kurzti88066/Fahrsimulator_MSY2526_AI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

revert c5a61c9e55c9a92869db3e7108be64864c09cc23

Browse Source 
revert Merge branch 'main' of https://git.efi.th-nuernberg.de/gitea/kurzti88066/Fahrsimulator_MSY2526_AI
This commit is contained in:
Michael Weig 2025-11-02 19:59:39 +00:00
parent c5a61c9e55
commit ab3ba28a71
3 changed files with 30 additions and 179 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
EDA/EDA.ipynb
View File

@ -237,7 +237,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "base",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -251,7 +251,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.12.10" "version": "3.11.5"
} }
}, },
"nbformat": 4, "nbformat": 4,

110
EDA/check_if_performance_tables_are_same.ipynb
View File

@ -1,110 +0,0 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "8fb02733",
"metadata": {},
"source": [
"Imports"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ebd32616-1e11-4b15-805e-481e010e03fc",
"metadata": {},
"outputs": [],
"source": [
"%pip install pyocclient\n",
"import yaml\n",
"import owncloud\n",
"import pandas as pd\n",
"import numpy as np\n",
"import hashlib"
]
},
{
"cell_type": "markdown",
"id": "c20cee7c",
"metadata": {},
"source": [
"Connection to Owncloud"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c4c94558",
"metadata": {},
"outputs": [],
"source": [
"# Load credentials\n",
"with open(\"../login.yaml\") as f:\n",
" cfg = yaml.safe_load(f)\n",
" \n",
"url, password = cfg[0][\"url\"], cfg[1][\"password\"]\n",
"\n",
"# Connect once\n",
"oc = owncloud.Client.from_public_link(url, folder_password=password)\n",
"# File pattern\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "485149e6-f26c-4aac-a742-c0111f0272cb",
"metadata": {},
"outputs": [],
"source": [
"num_files = 30\n",
"base = \"adabase-public-{num:04d}-v_0_0_2.h5py\"\n",
"\n",
"for i in range(num_files):\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",
"\n",
" print(f\"\\n===== FILE {i}: {file_name} =====\")\n",
"\n",
" try:\n",
" with pd.HDFStore(local_tmp, mode=\"r\") as store:\n",
" perf_df = store.select(\"PERFORMANCE\", columns=[\"AUDITIVE F1\", \"VISUAL F1\", \"F1\"])\n",
" print(perf_df)\n",
" except Exception as e:\n",
" print(f\"Error reading PERFORMANCE table: {e}\")\n",
"\n",
" print(\"===========================================\\n\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1ff28917-860a-4900-906c-f38ac2fe9d64",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.12.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

