5 Some ideas to visualise the data
Let´s see if we can see the most frequent days before Christmas … I think it could be Saturday ;-). Also nice to see the 25th and 26th of December … holidays in Germany :-).
location_71 <- get_hystreet_station_data(
hystreetId = 71,
query = list(from = "2021-12-01", to = "2022-01-01", resolution = "hour"))ggplot(location_71$measurements, aes(x = timestamp, y = pedestrians_count, colour = weekdays(timestamp))) +
geom_path(group = 1) +
scale_x_datetime(date_breaks = "7 days") +
scale_x_datetime(labels = date_format("%d.%m.%Y")) +
labs(x = "Date",
y = "Pedestrians",
colour = "Day")## Scale for x is already present.
## Adding another scale for x, which will replace the existing scale.
5.1 Compare different stations
Now let´s compare different stations:
- Load the data
location_73 <- get_hystreet_station_data(
hystreetId = 73,
query = list(from = "2022-01-01", to = "2022-01-31", resolution = "day"))$measurements %>%
select(pedestrians_count, timestamp) %>%
mutate(station = 73)
location_74 <- get_hystreet_station_data(
hystreetId = 74,
query = list(from = "2022-01-01", to = "2019-01-22", resolution = "day"))$measurements %>%
select(pedestrians_count, timestamp) %>%
mutate(station = 74)
data_73_74 <- bind_rows(location_73, location_74)ggplot(data_73_74, aes(x = timestamp, y = pedestrians_count, fill = weekdays(timestamp))) +
geom_bar(stat = "identity") +
scale_x_datetime(labels = date_format("%d.%m.%Y")) +
facet_wrap(~station, scales = "free_y") +
theme(legend.position = "bottom",
axis.text.x = element_text(angle = 45, hjust = 1))
5.2 Highest ratio (pedestrians/day)
Now a little bit of big data analysis. Let´s find the station with the highest pedestrians per day ratio:
hystreet_ids <- get_hystreet_locations()
all_data <- lapply(hystreet_ids[,"id"], function(ID){
temp <- get_hystreet_station_data(
hystreetId = ID,
query = list(from = "2021-01-01", to = "2021-12-31", resolution = "day"))
lifetime_count <- temp$statistics$timerange_count
days_counted <- as.integer(ymd(temp$metadata$measured_to) - ymd(temp$metadata$measured_from))
return(data.frame(
id = ID,
station = paste0(temp$city, " (",temp$name,")"),
ratio = lifetime_count/days_counted))
})
ratio <- bind_rows(all_data)What stations have the highest ratio?
ratio %>%
top_n(5, ratio) %>%
arrange(desc(ratio))## id station ratio
## 1 73 München (Neuhauser Straße (Ost)) 45510.15
## 2 165 München (Kaufingerstraße) 42458.42
## 3 305 Wien (Kärntner Straße (Mitte)) 40067.34
## 4 306 Wien (Mariahilfer Straße (Mitte)) 39642.14
## 5 63 Hannover (Georgstraße) 38442.91Now let´s visualise the top 10 cities:
ggplot(ratio %>%
top_n(10,ratio), aes(station, ratio)) +
geom_bar(stat = "identity") +
labs(x = "City",
y = "Pedestrians per day") +
theme(legend.position = "bottom",
axis.text.x = element_text(angle = 45, hjust = 1))
5.3 Corona effects
The Hystreet-API is a great source of analysing the social effects of the Corona pandemic in 2020. Let´s collect all german stations since March 2020 and analyse the pedestrian count until 10th June 2020.
data <- lapply(hystreet_ids[,"id"], function(ID){
temp <- get_hystreet_station_data(
hystreetId = ID,
query = list(from = "2020-03-01", to = "2020-06-10", resolution = "day")
)
return(data.frame(
name = temp$name,
city = temp$city,
timestamp = format(as.POSIXct(temp$measurements$timestamp), "%Y-%m-%d"),
pedestrians_count = temp$measurements$pedestrians_count,
legend = paste(temp$city, temp$name, sep = " - ")
))
})
corona_data_all <- bind_rows(data)corona_data_all %>%
ggplot(aes(ymd(timestamp), pedestrians_count, colour = legend)) +
geom_line(alpha = 0.2) +
scale_x_date(labels = date_format("%d.%m.%Y"),
breaks = date_breaks("7 days")
) +
theme(legend.position = "none",
legend.title = element_text("Legende"),
axis.text.x = element_text(angle = 45, hjust = 1)) +
labs(x = "Date",
y = "Persons/Day")