Deliverable For Analysis Phase

DESCRIPTIVE ANALYSIS

# Descriptive analysis on ride_length (all figures in seconds)

mean(all_trips_V2$ride_length) #straight average (total ride length / rides)

median(all_trips_V2$ride_length) #midpoint number in the ascending array of ride lengths

max(all_trips_V2$ride_length) #longest ride

min(all_trips_V2$ride_length) #shortest ride

# You can condense the four lines above to one line using summary() on the specific attribute

summary(all_trips_V2$ride_length)

# Compare members and casual users

aggregate(all_trips_V2$ride_length ~ all_trips_V2$member_casual, FUN = mean)

aggregate(all_trips_V2$ride_length ~ all_trips_V2$member_casual, FUN = median)

aggregate(all_trips_V2$ride_length ~ all_trips_V2$member_casual, FUN = max)

aggregate(all_trips_V2$ride_length ~ all_trips_V2$member_casual, FUN = min)

# See the average ride time by each day for members vs casual users

# Notice that the days of the week are out of order. Let's fix that.

all_trips_V2$day_of_week <- ordered(all_trips_V2$day_of_week, levels=c("Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"))

# Now, let's run the average ride time by each day for members vs casual users

aggregate(all_trips_V2$ride_length ~ all_trips_V2$member_casual + all_trips_V2$day_of_week, FUN = mean)

# analyze ridership data by type and weekday

#creates weekday field using wday()

#groups by usertype and weekday

#calculates the number of rides and average duration

# calculates the average duration

all_trips_V2 %>%

mutate(weekday = wday(started_at, label = TRUE)) %>%

group_by(member_casual, weekday) %>%

summarise(number_of_rides = n()

,average_duration = mean(ride_length)) %>%

arrange(member_casual, weekday)