ben/madison-metro
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

changed query to be more efficient

Browse Source
This commit is contained in:
Ben Varick 2024-11-23 23:14:49 -06:00
parent 93b97f3cec
commit f7c2a39889
Signed by: ben
SSH Key Fingerprint: SHA256:jWnpFDAcacYM5aPFpYRqlsamlDyKNpSj3jj+k4ojtUo
1 changed files with 19 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
madison-metro.R
View File

@ -17,42 +17,24 @@ influx_connection <- InfluxDBClient$new(url = "https://influxdb.dendroalsia.net"
org = org) org = org)
#--- Query influxdb for data #--- Query influxdb for data
# Fields to query
fields <- c("des", "spd", "pdist", "lon", "lat", "dly", "origtatripno")
# An empty list to store results for each field
results <- vector("list", length(fields))
time_start <- Sys.time() time_start <- Sys.time()
# Loop through each field, get data, and coerce types if needed
for (i in seq_along(fields)) {
field <- fields[i]
query_string <- glue('from(bucket: "{bucket}") ',
'|> range(start: -{days}d) ',
'|> filter(fn: (r) => r["_measurement"] == "vehicle_data")',
'|> filter(fn: (r) => r["_field"] == "{field}")')
data <- influx_connection$query(query_string)
# Ensure the columns are coerced to consistent types
# (Optionally add coercion based on your expected types)
data <- bind_rows(data) %>%
mutate(value = as.character(`_value`),
field = `_field`) %>%
select(time, rt, pid, vid, value, field)
results[[i]] <- data
}
# Bind all results together query_string <- glue('from(bucket: "{bucket}") ',
metro_raw <- bind_rows(results) '|> range(start: -{days}d) ',
'|> filter(fn: (r) => r["_measurement"] == "vehicle_data")',
'|> pivot(rowKey:["_time"], columnKey: ["_field"], valueColumn: "_value")')
metro_raw <- pivot_wider(metro_raw, values_from = value, names_from = field) %>% results <- influx_connection$query(query_string)
distinct(pid, vid, lat, lon, spd, .keep_all = TRUE) rm(influx_connection, query_string, bucket, org, token)
metro_raw <- results %>%
bind_rows() %>%
distinct(`_time`, pid, vid, lat, lon, spd, .keep_all = TRUE)
nrow(metro_raw)
time_end <- Sys.time() time_end <- Sys.time()
difftime(time_start, time_end) difftime(time_end, time_start)
rm(time_end, time_start, results)
#-----
routes_categorized <- read_csv(file = "routes_categorized.csv", col_types = "cc") routes_categorized <- read_csv(file = "routes_categorized.csv", col_types = "cc")
metro_data <- metro_raw %>% metro_data <- metro_raw %>%
@ -107,17 +89,17 @@ metro_segments <- metro_summary %>%
route_counts <- metro_data %>% group_by(pid, rt, des) %>% summarise(route_count = length(unique(origtatripno))) route_counts <- metro_data %>% group_by(pid, rt, des) %>% summarise(route_count = length(unique(origtatripno)))
# make charts # make charts
ggplot(data = metro_summary %>% filter(pid %in% (routes_categorized %>% filter(name %in% c("B_North", "B_South")) %>% pull (pid))), ggplot(data = metro_data %>% filter(pid %in% (routes_categorized %>% filter(name %in% c("B_North", "B_South")) %>% pull (pid))),
aes(x = pdist, aes(x = pdist,
y = spd_calc)) + y = spd)) +
geom_point() + geom_point(size = 0.1) +
geom_smooth() + geom_smooth() +
facet_grid(name ~ .) facet_grid(name ~ .)
ggplot(data = metro_summary %>% filter(!is.na(name)), ggplot(data = metro_data %>% filter(!is.na(name)),
aes(x = name, aes(x = name,
y = spd_calc)) + y = spd_calc)) +
geom_boxplot() geom_boxplot(outlier.shape = NA)
register_stadiamaps(key = substr(read_file(file = "api_keys/stadia_api_key"), 1, 36)) register_stadiamaps(key = substr(read_file(file = "api_keys/stadia_api_key"), 1, 36))
@ -180,24 +162,4 @@ for (route in unique(routes_categorized$name)){
width = 11, width = 11,
units = "in", units = "in",
create.dir = TRUE) create.dir = TRUE)
} }
# ggmap(basemap) +
# labs(title = paste0("Metro Route Speed - ", route),
# subtitle = paste0("averaged between ",
# sum(route_counts %>% filter(pid %in% route_focus) %>% pull(route_count)),
# " bus trips - ",
# min(date(metro_data$time)),
# " to ",
# max(date(metro_data$time))),
# x = NULL,
# y = NULL) +
# theme(axis.text=element_blank(),
# axis.ticks=element_blank(),
# plot.caption = element_text(color = "grey")) +
# geom_sf(data = metro_segments %>% filter(name %in% route),
# inherit.aes = FALSE,
# aes(color = spd_calc),
# linewidth = 1) +
# scale_color_distiller(palette = "RdYlGn", direction = "reverse", limits = c(0,70), name = "Average speed or segment\n(calculated with locations, not reported speed)")