Indego Bike Share Analysis

# Q.1 Number of starts per station

starts_counts_with_names <- combined_data %>%

  group_by(start_station) %>%

  summarize(num_starts = n(), .groups = 'drop') %>%

  left_join(station_name, by = c("start_station" = "Station_ID"))

top_stations_starts <- starts_counts_with_names %>%

  arrange(desc(num_starts)) %>%

  slice_head(n = 15)

write.csv(top_stations_starts, "top_stations_starts.csv", row.names = FALSE)

bottom_stations_starts <- starts_counts_with_names %>%

  arrange(num_starts) %>%

  slice_head(n = 10)

ends_with_names <- combined_data %>%

  group_by(end_station) %>%

  summarize(num_ends = n(), .groups = 'drop') %>%

  left_join(station_name, by = c("end_station" = "Station_ID"))

write.csv(bottom_stations_starts, "bottom_stations_starts.csv", row.names = FALSE)

#MOST USED IN TOTAL

# Merge start and end counts by station

station_activity <- starts_counts_with_names %>%

  full_join(ends_with_names, by = c("start_station" = "end_station")) %>%

  rename(Station_ID = start_station) %>%

  replace_na(list(num_starts = 0, num_ends = 0)) %>%  # Replace NAs with 0

  mutate(total_activity = num_starts + num_ends) %>%  # Calculate total activity

  arrange(desc(total_activity))  # Sort by highest total activity

# Get the top 15 most active stations

top_stations_activity <- station_activity %>%

  slice_head(n = 15)

write.csv(top_stations_activity, "top_stations_activity.csv", row.names = FALSE)

bottom_stations_activity <- station_activity %>%

  arrange(total_activity) %>%

  slice_head(n = 15)

write.csv(bottom_stations_activity, "bottom_stations_activity.csv", row.names = FALSE)

#Q.2

ends_count <- combined_data %>%

  group_by(end_station) %>%

  summarize(num_ends = n(), .groups = 'drop')

ends_with_names <- ends_count %>%

  left_join(station_name, by = c("end_station" = "Station_ID"))

top_end_stations <- ends_with_names %>%

  arrange(desc(num_ends)) %>%

  slice_head(n = 15)

write.csv(top_end_stations, "top_end_stations2.csv", row.names = FALSE)

bottom_end_stations <- ends_with_names %>%

  arrange(num_ends) %>%

  slice_head(n = 10)

#need to make sure all duration data is numeric 

combined_data <- combined_data %>%

  mutate(duration = as.numeric(duration))

#Find average duration

avg_duration <- combined_data %>%

  group_by(start_station) %>%

  summarize(avg_trip_duration = mean(duration, na.rm = TRUE), .groups = 'drop')

avg_duration_with_names <- avg_duration %>%

  left_join(station_name, by = c("start_station" = "Station_ID"))

#Find longest average durations

longest_avg_durations <- avg_duration_with_names %>%

  arrange(desc(avg_trip_duration)) %>%

  slice_head(n = 5)

#Find shortest average durations

shortest_avg_durations <- avg_duration_with_names %>%

  arrange(avg_trip_duration) %>%

  slice_head(n = 5)