Exploratory household energy usage data analysis, with R

Exploratory household energy usage data analysis, with R

Examine how household energy usage varies over a 2-day period in February, 2007. Your task is to reconstruct the following plots below, all of which were constructed using the base plotting system.

Step 1: fork and clone this GitHub repository

Step 2: Download the data to your working directory.

Let’s explore:

plot1<- function(){
        ## Aim of this function is to 
        ## 1. read the household_power_consumption.txt file
        ## 2. subset for data taken from 2 days: 2007-02-01 and 2007-02-02
        ## 3. generate a histogram of global active power(kilowatts)
        
        ## Parameters: none
        ## Assumes household_power_consumption.txt file located in working dir
        
        ## read data
        powerdata <- read.table("C:/Users/angul/OneDrive/R/ExploreData/Data/household_power_consumption.txt", stringsAsFactors = FALSE, header = TRUE, sep =";"  )
        
        ## change class of all columns to correct class
        powerdata$Date <- as.Date(powerdata$Date, format="%d/%m/%Y")
        powerdata$Time <- format(powerdata$Time, format="%H:%M:%S")
        powerdata$Global_active_power <- as.numeric(powerdata$Global_active_power)
        powerdata$Global_reactive_power <- as.numeric(powerdata$Global_reactive_power)
        powerdata$Voltage <- as.numeric(powerdata$Voltage)
        powerdata$Global_intensity <- as.numeric(powerdata$Global_intensity)
        powerdata$Sub_metering_1 <- as.numeric(powerdata$Sub_metering_1)
        powerdata$Sub_metering_2 <- as.numeric(powerdata$Sub_metering_2)
        powerdata$Sub_metering_3 <- as.numeric(powerdata$Sub_metering_3)
        
        ## subset data from 2007-02-01 and 2007-02-02
        subsetdata <- subset(powerdata, Date == "2007-02-01" | Date =="2007-02-02")
        
        ## plot histogram of global active power for those 2 days
        png("plot1.png", width=480, height=480)
        hist(subsetdata$Global_active_power, col="red", border="black", main ="Global Active Power", xlab="Global Active Power (kilowatts)", ylab="Frequency")
        dev.off()
}

plot1()

## Warning in plot1(): NAs introduced by coercion

## Warning in plot1(): NAs introduced by coercion

## Warning in plot1(): NAs introduced by coercion

## Warning in plot1(): NAs introduced by coercion

## Warning in plot1(): NAs introduced by coercion

## Warning in plot1(): NAs introduced by coercion

## png 
##   2

plot2 <- function(){
        ## Aim of this function is to 
        ## 1. read the household_power_consumption.txt file
        ## 2. subset for data taken from 2 days: 2007-02-01 and 2007-02-02
        ## 3. generate a plot of global active power vs. time
        
        ## Parameters: none
        ## Assumes household_power_consumption.txt file located in working dir
        
        ## read data
        powerdata <- read.table("C:/Users/angul/OneDrive/R/ExploreData/Data/household_power_consumption.txt", stringsAsFactors = FALSE, header = TRUE, sep =";"  )
        
        ## Create column in table with date and time merged together
        FullTimeDate <- strptime(paste(powerdata$Date, powerdata$Time, sep=" "), "%d/%m/%Y %H:%M:%S")
        powerdata <- cbind(powerdata, FullTimeDate)
        
        ## change class of all columns to correct class
        powerdata$Date <- as.Date(powerdata$Date, format="%d/%m/%Y")
        powerdata$Time <- format(powerdata$Time, format="%H:%M:%S")
        powerdata$Global_active_power <- as.numeric(powerdata$Global_active_power)
        powerdata$Global_reactive_power <- as.numeric(powerdata$Global_reactive_power)
        powerdata$Voltage <- as.numeric(powerdata$Voltage)
        powerdata$Global_intensity <- as.numeric(powerdata$Global_intensity)
        powerdata$Sub_metering_1 <- as.numeric(powerdata$Sub_metering_1)
        powerdata$Sub_metering_2 <- as.numeric(powerdata$Sub_metering_2)
        powerdata$Sub_metering_3 <- as.numeric(powerdata$Sub_metering_3)
        
        ## subset data from 2007-02-01 and 2007-02-02
        subsetdata <- subset(powerdata, Date == "2007-02-01" | Date =="2007-02-02")
        
        ## plot globalactivepower vs date&time
        png("plot2.png", width=480, height=480)
        with(subsetdata, plot(FullTimeDate, Global_active_power, type="l", xlab="Day", ylab="Global Active Power (kilowatts)"))
        dev.off()
}

plot2()

## Warning in plot2(): NAs introduced by coercion

## Warning in plot2(): NAs introduced by coercion

## Warning in plot2(): NAs introduced by coercion

## Warning in plot2(): NAs introduced by coercion

## Warning in plot2(): NAs introduced by coercion

## Warning in plot2(): NAs introduced by coercion

## png 
##   2

plot3 <- function(){
        ## Aim of this function is to 
        ## 1. read the household_power_consumption.txt file
        ## 2. subset for data taken from 2 days: 2007-02-01 and 2007-02-02
        ## 3. generate a plot of different submetering vs time
        
        ## Parameters: none
        ## Assumes household_power_consumption.txt file located in working dir
        
        ## read data
        powerdata <- read.table("C:/Users/angul/OneDrive/R/ExploreData/Data/household_power_consumption.txt", stringsAsFactors = FALSE, header = TRUE, sep =";"  )
    
