The aim of this coursework is to perform univariate analysis with the dplyr package. Furthermore, the ggplot2 packages will be used for incremental plots and the other packages for extra support.The dataset contains ten attributes and two responses denoted by HeatingLoad and CoolingLoad). The purpose is to use the eight features to predict each of the two responses.
library(here)
## here() starts at /Users/kelvinosuagwu/Desktop/parent/datavisualisation_&Analysis_CW
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
library(tidyr)
setwd(here::here())
energy <- read.csv("data/energy.csv", header = T, stringsAsFactors = T)
#check the class, if it is a data.frame
class(energy)
## [1] "data.frame"
#print few rows of the dataset
head(energy)
# let us check the structure of the dataset to view the datatype
str(energy)
## 'data.frame': 795 obs. of 10 variables:
## $ Instance : int 1 2 3 4 5 6 7 8 9 10 ...
## $ AproxArea : num 556 463 463 540 514 ...
## $ WallArea : num 279 283 296 294 297 ...
## $ RoofArea : num 104 117 108 104 105 ...
## $ GlassArea : num 0 0 0 0 30 ...
## $ Height : Factor w/ 2 levels "high","low": 1 1 1 1 1 1 1 1 1 1 ...
## $ Condition : Factor w/ 5 levels "A","B","C","D",..: 1 3 2 2 1 3 3 3 3 3 ...
## $ Orientation: Factor w/ 4 levels "E","N","S","W": 1 2 3 4 1 1 1 1 1 2 ...
## $ HeatingLoad: num 15.6 15.6 15.6 15.6 24.6 ...
## $ CoolingLoad: num 21.3 21.3 21.3 21.3 26.3 ...
# view dataset if NA is present
summary(energy) #heating load variable has 4NA'S
## Instance AproxArea WallArea RoofArea
## Min. : 1.0 Min. :463.1 Min. :227.8 Min. :103.6
## 1st Qu.:199.5 1st Qu.:602.0 1st Qu.:285.2 1st Qu.:138.2
## Median :398.0 Median :673.8 Median :314.6 Median :207.3
## Mean :398.0 Mean :674.1 Mean :319.1 Mean :179.0
## 3rd Qu.:596.5 3rd Qu.:746.7 3rd Qu.:344.2 3rd Qu.:220.5
## Max. :795.0 Max. :889.4 Max. :550.8 Max. :238.1
##
## GlassArea Height Condition Orientation HeatingLoad
## Min. : 0.00 high:384 A:117 E:202 Min. : 6.01
## 1st Qu.: 32.49 low :411 B:135 N:197 1st Qu.:12.93
## Median : 75.71 C:517 S:195 Median :17.37
## Mean : 75.00 D: 4 W:201 Mean :21.98
## 3rd Qu.:112.90 E: 22 3rd Qu.:31.20
## Max. :174.93 Max. :43.10
## NA's :4
## CoolingLoad
## Min. :10.90
## 1st Qu.:15.49
## Median :21.33
## Mean :24.28
## 3rd Qu.:32.92
## Max. :48.03
##
# this is a dependent variable, check if the datatype is numeric
is.numeric(energy$HeatingLoad) #TRUE
## [1] TRUE
# drop the instance variable using subset function
energy <- subset(energy, select = -c(Instance) )
# check for NA
energy.isNa <- is.na(energy) #check for missing values
sum(energy.isNa) #4 missing values double checked
## [1] 4
# This function replaces missing(NA'S) Heating load data with Mean
# returns a mean with decimals up to 5 places
energy$HeatingLoad <- ifelse(is.na(energy$HeatingLoad),
ave(energy$HeatingLoad,
FUN = function(x) mean(x, na.rm = TRUE) )
,energy$HeatingLoad)
str(energy$HeatingLoad)
## num [1:795] 15.6 15.6 15.6 15.6 24.6 ...
class(energy$HeatingLoad)
## [1] "numeric"
#format and round the variable to the nearest decimal number of 2
# to be at par with the other features/variables
energy$HeatingLoad <- format(round(energy$HeatingLoad, digits = 2), nsmall = 2)
# convert to numeric datatype after formatting
energy$HeatingLoad <- as.numeric(energy$HeatingLoad)
summary(energy)
