Emissions trends over time (by city and source)
Plot 1: total emmissions trends Loading in emissions data:
setwd("C:/Users/dhnsingh/Downloads/wk4_case_study/exdata_data_NEI_data")
x <- readRDS("summarySCC_PM25.rds")
y <- readRDS("Source_Classification_Code.rds")Checking variable types:
str(x)## 'data.frame': 6497651 obs. of 6 variables:
## $ fips : chr "09001" "09001" "09001" "09001" ...
## $ SCC : chr "10100401" "10100404" "10100501" "10200401" ...
## $ Pollutant: chr "PM25-PRI" "PM25-PRI" "PM25-PRI" "PM25-PRI" ...
## $ Emissions: num 15.714 234.178 0.128 2.036 0.388 ...
## $ type : chr "POINT" "POINT" "POINT" "POINT" ...
## $ year : int 1999 1999 1999 1999 1999 1999 1999 1999 1999 1999 ...summary(x)## fips SCC Pollutant
## Length:6497651 Length:6497651 Length:6497651
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
##
##
##
## Emissions type year
## Min. : 0.0 Length:6497651 Min. :1999
## 1st Qu.: 0.0 Class :character 1st Qu.:2002
## Median : 0.0 Mode :character Median :2005
## Mean : 3.4 Mean :2004
## 3rd Qu.: 0.1 3rd Qu.:2008
## Max. :646952.0 Max. :2008Collapsing to totals by year:
ag <- aggregate(Emissions~year, data = x, FUN = sum)Plotting totals by year:
par(bg = "yellow")
plot(ag$year, ag$Emissions, cex = 3, pch = 18, col = "darkgreen",
main = "Total Emissions over Time",
xlab = "Total Emissions", ylab = "Year")
lines(ag$year, ag$Emissions, col = "red", lwd = 2)
Total emissions of all types show a decrease over a period of time
Plot 2: total emmissions trends in Baltimore, MD Subsetting data to Baltimore, MD:
x_sub2 <- subset(x, fips == "24510")Collapsing to totals by year:
ag2 <- aggregate(Emissions~year, data = x_sub2, FUN = sum)Plotting emissions totals in Baltimore, MD:
par(bg = "lightblue")
plot(ag2$year, ag2$Emissions, cex = 3, pch = 18, col = "maroon",
main = "Baltimore: Total Emissions over Time",
xlab = "Total Emissions", ylab = "Year")
lines(ag2$year, ag2$Emissions, col = "white", lwd = 2)
Total emissions of any type have decreased in Baltimore city between 1999 and 2008
Installing ggplot:
library(ggplot2)
library(ggthemes)Plot 3: total emmissions trends in Baltimore, md by emmission type Subsetting data to Baltimore, MD:
x_sub3 <- subset(x, fips == "24510")Collapsing to totals by year and type:
ag3 <- aggregate(Emissions~year+type, data = x_sub3, FUN = sum)Plotting emissions totals in Baltimore, MD by type:
g3 <- ggplot(ag3, aes(year, Emissions, color = type))
g3 + geom_point(size = 2.5) + geom_line(size = 1.25) +
xlab("Emissions") + ylab("Year") + ggtitle("Emissions by Type") +
theme_wsj()
All types of emissions decreased between 1999 and 2008, except for points source emissions which saw a spike around year 2005 and reversion to mean
Plot 4: coal emmissions Subsetting columns
x4 <- x[c("SCC", "Emissions", "year")]
y4 <- y[c("SCC", "Short.Name", "SCC.Level.Three")]Subsetting to labels capturing coal caused pollution:
y_coal <- y4[grepl("Coal", y4$Short.Name)|grepl("coal", y4$Short.Name)|grepl("Coal", y4$SCC.Level.Three)|grepl("coal", y4$SCC.Level.Three),]Merging emissions for rows caused by coal:
mrg4 <- merge(x, y_coal, by = "SCC", all.y = TRUE)Collapsing to totals by year and type:
ag4 <- aggregate(Emissions~year, data = mrg4, FUN = sum)Plotting coal emissions trends:
g4 <- ggplot(ag4, aes(year, Emissions))
g4 + geom_point(size = 3, color = "black") + geom_line(size = 1.25, color = "gray") +
xlab("Emissions") + ylab("Year") + ggtitle("Coal Emissions Trends") +
theme_economist() + scale_color_economist()
Coal emissions trends have shown a steady decline from 1999 to 2008, a healthy trend indeed
Plot 5: motor vehicle emmissions Subsetting data to Baltimore, MD
x_sub5 <- subset(x, fips == "24510")Using on-road as vehicle:
x_sub5 <- x_sub5[x_sub5$type == "ON-ROAD",]Collapsing to totals by year:
ag5 <- aggregate(Emissions~year, data = x_sub5, FUN = sum)Plotting motor emissions trends:
g5 <- ggplot(ag5, aes(year, Emissions))
g5 + geom_point(size = 3, shape = 22, color = "red", stroke = 2, fill = "gray") + geom_line(size = 1.25, color = "darkblue") +
xlab("Emissions") + ylab("Year") + ggtitle("Baltimore: Motor Emissions Trends") +
theme_stata()
Emissions due to on-road (motor vehicle) sources in Baltimore have steadily fallen between 1999-2008!
Plot 6: motor vehicles, comparative measure across cities Subsetting data to Baltimore city and Los Angeles:
x_sub6 <- subset(x, fips == "24510" | fips == "06037")Using on-road as vehicle:
x_sub6 <- x_sub6[x_sub6$type == "ON-ROAD",]Collapsing to totals by year and area:
ag6 <- aggregate(Emissions~year+fips, data = x_sub6, FUN = sum)Plotting motor emissions trends comparison:
g6 <- ggplot(ag6, aes(year, Emissions, color = fips))
g6 + geom_point(size = 3, shape = 22, color = "red", stroke = 2, fill = "gray") + geom_line(size = 1.25, color = "darkblue") +
xlab("Emissions") + ylab("Year") + ggtitle("LA vs Ba.: Motor Emissions Trends") +
theme_stata() + facet_wrap(~fips)
LA county has seen far more change in motor vehicle emissions over a period of time than Baltimore city. This can be owing to its population size, density, or sprawl!