It seems that weather plays a huge role as far as when both members and casual riders choose to ride their bikes. July being the busiest month for the bike share, and December being the lowest supports this information.
When it comes to specific days of the week, it seems that Tuesday and Thursday are the days where members are riding their bikes the most.
Members and casual riders tend to ride during 3PM-6PM. This makes sense suggesting that our member users would mostly be riding home to their place of work and our casual riders could be running errands or riding for leisure.
Members typically start or end their rides at Kingsbury and Kinzie St, while our casual riders tend to start at and at Streeter Dr and Grand Ave. I did not find any solid explanation as to why other than the possibility that they may live in the area.
When it comes to casual riders, the largest spike tends to happen over the weekends.
With both members and casual bike users, Saturdays are the busiest day.
Ultimately, the members ride more often than our casual riders.
Casual users ride for longer distances than our member rides, which to me indicates that our member users are likely riding to and from work, where the casual users are riding for exercise/leisure.
From a consumer perspective, I think that an option for different lengths of membership subscriptions would be very valuable. Some consumers may be intimidated by the up front payment for a year subscription where an option for month to month, or even a 3 month subscription could be beneficial. Seeing how the ride count is at its highest during the summer months, specifically the 3 month membership suggestion would be a perfect way to efficiently increase membership and provide flexible pricing.
Increasing visibility of our marketing campaign at locations where casual users frequent the most could make the marketing efforts more effective.
Incentives could be an efficient way to encourage casual riders to pursue a membership. Emphasizing the benefits could persuade our casual riders to make the decision to secure their membership.
The provided information is specific to annual members and casual riders of the Cyclistic Bike Share program. The data used for these findings is during the period from July of 2022 to June of 2023.
The data has been made available by Motivate International Inc. under this license
knitr::opts_chunk$set(echo = FALSE,message = FALSE,error = FALSE)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(janitor)
##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
library(lubridate)
library(scales)
##
## Attaching package: 'scales'
##
## The following object is masked from 'package:purrr':
##
## discard
##
## The following object is masked from 'package:readr':
##
## col_factor
rm(list=ls())
df1 <- read_csv("Updated Bikeshare/202207-divvy-tripdata.csv")
df2 <- read_csv("Updated Bikeshare/202208-divvy-tripdata.csv")
df3 <- read_csv("Updated Bikeshare/202209-divvy-tripdata.csv")
df4 <- read_csv("Updated Bikeshare/202210-divvy-tripdata.csv")
df5 <- read_csv("Updated Bikeshare/202211-divvy-tripdata.csv")
df6 <- read_csv("Updated Bikeshare/202212-divvy-tripdata.csv")
df7 <- read_csv("Updated Bikeshare/202301-divvy-tripdata.csv")
df8 <- read_csv("Updated Bikeshare/202302-divvy-tripdata.csv")
df9 <- read_csv("Updated Bikeshare/202303-divvy-tripdata.csv")
df10 <- read_csv("Updated Bikeshare/202304-divvy-tripdata.csv")
df11 <- read_csv("Updated Bikeshare/202305-divvy-tripdata.csv")
df12 <- read_csv("Updated Bikeshare/202306-divvy-tripdata.csv")
bikes_rides <- rbind(df1,df2,df3,df4,df5,df6,df7,df8,df9,df10,df11,df12)
bikes_rides <- janitor::remove_empty(bikes_rides,which = c("cols"))
bikes_rides <- janitor::remove_empty(bikes_rides,which = c("rows"))
bikes_rides <- bikes_rides %>% filter(start_station_name !="")
bikes_rides$Ymd <- as.Date(bikes_rides$started_at)
bikes_rides$started_at <- lubridate::ymd_hms(bikes_rides$started_at)
## Warning: 19 failed to parse.
bikes_rides$ended_at <- lubridate::ymd_hms(bikes_rides$ended_at)