## AproxArea WallArea RoofArea GlassArea Height
## Min. :463.1 Min. :227.8 Min. :103.6 Min. : 0.00 high:384
## 1st Qu.:602.0 1st Qu.:285.2 1st Qu.:138.2 1st Qu.: 32.49 low :411
## Median :673.8 Median :314.6 Median :207.3 Median : 75.71
## Mean :674.1 Mean :319.1 Mean :179.0 Mean : 75.00
## 3rd Qu.:746.7 3rd Qu.:344.2 3rd Qu.:220.5 3rd Qu.:112.90
## Max. :889.4 Max. :550.8 Max. :238.1 Max. :174.93
## Condition Orientation HeatingLoad CoolingLoad
## A:117 E:202 Min. : 6.01 Min. :10.90
## B:135 N:197 1st Qu.:12.93 1st Qu.:15.49
## C:517 S:195 Median :17.50 Median :21.33
## D: 4 W:201 Mean :21.98 Mean :24.28
## E: 22 3rd Qu.:30.59 3rd Qu.:32.92
## Max. :43.10 Max. :48.03
# Check the summary again to see if the values where HeatingLoad values were rounded.
head(energy)
Central tendency and Spread for APROX AREA variable: This is going to be considered as a continuous scale
#check the summary statistics for this variable
summary(energy$AproxArea)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 463.1 602.0 673.8 674.1 746.7 889.4
sd(energy$AproxArea)
## [1] 96.66033
Median value using a vertical red line
# let us use dot plot to describe the data
#using line to check if the median is a typical value of this dataset
aproxArea.plot <- ggplot(energy, aes(x= AproxArea)) +
geom_dotplot(col="black", fill="gold" , binwidth= 7) +
labs(x="Approximate area of home", y="") +
theme_classic() +
geom_vline(xintercept = 673.8, color = "red", size=0.5)
aproxArea.plot
aproxArea.plot<- ggplot(energy, aes(y= AproxArea)) +
geom_boxplot(col="blue", fill="lightblue") +
labs(title="The Approximate area of the Home per energy usage in 2016", x="",y="AproxArea")+
theme_classic()
aproxArea.plot
Histograms
aproxArea.plot <- ggplot(energy, aes(x= AproxArea)) +
geom_histogram(aes(y=..density..),col="red", fill="grey" , binwidth=20) +
geom_vline(xintercept = median(energy$AproxArea), lwd = 2, size=0.01) +
labs(x="Distribution of Approximate area of the Home per energy usage in 2016", y="Density") +
geom_density(col="blue") + theme_classic()
## Warning: Duplicated aesthetics after name standardisation: size
aproxArea.plot
Description
Central tendency and Spread for WALL AREA variable: This is going to be considered as a continuous scale
#check the summary statistics for this variable
summary(energy$WallArea)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 227.8 285.2 314.6 319.1 344.2 550.8
Histograms plus the spread(density)
# The line is the median
wallArea.plot <- ggplot(energy, aes(x= WallArea)) +
geom_histogram(aes(y=..density..),col="red", fill="grey" , binwidth=20) +
geom_vline(xintercept = median(energy$WallArea), lwd = 2, size=0.01) +
labs(x="Distribution of Approximate area of the Home per energy usage in 2016", y="Density") +
geom_density(col="blue") + theme_classic()
## Warning: Duplicated aesthetics after name standardisation: size
wallArea.plot
# let us use dot plot to describe the data
#using line to check if the median is a typical value of this dataset
library(cowplot) #cowplot package for grid
wallA.plotMedian <- ggplot(energy, aes(x= WallArea)) +
geom_dotplot(col="black", fill="gold" , binwidth= 7) +
labs(x="Distribution of wall Area", y="") +
theme_classic() +
geom_vline(xintercept = 314.6, color = "red", size=0.7)
#using line to check if the mean is a typical value of this dataset
wallA.plotMean <- ggplot(energy, aes(x= WallArea)) +
geom_dotplot(col="black", fill="gold" , binwidth= 7) +
labs(x="Distribution of wall Area", y="") +
theme_classic() +
geom_vline(xintercept = 319.1, color = "red", size=0.7)
plot_grid(wallA.plotMedian, wallA.plotMean, labels = "AUTO") #grid of two rows
#box plot
wallArea.plot<- ggplot(energy, aes(y= WallArea)) +
geom_boxplot(col="blue", fill="lightblue") +
labs(title="The Wall area in (sqft) for Home energy usage in 2016", x="",y="Average Wall Area in sqft") +
theme_classic()
wallArea.plot
Description
Central tendency and Spread for ROOF AREA variable: This is going to be considered as a continuous scale
#check the summary statistics for this variable
summary(energy$RoofArea)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 103.6 138.2 207.3 179.0 220.5 238.1
roofArea.plot <- ggplot(energy, aes(y= RoofArea)) +
geom_boxplot(col="blue", fill="lightblue") +
labs(title="The Roof area in (sqft) for Home energy usage in 2016", x="",y="Average roofArea sqft") +
theme_classic()
roofArea.plot
# The line is the mean
roofArea.plotMean <- ggplot(energy, aes(x= RoofArea)) +
geom_histogram(aes(y=..density..),col="red", fill="grey" , binwidth=20) +
geom_vline(xintercept = mean(energy$RoofArea), lwd = 2, size=0.01) +
labs(x="Distribution of Roof area ", y="Density") +
