Case study bike share
Mohammed Bawahab
2025-10-16
Introduction
This report analyzes bike ride data from multiple CSV files. The analysis includes data cleaning, summary statistics, and visualizations of ride patterns based on membership type.
Load Libraries
library(readr)
library(ggplot2)
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ stringr 1.5.2
## ✔ forcats 1.0.1 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── 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 errorslibrary(tidyr)
library(dplyr)
library(lubridate)Data
Data Sources
Cyclistic’s historical bike trip data, provided publicly by Motivate International Inc., was used for this analysis. • Data Link: Divvy Trip Data (Public Dataset) • License: Data is made available under the Divvy Data License Agreement. • Timeframe: The previous 12 months of ride data ( 2024/10 to 2025/9 ) were downloaded to ensure recent and relevant insights.
Load and Merge Data
Set the working directory and read all CSV files into a single data frame.
setwd("~/my R files/case study cvc")
files <- list.files(pattern = "\\.csv$")
full_data <- files %>%
lapply(read.csv, stringsAsFactors = FALSE) %>%
bind_rows()Explore the data
head(full_data)## ride_id rideable_type started_at
## 1 4422E707103AA4FF electric_bike 2024-10-14 03:26:04.083
## 2 19DB722B44CBE82F electric_bike 2024-10-13 19:33:38.926
## 3 20AE2509FD68C939 electric_bike 2024-10-13 23:40:48.522
## 4 D0F17580AB9515A9 electric_bike 2024-10-14 02:13:41.602
## 5 A114A483941288D1 electric_bike 2024-10-13 19:26:41.383
## 6 97833F00E6A67DC6 electric_bike 2024-10-14 06:35:06.130
## ended_at start_station_name start_station_id end_station_name
## 1 2024-10-14 03:32:56.535
## 2 2024-10-13 19:39:04.490
## 3 2024-10-13 23:48:02.339
## 4 2024-10-14 02:25:40.057
## 5 2024-10-13 19:28:18.560
## 6 2024-10-14 06:42:10.776
## end_station_id start_lat start_lng end_lat end_lng member_casual
## 1 41.96 -87.65 41.98 -87.67 member
## 2 41.98 -87.67 41.97 -87.66 member
## 3 41.97 -87.66 41.95 -87.65 member
## 4 41.95 -87.65 41.96 -87.65 member
## 5 41.98 -87.67 41.98 -87.67 member
## 6 41.88 -87.65 41.89 -87.64 membercolnames(full_data)## [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"str(full_data)## 'data.frame': 5539521 obs. of 13 variables:
## $ ride_id : chr "4422E707103AA4FF" "19DB722B44CBE82F" "20AE2509FD68C939" "D0F17580AB9515A9" ...
## $ rideable_type : chr "electric_bike" "electric_bike" "electric_bike" "electric_bike" ...
## $ started_at : chr "2024-10-14 03:26:04.083" "2024-10-13 19:33:38.926" "2024-10-13 23:40:48.522" "2024-10-14 02:13:41.602" ...
## $ ended_at : chr "2024-10-14 03:32:56.535" "2024-10-13 19:39:04.490" "2024-10-13 23:48:02.339" "2024-10-14 02:25:40.057" ...
## $ start_station_name: chr "" "" "" "" ...
## $ start_station_id : chr "" "" "" "" ...
## $ end_station_name : chr "" "" "" "" ...
## $ end_station_id : chr "" "" "" "" ...
## $ start_lat : num 42 42 42 42 42 ...
## $ start_lng : num -87.7 -87.7 -87.7 -87.7 -87.7 ...
## $ end_lat : num 42 42 42 42 42 ...
## $ end_lng : num -87.7 -87.7 -87.7 -87.7 -87.7 ...
## $ member_casual : chr "member" "member" "member" "member" ...Data Cleaning
Check for duplicates, missing values, and invalid ride times.
Duplicate ride IDs
sum(duplicated(full_data$ride_id))## [1] 0Missing ride IDs
sum(is.na(full_data$ride_id) | full_data$ride_id == "")## [1] 0Length of ride IDs
full_data <- full_data %>%
mutate(length_id = nchar(ride_id))
table(full_data$length_id) # To check how many different length id we have##
## 16
## 5539521max(full_data$length_id) ## [1] 16min(full_data$length_id)## [1] 16Missing started_at or ended_at
sum(is.na(full_data$started_at) | full_data$started_at == "")## [1] 0sum(is.na(full_data$ended_at) | full_data$ended_at == "")## [1] 0Convert to datetime
full_data$started_at <- ymd_hms(full_data$started_at)
full_data$ended_at <- ymd_hms(full_data$ended_at)Calculations
Ride length
full_data <- full_data %>% mutate(ride_length = ended_at - started_at)Remove invalid rides
full_data <- full_data %>% filter(ended_at >= started_at)Extract month and weekday
full_data <- full_data %>%
mutate(month_name = month(started_at, label = TRUE, abbr = FALSE),
weekday_num = wday(started_at, week_start = 7),
weekday_name = wday(started_at, label = TRUE, abbr = FALSE))Summary Statistics
Define a mode function and calculate summary statistics.