## Warning: 20 failed to parse.
bikes_rides$start_hour <- lubridate::hour(bikes_rides$started_at)
bikes_rides$end_hour <- lubridate::hour(bikes_rides$ended_at)
bikes_rides$Hours <- difftime(bikes_rides$ended_at,bikes_rides$started_at,units = c("hours"))
bikes_rides$Minutes <- difftime(bikes_rides$ended_at,bikes_rides$started_at,units = c("mins"))
bikes_rides <- bikes_rides %>% filter(Minutes >0)
summary(bikes_rides)
## ride_id rideable_type started_at
## Length:4921002 Length:4921002 Min. :2022-07-01 00:00:01.00
## Class :character Class :character 1st Qu.:2022-08-24 18:34:05.00
## Mode :character Mode :character Median :2022-11-01 17:17:51.50
## Mean :2022-12-12 22:39:56.88
## 3rd Qu.:2023-04-20 17:50:14.50
## Max. :2023-06-30 23:59:45.00
##
## ended_at start_station_name start_station_id
## Min. :2022-07-01 00:06:23.00 Length:4921002 Length:4921002
## 1st Qu.:2022-08-24 18:52:25.00 Class :character Class :character
## Median :2022-11-01 17:31:58.50 Mode :character Mode :character
## Mean :2022-12-12 22:59:17.61
## 3rd Qu.:2023-04-20 18:04:13.75
## Max. :2023-07-10 20:26:44.00
##
## end_station_name end_station_id start_lat start_lng
## Length:4921002 Length:4921002 Min. :41.65 Min. :-87.84
## Class :character Class :character 1st Qu.:41.88 1st Qu.:-87.66
## Mode :character Mode :character Median :41.90 Median :-87.64
## Mean :41.90 Mean :-87.65
## 3rd Qu.:41.93 3rd Qu.:-87.63
## Max. :42.06 Max. :-87.53
##
## end_lat end_lng member_casual Ymd
## Min. : 0.00 Min. :-88.16 Length:4921002 Min. :2022-07-01
## 1st Qu.:41.88 1st Qu.:-87.66 Class :character 1st Qu.:2022-08-24
## Median :41.90 Median :-87.64 Mode :character Median :2022-11-01
## Mean :41.90 Mean :-87.65 Mean :2022-12-12
## 3rd Qu.:41.93 3rd Qu.:-87.63 3rd Qu.:2023-04-20
## Max. :42.37 Max. : 0.00 Max. :2023-06-30
## NA's :5795 NA's :5795
## start_hour end_hour Hours Minutes
## Min. : 0.00 Min. : 0.00 Length:4921002 Length:4921002
## 1st Qu.:11.00 1st Qu.:11.00 Class :difftime Class :difftime
## Median :15.00 Median :15.00 Mode :numeric Mode :numeric
## Mean :14.14 Mean :14.29
## 3rd Qu.:18.00 3rd Qu.:18.00
## Max. :23.00 Max. :23.00
##
head(bikes_rides)
## # A tibble: 6 × 18
## ride_id rideable_type started_at ended_at
## <chr> <chr> <dttm> <dttm>
## 1 954144C2F67B1932 classic_bike 2022-07-05 08:12:47 2022-07-05 08:24:32
## 2 292E027607D218B6 classic_bike 2022-07-26 12:53:38 2022-07-26 12:55:31
## 3 57765852588AD6E0 classic_bike 2022-07-03 13:58:49 2022-07-03 14:06:32
## 4 B5B6BE44314590E6 classic_bike 2022-07-31 17:44:21 2022-07-31 18:42:50
## 5 A4C331F2A00E79E0 classic_bike 2022-07-13 19:49:06 2022-07-13 20:15:24
## 6 579D73BE2ED880B3 electric_bike 2022-07-01 17:04:35 2022-07-01 17:13:18
## # ℹ 14 more variables: start_station_name <chr>, start_station_id <chr>,
## # end_station_name <chr>, end_station_id <chr>, start_lat <dbl>,
## # start_lng <dbl>, end_lat <dbl>, end_lng <dbl>, member_casual <chr>,
## # Ymd <date>, start_hour <int>, end_hour <int>, Hours <drtn>, Minutes <drtn>
dim(bikes_rides)
## [1] 4921002 18
colnames(bikes_rides)
## [1] "ride_id" "rideable_type" "started_at"
## [4] "ended_at" "start_station_name" "start_station_id"
## [7] "end_station_name" "end_station_id" "start_lat"
## [10] "start_lng" "end_lat" "end_lng"
## [13] "member_casual" "Ymd" "start_hour"
## [16] "end_hour" "Hours" "Minutes"
str(bikes_rides)
## tibble [4,921,002 × 18] (S3: tbl_df/tbl/data.frame)
## $ ride_id : chr [1:4921002] "954144C2F67B1932" "292E027607D218B6" "57765852588AD6E0" "B5B6BE44314590E6" ...
## $ rideable_type : chr [1:4921002] "classic_bike" "classic_bike" "classic_bike" "classic_bike" ...
## $ started_at : POSIXct[1:4921002], format: "2022-07-05 08:12:47" "2022-07-26 12:53:38" ...
## $ ended_at : POSIXct[1:4921002], format: "2022-07-05 08:24:32" "2022-07-26 12:55:31" ...
## $ start_station_name: chr [1:4921002] "Ashland Ave & Blackhawk St" "Buckingham Fountain (Temp)" "Buckingham Fountain (Temp)" "Buckingham Fountain (Temp)" ...
## $ start_station_id : chr [1:4921002] "13224" "15541" "15541" "15541" ...
## $ end_station_name : chr [1:4921002] "Kingsbury St & Kinzie St" "Michigan Ave & 8th St" "Michigan Ave & 8th St" "Woodlawn Ave & 55th St" ...
