code

library("lubridate")
library("janitor")
library("tidyverse")
library("dplyr")
library("readr")
library("tidyr")
library("ggplot2")
library("stringr") 
library("skimr")
library("scales")
library("data.table")
library("plyr")
library("viridis")

setwd("C:/Users/admin/Documents/bikeshare")
getwd()

apr <- read.csv("202004-divvy-tripdata.csv")
may <- read.csv("202005-divvy-tripdata.csv")
jun <- read.csv("202006-divvy-tripdata.csv")
jul <- read.csv("202007-divvy-tripdata.csv")
aug <- read.csv("202008-divvy-tripdata.csv")
sept <- read.csv("202009-divvy-tripdata.csv")
oct <- read.csv("202010-divvy-tripdata.csv")
nov <- read.csv("202011-divvy-tripdata.csv")
dec <- read.csv("202012-divvy-tripdata.csv")
jan <- read.csv("202101-divvy-tripdata.csv")
feb <- read.csv("202102-divvy-tripdata.csv")
mar <- read.csv("202103-divvy-tripdata.csv")

trips <- rbind(apr,may,jun,jul,aug,sept,oct,nov,dec,jan,feb,mar)

trips <- remove_empty(trips,which = c("cols"))
trips <- remove_empty(trips,which = c("rows"))

colnames(trips)[13] <- "user"
colnames(trips)[2] <- "bike"
colnames(trips)[3] <- "start_time"
colnames(trips)[4] <- "end_time"
colnames(trips)[5] <- "start_station"
colnames(trips)[7] <- "end_station"

trips = trips %>% 
     mutate(
         start_time = ymd_hms(as_datetime(start_time)),
         end_time = ymd_hms(as_datetime(end_time))
       )

trips = trips %>%
mutate(
    bike = as_factor(bike),
    user = as_factor(user)
  )

trips_1 = trips %>% 
  mutate(
    hours = hour(start_time),
    weekday = lubridate::wday(start_time, label = T, abbr = F),
    month = lubridate::month(start_time, label = T, abbr =F)
  )

trips_1 = trips_1 %>% 
  mutate(
    trip_time = difftime(end_time, start_time, units = "mins")
  )


glimpse(trips_1)
colnames(trips_1)
head(trips_1)
colSums(is.na(trips_1))


remove(trips)

trips_1 <- distinct(trips_1)

trips_2 = trips_1 %>% 
  filter(between(trip_time, 1, 1440))

# ANALYZE

glimpse(trips_2)
max(trips_2$trip_time)
min(trips_2$trip_time)

colSums(is.na(trips_2))

skim_without_charts(trips_2)

mean(trips_2$trip_time)
median(trips_2$trip_time)

aggregate(trips_2$trip_time ~ trips_2$user, FUN = mean)

analyse_table <- trips_2 %>% 
  select (ride_id,bike,start_station,end_station,user,trip_time,hours,weekday,month)

glimpse(analyse_table)
colnames(analyse_table)

remove(trips_1)
remove(trips_2)


# VISUALIZE

ride_hours = analyse_table %>% 
  group_by(user, hours) %>% 
  dplyr::summarise(no_of_rides = n(),
    avg_trip = mean(trip_time),
    total_trip = sum(trip_time)
  )

ride_hours %>% 
  ggplot(aes(hours, no_of_rides, fill = user))+ 
  geom_col(position = "dodge")+ 
  scale_y_continuous()+ 
  labs(
    title = "Number of Trips per Hour",
    subtitle = "Number of trips for every hour and by user",
    caption = "Figure 1",
    x = "hour of the day",
    y = "number of rides",
  )

ride_hours %>% 
  ggplot(aes(hours, avg_trip, fill = user))+ 
  geom_col(position = "dodge")+ 
  scale_y_continuous()+ 
  labs(
    title = "Average trips per Hour",
    subtitle = "Average trip time for every hour and by user",
    caption = "Figure 2",
    x = "hour of the day",
    y = "avg time of rides",
  )


ride_hours %>% 
  ggplot(aes(hours, total_trip, fill = user))+ 
  geom_col(position = "dodge")+ 
  scale_y_continuous()+
  labs(
    title = "Total Trip Time per Hour",
    subtitle = "Sum of trip time for every hour and by user",
    caption = "Figure 3",
    x = "hour of the day",
    y = "total time of rides",
  )


