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

Fix download_dataset.R to handle non sensor tables

pull/95/head
JulioV 2020-03-05 14:10:36 -05:00
parent 2548539dc4
commit f25dd026fd
1 changed files with 25 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
src/data/download_dataset.R
View File

@ -13,24 +13,36 @@ sensor_file <- snakemake@output[[1]]
device_ids <- readLines(participant, n=1) device_ids <- readLines(participant, n=1)
unified_device_id <- tail(strsplit(device_ids, ",")[[1]], 1) unified_device_id <- tail(strsplit(device_ids, ",")[[1]], 1)
# Read start and end date from the participant file to filter data within that range
start_date <- strsplit(readLines(participant, n=4)[4], ",")[[1]][1] start_date <- strsplit(readLines(participant, n=4)[4], ",")[[1]][1]
end_date <- strsplit(readLines(participant, n=4)[4], ",")[[1]][2] end_date <- strsplit(readLines(participant, n=4)[4], ",")[[1]][2]
start_datetime_utc = format(as.POSIXct(paste0(start_date, " 00:00:00"),format="%Y/%m/%d %H:%M:%S",origin="1970-01-01",tz=timezone), tz="UTC") start_datetime_utc = format(as.POSIXct(paste0(start_date, " 00:00:00"),format="%Y/%m/%d %H:%M:%S",origin="1970-01-01",tz=timezone), tz="UTC")
end_datetime_utc = format(as.POSIXct(paste0(end_date, " 23:59:59"),format="%Y/%m/%d %H:%M:%S",origin="1970-01-01",tz=timezone), tz="UTC") end_datetime_utc = format(as.POSIXct(paste0(end_date, " 23:59:59"),format="%Y/%m/%d %H:%M:%S",origin="1970-01-01",tz=timezone), tz="UTC")
rmysql.settingsfile <- "./.env" stopDB <- dbConnect(MySQL(), default.file = "./.env", group = group)
stopDB <- dbConnect(MySQL(), default.file = rmysql.settingsfile, group = group) # Get existent columns in table
query <- paste0("SELECT * FROM ", table, " WHERE device_id IN ('", gsub(",", "','", device_ids), "')") query <- paste0("SELECT * FROM ", table, " LIMIT 1")
if(!(is.na(start_datetime_utc)) && !(is.na(end_datetime_utc)) && start_datetime_utc < end_datetime_utc){ available_columns <- colnames(dbGetQuery(stopDB, query))
query <- paste0(query, "AND timestamp BETWEEN 1000*UNIX_TIMESTAMP('", start_datetime_utc, "') AND 1000*UNIX_TIMESTAMP('", end_datetime_utc, "')")
if("device_id" %in% available_columns){
query <- paste0("SELECT * FROM ", table, " WHERE device_id IN ('", gsub(",", "','", device_ids), "')")
if("timestamp" %in% available_columns && !(is.na(start_datetime_utc)) && !(is.na(end_datetime_utc)) && start_datetime_utc < end_datetime_utc){
query <- paste0(query, "AND timestamp BETWEEN 1000*UNIX_TIMESTAMP('", start_datetime_utc, "') AND 1000*UNIX_TIMESTAMP('", end_datetime_utc, "')")
}
sensor_data <- dbGetQuery(stopDB, query)
if("timestamp" %in% available_columns){
sensor_data <- sensor_data %>% arrange(timestamp)
}
# Unify device_id
sensor_data <- sensor_data %>% mutate(device_id = unified_device_id)
# Droping duplicates on all columns except for _id or id
sensor_data <- sensor_data %>% distinct(!!!syms(setdiff(names(sensor_data), c("_id", "id"))))
} else {
print(paste0("Table ", table, "does not have a device_id column (Aware ID) to link its data to a participant"))
} }
sensor_data <- dbGetQuery(stopDB, query)
sensor_data <- sensor_data %>%
arrange(timestamp) %>%
mutate(device_id = unified_device_id)
# Droping duplicates on all columns except for _id
sensor_data <- sensor_data %>% distinct(!!!syms(setdiff(names(sensor_data), "_id")))
write.csv(sensor_data, sensor_file, row.names = FALSE) write.csv(sensor_data, sensor_file, row.names = FALSE)
dbDisconnect(stopDB) dbDisconnect(stopDB)