Assignment #5

#install.packages("readxl")
library(readxl)
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

library(ggplot2)
library(tidyr)

library(readxl)
tallestbuildings = read_excel("tallestbuildings.xlsx")

Question: #1

Please display how many buildings are there in each city represented in that dataset. An arrangement in either an ascending or a descending order of number of buildings is always helpful.

City_Counts = tallestbuildings %>% group_by(City) %>% summarize(number=length(City))

Question #2

Please plot different cities in order of the mean height of buildings in a city.

ggplot(City_Counts,aes(reorder(City,-number),number))+geom_bar(stat = "identity",fill="dark green")+coord_flip()

colnames(tallestbuildings)[colnames(tallestbuildings)=="Height (ft)"] <- "Height"

City_Mean = tallestbuildings%>%group_by(City)%>%summarize(number=mean(Height))

ggplot(City_Mean,aes(reorder(City,-number),number))+geom_bar(stat = "identity",fill="dark green")+coord_flip()

Question #3 & #4

Please redo 1 and 2 using the country information that is given. (Note that the country variable is present with the city variable. Perhaps a split of that variable is necessary.) You may want to check out the countrycode package to get the full names of different countries instead of relying on the cryptic country codes that are present in that dataset.

Download the country code package

library(countrycode)

Seperate (split) city and country into two columns

tallestbuildings2 = tallestbuildings %>% separate(City, c("City", "Country"), sep="[:punct:]")

## Warning: Expected 2 pieces. Additional pieces discarded in 100 rows [1, 2, 3, 4,
## 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, ...].

Applying Country Code Pkg to our data set

tallestbuildings2$Country=countrycode(tallestbuildings2$Country, "iso2c", "country.name", warn = TRUE, custom_dict = NULL, custom_match = NULL, origin_regex = FALSE)

Create New Set: Displays Number of Buildings per Country

Country_Counts = tallestbuildings2 %>% group_by(Country) %>% summarise(number=length(Country))

Creating Bar Graph with Country Name on Y-Axis & Num of Buildings on X-axis

ggplot(Country_Counts,aes(reorder(Country,-number),number))+geom_bar(stat = "identity",fill="dark green")+coord_flip()

Creating a Data Set that Displays Mean Height of Buildings in Each Country

Country_Mean = tallestbuildings2 %>% group_by(Country) %>% summarise(number=mean(Height))

Creating Bar Graph w/ Country Name on the Y-Axis & Mean Height of Buildings by Country on the X-Axis

ggplot(Country_Mean,aes(reorder(Country,-number),number))+geom_bar(stat = "identity",fill="dark green")+coord_flip()

5. In 4 above, you would’ve plot different countries in order of their mean height of a buildings in a city. If you have not used a bar graph there, please create a bar graph. In this bar graph, please color each bar for a country based on the number of buildings from this dataset that are present in that country.

Create data set which displays the country name with the number of buildings in each country and the mean height of the buildings in each country

Country_Mean_Count=tallestbuildings2 %>% group_by(Country) %>% summarize(Country_Counts=n(), Country_Mean=mean(Height))

Create a bar graph with country name on the vertical axis and mean height of the buildings in each country on the horizontal axis. Have each bar be colored on the basis of the building count of each country

ggplot(Country_Mean_Count,aes(reorder(Country,-Country_Mean),Country_Mean, fill = as.factor(Country_Counts))) + geom_bar(stat = "identity", position="dodge") + coord_flip() + labs(list(title= "Countries Ranked by the Mean Height of Tall Buildings", x="", y="Country Mean"))

6. What are the mean heights (in feet) of buildings that are used for different purposes. (Here, you will have different purposes in a column and the corresponding mean height in a different column.) In computing this, it is okay to double or triple count a building if it has multiple uses.

uses = tallestbuildings2 %>% group_by(Use) %>%
  summarise(Mean.Height = mean(`Height`))

uses %>%
  ggplot(aes(x= reorder(Use,Mean.Height),y=Mean.Height)) +
  geom_bar(stat = "identity", fill = "dark green", position="dodge") + coord_flip() + labs(x = "Use") + labs(y = "Avg. Height")

Assignment #5

Bryce J. Parsons

3/2/2020

Question: #1

Please display how many buildings are there in each city represented in that dataset. An arrangement in either an ascending or a descending order of number of buildings is always helpful.

Question #2

Please plot different cities in order of the mean height of buildings in a city.

Question #3 & #4

Download the country code package

Seperate (split) city and country into two columns

Applying Country Code Pkg to our data set

Create New Set: Displays Number of Buildings per Country

Creating Bar Graph with Country Name on Y-Axis & Num of Buildings on X-axis

Creating a Data Set that Displays Mean Height of Buildings in Each Country

Creating Bar Graph w/ Country Name on the Y-Axis & Mean Height of Buildings by Country on the X-Axis

Create data set which displays the country name with the number of buildings in each country and the mean height of the buildings in each country

Create a bar graph with country name on the vertical axis and mean height of the buildings in each country on the horizontal axis. Have each bar be colored on the basis of the building count of each country

6. What are the mean heights (in feet) of buildings that are used for different purposes. (Here, you will have different purposes in a column and the corresponding mean height in a different column.) In computing this, it is okay to double or triple count a building if it has multiple uses.