geom_density(col="blue") + theme_classic()
## Warning: Duplicated aesthetics after name standardisation: size
# The line is the median
roofArea.plotMedian <- ggplot(energy, aes(x= RoofArea)) +
geom_histogram(aes(y=..density..),col="red", fill="grey" , binwidth=20) +
geom_vline(xintercept = median(energy$RoofArea), lwd = 2, size=0.01) +
labs(x="Distribution of Roof area ", y="Density") +
geom_density(col="blue") + theme_classic()
## Warning: Duplicated aesthetics after name standardisation: size
plot_grid(roofArea.plotMean , roofArea.plotMedian, labels = "AUTO") #grid of two rows
#using line to check if the median is representative of this dataset
roofA.plotMedian <- ggplot(energy, aes(x= RoofArea)) +
geom_dotplot(col="black", fill="gold" , binwidth= 4) +
labs(x="Distribution of roof Area", y="") +
theme_classic() +
geom_vline(xintercept = 207.3 , color = "red", size=0.2)
#using line to check if the mean is representative of this dataset
roofB.plotMean <- ggplot(energy, aes(x= RoofArea)) +
geom_dotplot(col="black", fill="gold" , binwidth= 4) +
labs(x="Distribution of roof Area", y="") +
theme_classic() +
geom_vline(xintercept = 179.0, color = "red", size=0.2)
plot_grid(roofA.plotMedian, roofB.plotMean, labels = "AUTO") #grid of two rows
Description
Central tendency and Spread for GLASS AREA variable: This is going to be considered as a continuous variable
#check the summary statistics for this variable
summary(energy$GlassArea)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 32.49 75.71 75.00 112.90 174.93
#boxplot
glassArea.plot <- ggplot(energy, aes(y= GlassArea)) +
geom_boxplot(col="red", fill="lightblue") +
labs(title="The glass area in (sqft) for Home energy usage in 2016", x="glass area ",y="Average glassArea sqft") +
theme_classic()
glassArea.plot
Description
Central tendency and Spread for Height variable: This is going to be considered as a discrete /categorical variable
#check the summary statistics for this variable
summary(energy$Height)
## high low
## 384 411
# plot the bars in ascending order
ggplot(energy, aes(x = Height)) +
geom_bar(fill = "light blue",
color="black") +
labs(x = "Height of building",
y = "Frequency",
title = "The Height of building for Home energy usage in 2016")
Plot By Percentage
# plot the distribution as percentages
ggplot(energy,
aes(x = Height,
y = ..count.. / sum(..count..))) +
geom_bar() +
labs(x = "Height of building",
y = "Percent",
title = "The Height of building for Home energy usage in 2016") +
scale_y_continuous(labels = scales::percent)
Description
Central tendency and Spread for Condition variable: This is going to be considered as a discrete /categorical variable
#check the summary statistics for this variable
summary(energy$Condition)
## A B C D E
## 117 135 517 4 22
# plot the bars in ascending order
ggplot(energy, aes(x = Condition)) +
geom_bar(fill = "light blue",
color="black") +
labs(x = "Condition of building",
y = "Frequency",
title = "The Condition of building that affects Home energy usage in 2016")
# plot the distribution as percentages
ggplot(energy,
aes(x = Condition,
y = ..count.. / sum(..count..))) +
geom_bar() +
labs(x = "Condition of building",
y = "Percent",
title = "The Condition of building for Home energy usage in 2016") +
scale_y_continuous(labels = scales::percent)
# Basic piechart for the Condition dataset
library(plyr)
## ------------------------------------------------------------------------------
## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)
## ------------------------------------------------------------------------------
##
## Attaching package: 'plyr'
## The following objects are masked from 'package:dplyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize
## The following object is masked from 'package:here':
##
## here
# counting the number of staff per site.
pieData <- count(energy$Condition)
#rename the column
names(pieData) <- c("Condition", "frequency")
pieData
# order data according to the site (important for placing labels later on)
pieData <- arrange(pieData,desc(Condition))
# create new column with position for label
pieData <- mutate(pieData, positionLabel = cumsum(pieData$frequency) - 0.5*pieData$frequency)
# creating plot
pieData.plot <- ggplot(pieData, aes(x="", y= frequency, fill = Condition)) +
geom_bar(width = 1, stat="identity") +
coord_polar("y", start=0) +
geom_text(aes(y = positionLabel, label = frequency)) +
scale_fill_manual(values = c("red","blue", "lightblue", "purple", "grey"))
pieData.plot
Description
Central tendency and Spread for Orientation variable: This is going to be considered as a discrete /categorical variable
#check the summary statistics for this variable
summary(energy$Orientation)
