library(readxl)
Yelp_Dataset_Copy <- read_excel("Yelp Dataset - Copy.xlsx",col_types = c("text", "numeric", "numeric", "numeric", "text", "text", "text", "numeric", "numeric"))
#Randomly pick up 2000 samples and use set.seed(123) function to make result repeatable.
set.seed(123)
yelp <- Yelp_Dataset_Copy[sample(nrow(Yelp_Dataset_Copy), 2000),]
library(ggplot2)
pie <- ggplot(yelp, aes(x = "", y=yelp$Open, fill = factor(yelp$`Business Category`))) +
geom_bar(width = 1, stat = "identity") +
scale_fill_brewer(type = "seq", palette = "Set3", direction = 1) +
theme(axis.line = element_blank(),
plot.title = element_text(hjust=0.5)) +
labs(fill="Business type",
x=NULL,
y=NULL,
title="Pie Chart of Business on Yelp",
caption="Yelp Business Categories")
pie + coord_polar(theta = "y", start=0)
# Plot2: Stars of review
ggplot(yelp, aes(x=yelp$Stars)) +
geom_bar() +
xlab("Stars")+
ylab("Count") +
labs(title="Stars of Review")
#Plot 3: Map #reference:https://amunategui.github.io/ggmap-example/
library(ggplot2)
library(ggmap)
map<-get_map(location='united states', zoom=4, maptype = "terrain",
source='google',color='color')
## Map from URL : http://maps.googleapis.com/maps/api/staticmap?center=united+states&zoom=4&size=640x640&scale=2&maptype=terrain&language=en-EN&sensor=false
## Information from URL : http://maps.googleapis.com/maps/api/geocode/json?address=united%20states&sensor=false
ggmap(map) + geom_point(data = yelp, aes(x = yelp$Longitude, y = yelp$Latitude), size = 0.5, col = "red") +
labs(title = "Dot Map of Reviews",
x = " ",
y = " ")
## Warning: Removed 73 rows containing missing values (geom_point).
#Plot 4: Review Counts
plot(yelp$Review_Count, yelp$Stars, main = "Scatterplot of x1 vs. y1", type = 'p', col = 'red', pch = 16)
qplot(yelp$Stars, yelp$Review_Count, data = yelp)