Jiarui Li
5e979e061b
- Implemented target construction in `targets.py` for next-token and unique-time set supervision. - Added validation functions and utility methods for target building. - Created a comprehensive training script in `train.py` that includes data loading, model building, optimizer setup, and training loop with early stopping and logging. - Integrated loss functions and readout mechanisms based on target modes. - Established dataset splitting and DataLoader configurations for training, validation, and testing.
26 lines
1.0 KiB
R
26 lines
1.0 KiB
R
library(data.table)
|
|
setDTthreads(40)
|
|
library(readr)
|
|
|
|
field_id <- read.csv("field_ids_enriched.csv", header = TRUE, stringsAsFactors = FALSE)
|
|
uid <- unique(c("eid", field_id$field_instance))
|
|
|
|
big_path <- "/mnt/storage/shared_data/UKBB/20230518-from-zhourong/HHdata_221103_0512.csv"
|
|
header_dt <- fread(big_path, nrows = 0) # Read 0 rows => only column names
|
|
all_names <- names(header_dt)
|
|
keep_names <- intersect(all_names,uid)
|
|
ukb_disease <- fread(big_path,
|
|
select = keep_names,
|
|
showProgress = TRUE)
|
|
|
|
big_path <- "/mnt/storage/shared_data/UKBB/20230518-from-zhourong/HH_data_220812_0512.csv"
|
|
header_dt <- fread(big_path, nrows = 0) # Read 0 rows => only column names
|
|
all_names <- names(header_dt)
|
|
keep_names <- intersect(all_names,uid)
|
|
ukb_others <- fread(big_path,
|
|
select = keep_names,
|
|
showProgress = TRUE)
|
|
|
|
# merge disease and other data by "eid"
|
|
ukb_data <- merge(ukb_disease, ukb_others, by = "eid", all = TRUE)
|
|
fwrite(ukb_data, "ukb_data.csv") |