Studying pollution.
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, unionlibrary(ggplot2)
library(stringr)Setting up the working directory.
getwd()## [1] "/Users/marinazub/MyProjects/EDA/week4"setwd("~/MyProjects/EDA/week4")Reading the data
NEI <- readRDS("FNEI_data/summarySCC_PM25.rds")
SCC <- readRDS("FNEI_data/Source_Classification_Code.rds")Exploring the data
str(NEI)## '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 ...head(NEI)## fips SCC Pollutant Emissions type year
## 4 09001 10100401 PM25-PRI 15.714 POINT 1999
## 8 09001 10100404 PM25-PRI 234.178 POINT 1999
## 12 09001 10100501 PM25-PRI 0.128 POINT 1999
## 16 09001 10200401 PM25-PRI 2.036 POINT 1999
## 20 09001 10200504 PM25-PRI 0.388 POINT 1999
## 24 09001 10200602 PM25-PRI 1.490 POINT 1999names(NEI)## [1] "fips" "SCC" "Pollutant" "Emissions" "type" "year"str(SCC)## 'data.frame': 11717 obs. of 15 variables:
## $ SCC : Factor w/ 11717 levels "10100101","10100102",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ Data.Category : Factor w/ 6 levels "Biogenic","Event",..: 6 6 6 6 6 6 6 6 6 6 ...
## $ Short.Name : Factor w/ 11238 levels "","2,4-D Salts and Esters Prod /Process Vents, 2,4-D Recovery: Filtration",..: 3283 3284 3293 3291 3290 3294 3295 3296 3292 3289 ...
## $ EI.Sector : Factor w/ 59 levels "Agriculture - Crops & Livestock Dust",..: 18 18 18 18 18 18 18 18 18 18 ...
## $ Option.Group : Factor w/ 25 levels "","C/I Kerosene",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Option.Set : Factor w/ 18 levels "","A","B","B1A",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ SCC.Level.One : Factor w/ 17 levels "Brick Kilns",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ SCC.Level.Two : Factor w/ 146 levels "","Agricultural Chemicals Production",..: 32 32 32 32 32 32 32 32 32 32 ...
## $ SCC.Level.Three : Factor w/ 1061 levels "","100% Biosolids (e.g., sewage sludge, manure, mixtures of these matls)",..: 88 88 156 156 156 156 156 156 156 156 ...
## $ SCC.Level.Four : Factor w/ 6084 levels "","(NH4)2 SO4 Acid Bath System and Evaporator",..: 4455 5583 4466 4458 1341 5246 5584 5983 4461 776 ...
## $ Map.To : num NA NA NA NA NA NA NA NA NA NA ...
## $ Last.Inventory.Year: int NA NA NA NA NA NA NA NA NA NA ...
## $ Created_Date : Factor w/ 57 levels "","1/27/2000 0:00:00",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Revised_Date : Factor w/ 44 levels "","1/27/2000 0:00:00",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Usage.Notes : Factor w/ 21 levels ""," ","includes bleaching towers, washer hoods, filtrate tanks, vacuum pump exhausts",..: 1 1 1 1 1 1 1 1 1 1 ...head(SCC)## SCC Data.Category
## 1 10100101 Point
## 2 10100102 Point
## 3 10100201 Point
## 4 10100202 Point
## 5 10100203 Point
## 6 10100204 Point
## Short.Name
## 1 Ext Comb /Electric Gen /Anthracite Coal /Pulverized Coal
## 2 Ext Comb /Electric Gen /Anthracite Coal /Traveling Grate (Overfeed) Stoker
## 3 Ext Comb /Electric Gen /Bituminous Coal /Pulverized Coal: Wet Bottom
## 4 Ext Comb /Electric Gen /Bituminous Coal /Pulverized Coal: Dry Bottom
## 5 Ext Comb /Electric Gen /Bituminous Coal /Cyclone Furnace
## 6 Ext Comb /Electric Gen /Bituminous Coal /Spreader Stoker
## EI.Sector Option.Group Option.Set
## 1 Fuel Comb - Electric Generation - Coal
## 2 Fuel Comb - Electric Generation - Coal
## 3 Fuel Comb - Electric Generation - Coal
## 4 Fuel Comb - Electric Generation - Coal
## 5 Fuel Comb - Electric Generation - Coal
## 6 Fuel Comb - Electric Generation - Coal
## SCC.Level.One SCC.Level.Two
## 1 External Combustion Boilers Electric Generation
## 2 External Combustion Boilers Electric Generation
## 3 External Combustion Boilers Electric Generation
## 4 External Combustion Boilers Electric Generation
## 5 External Combustion Boilers Electric Generation
## 6 External Combustion Boilers Electric Generation
## SCC.Level.Three
## 1 Anthracite Coal
## 2 Anthracite Coal
## 3 Bituminous/Subbituminous Coal
## 4 Bituminous/Subbituminous Coal
## 5 Bituminous/Subbituminous Coal
## 6 Bituminous/Subbituminous Coal
## SCC.Level.Four Map.To Last.Inventory.Year
## 1 Pulverized Coal NA NA
## 2 Traveling Grate (Overfeed) Stoker NA NA
## 3 Pulverized Coal: Wet Bottom (Bituminous Coal) NA NA
## 4 Pulverized Coal: Dry Bottom (Bituminous Coal) NA NA
## 5 Cyclone Furnace (Bituminous Coal) NA NA
## 6 Spreader Stoker (Bituminous Coal) NA NA
## Created_Date Revised_Date Usage.Notes
## 1
## 2
## 3
## 4
## 5
## 6names(SCC)## [1] "SCC" "Data.Category" "Short.Name"
## [4] "EI.Sector" "Option.Group" "Option.Set"
## [7] "SCC.Level.One" "SCC.Level.Two" "SCC.Level.Three"
## [10] "SCC.Level.Four" "Map.To" "Last.Inventory.Year"
## [13] "Created_Date" "Revised_Date" "Usage.Notes"Just to be sure, let’s check is the all mentioned pollutants are PM 25 and the years are, as mentioned, 1999 2002 2005 2008
unique(NEI$Pollutant)## [1] "PM25-PRI"unique(NEI$year)## [1] 1999 2002 2005 2008- Of the four types of sources indicated by the ???????????????? (point, nonpoint, onroad, nonroad) variable, which of these four sources have seen decreases in emissions from 1999–2008 for Baltimore City? Which have seen increases in emissions from 1999–2008? Use the ggplot2 plotting system to make a plot answer this question.
