Pollution Project 2

About data collection (Introduction and Methods)

Sampling was done in the shared backyard of multiple housing units. In these units there is a variety of ages and lifestyles present. Often on weekends someone will use the communal backyard for a get together. Sampling was done on Tuesdays and Fridays at varying times due to work/school. Items found were marked with sharpie for reoccurence count. Data on new/reocurred taken by tally on paper then put into excel data sheet

Read in data and packages

library(tidyverse)

── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
✔ ggplot2 3.4.0      ✔ purrr   0.3.4 
✔ tibble  3.1.8      ✔ dplyr   1.0.10
✔ tidyr   1.2.1      ✔ stringr 1.4.1 
✔ readr   2.1.2      ✔ forcats 0.5.2 
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

library(ggplot2)
library(ggpubr)
data<-read.csv("pollution.csv", stringsAsFactors = T)
newdata<-data %>%  na.omit()

Quick plot of total number of pollutants present per month

plastic4<-ggplot(newdata, aes(plastic_bottlecup ))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
plastic2<-plastic1<-ggplot(newdata, aes(plastic_other ))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
plastic3<-ggplot(newdata, aes(plastic_cigarette ))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
glass1<-ggplot(newdata, aes(glass_bottle ))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
glass2<-ggplot(newdata, aes(glass_other ))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
paper1<-ggplot(newdata, aes(paper ))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
cardboard1<-ggplot(newdata, aes(cardboard))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
food1<-ggplot(newdata, aes(food))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
animal1<-ggplot(newdata, aes(animal))+
  geom_histogram(fill="lightblue")+facet_wrap(~months)
ggarrange(plastic4, plastic2, plastic3, glass1, glass2, paper1, cardboard1, food1, animal1 + rremove("x.text"), 
          labels = c("A", "B", "C", "D", "E", "F", "G", "H", "I"),
          ncol = 3, nrow = 3)

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Histograms of all pollutants

plastic<-ggplot(newdata, aes(x=plastic_bottlecup+plastic_other+plastic_cigarette))+
  geom_boxplot()
glass<-ggplot(newdata, aes(x=glass_bottle+glass_other))+
  geom_boxplot()
paper<-ggplot(newdata, aes(x=paper)) + geom_boxplot()
cardboard<-ggplot(newdata, aes(x=cardboard)) + geom_boxplot()
food<-ggplot(newdata, aes(x=food)) + geom_boxplot()
animal<-ggplot(newdata, aes(x=animal)) + geom_boxplot()
ggarrange(plastic, glass, paper, cardboard, food, animal + rremove("x.text"), 
          labels = c("A", "B", "C", "D", "E", "F"),
          ncol = 3, nrow = 2)

Summary of findings (Results and Discussion)

As we can see in the first plot given, where in order from left to right we have plastic bottles/cups, other plastics, and cigarettes in the first row, glass bottle, other glass and paper in the second row, and cardboard, food, and animal waste in the last row, each month there is a varying presence of pollution of each type. There was no real correlation between month and type of waste as a logistic regression did not give a significant value. However, it can be seen physically from the graph that cigarettes had the highest number of occurrences more frequently per month than the other kinds of waste. It is also important to note that in these graphs only one day of data was collected for August, so it is not an accurate representation of the data for August. In the second plot given, a boxplot of total number of occurrences, we see that plastics had the highest mean of a little over 4 with the maximum being around 8. For glass and paper the mean only reached 1 with the maximum being 3. For both cardboard and food there was a mean of 0.5 with a maximum of 4. For animals, the mean and maximum both fell at 2. It is important to note that despite mean and maximum values there are outliers that differ. In cardboard there is an outlier at 3, in plastics there is an outlier at 10, and in food there are two outliers at 3 and 4. From these plots we can determine that plastics occur most frequently and thus are of the biggest priority. Food and cardboard have the mowest mean and maximum values telling us that in this area it is of the least concern.

I chose to look at this shared backyard as people from all ages live here, but many of those who are younger will throw get togethers in the yard. There is also the difference of people that do and do not have pets living in this building. This is where I believe most of this trash was coming from. If my time had allowed I would have picked different days to sample like Sunday and Wednesday to get a fresh look at the waste left over (Sunday) and a more “fresh” look at the yard before a party (Wednesday). Metal cans were also present, but they weren’t recorded. This is something I would also change if I were to repeat this project. From what I can determine, and from what I saw, most of the waste left in this backyard wasn’t general litter but came from the lack of cleaning up after a get together and a lack of disposal during said get together.