Summary

In this project, we use Exploratory data analysis techniques in order to analyze PM2.5 emissions from different sources in different US states.

Plot 1:

NEI <- readRDS("~/exdata-data-NEI_data/summarySCC_PM25.rds")
NEI1 <- tapply(NEI$Emissions,NEI$year,sum)
plot(names(NEI1),NEI1,type="b",col="red",xlab="Year",ylab="Total Emissions PM2.5")

Plot 2:

NEI <- readRDS("~/exdata-data-NEI_data/summarySCC_PM25.rds")
NEI2 <- subset(NEI, NEI$fips=="24510")
NEI3 <- tapply(NEI2$Emissions,NEI2$year,sum)
plot(names(NEI3),NEI3,type="b",col="red",xlab="Year",ylab="Total Emissions PM2.5 in Baltimore")

Plot 3:

library(ggplot2)
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
NEI <- readRDS("~/exdata-data-NEI_data/summarySCC_PM25.rds")
NEI2 <- subset(NEI, NEI$fips=="24510")
GroupedData <- group_by(NEI2,year,type)
Summary <- summarise(GroupedData,EmissionsSum=sum(Emissions))
g <- ggplot(Summary,aes(year,EmissionsSum))
p <- g + geom_point()+geom_smooth()+labs(title= "PM2.5 Emissions Evolution per source type in Baltimore")+ labs(y="Total PM2.5 Emissions")+facet_grid(.~type)
print(p)

Plot 4:

library(dplyr)
NEI <- readRDS("~/exdata-data-NEI_data/summarySCC_PM25.rds")
SCC <- readRDS("~/exdata-data-NEI_data/Source_Classification_Code.rds")
NEISCC <- merge(NEI,SCC,by.x="SCC",by.y="SCC")
NEISCCCoal <- NEISCC[which(grepl("Coal",NEISCC$EI.Sector)==TRUE),]
NEISCCCoal2 <- tapply(NEISCCCoal$Emissions,NEISCCCoal$year,sum)
plot(names(NEISCCCoal2),NEISCCCoal2,type="b",col="red",xlab="Year",ylab="Total Emissions PM2.5 from Coal Combustion sources")

## Plot 5:

library(dplyr)
NEI <- readRDS("~/exdata-data-NEI_data/summarySCC_PM25.rds")
SCC <- readRDS("~/exdata-data-NEI_data/Source_Classification_Code.rds")
NEISCC <- merge(NEI2,SCC,by.x="SCC",by.y="SCC")
NEISCCVehicle <- NEISCC[which(grepl("Vehicles",NEISCC$EI.Sector)==TRUE),]
NEISCCVehicle2 <- subset(NEISCCVehicle,NEISCCVehicle$fips=="24510")
NEISCCVehicle3 <- tapply(NEISCCVehicle2$Emissions,NEISCCVehicle2$year,sum)
plot(names(NEISCCVehicle3),NEISCCVehicle3,type="b",col="red",xlab="Year",ylab="Total Emissions PM2.5 from Vehicles sources in Baltimore")

## Plot 6:

library(dplyr)
NEI <- readRDS("~/exdata-data-NEI_data/summarySCC_PM25.rds")
SCC <- readRDS("~/exdata-data-NEI_data/Source_Classification_Code.rds")
NEISCC <- merge(NEI,SCC,by.x="SCC",by.y="SCC")
NEISCCVehicle <- NEISCC[which(grepl("Vehicles",NEISCC$EI.Sector)==TRUE),]
NEISCCVehicle4 <- subset(NEISCCVehicle,NEISCCVehicle$fips=="24510")
NEISCCVehicle5 <- tapply(NEISCCVehicle4$Emissions,NEISCCVehicle4$year,sum)
NEISCCVehicle6 <- subset(NEISCCVehicle,NEISCCVehicle$fips=="06037")
NEISCCVehicle7 <- tapply(NEISCCVehicle6$Emissions,NEISCCVehicle6$year,sum)
par(mfrow=c(1,2))
plot(names(NEISCCVehicle5),NEISCCVehicle5,type="b",col="red",xlab="Year",ylab="Total Emissions PM2.5 from Vehicles sources",main="Baltimore") 
plot(names(NEISCCVehicle7),NEISCCVehicle7,type="b",col="red",xlab="Year",ylab="Total Emissions PM2.5 from Vehicles sources",main="Los Angeles")