# Reading the csv file
dataset <- read.csv("plastic - Sheet1 (1).csv")
# installing packages needed
install.packages("dplyr")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)
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
# Mutating data to get total number of plastics produces and getting ratio
dataset <- dataset %>%
mutate(Total.Plastic.Produced = `TOTAL.LBS.OF.PCR.PLASTIC` + `TOTAL.LBS.OF.VIRGIN.PLASTIC`)
dataset <- dataset %>%
mutate(Total.Plastic.over.networth = `Total.Plastic.Produced`/`COMPANY.NET.WORTH.IN.BILLIONS`)
# Making a bar graph to compare the ratio of each company
library("ggplot2")
ggplot(dataset, aes(x = reorder(COMPANY, -Total.Plastic.over.networth), y = Total.Plastic.over.networth, fill = COMPANY)) +
geom_bar(stat = "identity") +
labs(title = "Plastic produced by each company for 2023",
x = "Company",
y = "Plastic produced") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 5),
legend.text = element_text(size = 5),
legend.title = element_text(size = 3),
legend.key.size = unit(0.5, "lines")
)
# We realize that SVC Manfucaturing has way toohigh of a ratio. Out of the different food and beverage industries, SVC Manufacturing has the highest plastic produced for packaging in relation the company's networth for the year 2023.
# We still want to have a better visual of how much plastic each company produced for the year so for now, we will remove SVC Manufacturing the removing that row.
# Removing SVC Manufacturing
dataset2 <- dataset [-10,]
# Making another bar graph without SVC Manufacturing
library("ggplot2")
ggplot(dataset2, aes(x = reorder(COMPANY, -Total.Plastic.over.networth), y = Total.Plastic.over.networth, fill = COMPANY)) +
geom_bar(stat = "identity") +
labs(title = "Plastic produced by each company except SVC Manufacturing for 2023",
x = "Company",
y = "Plastic produced") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 5),
legend.text = element_text(size = 5),
legend.title = element_text(size = 3),
legend.key.size = unit(0.5, "lines")
)
dataset3 <- dataset %>%
mutate(Percentage = (`Total.Plastic.over.networth`/881848000000)*100)
dataset3
## COMPANY TOTAL.LBS.OF.PCR.PLASTIC
## 1 Niagara Bottling LLC 37259672
## 2 C.G. Roxane LLC 15895124
## 3 Reyes Coca-Cola Bottling LLC 15468783
## 4 Swire Coca-Cola USA 15468783
## 5 The Coca-Cola Company 15468783
## 6 Pepsi Cola Bottling Group 12483849
## 7 HPP Food Services 10102942
## 8 BlueTriton Brands, Inc. 7227332
## 9 North American Coffee Partnership 6967208
## 10 SVC Manufacturing 5943416
## 11 The American Bottling Company 4870184
## 12 Fiji Water Co LLC 2199651
## 13 Tropicana Manufacturing Company, Inc 1866570
## 14 Motts Inc 1811385
## 15 Nestle USA Inc 1639787
## 16 Premium Waters Inc 1601420
## 17 Pepsi Lipton Tea 1395468
## 18 Danone North America 1283816
## TOTAL.LBS.OF.VIRGIN.PLASTIC YEAR COMPANY.NET.WORTH.IN.BILLIONS
## 1 103914554 2023 28.00000
## 2 23623781 2023 0.05630
## 3 64420662 2023 19.90000
## 4 64420662 2023 3.00000
## 5 64420662 2023 309.59000
## 6 16671176 2023 214.53000
## 7 3429232 2023 0.01410
## 8 18930432 2023 4.70000
## 9 200579 2023 1.50000
## 10 38510946 2023 0.00766
## 11 15360053 2023 1.72700
## 12 5612681 2023 0.05000
## 13 2864574 2023 1.10000
## 14 4356468 2023 0.04320
## 15 7609226 2023 256.18000
## 16 7369267 2023 0.21000
## 17 6636067 2023 9.57000
## 18 2680223 2023 42.96000
## Total.Plastic.Produced Total.Plastic.over.networth Percentage
## 1 141174226 5.041937e+06 5.717467e-04
## 2 39518905 7.019344e+08 7.959811e-02
## 3 79889445 4.014545e+06 4.552423e-04
## 4 79889445 2.662982e+07 3.019774e-03
## 5 79889445 2.580492e+05 2.926232e-05
## 6 29155025 1.359019e+05 1.541103e-05
## 7 13532174 9.597287e+08 1.088315e-01
## 8 26157764 5.565482e+06 6.311158e-04
## 9 7167787 4.778525e+06 5.418762e-04
## 10 44454362 5.803442e+09 6.581000e-01
## 11 20230237 1.171409e+07 1.328357e-03
## 12 7812332 1.562466e+08 1.771809e-02
## 13 4731144 4.301040e+06 4.877303e-04
## 14 6167853 1.427744e+08 1.619036e-02
## 15 9249013 3.610357e+04 4.094081e-06
## 16 8970687 4.271756e+07 4.844095e-03
## 17 8031535 8.392409e+05 9.516843e-05
## 18 3964039 9.227279e+04 1.046357e-05
ggplot(dataset3, aes(x = reorder(COMPANY, -Percentage), y = Percentage, fill = COMPANY)) +
geom_bar(stat = "identity") +
labs(title = "Plastic produced by each company",
x = "Company",
y = "Plastic produced") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 5),
legend.text = element_text(size = 5),
legend.title = element_text(size = 3),
legend.key.size = unit(0.5, "lines")
)
