Scribe 2.R

#Basic_Opertator
5 + 7
abs(-17)

#Variable Assignment
x <- -12
x + 7
abs(x)

#Vector Creation and Operations
y <- c(-12, 6, 0, -1)
2 * y        # component-wise multiplication
abs(y)       # component-wise absolute value
sin(y)       # component-wise sine

#Importing Data (Excel/CSV) and Viewing
# If not already installed
install.packages("readxl")
library(readxl)

Scooby <- read_excel("scooby_dooby_doo.xlsx")
View(Scooby)

#Calculating Mean (with NA values handled)
mean(Scooby$runtime)
mean(Scooby$imdb, na.rm = TRUE)

#Scripts and Using Tidyverse
library(tidyverse)

#Listing and Previewing Datasets
data()              # list built-in datasets
View(mpg)           # view tidyverse's mpg dataset
?mpg                # help on the dataset
?mean               # help on mean function
glimpse(mpg)        # quick overview of a dataset

#Filtering Rows
library(dplyr)

mpg_efficient <- filter(mpg, cty >= 20)
View(mpg_efficient)

mpg_ford <- filter(mpg, manufacturer == "ford")
View(mpg_ford)

#Adding or Changing Columns
mpg_metric <- mutate(mpg, cty_metric = 0.425144 * cty)
glimpse(mpg_metric)

#Using Pipe Operator
mpg_metric <- mpg %>%
  mutate(cty_metric = 0.425144 * cty)

#Grouped Summaries
mpg %>%
  group_by(class) %>%
  summarise(
    mean_cty = mean(cty),
    median_cty = median(cty)
  )

#Data Visualization with ggplot2

library(ggplot2)

# Histogram
ggplot(mpg, aes(x = cty)) +
  geom_histogram()

# Scatter plot with regression line
ggplot(mpg, aes(x = cty, y = hwy)) +
  geom_point() +
  geom_smooth(method = "lm")

# Scatter plot colored by class
ggplot(mpg, aes(x = cty, y = hwy, color = class)) +
  geom_point() +
  scale_color_brewer(palette = "Dark2")