Fahrsimulator_MSY2526_AI/EDA/researchOnSubjectPerformance.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8fb02733",
   "metadata": {},
   "source": [
    "Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "96f3b128",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install pyocclient\n",
    "import yaml\n",
    "import owncloud\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c20cee7c",
   "metadata": {},
   "source": [
    "Connection to Owncloud"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c4c94558",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load credentials from YAML\n",
    "with open(\"login.yaml\", \"r\") as f:\n",
    "    cfg = yaml.safe_load(f)\n",
    "\n",
    "url = cfg[0][\"url\"]\n",
    "password = cfg[1][\"password\"]\n",
    "\n",
    "# Connect once to the public OwnCloud link\n",
    "oc = owncloud.Client.from_public_link(url, folder_password=password)\n",
    "\n",
    "num_files = 1  # number of subject IDs to process (min: 1, max: 30)\n",
    "performance_data = []\n",
    "\n",
    "# Read remote file list once\n",
    "remote_files = oc.list(\".\")\n",
    "remote_names = [f.get_name() for f in remote_files]\n",
    "\n",
    "for i in range(num_files):\n",
    "    prefix = f\"{i:04d}-\"\n",
    "    matching_files = [name for name in remote_names if name.startswith(prefix) and name.endswith(\".hdf5\")]\n",
    "\n",
    "    if not matching_files:\n",
    "        print(f\"No file found for pattern: {prefix}*.hdf5\")\n",
    "        continue\n",
    "\n",
    "    # Take the first matching file, e.g. 0000-AACA.hdf5\n",
    "    file_name = matching_files[0]\n",
    "    local_tmp = f\"tmp_{i:04d}.hdf5\"\n",
    "\n",
    "    try:\n",
    "        # Download the file locally\n",
    "        oc.get_file(file_name, local_tmp)\n",
    "        print(f\"Downloaded and opened file: {file_name} -> {local_tmp}\")\n",
    "    except Exception as e:\n",
    "        print(f\"Failed to download file {file_name}: {e}\")\n",
    "        continue\n",
    "\n",
    "    # Check SIGNALS table for AU columns\n",
    "    try:\n",
    "        with pd.HDFStore(local_tmp, mode=\"r\") as store:\n",
    "            cols = store.select(\"SIGNALS\", start=0, stop=1).columns\n",
    "    except Exception as e:\n",
    "        print(f\"Failed to read SIGNALS from {local_tmp}: {e}\")\n",
    "        continue\n",
    "\n",
    "    au_cols = [c for c in cols if c.startswith(\"AU\")]\n",
    "    if not au_cols:\n",
    "        print(f\"Subject {i:04d} contains no AU columns\")\n",
    "        continue\n",
    "\n",
    "    # Load PERFORMANCE table\n",
    "    try:\n",
    "        with pd.HDFStore(local_tmp, mode=\"r\") as store:\n",
    "            perf_df = store.select(\"PERFORMANCE\")\n",
    "    except Exception as e:\n",
    "        print(f\"Failed to read PERFORMANCE from {local_tmp}: {e}\")\n",
    "        continue\n",
    "\n",
    "    f1_cols = [c for c in [\"AUDITIVE F1\", \"VISUAL F1\", \"F1\"] if c in perf_df.columns]\n",
    "    if not f1_cols:\n",
    "        print(f\"Subject {i:04d}: no F1 columns found\")\n",
    "        continue\n",
    "\n",
    "    subject_entry = {\"subjectID\": i}\n",
    "    valid_scores = []\n",
    "\n",
    "    # Iterate through PERFORMANCE rows: each row is one (study, level, phase) combination\n",
    "    for _, row in perf_df.iterrows():\n",
    "        study = row[\"STUDY\"]\n",
    "        level = row[\"LEVEL\"]\n",
    "        phase = row[\"PHASE\"]\n",
    "        col_name = f\"STUDY_{study}_LEVEL_{level}_PHASE_{phase}\"\n",
    "\n",
    "        # Collect non-NaN F1 values from the available F1 columns\n",
    "        scores = [row[c] for c in f1_cols if pd.notna(row[c])]\n",
    "        if scores:\n",
    "            mean_score = float(np.mean(scores))\n",
    "            subject_entry[col_name] = mean_score\n",
    "            valid_scores.extend(scores)\n",
    "\n",
    "    # Compute overall average across all valid F1 values\n",
    "    if valid_scores:\n",
    "        subject_entry[\"overall_score\"] = float(np.mean(valid_scores))\n",
    "        performance_data.append(subject_entry)\n",
    "        print(\n",
    "            f\"Subject {i:04d}: {len(valid_scores)} valid scores, \"\n",
    "            f\"overall = {subject_entry['overall_score']:.3f}\"\n",
    "        )\n",
    "    else:\n",
    "        print(f\"Subject {i:04d}: no valid F1 scores found\")\n",
    "\n",
    "# Build final DataFrame and save CSV\n",
    "if performance_data:\n",
    "    performance_df = pd.DataFrame(performance_data)\n",
    "    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(\"performance.csv\", index=False)\n",
    "\n",
    "    print(f\"\\nTotal subjects with Action Units: {len(performance_df)}\")\n",
    "    print(\"Saved results to performance.csv\")\n",
    "else:\n",
    "    print(\"No valid data found.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0bcaf065",
   "metadata": {},
   "outputs": [],
   "source": [
    "performance_df.head()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "310",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}