## $ end_station_id : chr [1:4921002] "KA1503000043" "623" "623" "TA1307000164" ...
## $ start_lat : num [1:4921002] 41.9 41.9 41.9 41.9 41.9 ...
## $ start_lng : num [1:4921002] -87.7 -87.6 -87.6 -87.6 -87.6 ...
## $ end_lat : num [1:4921002] 41.9 41.9 41.9 41.8 41.9 ...
## $ end_lng : num [1:4921002] -87.6 -87.6 -87.6 -87.6 -87.7 ...
## $ member_casual : chr [1:4921002] "member" "casual" "casual" "casual" ...
## $ Ymd : Date[1:4921002], format: "2022-07-05" "2022-07-26" ...
## $ start_hour : int [1:4921002] 8 12 13 17 19 17 18 20 22 9 ...
## $ end_hour : int [1:4921002] 8 12 14 18 20 17 18 21 23 9 ...
## $ Hours : 'difftime' num [1:4921002] 0.195833333333333 0.0313888888888889 0.128611111111111 0.974722222222222 ...
## ..- attr(*, "units")= chr "hours"
## $ Minutes : 'difftime' num [1:4921002] 11.75 1.88333333333333 7.71666666666667 58.4833333333333 ...
## ..- attr(*, "units")= chr "mins"
nrow(bikes_rides)
## [1] 4921002
bikesrides2 <- bikes_rides %>%
group_by(Weekly = floor_date(started_at, "week"), start_hour) %>%
summarise(
Minutes = sum(Minutes),
Mean = mean(Minutes),
Median = median(Minutes),
Max = max(Minutes),
Min = min(Minutes),
Count = n(),
.groups = "drop")
summary(bikesrides2)
## Weekly start_hour Minutes Mean
## Min. :2022-06-26 Min. : 0.00 Length:1272 Length:1272
## 1st Qu.:2022-09-25 1st Qu.: 5.75 Class :difftime Class :difftime
## Median :2022-12-25 Median :11.50 Mode :numeric Mode :numeric
## Mean :2022-12-25 Mean :11.50
## 3rd Qu.:2023-03-26 3rd Qu.:17.25
## Max. :2023-06-25 Max. :23.00
## Median Max Min Count
## Length:1272 Length:1272 Length:1272 Min. : 52
## Class :difftime Class :difftime Class :difftime 1st Qu.: 1034
## Mode :numeric Mode :numeric Mode :numeric Median : 2792
## Mean : 3869
## 3rd Qu.: 5738
## Max. :16459
head(bikesrides2)
## # A tibble: 6 × 8
## Weekly start_hour Minutes Mean Median Max Min Count
## <dttm> <int> <drtn> <drtn> <drtn> <drt> <drt> <int>
## 1 2022-06-26 00:00:00 0 21939.33 mins 21939.3… 21939… 2193… 2193… 806
## 2 2022-06-26 00:00:00 1 16119.88 mins 16119.8… 16119… 1611… 1611… 607
## 3 2022-06-26 00:00:00 2 10671.18 mins 10671.1… 10671… 1067… 1067… 309
## 4 2022-06-26 00:00:00 3 5728.75 mins 5728.7… 5728… 572… 572… 157
## 5 2022-06-26 00:00:00 4 2150.65 mins 2150.6… 2150… 215… 215… 134
## 6 2022-06-26 00:00:00 5 6901.10 mins 6901.1… 6901… 690… 690… 288
dim(bikesrides2)
## [1] 1272 8
colnames(bikesrides2)
## [1] "Weekly" "start_hour" "Minutes" "Mean" "Median"
## [6] "Max" "Min" "Count"
str(bikesrides2)