95
EDA/researchOnSubjectPerformance.ipynb
View File

@ -11,16 +11,14 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "ebd32616-1e11-4b15-805e-481e010e03fc", "id": "96f3b128",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"%pip install pyocclient\n",
"import yaml\n", "import yaml\n",
"import owncloud\n", "import owncloud\n",
"import pandas as pd\n", "import pandas as pd\n",
"import numpy as np\n", "import numpy as np"
"import hashlib"
] ]
}, },
{ {
@ -46,7 +44,8 @@
"\n", "\n",
"# Connect once\n", "# Connect once\n",
"oc = owncloud.Client.from_public_link(url, folder_password=password)\n", "oc = owncloud.Client.from_public_link(url, folder_password=password)\n",
"# File pattern\n" "# File pattern\n",
"base = \"adabase-public-{num:04d}-v_0_0_2.h5py\""
] ]
}, },
{ {
@ -56,19 +55,15 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"num_files = 30\n", "num_files = 2 # number of files to process (min: 1, max: 30)\n",
"performance_data = []\n", "performance_data = []\n",
"base = \"adabase-public-{num:04d}-v_0_0_2.h5py\" # remote name pattern\n", "\n",
"for i in range(num_files):\n", "for i in range(num_files):\n",
" file_name = base.format(num=i)\n", " file_name = base.format(num=i)\n",
" local_tmp = f\"tmp_{i:04d}.h5\"\n", " local_tmp = f\"tmp_{i:04d}.h5\"\n",
"\n", "\n",
" #oc.get_file(file_name, local_tmp)\n", " oc.get_file(file_name, local_tmp)\n",
"\n", " print(f\"{file_name} geöffnet\")\n",
" # quick checksum to detect identical downloads\n",
" with open(local_tmp, \"rb\") as fh:\n",
" file_hash = hashlib.sha1(fh.read()).hexdigest()\n",
" print(f\"File {i}: {file_name} checksum={file_hash}\")\n",
"\n", "\n",
" # check SIGNALS table for AUs\n", " # check SIGNALS table for AUs\n",
" with pd.HDFStore(local_tmp, mode=\"r\") as store:\n", " with pd.HDFStore(local_tmp, mode=\"r\") as store:\n",
@ -78,57 +73,49 @@
" print(f\"Subject {i} enthält keine AUs\")\n", " print(f\"Subject {i} enthält keine AUs\")\n",
" continue\n", " continue\n",
"\n", "\n",
" # load performance table (make a copy)\n", " # load performance table\n",
" with pd.HDFStore(local_tmp, mode=\"r\") as store:\n", " with pd.HDFStore(local_tmp, mode=\"r\") as store:\n",
" perf_df = store.select(\"PERFORMANCE\").copy()\n", " perf_df = store.select(\"PERFORMANCE\")\n",
"\n",
" # print(f\"Subject {i}: PERFORMANCE rows={len(perf_df)}\")\n",
" # print(perf_df.head(3).to_string(index=False))\n",
"\n", "\n",
" f1_cols = [c for c in [\"AUDITIVE F1\", \"VISUAL F1\", \"F1\"] if c in perf_df.columns]\n", " f1_cols = [c for c in [\"AUDITIVE F1\", \"VISUAL F1\", \"F1\"] if c in perf_df.columns]\n",
" if not f1_cols:\n", " if not f1_cols:\n",
" print(f\"Subject {i}: keine F1-Spalten gefunden\")\n", " print(f\"Subject {i}: keine F1-Spalten gefunden\")\n",
" continue\n", " continue\n",
"\n", "\n",
" # drop rows that have all F1s NaN (no valid score for that combo)\n",
" perf_df = perf_df.dropna(subset=f1_cols, how=\"all\")\n",
" if perf_df.empty:\n",
" print(f\"Subject {i}: keine gültigen F1-Daten nach Filter\")\n",
" continue\n",
"\n",
" subject_entry = {\"subjectID\": i}\n", " subject_entry = {\"subjectID\": i}\n",
" combo_means = []\n", " valid_scores = []\n",
"\n", "\n",
" # iterate rows: each (study, level, phase)\n",
" for _, row in perf_df.iterrows():\n", " for _, row in perf_df.iterrows():\n",
" study, level, phase = row[\"STUDY\"], row[\"LEVEL\"], row[\"PHASE\"]\n", " study, level, phase = row[\"STUDY\"], row[\"LEVEL\"], row[\"PHASE\"]\n",
" col_name = f\"STUDY_{study}_LEVEL_{level}_PHASE_{phase}\"\n", " col_name = f\"STUDY_{study}_LEVEL_{level}_PHASE_{phase}\"\n",
"\n", "\n",
" # mean of available F1 cols for this single combination\n", " # collect valid F1 values among the three columns\n",
" vals = [float(row[c]) for c in f1_cols if pd.notna(row[c])]\n", " scores = [row[c] for c in f1_cols if pd.notna(row[c])]\n",
" if not vals:\n", " if scores:\n",
" continue\n", " mean_score = float(np.mean(scores))\n",
" mean_for_combo = float(np.mean(vals))\n", " subject_entry[col_name] = mean_score\n",
" subject_entry[col_name] = mean_for_combo\n", " valid_scores.extend(scores)\n",
" combo_means.append(mean_for_combo)\n",
"\n", "\n",
" # overall: mean of per-combination means (not flattened raw F1s)\n", " # compute overall average across all valid combinations\n",
" if combo_means:\n", " if valid_scores:\n",
" subject_entry[\"overall_score\"] = float(np.mean(combo_means))\n", " subject_entry[\"overall_score\"] = float(np.mean(valid_scores))\n",
" performance_data.append(subject_entry)\n", " performance_data.append(subject_entry)\n",
" print(f\"Subject {i}: combos={len(combo_means)} overall={subject_entry['overall_score']:.4f}\")\n", " print(f\"Subject {i}: {len(valid_scores)} gültige Scores, Overall = {subject_entry['overall_score']:.3f}\")\n",
" else:\n", " else:\n",
" print(f\"Subject {i}: keine gültigen Kombinationen\")\n", " print(f\"Subject {i}: keine gültigen F1-Scores\")\n",
"\n", "\n",
"# build dataframe\n", "# build dataframe\n",
"if performance_data:\n", "if performance_data:\n",
" performance_df = pd.DataFrame(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", " combination_cols = sorted([c for c in performance_df.columns if c.startswith(\"STUDY_\")])\n",
" final_cols = [\"subjectID\", \"overall_score\"] + combination_cols\n", " final_cols = [\"subjectID\", \"overall_score\"] + combination_cols\n",
" performance_df = performance_df.reindex(columns=final_cols) # keeps missing combo cols as NaN\n", " performance_df = performance_df[final_cols]\n",
" performance_df.to_csv(\"au_performance.csv\", index=False)\n", " performance_df.to_csv(\"au_performance.csv\", index=False)\n",
"\n",
" print(f\"\\nGesamt Subjects mit Action Units: {len(performance_df)}\")\n", " print(f\"\\nGesamt Subjects mit Action Units: {len(performance_df)}\")\n",
"else:\n", "else:\n",
" print(\"Keine gültigen Daten gefunden.\")\n" " print(\"Keine gültigen Daten gefunden.\")"
] ]
}, },
{ {
@ -152,37 +139,11 @@
" performance = store.select(\"PERFORMANCE\")\n", " performance = store.select(\"PERFORMANCE\")\n",
"performance" "performance"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e17fd7eb-8600-4c31-9212-d1eeb9e74736",
"metadata": {},
"outputs": [],
"source": [
"\n",
"\n",
"def hash_perf(local_tmp):\n",
" with pd.HDFStore(local_tmp, mode=\"r\") as s:\n",
" df = s.select(\"PERFORMANCE\")\n",
" # hash based on data values only\n",
" return hashlib.sha1(pd.util.hash_pandas_object(df, index=True).values).hexdigest()\n",
"\n",
"hashes = []\n",
"for i in range(5):\n",
" local_tmp = f\"tmp_{i:04d}.h5\"\n",
" try:\n",
" hashes.append((i, hash_perf(local_tmp)))\n",
" except Exception as e:\n",
" hashes.append((i, str(e)))\n",
"\n",
"print(hashes)\n"
]
} }
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "Python 3 (ipykernel)", "display_name": "base",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -196,7 +157,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.12.10" "version": "3.11.5"
} }
}, },
"nbformat": 4, "nbformat": 4,