Project2

library(tidyr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

1. import data from github

mydata <- read.csv("https://raw.githubusercontent.com/arinolan/Nolan_Project-2/main/Untidy_Dog_Data.csv")

mydata

##    Breed    Weight           Color
## 1    Lab     90lbs          yellow
## 2  Yorki 10 pounds black and brown
## 3 Aussie     60lbs            blue
## 4  Corgi        35           beige
## 5  Husky     40kgs           white

2. clean data

kgs_calc <- 40 * 2.2
df_mydata <- mydata

df_mydata$Weight[df_mydata$Weight == '90lbs'] <- 90
df_mydata$Weight[df_mydata$Weight == '10 pounds'] <- 10
df_mydata$Weight[df_mydata$Weight == '60lbs'] <- 60
df_mydata$Weight[df_mydata$Weight == '35'] <- 35
df_mydata$Weight[df_mydata$Weight == '40kgs'] <- kgs_calc

df_mydata

##    Breed Weight           Color
## 1    Lab     90          yellow
## 2  Yorki     10 black and brown
## 3 Aussie     60            blue
## 4  Corgi     35           beige
## 5  Husky     88           white

3. analysis

1. which dog breeds are less than 50lbs?
2. which dog breeds are heavier than 50lbs?

df_mydata[order(as.numeric(as.character(df_mydata$Weight))),]

##    Breed Weight           Color
## 2  Yorki     10 black and brown
## 4  Corgi     35           beige
## 3 Aussie     60            blue
## 5  Husky     88           white
## 1    Lab     90          yellow

small <- df_mydata %>%
  filter(Weight < 50)
small$Breed

## [1] "Yorki" "Corgi"

large <- df_mydata %>%
  filter(Weight > 50)
large$Breed

## [1] "Lab"    "Aussie" "Husky"