ride_week = analyse_table %>% 
  group_by(user, weekday) %>% 
  dplyr::summarise(no_of_rides = n(),
            avg_trip = mean(trip_time),
            total_trip = sum(trip_time)
            )


ride_week %>% 
  ggplot(aes(weekday, no_of_rides, fill=user)) + 
  geom_col(position="dodge") + 
  scale_y_continuous(labels=comma) + 
  labs(
    title = "No. of Rides by Days of a Week",
    subtitle = "Number of rides on each weekday by users", 
    caption = "Figure 4", 
    x = "Days of a Week",
    y = "Number of Rides"
  )



ride_week %>% 
  ggplot(aes(weekday,avg_trip,fill=user)) + 
  geom_col(position = "dodge") + 
  scale_y_continuous(labels=comma) + 
  labs(
    title = "Average Trip Time by Day of a Week",
    subtitle = "Average trip time for each day of a week by user",
    caption = "Figure 5",
    x = "Days of a Week",
    y = "Average Trip Time"
  )


ride_week %>% 
  ggplot(aes(weekday,total_trip,fill=user)) + 
  geom_col(position = "dodge") + 
  scale_y_continuous(labels=comma) + 
  labs(
    title = "Total Trip Time by Day of a Week",
    subtitle = "Total trip time for each day of a week by user",
    caption = "Figure 6",
    x = "Days of a Week",
    y = "Total Trip Time"
  )


ride_month = analyse_table %>% 
  group_by(user, month) %>% 
  dplyr::summarise(no_of_rides = n(),
            avg_trip = mean(trip_time),
            total_trip = sum(trip_time)
  )

ride_month %>% 
  ggplot(aes(month, no_of_rides, fill=user)) + 
  geom_col(position="dodge") + 
  scale_y_continuous(labels=comma) + 
  labs(
    title = "No. of Rides by Month of the Year",
    subtitle = "Number of rides on each month by users", 
    caption = "Figure 7", 
    x = "Month of the Year",
    y = "Number of Rides"
  )


ride_month %>% 
  ggplot(aes(month, avg_trip, fill=user)) + 
  geom_col(position = "dodge") + 
  scale_y_continuous(labels=comma) + 
  labs(
    title = "Average Trip Time by Month of a Year",
    subtitle = "Average trip time for each month of the year by user",
    caption = "Figure 8",
    x = "Month of the Year",
    y = "Average Trip Time"
  )


ride_month %>% 
  ggplot(aes(month, total_trip, fill=user)) + 
  geom_col(position = "dodge") + 
  scale_y_continuous(labels=comma) +
  labs(
    title = "Total Trip Time by Month of a Year",
    subtitle = "Total trip time for each month of a year by user", 
    caption = "Figure 9",
    x = "Month of a Year",
    y = "Total Trip Time"
  )

ride_bike = analyse_table %>% 
  group_by(user, bike) %>% 
  dplyr::summarise(no_of_rides = n(),
            avg_trip = mean(trip_time),
            total_trip = sum(trip_time)
  )


ride_bike %>% 
  ggplot(aes(bike, no_of_rides, fill = user))+
  geom_col(position = "dodge")+
  scale_y_continuous(labels = comma)+
  labs(
    title = "Number of Trips per Bike Type and Segregated by User",
    subtitle = "Number of trips per bike type",
    caption = "Fig 10",
    x = "Types of Bikes",
    y = "Number of Trips"
  )


ride_bike %>% 
  ggplot(aes(bike, avg_trip, fill = user))+
  geom_col(position = "dodge")+
  scale_y_continuous(labels = comma)+
  labs(
    title = "Average Trip Time per Bike Type and Segregated by User",
    subtitle = "Average trip time per bike type",
    caption = "Fig 12",
    x = "Type of Bikes",
    y = "Avg Trip Time"
  )



ride_bike %>% 
  ggplot(aes(bike, total_trip, fill = user))+
  geom_col(position = "dodge")+
  scale_y_continuous(labels = comma)+
  labs(
    title = "Total Trip Time per Bike Type and Segregated by User",
    subtitle = "Total trip time per bike type",
    caption = "Fig 13",
    x = "Type of Bikes",
    y = "Total Trip Time"
  )