## E N S W
## 202 197 195 201
# Basic piechart for the Condition dataset
# counting the number of staff per site.
pieData <- count(energy$Orientation)
#rename the column
names(pieData) <- c("Orientation", "frequency")
pieData
# order data according to the site (important for placing labels later on)
pieData <- arrange(pieData,desc(Orientation))
# create new column with position for label
pieData <- mutate(pieData, positionLabel = cumsum(pieData$frequency) - 0.5*pieData$frequency)
# creating plot
pieData.plot <- ggplot(pieData, aes(x="", y= frequency, fill = Orientation)) +
geom_bar(width = 1, stat="identity") +
coord_polar("y", start=0) +
geom_text(aes(y = positionLabel, label = frequency)) +
scale_fill_manual(values = c("red","blue", "lightblue", "purple", "grey")) +
# removing outer "ring"
theme_void()
pieData.plot
Description
Central tendency and Spread for Heating Load dependent variable: This is going to be considered as a continuous variable
#check the summary statistics for this variable
summary(energy$HeatingLoad)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 6.01 12.93 17.50 21.98 30.59 43.10
#using line to check if the median is representative of this dataset
heatLoadA.plotMedian <- ggplot(energy, aes(x= HeatingLoad)) +
geom_dotplot(col="black", fill="gold" , binwidth= 1) +
labs(x="Distribution of HeatingLoad data", y="") +
theme_classic() +
geom_vline(xintercept = 17.50 , color = "red", size=0.7)
#using line to check if the mean is representative of this dataset
heatLoadB.plotMean <- ggplot(energy, aes(x= HeatingLoad)) +
geom_dotplot(col="black", fill="gold" , binwidth= 1) +
labs(x="Distribution of HeatingLoad data", y="") +
theme_classic() +
geom_vline(xintercept = 21.98, color = "red", size=0.7)
plot_grid(heatLoadA.plotMedian, heatLoadB.plotMean, labels = "AUTO") #grid of two rows
#boxplot on heating load object
hl.plot <- ggplot(energy, aes(y= HeatingLoad)) +
geom_boxplot(col="black", fill="lightblue") +
labs(title="The heating Load for Homes in 2016", x="heating ",y="Average heating Load in British Thermal Unit") +
theme_classic()
hl.plot
Description
Central tendency and Spread for Cooling Load dependent variable: This is going to be considered as a continuous variable
#check the summary statistics for this variable
summary(energy$CoolingLoad)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.90 15.49 21.33 24.28 32.92 48.03
#boxplot on cooling load object
cl.plot <- ggplot(energy, aes(y= CoolingLoad)) +
geom_boxplot(col="black", fill="lightblue") +
labs(title="The Cooling Load for Homes in 2016", x="cooling ",y="Average cooling Load in British Thermal Unit") +
theme_classic()
cl.plot
#using line to check if the mean is representative of this dataset
cLoad.plotMean <- ggplot(energy, aes(x= CoolingLoad)) +
geom_dotplot(col="black", fill="gold" , binwidth= 0.5) +
labs(x="Distribution of Cooling Load data", y="") +
theme_classic() +
geom_vline(xintercept = 24.28, color = "red", size=0.7)
cLoad.plotMean
Description
noDCondition = droplevels(energy[!energy$Condition == 'D',])
table(noDCondition$Condition)
##
## A B C E
## 117 135 517 22
datasetNumber <- c(1:18)
coolingLoad <- c(23,24,23,25,24,23,26,24,23,25,24,23,26,22,25,25,22,24)
combine<- data.frame(datasetNumber, coolingLoad)
print(combine)
## datasetNumber coolingLoad
## 1 1 23
## 2 2 24
## 3 3 23
## 4 4 25
## 5 5 24
## 6 6 23
## 7 7 26
## 8 8 24
## 9 9 23
## 10 10 25
## 11 11 24
## 12 12 23
## 13 13 26
## 14 14 22
## 15 15 25
## 16 16 25
## 17 17 22
## 18 18 24
t.test(x=combine$coolingLoad, alternative="two.sided", paired=F, mu=23.5, conf.level = 0.99)
##
## One Sample t-test
##
## data: combine$coolingLoad
## t = 1.5567, df = 17, p-value = 0.138
## alternative hypothesis: true mean is not equal to 23.5
## 99 percent confidence interval:
## 23.11696 24.77193
## sample estimates:
## mean of x
## 23.94444
# shapiro.test(combine$coolingLoad)