From 7c4fadb951870ce5eb085b7e65846c58a9cd31b3 Mon Sep 17 00:00:00 2001
From: Michael <weigmi87303@th-nuernberg.de>
Date: Mon, 10 Nov 2025 11:31:42 +0100
Subject: [PATCH] new files

---
 EDA/researchOnSubjectPerformance.ipynb | 66 ++++++++++++++++++++++----
 1 file changed, 57 insertions(+), 9 deletions(-)

diff --git a/EDA/researchOnSubjectPerformance.ipynb b/EDA/researchOnSubjectPerformance.ipynb
index 4895576..5a53635 100644
--- a/EDA/researchOnSubjectPerformance.ipynb
+++ b/EDA/researchOnSubjectPerformance.ipynb
@@ -45,7 +45,8 @@
     "# Connect once\n",
     "oc = owncloud.Client.from_public_link(url, folder_password=password)\n",
     "# File pattern\n",
-    "base = \"adabase-public-{num:04d}-v_0_0_2.h5py\""
+    "# base = \"adabase-public-{num:04d}-v_0_0_2.h5py\"\n",
+    "base = \"{num:04d}-*.h5py\""
    ]
   },
   {
@@ -59,11 +60,25 @@
     "performance_data = []\n",
     "\n",
     "for i in range(num_files):\n",
-    "    file_name = base.format(num=i)\n",
-    "    local_tmp = f\"tmp_{i:04d}.h5\"\n",
+    "    file_pattern = f\"{i:04d}-*\"\n",
+    "    \n",
+    "    # Get list of files matching the pattern\n",
+    "    files = oc.list('.')\n",
+    "    matching_files = [f.get_name() for f in files if f.get_name().startswith(f\"{i:04d}-\")]\n",
+    "    \n",
+    "    if matching_files:\n",
+    "        file_name = matching_files[0]  # Take the first matching file\n",
+    "        local_tmp = f\"tmp_{i:04d}.h5\"\n",
+    "        \n",
+    "        oc.get_file(file_name, local_tmp)\n",
+    "        print(f\"{file_name} geöffnet\")\n",
+    "    else:\n",
+    "        print(f\"Keine Datei gefunden für Muster: {file_pattern}\")\n",
+    "    # file_name = base.format(num=i)\n",
+    "    # local_tmp = f\"tmp_{i:04d}.h5\"\n",
     "\n",
-    "    oc.get_file(file_name, local_tmp)\n",
-    "    print(f\"{file_name} geöffnet\")\n",
+    "    # oc.get_file(file_name, local_tmp)\n",
+    "    # print(f\"{file_name} geöffnet\")\n",
     "\n",
     "    # check SIGNALS table for AUs\n",
     "    with pd.HDFStore(local_tmp, mode=\"r\") as store:\n",
@@ -111,7 +126,7 @@
     "    combination_cols = sorted([c for c in performance_df.columns if c.startswith(\"STUDY_\")])\n",
     "    final_cols = [\"subjectID\", \"overall_score\"] + combination_cols\n",
     "    performance_df = performance_df[final_cols]\n",
-    "    performance_df.to_csv(\"au_performance.csv\", index=False)\n",
+    "    performance_df.to_csv(\"n_au_performance.csv\", index=False)\n",
     "\n",
     "    print(f\"\\nGesamt Subjects mit Action Units: {len(performance_df)}\")\n",
     "else:\n",
@@ -135,9 +150,42 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with pd.HDFStore(local_tmp, mode=\"r\") as store:\n",
-    "    performance = store.select(\"PERFORMANCE\")\n",
-    "performance"
+    "with pd.HDFStore(\"tmp_0000.h5\", mode=\"r\") as store:\n",
+    "    md = store.select(\"META\")\n",
+    "print(\"File 0:\")\n",
+    "print(md)\n",
+    "with pd.HDFStore(\"tmp_0001.h5\", mode=\"r\") as store:\n",
+    "    md = store.select(\"META\")\n",
+    "print(\"File 1\")\n",
+    "print(md)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8067036b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pd.set_option('display.max_columns', None)\n",
+    "pd.set_option('display.max_rows', None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f18e7385",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with pd.HDFStore(\"tmp_0000.h5\", mode=\"r\") as store:\n",
+    "    md = store.select(\"SIGNALS\", start=0, stop=1)\n",
+    "print(\"File 0:\")\n",
+    "md.head()\n",
+    "# with pd.HDFStore(\"tmp_0001.h5\", mode=\"r\",start=0, stop=1) as store:\n",
+    "#     md = store.select(\"SIGNALS\")\n",
+    "# print(\"File 1\")\n",
+    "# print(md.columns)"
    ]
   }
  ],