Course project 2.Rmd

---
title: "Course Project 2"
author: "Tanishq"
date: "6 November 2016"
output: pdf_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```





```{r}
require(ggplot2)
NEI<-readRDS("/media/hduser/New Volume1/course /course1/exploratory-data-analysis/summarySCC_PM25.rds")

Source_classification<-readRDS("/media/hduser/New Volume1/course /course1/exploratory-data-analysis/Source_Classification_Code.rds")
#for question 1
#First we'll aggregate the total PM2.5 emission from 
#all sources for each of the years 1999, 2002, 2005, and 2008.
Total_agg <- aggregate(Emissions ~ year,NEI, sum)
barplot( (Total_agg$Emissions)/10^6,names.arg = Total_agg$year,
             xlab = "YEAR",ylab = "PM2.5 Emission (10^6)",
                main="Emission From All US Sources")
#for Question 2 
#Have total emissions from PM2.5 decreased in the Baltimore 
#City, Maryland (fips == "24510") from 1999 to 2008?
baltimoreNEI <- NEI[NEI$fips=="24510",]
Total_agg_Baltimore <- aggregate(Emissions ~ year, baltimoreNEI,sum)
barplot(Total_agg_Baltimore$Emissions,names.arg = Total_agg_Baltimore$year,
        xlab="YEAR",ylab="PM2.5 Emissions (Tons)",
        main="ALL Emission From Baltimore City Sources")
#for question 3
#Overall total emissions from PM2.5 have decreased in Baltimore City,
#Maryland from 1999 to 2008.
ggpq3<-ggplot(baltimoreNEI,aes(factor(year),Emissions,fill=type))+
        geom_bar(stat="identity")+theme_bw()+guides(fill=FALSE)+
        facet_grid(.~type,scales = "free",space = "free")+
        labs(x="YEAR",y=expression("TOTAL PM2.5 IN TONS"))+
        labs(title=expression(("PM[2.5]"*"Emissions,baltimore city 99-08 by all source")))

print(ggpq3)
#for question 4
#Which have seen increases in emissions from 1999–2008?
#subset the required data
coal_realted<-grepl("coal",Source_classification$SCC.Level.Four,ignore.case = TRUE)
combustion_realted<-grepl("comb",Source_classification$SCC.Level.One,ignore.case = TRUE)

coal_combustion<-(combustion_realted & coal_realted)
combustion_Source_classification <- Source_classification[coal_combustion,]$SCC
combustionNEI <- NEI[NEI$SCC%in% combustion_Source_classification ,]
ggpq4 <- ggplot(combustionNEI,aes(factor(year),Emissions/10^5)) +
geom_bar(stat="identity",fill="grey",width=0.75) +
theme_bw() +  guides(fill=FALSE) +
labs(x="year", y=expression("Total PM"[2.5]*" Emission (10^5 Tons)")) +
labs(title=expression("PM"[2.5]*" Coal Combustion Source Emissions Across US from 1999-2008"))
print(ggpq4)
# for question 5
#First we subset the motor vehicles, 
#which we assume is anything like Motor Vehicle in SCC.Level.Two.

vehicles <- grepl("vehicle",Source_classification$SCC.Level.Two,ignore.case = TRUE)
vehiclesSCC <- Source_classification[vehicles,]$SCC
vehiclesNEI <- NEI[NEI$SCC %in% vehiclesSCC,]
#we subset for motor vehicles in Baltimore
baltimoreVehiclesNEI <- vehiclesNEI[vehiclesNEI$fips==24510,]
ggpq5<- ggplot(baltimoreVehiclesNEI,aes(factor(year),Emissions)) +
geom_bar(stat="identity",fill="grey",width=0.75) +
theme_bw() +  guides(fill=FALSE) +
labs(x="year", y=expression("Total PM"[2.5]*" Emission (10^5 Tons)")) +
labs(title=expression("PM"[2.5]*" Motor Vehicle Source Emissions in Baltimore from 1999-2008"))
print(ggpq5)
#for question 6
#Emissions from motor vehicle sources have dropped from 1999-2008 in Baltimore City!
vehiclesBaltimoreNEI <- vehiclesNEI[vehiclesNEI$fips == 24510,]
vehiclesBaltimoreNEI$city <- "Baltimore City"
vehiclesLANEI <- vehiclesNEI[vehiclesNEI$fips=="06037",]
vehiclesLANEI$city <- "Los Angeles County"
bothNEI <- rbind(vehiclesBaltimoreNEI,vehiclesLANEI)

ggpq6 <- ggplot(bothNEI, aes(x=factor(year), y=Emissions, fill=city)) +
        geom_bar(aes(fill=year),stat="identity") +
        facet_grid(scales="free", space="free", .~city) +
        guides(fill=FALSE) + theme_bw() +
        labs(x="year", y=expression("Total PM"[2.5]*" Emission (Kilo-Tons)")) + 
        labs(title=expression("PM"[2.5]*" Motor Vehicle Source Emissions in Baltimore & LA, 1999-2008"))

print(ggpq6)
```