From 9e884bcc9923a98e9d1b44dd6ef3b42694dd49e5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Max=20L=C3=BCbke?= <mluebke@uni-potsdam.de>
Date: Wed, 15 Jan 2025 13:42:27 +0100
Subject: [PATCH] Add convert script and new data set

---
 barite_50_4_corner.h5 |  3 ++
 convert_barite.jl     | 78 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)
 create mode 100644 barite_50_4_corner.h5
 create mode 100755 convert_barite.jl

diff --git a/barite_50_4_corner.h5 b/barite_50_4_corner.h5
new file mode 100644
index 0000000..f55a844
--- /dev/null
+++ b/barite_50_4_corner.h5
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d135c6696d4a0068b442f8e58c77842dcc8c229b79fe9ae0af030cfc3e813bf7
+size 62127814
diff --git a/convert_barite.jl b/convert_barite.jl
new file mode 100755
index 0000000..6830d32
--- /dev/null
+++ b/convert_barite.jl
@@ -0,0 +1,78 @@
+#!/usr/bin/env julia
+
+# qs_read = []
+
+
+# # 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
+qs_files = filter(x -> occursin(r".*\.qs2", x) && occursin(r"iter", x), readdir(to_read_dir; join=true))[2:end]
+
+df_design = DataFrame()
+df_result = DataFrame()
+
+for file in qs_files
+    # Load the RDS file
+    data = qs_read(file)
+
+    @rput data
+
+    R"transport <- data$T"
+    R"chemistry <- data$C"
+
+    @rget transport
+    @rget chemistry
+
+    # Append the DataFrame to the big DataFrame
+    append!(df_design, transport)
+    append!(df_result, chemistry)
+end
+
+# remove ID, Barite_p1, Celestite_p1 columns
+df_design = df_design[:, Not([:ID, :Barite_p1, :Celestite_p1])]
+df_result = df_result[:, Not([:ID, :Barite_p1, :Celestite_p1])]
+
+
+h5open(output_file_name, "w") do fid
+    group_in = create_group(fid, "design")
+    group_out = create_group(fid, "result")
+
+    group_in["names"] = names(df_design)
+    group_in["data", compress=9] = Matrix(df_design)
+
+    group_out["names"] = names(df_result)
+    group_out["data", compress=9] = Matrix(df_result)
+end