Example 1: Using iris dataset
# Nessasory libraries
library(ggplot2)
library(dplyr)
str(iris)
## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
# In iris data set we have 4 cotinuous numerical variable and,
# one categorical(factor) variable.
table(iris$Species)
##
## setosa versicolor virginica
## 50 50 50
ggplot(data = iris, aes(x=Sepal.Length, y=Petal.Length))
ggplot(data = iris, aes(x=Sepal.Length, y=Petal.Length)) + geom_point()
ggplot(data = iris, aes(x=Sepal.Length, y=Petal.Length)) + geom_point()
ggplot(data = iris, aes(x=Sepal.Length, y=Petal.Length, col=Species)) + geom_point()
ggplot(data = iris, aes(x=Sepal.Length, y=Petal.Length, col=Species, shape=Species)) +
geom_point() + xlab("Sepal Length") + ylab("Petal Length")
Example 2:
# Nessasory libraries
library(ggplot2)
library(dplyr)
# First import the data set
londonBike <- read.csv("londonBike.csv")
# Since in this data set x column is not usable
londonBike %>% select(c(-1)) -> mydata
# First lets underestand of this data set
# we have
table(mydata$hour)
##
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
## 724 724 721 721 721 721 726 726 724 727 725 727 729 728 728 729 730 728 728 727
## 20 21 22 23
## 727 726 725 722
##
## 0 1 2 3
## 4394 4387 4303 4330
##
## 1 2 3 4 5 6 7
## 2508 2505 2489 2492 2450 2465 2505
##
## 0 1
## 17030 384
table(mydata$weatherCond)
##
## 1 2 3 4 7 10 26
## 6150 4034 3551 1464 2141 14 60
# Lets do some basic graphing
# 1). Scatter plot
plot(mydata$temp ~ mydata$count)
plot(mydata$humidity ~ mydata$count)
plot(mydata$humidity ~ mydata$wind_speed,
ylab = "Humidity", xlab = "Wind Speed", main = "Humidity vs Wind Speed",
col = "blue", pch = 16)
# 2). Histogram
hist(mydata$count)
hist(mydata$temp,
xlab = "Temperature", main = "Histogram of Temperature", col = "purple")
# 3). Box plot
boxplot(mydata$temp)
boxplot(mydata$wind_speed)
boxplot(mydata$count ~ mydata$is_holiday,
xlab = "Is Holiday", ylab = "Bike count",
main = "Bike count based on Holiday or not",
col = "green", pch = 16)
boxplot(mydata$count ~ mydata$day,
xlab = "Days", ylab = "Bike count",
main = "Bike count based on Days",
col = "purple", pch = 16)
boxplot(mydata$count ~ mydata$season,
xlab = "Seasons", ylab = "Bike count",
main = "Bike count based on Seasons",
col = "red", pch = 16)
boxplot(mydata$count ~ mydata$hour,
xlab = "Hours", ylab = "Bike count",
main = "Bike count based on Hours",
col = "yellow", pch = 16)
# Now we do some more on these graphs by ggplot
ggplot(data = mydata)
ggplot(data = mydata, aes(y = count, x = hour))
ggplot(data = mydata) + geom_boxplot(aes(x=factor(hour),
y=count, fill=factor(hour)),
position=position_dodge(1),
show.legend = FALSE) +
ylab("Number of rentals per hour") +
xlab("Hour of the day")
# Here we use ggplot to create some awsome graphs.
# Nessasory libraries
library(ggplot2)
library(dplyr)
# We use LondonBike data set to perform this.
# ?select
# also like this >londonBike %>% select(c(-1)) -> mydata
select(londonBike, c(-1)) -> lb
#****************** ggplot *********************
# 1). Histogram
ggplot(data = lb)
ggplot(data = lb, aes(x = count))
ggplot(data = lb, aes(x = count)) + geom_histogram(bins = 75,
fill = "green",
col = "purple")
# positioning
ggplot(data = lb, aes(x=humidity, fill=is_holiday)) + geom_histogram(bins = 75)