get_mode <- function(x) {
ux <- unique(x)
ux[which.max(tabulate(match(x, ux)))]
}summary_stats <- full_data %>%
summarise(
min_ride_length = min(ride_length, na.rm = TRUE),
max_ride_length = max(ride_length, na.rm = TRUE),
avg_ride_length = mean(ride_length, na.rm = TRUE),
mode_weekday = get_mode(weekday_name)
)
summary_stats## min_ride_length max_ride_length avg_ride_length mode_weekday
## 1 0.046 secs 94494.01 secs 963.5568 secs SaturdayGrouped summary by membership type:
summary_by_member <- full_data %>%
group_by(member_casual) %>%
summarise(
min_ride_length_seconds = min(as.numeric(ride_length, units = "secs"), na.rm = TRUE),
max_ride_length_hours = max(as.numeric(ride_length, units = "secs"), na.rm = TRUE) / 3600,
avg_ride_length_minutes = mean(as.numeric(ride_length, units = "secs"), na.rm = TRUE) / 60,
mode_weekday = get_mode(weekday_name),
.groups = 'drop'
)
summary_by_member## # A tibble: 2 × 5
## member_casual min_ride_length_seconds max_ride_length_hours
## <chr> <dbl> <dbl>
## 1 casual 0.0460 26.2
## 2 member 0.0780 25.0
## # ℹ 2 more variables: avg_ride_length_minutes <dbl>, mode_weekday <ord>Visualizations
Number of Rides by Membership
Daily
ggplot(full_data) +
geom_bar(aes(x = member_casual, fill = member_casual)) +
facet_wrap(~weekday_name) +
labs(title = 'Daily View', y="Number of Rides",
subtitle = 'Membership type vs Number of Rides',
caption = "Data collected from 2024/10 to 2025/9") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Monthly
ggplot(full_data) +
geom_bar(aes(x = member_casual, fill = member_casual)) +
facet_wrap(~month_name) +
labs(title = 'Monthly View', y="Number of Rides",
subtitle = 'Membership type vs Number of Rides',
caption = "Data collected from 2024/10 to 2025/9") +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Average Ride Length
Daily
Daily_data <- full_data %>%
group_by(weekday_name, member_casual) %>%
summarise(
min_ride_Daily_length_seconds = min(as.numeric(ride_length, units = "secs"), na.rm = TRUE),
max_ride_Daily_length_hours = max(as.numeric(ride_length, units = "secs"), na.rm = TRUE) / 3600,
avg_ride_Daily_length_minutes = mean(as.numeric(ride_length, units = "secs"), na.rm = TRUE) / 60,
.groups = 'drop'
)ggplot(data = Daily_data)+
geom_col(mapping = aes(x=weekday_name,y=avg_ride_Daily_length_minutes,fill =member_casual),position = "dodge")+
labs(title = 'Weekly View ',y="Average Ride length in minutes",
subtitle = 'Membership type vs Average Ride length ',
caption = "Data collected from 2024/10 to 2025/9")+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Monthly
Monthly_data <- full_data %>%
group_by(month_name, member_casual) %>%
summarise(avg_Monthly_ride_length_minutes = mean(as.numeric(ride_length, units = "secs"), na.rm = TRUE) / 60,
.groups = "drop")ggplot(data = Monthly_data)+
geom_col(position = 'dodge',mapping = aes(x=month_name,y=avg_Monthly_ride_length_minutes,fill =member_casual))+
labs(title = 'Monthly View ',y="Average Ride length in minutes",
subtitle = 'Membership type vs Average Ride length ',
caption = "Data collected from 2024/10 to 2025/9")+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Total Ride Length by Membership
Total_data <- full_data %>%
group_by(member_casual) %>%
summarise(Total_ride_length_Days = sum(as.numeric(ride_length, units = "secs"), na.rm = TRUE) / (60*60*24),
.groups = "drop")ggplot(data = Total_data)+
geom_col(mapping = aes(x=member_casual,y=Total_ride_length_Days,fill =member_casual))+
coord_cartesian(ylim = c(25000, NA)) +labs(title = 'Total View ',y="Total Ride length in days",
subtitle = 'Membership type vs Total Ride length ',
caption = "Data collected from 2024/10 to 2025/9")+
theme(axis.text.x = element_text(angle = 45, hjust = 1))