer ===============================

(coerce2 <- 5)
typeof(coerce2)

(coerce3 <- as.integer(5))
typeof(coerce3)

## Coerce Character to Numeric =============================

(coerce4 <- c("1", "2", "3"))
typeof(coerce4)

(coerce5 <- as.numeric(c("1", "2", "3")))
typeof(coerce5)

## Coerce Matrix to Data Frame =============================

(coerce6 <- matrix(1:9, nrow= 3))
is.matrix(coerce6)

(coerce7 <- as.data.frame(matrix(1:9, nrow= 3)))
is.data.frame(coerce7)

# CLEAN UP #################################################

# Clear environment
rm(list = ls()) 

# Clear console
cat("\014")  # ctrl+L

# Clear mind :)

Comments

# Title:    Comments and headers
#           Wrangling and Visualizing Data

# INSTALL AND LOAD PACKAGES ################################

# Load base packages manually
library(datasets)  # For example datasets

# LOAD AND PREPARE DATA ####################################

df <- iris
head(df)

# COMMENT OUT LINES ########################################

# Comment/uncomment lines in RStudio with shift-cmd/ctrl-C

# Use comments to disable commands
hist(df$Sepal.Width,
  # col  = "#CD0000",  # red3
  # border = NA,  # No borders
  main = "Histogram of Sepal Width",
  xlab = "Sepal Width (in cm)")

# THIS IS A LEVEL 1 HEADER #################################

## This Is a Level 2 Header ================================

### This is a level 3 header. ------------------------------

# CLEAN UP #################################################

# Clear environment
rm(list = ls()) 

# Clear packages
detach("package:datasets", unload = TRUE)  # For base

# Clear plots
graphics.off()  # Clears plots, closes all graphics devices

# Clear console
cat("\014")  # ctrl+L

# Clear mind :)

Packages

# Title:    Packages for R
#           Wrangling and Visualizing Data

# INSTALL AND LOAD PACKAGES ################################

# Install pacman ("package manager") if needed
if (!require("pacman")) install.packages("pacman")

# Load contributed packages with pacman
pacman::p_load(pacman, party, psych, rio, tidyverse)
# pacman: for loading/unloading packages
# party: for decision trees
# psych: for many statistical procedures
# rio: for importing data
# tidyverse: for so many reasons

# Load base packages manually
library(datasets)  # For example datasets

# LOAD AND PREPARE DATA ####################################

# Save data to "df" (for "data frame")
# Rename outcome as "y" (if it helps)
# Specify outcome with df$y

# Import CSV files with readr::read_csv() from tidyverse
(df <- read_csv("data/StateData.csv"))

# Import other formats with rio::import() from rio
(df <- import("data/StateData.xlsx") %>% as_tibble())

# or...

df <- import("data/StateData.xlsx") %>%
  as_tibble() %>%
  select(state_code, 
    psychRegions,
    instagram:modernDance) %>% 
  mutate(psychRegions = as.factor(psychRegions)) %>%
  rename(y = psychRegions) %>%
  print()

# CLEAN UP #################################################

# Clear environment
rm(list = ls()) 

# Clear packages
p_unload(all)  # Remove all add-ons
detach("package:datasets", unload = TRUE)  # For base

# Clear console
cat("\014")  # ctrl+L

# Clear mind :)