        ## Create column in table with date and time merged together
        FullTimeDate <- strptime(paste(powerdata$Date, powerdata$Time, sep=" "), "%d/%m/%Y %H:%M:%S")
        powerdata <- cbind(powerdata, FullTimeDate)
            
        ## change class of all columns to correct class
        powerdata$Date <- as.Date(powerdata$Date, format="%d/%m/%Y")
        powerdata$Time <- format(powerdata$Time, format="%H:%M:%S")
        powerdata$Global_active_power <- as.numeric(powerdata$Global_active_power)
        powerdata$Global_reactive_power <- as.numeric(powerdata$Global_reactive_power)
        powerdata$Voltage <- as.numeric(powerdata$Voltage)
        powerdata$Global_intensity <- as.numeric(powerdata$Global_intensity)
        powerdata$Sub_metering_1 <- as.numeric(powerdata$Sub_metering_1)
        powerdata$Sub_metering_2 <- as.numeric(powerdata$Sub_metering_2)
        powerdata$Sub_metering_3 <- as.numeric(powerdata$Sub_metering_3)
        
        ## subset data from 2007-02-01 and 2007-02-02
        subsetdata <- subset(powerdata, Date == "2007-02-01" | Date =="2007-02-02")
        
        ## plot globalactivepower vs date&time
        png("plot3.png", width=480, height=480)
        with(subsetdata, plot(FullTimeDate, Sub_metering_1, type="l", xlab="Day", ylab="Energy sub metering"))
        lines(subsetdata$FullTimeDate, subsetdata$Sub_metering_2,type="l", col= "red")
        lines(subsetdata$FullTimeDate, subsetdata$Sub_metering_3,type="l", col= "blue")
        legend(c("topright"), c("Sub_metering_1", "Sub_metering_2", "Sub_metering_3"), lty= 1, lwd=2, col = c("black", "red", "blue"))
        dev.off()
}

plot3()

## Warning in plot3(): NAs introduced by coercion

## Warning in plot3(): NAs introduced by coercion

## Warning in plot3(): NAs introduced by coercion

## Warning in plot3(): NAs introduced by coercion

## Warning in plot3(): NAs introduced by coercion

## Warning in plot3(): NAs introduced by coercion

## png 
##   2

plot4 <- function() {
        ## Aim of this function is to 
        ## 1. read the household_power_consumption.txt file
        ## 2. subset for data taken from 2 days: 2007-02-01 and 2007-02-02
        ## 3. generate 4 plots in 1 space (GAP vs. time, Vol vs. time, submetering vs. time and GRP vs. time)
        
        ## Parameters: none
        ## Assumes household_power_consumption.txt file located in working dir
        
        ## read data
        powerdata <- read.table("C:/Users/angul/OneDrive/R/ExploreData/Data/household_power_consumption.txt", stringsAsFactors = FALSE, header = TRUE, sep =";"  )
        
        ## Create column in table with date and time merged together
        FullTimeDate <- strptime(paste(powerdata$Date, powerdata$Time, sep=" "), "%d/%m/%Y %H:%M:%S")
        powerdata <- cbind(powerdata, FullTimeDate)
        
        ## change class of all columns to correct class
        powerdata$Date <- as.Date(powerdata$Date, format="%d/%m/%Y")
        powerdata$Time <- format(powerdata$Time, format="%H:%M:%S")
        powerdata$Global_active_power <- as.numeric(powerdata$Global_active_power)
        powerdata$Global_reactive_power <- as.numeric(powerdata$Global_reactive_power)
        powerdata$Voltage <- as.numeric(powerdata$Voltage)
        powerdata$Global_intensity <- as.numeric(powerdata$Global_intensity)
        powerdata$Sub_metering_1 <- as.numeric(powerdata$Sub_metering_1)
        powerdata$Sub_metering_2 <- as.numeric(powerdata$Sub_metering_2)
        powerdata$Sub_metering_3 <- as.numeric(powerdata$Sub_metering_3)
        
        ## subset data from 2007-02-01 and 2007-02-02
        subsetdata <- subset(powerdata, Date == "2007-02-01" | Date =="2007-02-02")
        
        ## plot the 4 graphs
        png("plot4.png", width=480, height=480)
        par(mfrow=c(2,2))
        with(subsetdata, plot(FullTimeDate, Global_active_power, type="l", xlab="", ylab="Global Active Power"))
        with(subsetdata, plot(FullTimeDate, Voltage, type = "l", xlab="datetime", ylab="Voltage"))
        with(subsetdata, plot(FullTimeDate, Sub_metering_1, type="l", xlab="", ylab="Energy sub metering"))
        lines(subsetdata$FullTimeDate, subsetdata$Sub_metering_2,type="l", col= "red")
        lines(subsetdata$FullTimeDate, subsetdata$Sub_metering_3,type="l", col= "blue")
        legend(c("topright"), c("Sub_metering_1", "Sub_metering_2", "Sub_metering_3"), lty= 1, lwd=2, col = c("black", "red", "blue"))
        with(subsetdata, plot(FullTimeDate, Global_reactive_power, type="l", xlab="datetime", ylab="Global_reactive_power"))
        dev.off()
}

plot4()

## Warning in plot4(): NAs introduced by coercion

## Warning in plot4(): NAs introduced by coercion

## Warning in plot4(): NAs introduced by coercion

## Warning in plot4(): NAs introduced by coercion

## Warning in plot4(): NAs introduced by coercion

## Warning in plot4(): NAs introduced by coercion

## png 
##   2

#by Linda, September 2020