junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix location processing when certain columns don't exist

pull/114/head
JulioV 2021-02-01 11:49:22 -05:00
parent 5296f9130f
commit aefc794274
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/data/process_location_types.R
View File

@ -51,10 +51,9 @@ if(locations_to_use == "ALL"){
# Filter those rows that are further away than time_since_valid_location since the last fused location
mutate(time_from_fused = timestamp - first(timestamp)) %>%
filter(provider %in% providers_to_keep | (time_from_fused < (1000 * 60 * time_since_valid_location))) %>%
select(-consecutive_time_diff, -time_from_fused, -device_id) %>%
# Summarise the period to resample for
summarise(limit = max(timestamp), timestamp = first(timestamp), double_latitude = first(double_latitude), double_longitude = first(double_longitude),
double_bearing=first(double_bearing), double_speed = first(double_speed), double_altitude=first(double_altitude), provider=first(provider),
accuracy=first(accuracy), label=first(label)) %>%
summarise(across(timestamp, max, .names = "limit"), across(everything(), first)) %>%
# the limit will be equal to the next timestamp-1 or the last binded timestamp (limit) plus the consecutive_threshold buffer
# you can think of consecutive_threshold as the period a location row is valid for
mutate(limit = pmin(lead(timestamp, default = 9999999999999) - 1, limit + (1000 * 60 * consecutive_threshold)),