Uber Data Analysis Project
Unsa Jamil
3/6/2020
Import Libraries
library(ggplot2)
library(ggthemes)
library(lubridate)
library(dplyr)
library(tidyr)
library(DT)
library(scales)Create Vector Of Colors To Be Implemented In Our Plots
colorsData <- c("#CC1011", "#665555", "#05a399", "#cfcaca", "#f5e840", "#0683c9", "#e075b0")Reading Data
Now, we will read several csv files that contain the data from April 2014 to September 2014.
aprilData <- read.csv("uber-raw-data-apr14.csv")
mayData <- read.csv("uber-raw-data-may14.csv")
juneData <- read.csv("uber-raw-data-jun14.csv")
julyData <- read.csv("uber-raw-data-jul14.csv")
augustData <- read.csv("uber-raw-data-aug14.csv")
septemberData <- read.csv("uber-raw-data-sep14.csv")Combine All Files In One Dataset
Now we will combine all of these files into a single dataframe.
uberData <- rbind(aprilData,mayData,juneData,julyData,augustData,septemberData)
head(uberData)## Date.Time Lat Lon Base
## 1 4/1/2014 0:11:00 40.7690 -73.9549 B02512
## 2 4/1/2014 0:17:00 40.7267 -74.0345 B02512
## 3 4/1/2014 0:21:00 40.7316 -73.9873 B02512
## 4 4/1/2014 0:28:00 40.7588 -73.9776 B02512
## 5 4/1/2014 0:33:00 40.7594 -73.9722 B02512
## 6 4/1/2014 0:33:00 40.7383 -74.0403 B02512dim(uberData)## [1] 4534327 4Formatting Of Date And Time Column
we will perform the appropriate formatting of Date.Time column.
uberData$Date.Time <- as.POSIXct(uberData$Date.Time,format="%m/%d/%Y%H:%M:%S")
uberData$Time <- format(as.POSIXct(uberData$Date.Time,format="%m/%d/%Y %H:%M:%S"), format="%H:%M:%S")
uberData$Date.Time <- ymd_hms(uberData$Date.Time)Create Factors
Now create factors of time objects like day, month, year etc.
uberData$day <- factor(day(uberData$Date.Time))
uberData$month <- factor(month(uberData$Date.Time,label = TRUE))
uberData$year <- factor(year(uberData$Date.Time))
uberData$daysofweek <- factor(wday(uberData$Date.Time,label = TRUE))
uberData$hour <- factor(hour(hms(uberData$Time)))
uberData$minute <- factor(minute(hms(uberData$Time)))
uberData$second <- factor(second(hms(uberData$Time)))Plotting the trips by the hours in a day
In the next step we will use the ggplot function to plot the number of trips that the passengers had made in a day. We will also use dplyr to aggregate our data. In the resulting visualizations, we can understand how the number of passengers fares throughout the day.
dataUber <- uberData
hourData <- dataUber%>%group_by(hour)%>%
dplyr::summarize(Total=n())
head(hourData,10)## # A tibble: 10 x 2
## hour Total
## <fct> <int>
## 1 0 103836
## 2 1 67227
## 3 2 45865
## 4 3 48287
## 5 4 55230
## 6 5 83939
## 7 6 143213
## 8 7 193094
## 9 8 190504
## 10 9 159967Trips Every Hour
ggplot(hourData,aes(hour,Total))+
geom_bar(stat = "identity",fill="orange",color="black")+
ggtitle("Trips Every Hour")+
theme(legend.position = "none")+theme_light()+
scale_y_continuous(labels = comma)+xlab("Hour")+ylab("Total Trips")
Trips By Hour And Month
monthHour <- dataUber%>%group_by(month,hour)%>%
dplyr::summarize(Total=n())
ggplot(monthHour,aes(hour,Total,fill=month))+
geom_bar(stat = "identity")+ggtitle("Trips By Hour And Month")+
theme_light()+scale_y_continuous(labels = comma)+xlab("Hour")
Plotting Data By Trips During Every Day Of The Month
We observe from the resulting visualization that 30th of the month had the highest trips in the year which is mostly contributed by the month of April.
dayGroup <- dataUber%>%group_by(day)%>%
dplyr::summarize(Total=n())
head(dayGroup,10)## # A tibble: 10 x 2
## day Total
## <fct> <int>
## 1 1 127430
## 2 2 143201
## 3 3 142983
## 4 4 140923
## 5 5 147054
## 6 6 139886
## 7 7 143503
## 8 8 145984
## 9 9 155135
## 10 10 152500ggplot(dayGroup,aes(day,Total))+
geom_bar(stat = "identity",fill="salmon",color="white")+
ggtitle("Trips Every Day")+
theme(legend.position = "none")+
scale_y_continuous(labels = comma)+theme_light()+xlab("Day")
Trips By Day And Month
daymg <- dataUber%>%
group_by(month,day,daysofweek)%>%
dplyr::summarize(Total=n())
ggplot(daymg,aes(month,Total,fill=daysofweek))+
geom_bar(stat = "identity",position = "dodge")+
ggtitle("Trips By Day And Month")+
scale_y_continuous(labels = comma)+
scale_fill_manual(values = colorsData)+xlab("Month")+
theme_light()
Number Of Trips Taking Place During Months In A Year
We will visualize the number of trips that are taking place each month of the year. In the output visualization, we observe that most trips were made during the month of September. Furthermore, we also obtain visual reports of the number of trips that were made on every day of the week.