## tibble [1,272 × 8] (S3: tbl_df/tbl/data.frame)
## $ Weekly : POSIXct[1:1272], format: "2022-06-26" "2022-06-26" ...
## $ start_hour: int [1:1272] 0 1 2 3 4 5 6 7 8 9 ...
## $ Minutes : 'difftime' num [1:1272] 21939.3333333333 16119.8833333333 10671.1833333333 5728.75 ...
## ..- attr(*, "units")= chr "mins"
## $ Mean : 'difftime' num [1:1272] 21939.3333333333 16119.8833333333 10671.1833333333 5728.75 ...
## ..- attr(*, "units")= chr "mins"
## $ Median : 'difftime' num [1:1272] 21939.3333333333 16119.8833333333 10671.1833333333 5728.75 ...
## ..- attr(*, "units")= chr "mins"
## $ Max : 'difftime' num [1:1272] 21939.3333333333 16119.8833333333 10671.1833333333 5728.75 ...
## ..- attr(*, "units")= chr "mins"
## $ Min : 'difftime' num [1:1272] 21939.3333333333 16119.8833333333 10671.1833333333 5728.75 ...
## ..- attr(*, "units")= chr "mins"
## $ Count : int [1:1272] 806 607 309 157 134 288 717 1051 1537 1913 ...
nrow(bikesrides2)
## [1] 1272
bikesrides2$CntMA <- forecast::ma(bikesrides2$Count,28)
summary(bikesrides2$Count)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 52 1034 2792 3869 5738 16459
xtabs(bikesrides2$Count~bikesrides2$start_hour)
## bikesrides2$start_hour
## 0 1 2 3 4 5 6 7 8 9 10
## 64550 40687 23862 13898 12246 38237 115225 207758 261167 197165 201692
## 11 12 13 14 15 16 17 18 19 20 21
## 245634 284739 288746 296755 348493 438899 509893 418022 301119 210347 169896
## 22 23
## 136588 95384
bikesrides2$Monthly <- lubridate::month(bikesrides2$Weekly)
bikesrides2 %>% ggplot() + geom_col(aes(x=Weekly,y=Count)) +
scale_y_continuous(labels = comma) +
labs(title = "Rides Per Day Count",
subtitle = "Based on 28 day moving average",
y="Average rides per day")
bikesrides2 %>% ggplot() + geom_col(aes(x=start_hour,y=Count)) +
scale_y_continuous(labels = comma) +
labs(title = "Rides per Hour Count",
y="Rides per Hour")
ggplot(bikesrides2) + geom_col(aes(x=Weekly,y=Mean)) +
labs(title="Trip Minutes Weekly Average", y ="Ride Time Average(min)") +
scale_y_continuous(labels = comma)
bikes_rides %>%
mutate(weekday = wday(started_at, label = TRUE)) %>%
group_by(member_casual, weekday) %>%
summarise(
number_of_rides = n(),
average_duration = mean(Minutes)
) %>%
arrange(member_casual, weekday) %>%
ggplot(aes(x = weekday, y = number_of_rides, fill = member_casual)) +
geom_col(position = position_dodge()) +
scale_y_continuous(labels = scales::comma) +
labs(
title = "Total Rides By Weekday",
x = "Weekday",
y = "Number of Rides",
fill = "Member Type"
)
bikes_rides %>%
mutate(weekday = wday(started_at, label = TRUE)) %>%
group_by(member_casual, weekday, .groups = "drop") %>%
summarise(
number_of_rides = n(),
average_duration = mean(Minutes)
) %>%
arrange(member_casual, weekday) %>%
ggplot(aes(x = weekday, y = average_duration / 60, fill = member_casual)) +
geom_col(position = position_dodge()) +
scale_y_continuous(labels = scales::comma, name = "Average Duration (hours)") +
labs(
title = "Average Ride Duration by Weekday",
x = "Weekday",
fill = "Member Type"
)
bikestype <- bikes_rides %>%
group_by(member_casual, rideable_type, Weekly = floor_date(started_at, "week")) %>%
summarise(
Minutes = sum(Minutes),
Mean = mean(Minutes),
Median = median(Minutes),
Max = max(Minutes),
Min = min(Minutes),
Count = n(),
.groups = "drop"
)
ggplot(bikestype) + geom_area(aes(x=Weekly,y=Count,col=rideable_type)) +
scale_y_continuous(labels = comma) +
labs(title="Rides by Bike Type")
ggplot(bikestype) + geom_col(aes(x=Weekly,y=Count,fill=member_casual)) +
scale_y_continuous(labels = comma) +
labs(title="Rides by Rider Type")
ggplot(bikestype) + geom_col(aes(x=Weekly,y=Minutes)) +
scale_y_continuous(labels = comma) + facet_wrap(~rideable_type) +
labs(title="Ride Minutes per week")
ggplot(bikestype,aes(x=Weekly,y=Minutes,fill=rideable_type)) +
geom_area(stat = "identity", position = position_dodge(), alpha = 0.50) +
scale_y_continuous(labels = comma) +
labs(title = "Rides Minutes by Bike Type/Week",
y="Trip In Minutes")
## Warning: Width not defined
## ℹ Set with `position_dodge(width = ...)`
bikes_rides %>% count(start_station_name, sort = TRUE) %>%
top_n(10) %>% ggplot() + geom_col(aes(x=reorder(start_station_name,n),y=n)) +
coord_flip() + labs(title = "Top 10 Start Stations",
y = "Ride Count",x="Station Name") +
scale_y_continuous(labels = comma)
bikes_rides %>%
count(start_station_name, member_casual, sort = TRUE) %>%
top_n(10) %>%
ggplot() +
geom_col(aes(x = reorder(start_station_name, n), y = n, fill = member_casual)) +
coord_flip() +
labs(title = "Top 10 Start Stations with Member and Casual Riders",
y = "Count of Rides", x = "Station Name") +
scale_y_continuous(labels = comma)