4.0.1 Load some statistics

The function ‘get_hystreet_stats()’ summarises the number of available stations and the sum of all counted pedestrians.

library(hystReet)

stats <- get_hystreet_stats()

4.1 Request all stations

The function ‘get_hystreet_locations()’ requests all available stations of the project.

locations <- get_hystreet_locations()

4.2 Request data from a specific station

The (probably) most interesting function is ‘get_hystreet_station_data()’. With the hystreetID it is possible to request a specific station. By default, all the data from the current day are received. With the ‘query’ argument it is possible to set the received data more precise: * from: datetime of earliest measurement (default: today 00:00:00:): e.g. “2018-10-01 12:00:00” or “2018-10-01” * to : datetime of latest measurement (default: today 23:59:59): e.g. “2018-12-01 12:00:00” or “2018-12-01” * resoution: Resultion for the measurement grouping (default: hour): “day”, “hour”, “month”, “week”

location_71 <- get_hystreet_station_data(
  hystreetId = 71,
  query = list(from = "2018-12-01", to = "2019-01-01", resolution = "day"))

5.1 Compare different stations

Now let´s compare different stations:

1. Load the data

location_73 <- get_hystreet_station_data(
    hystreetId = 73, 
    query = list(from = "2019-01-01", to = "2019-01-31", resolution = "day"))$measurements %>% 
  select(pedestrians_count, timestamp) %>% 
  mutate(station = 73)

location_74 <- get_hystreet_station_data(
    hystreetId = 74, 
    query = list(from = "2019-01-01", to = "2019-01-31", 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 = "2019-01-01", to = today(), resolution = "day"))
  
    lifetime_count <- temp$statistics$timerange_count
    days_counted <- as.numeric(temp$metadata$latest_measurement_at  - temp$metadata$earliest_measurement_at)
    
    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
## 1 165     München (Kaufingerstraße) 64469.29
## 2 150 Frankfurt a.M. (Zeil (Mitte)) 52520.83
## 3 159  Köln (Schildergasse (Mitte)) 50318.07
## 4  73    München (Neuhauser Straße) 49996.25
## 5 158      Köln (Hohe Straße (Süd)) 39806.93

Now 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.

corona_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")