NEI2<-NEI%>%
select(year, Emissions, fips, type)%>%
filter(fips == "24510")%>%
group_by(year, type)%>%
summarise(amount = sum(Emissions))
print(NEI2)## # A tibble: 16 x 3
## # Groups: year [?]
## year type amount
## <int> <chr> <dbl>
## 1 1999 NON-ROAD 522.94000
## 2 1999 NONPOINT 2107.62500
## 3 1999 ON-ROAD 346.82000
## 4 1999 POINT 296.79500
## 5 2002 NON-ROAD 240.84692
## 6 2002 NONPOINT 1509.50000
## 7 2002 ON-ROAD 134.30882
## 8 2002 POINT 569.26000
## 9 2005 NON-ROAD 248.93369
## 10 2005 NONPOINT 1509.50000
## 11 2005 ON-ROAD 130.43038
## 12 2005 POINT 1202.49000
## 13 2008 NON-ROAD 55.82356
## 14 2008 NONPOINT 1373.20731
## 15 2008 ON-ROAD 88.27546
## 16 2008 POINT 344.97518ggplot(NEI2, aes(y = amount, x = year, fill = type))+geom_point ( aes (color = type), size = 4) +labs ( x = "Year", y = "Amount of emissions", title = "Changes of emissions in Maryland") +geom_smooth ( method = "lm", se = FALSE, lwd = 0.5)
dev.copy(png, file="plot3.png", height=480, width=480)## quartz_off_screen
## 3dev.off()## quartz_off_screen
## 2According to the graph, we can track decreasing of all emission sources by the 2008, excepr point emission
- Across the United States, how have emissions from coal combustion-related sources changed from 1999–2008?
SCC_Coal<-SCC[grep("Coal", SCC$EI.Sector),]
NEI_Coal<-subset(NEI, NEI$SCC %in% SCC_Coal$SCC)
NEI_Coal$year<-as.factor(NEI_Coal$year)
val<-tapply(X = NEI_Coal$Emissions, NEI_Coal$year, sum)
with(NEI_Coal, plot( levels(year), val, xlab= "Year", ylab="Amount of emissions", type = "l"))
dev.copy(png, file="plot4.png")## quartz_off_screen
## 3dev.off()## quartz_off_screen
## 2The graph shows decreasing of coal emissions in US 1999-2008.
5.How have emissions from motor vehicle sources changed from 1999–2008 in Baltimore City?
“NEI ONROAD sources include emissions from onroad vehicles that use gasoline, diesel, and other fuels. # These sources include light duty and heavy duty vehicle emissions from operation on roads, highway ramps, and during idling.”
#(Taken from http://www.epa.gov/ttn/chief/eiinformation.html))
NEI3<-NEI%>%
select(year, Emissions, fips, type)%>%
filter(fips == "24510" | type == "ONROAD")%>%
group_by(year)%>%
summarise(amount = sum(Emissions))
print(NEI3)## # A tibble: 4 x 2
## year amount
## <int> <dbl>
## 1 1999 3274.180
## 2 2002 2453.916
## 3 2005 3091.354
## 4 2008 1862.282Plotting
ggplot(NEI3, aes(y = amount, x = year))+geom_line() +labs(title = "Changes of motor vehicle emissions in Maryland", x = "Year", y = "Amount of emissions") + geom_smooth(method = "lm", se = FALSE)
dev.copy(png, file="plot5.png", height=480, width=480)## quartz_off_screen
## 3dev.off()## quartz_off_screen
## 2The plot shows that the emossions from motor vehicle for the 1999-2008 period went down.
6.Compare emissions from motor vehicle sources in Baltimore City with emissions from motor vehicle sources in Los Angeles County, California (???????????????? == “????????????????????”). Which city has seen greater changes over time in motor vehicle emissions?
NEI4<-NEI%>%
select(year, Emissions, fips, type)%>%
filter(fips == "24510" | fips == "06037" | type == "ONROAD")%>%
group_by(fips, year)%>%
summarise(amount = sum(Emissions))
print(NEI4)## # A tibble: 8 x 3
## # Groups: fips [?]
## fips year amount
## <chr> <int> <dbl>
## 1 06037 1999 47103.192
## 2 06037 2002 26968.795
## 3 06037 2005 22939.780
## 4 06037 2008 32135.482
## 5 24510 1999 3274.180
## 6 24510 2002 2453.916
## 7 24510 2005 3091.354
## 8 24510 2008 1862.282plotting
c<-ggplot(NEI4, aes(fips, amount, fill = year))
c+geom_point(aes(color=year), size = 4) +labs ( x = "Year", y = "Amount of emissions", title = "Compare Baltimore and Los Angeles")+scale_x_discrete(labels=c("06037" = "Los Angeles", "24510" = "Baltimore"))
dev.copy(png, file="plot6.png", height=480, width=480)## quartz_off_screen
## 3dev.off()## quartz_off_screen
## 2The graph shows that Los Angeles has a greater changes in emoosions from motor vihecles over the time.