dplyr

library(dplyr) library(tidyverse) penguines <- read.csv(file.choose())

#WE will use arrange(), select(), filter(), mutate(), summarize()

residence1 <- penguines %>% filter(island ==“Torgersen”) residence1

residence1 %>% arrange(culmen_length_mm)

#Random sampling from a table

set.seed(406) pen_subset <- penguines %>% sample_n(15) pen_subset

#ascending & descending order

pen_subset %>% arrange(species) pen_subset %>% arrange(desc(culmen_length_mm))

#Filter

pen_subset %>% filter(culmen_depth_mm> 15) penguines %>% filter(island == “Dream”)

penguines %>% filter(sex == “MALE”)

pen_subset %>% filter(between(culmen_depth_mm, 16.2, 18.1))

#Select

pen_subset %>% select(species,flipper_length_mm, sex)

pen_subset %>% select(where(is.numeric))

pen_subset %>% select(where(is.character))

penguines

Comparing Avgerage weight

male <- penguines %>% filter(sex == “MALE”) male

avg_male <- mean(male$body_mass_g, na.rm = T) avg_male

female <- penguines %>% filter(sex == “FEMALE”) female

avg_female <- mean(female$body_mass_g, na.rm = T) avg_female

print(paste(“Male penguines Average Weight:” ,avg_male, “Female penguines average Weight:”,avg_female))

pen_subset1 <- pen_subset %>% mutate(body_weight_pounds = body_mass_g/ 453.59237) %>% select(species,body_mass_g ,body_weight_pounds,everything())

Summarize

pen_subset %>% summarise(avg_body_mass = mean(body_mass_g))