monthGroup <- dataUber%>%
group_by(month)%>%
dplyr::summarize(Total=n())
head(monthGroup)## # A tibble: 6 x 2
## month Total
## <ord> <int>
## 1 Apr 564516
## 2 May 652435
## 3 Jun 663844
## 4 Jul 796121
## 5 Aug 829275
## 6 Sep 1028136ggplot(monthGroup,aes(month,Total,fill=month))+
geom_bar(stat = "identity")+
ggtitle("Trips By Month")+theme(legend.position = "none")+
scale_y_continuous(labels = comma)+theme_light()+xlab("Month")
monthWeekday <- dataUber%>%
group_by(month,daysofweek)%>%
summarize(Total=n())
ggplot(monthWeekday,aes(month,Total,fill=daysofweek))+
geom_bar(stat = "identity",position = "dodge")+
ggtitle("Trips By Day And Month")+
scale_y_continuous(labels = comma)+
scale_fill_manual(values = colorsData)+xlab("Month")+
theme_light()
Number Of Trips By Bases
In the following visualization, we plot the number of trips that have been taken by the passengers from each of the bases. There are five bases in all out of which, we observe that B02617 had the highest number of trips. Furthermore, this base had the highest number of trips in the month B02617. Thursday observed highest trips in the three bases – B02598, B02617, B02682.
ggplot(dataUber,aes(Base))+
geom_bar(fill="salmon")+
scale_y_continuous(labels = comma)+
ggtitle("Trips By Bases")+ylab("Count")+
theme_light()
ggplot(dataUber,aes(Base,fill=month))+
geom_bar(position = "dodge")+
scale_y_continuous(labels = comma)+
ggtitle("Trips By Bases And Month")+
scale_fill_manual(values = colorsData)+ylab("Count")+
theme_light()
ggplot(dataUber,aes(Base,fill=daysofweek))+
geom_bar(position = "dodge")+
scale_y_continuous(labels = comma)+
ggtitle("Trips By Bases And Day Of Week")+
scale_fill_manual(values = colorsData)+ylab("Count")+
theme_light()
Creating A Heatmap Visualization Of Day, Hour And Month
- Day and hour
dayHour <- dataUber%>%
group_by(day,hour)%>%
summarize(Total=n())
ggplot(dayHour,aes(day,hour,fill=Total))+
geom_tile(color="White")+
ggtitle("Heat Map By Hour And Day")
- Day And Month
ggplot(daymg,aes(day,month,fill=Total))+
geom_tile(color="white")+
ggtitle("Heat Map By Month And Day")
- Month And Week Days
ggplot(monthWeekday,aes(daysofweek,month,fill=Total))+
geom_tile(color="white")+
ggtitle("Heat Map By Month And Day Of Week")
- Month And Bases
monthBase <- dataUber%>%
group_by(Base,month)%>%
summarize(Total=n())
ggplot(monthBase,aes(Base,month,fill=Total))+
geom_tile(color="white")+
ggtitle("Heat Map By Month And Bases")+ylab("Month")+
theme_light()
- Day Of Week And Bases
daysBases <- dataUber%>%
group_by(Base,daysofweek)%>%
summarize(Total=n())
ggplot(daysBases,aes(Base,daysofweek,fill=Total))+
geom_tile(color="white")+
ggtitle("Heat Map By Day Of Week And Bases")+
ylab("Day Of Week")
Creating A Map Visualization Of Rides In New York
Now we will visualize the rides in New York city by creating a geo-plot that will help us to visualize the rides during 2014 (Apr – Sep) and by the bases in the same period.
minLat <- 40.5774
maxLat <- 40.9176
minLong <- -74.15
maxLong <- -73.7004
uber <- na.omit(dataUber)
ggplot(uber,aes(Lon,Lat))+
geom_point(size=1,color="blue")+
scale_x_continuous(limits = c(minLong,maxLong))+
scale_y_continuous(limits = c(minLat,maxLat))+
theme_map()+
ggtitle("New York Map Based On Uber Rides During 2014 From April To September")
ggplot(dataUber,aes(x=Lon,y=Lat,color=Base))+
geom_point(size=1)+
scale_x_continuous(limits = c(minLong,maxLong))+
scale_y_continuous(limits = c(minLat,maxLat))+
theme_map()+
ggtitle("New York Map Based On Uber Rides During 2014 From April To September By Base")