From 1d9d193668345695f07d07991e5dfc8cfd88058f Mon Sep 17 00:00:00 2001
From: Hannes Martin Signer <hannes.martin.signer@uni-potsdam.de>
Date: Thu, 27 Feb 2025 11:44:51 +0100
Subject: [PATCH] update julia script

---
 src/convert_data.jl | 112 +++++++++++++++++++++++++++-----------------
 1 file changed, 70 insertions(+), 42 deletions(-)

diff --git a/src/convert_data.jl b/src/convert_data.jl
index 3cd3cc9..d57df53 100644
--- a/src/convert_data.jl
+++ b/src/convert_data.jl
@@ -1,60 +1,88 @@
-using HDF5
-using RData
+#!/usr/bin/env julia
 
-using DataFrames
+# qs_read = []
 
-# Load Training Data 
-# train_data = load("Barite_50_Data.rds")
 
-# training_h5_name = "Barite_50_Data.h5"
-# h5open(training_h5_name, "w") do fid
-#     for key in keys(train_data)
-#         group = create_group(fid, key)
-#         group["names"] = names(train_data[key])
-#         group["data", compress=3] = Matrix(train_data[key])
-#         # group = create_group(fid, key)
-#         # grou["names"] = coln
-#     end
-# end
+# # find all the files in 'barite_out'
+# files = readdir("barite_out"; join=true)
+
+# # remove files which do not have the extension '.qs2' and contains 'iter'
+# files = filter(x -> occursin(r".*\.qs2", x) && occursin(r"iter", x), files)
+
+# # remove first entry as it is iteration 0
+# files = files[2:end]
+
+# test1 = qs_read(files[1])
+
+# @rput test1
+
+# R"test1 <- test1$C"
+
+# @rget test1
+
+# check if ARGS contains 2 elements
+if length(ARGS) != 2
+    println("Usage: julia convert.jl <directory> <output_file_name>.h5")
+    exit(1)
+end
+
+to_read_dir = ARGS[1]
+output_file_name = ARGS[2] * ".h5"
+
+# check if the directory exists
+if !isdir(to_read_dir)
+    println("The directory \"$to_read_dir\" does not exist")
+    exit(1)
+end
+
+using HDF5, RCall, DataFrames
+@rlibrary qs2
 
 # List all .rds files starting with "iter" in a given directory
-rds_files = filter(x -> startswith(x, "iter"), readdir("barite_out/"))
+qs_files = filter(x -> occursin(r".*\.qs2", x) && occursin(r"iter", x), readdir(to_read_dir; join=true))[2:end]
 
-# remove "iter_0.rds" from the list 
-rds_files = rds_files[2:end]
+df_design = DataFrame()
+df_result = DataFrame()
 
-big_df_in = DataFrame()
-big_df_out = DataFrame()
-
-for rds_file in rds_files
+for file in qs_files
     # Load the RDS file
-    data = load("barite_out/$rds_file")
-    # Convert the data to a DataFrame
-    df_T = DataFrame(data["T"])
-    df_C = DataFrame(data["C"])
+    data = qs_read(file)
+
+    # get basename of the file
+    basename = split(file, "/")[end]
+
+    # get the iteration number by splitting the basename and parse the second element
+    iteration = parse(Int, split(split(basename, "_")[2], ".")[1])
+
+    @rput data
+
+    R"transport <- data$T"
+    R"chemistry <- data$C"
+
+    @rget transport
+    @rget chemistry
+
+    # Add iteration number to the DataFrame
+    transport.iteration = fill(iteration, size(transport, 1))
+    chemistry.iteration = fill(iteration, size(chemistry, 1))
+
     # Append the DataFrame to the big DataFrame
-    append!(big_df_in, df_T)
-    append!(big_df_out, df_C)
+    append!(df_design, transport)
+    append!(df_result, chemistry)
 end
 
 # remove ID, Barite_p1, Celestite_p1 columns
-big_df_in = big_df_in[:, Not([:ID, :Barite_p1, :Celestite_p1])]
-big_df_out = big_df_out[:, Not([:ID, :Barite_p1, :Celestite_p1])]
+df_design = df_design[:, Not([:ID, :Barite_p1, :Celestite_p1])]
+df_result = df_result[:, Not([:ID, :Barite_p1, :Celestite_p1])]
 
-inference_h5_name = "Barite_50_Data_inference.h5"
-h5open(inference_h5_name, "w") do fid
-    fid["names"] = names(big_df_in)
-    fid["data", compress=9] = Matrix(big_df_in)
-end
 
-training_h5_name = "Barite_50_Data_training.h5"
-h5open(training_h5_name, "w") do fid
+h5open(output_file_name, "w") do fid
     group_in = create_group(fid, "design")
     group_out = create_group(fid, "result")
 
-    group_in["names"] = names(big_df_in)
-    group_in["data", compress=9] = Matrix(big_df_in)
+    group_in["names"] = names(df_design)
+    group_in["data", compress=9] = Matrix(df_design)
 
-    group_out["names"] = names(big_df_out)
-    group_out["data", compress=9] = Matrix(big_df_out)
-end
\ No newline at end of file
+    group_out["names"] = names(df_result)
+    group_out["data", compress=9] = Matrix(df_result)
+end