From 37ab7cb6204758b91c270cd9f316ba12317199c3 Mon Sep 17 00:00:00 2001
From: Michael <weigmi87303@th-nuernberg.de>
Date: Mon, 3 Nov 2025 10:24:02 +0100
Subject: [PATCH] added histogramms for AU EDA

---
 EDA/histogramms.ipynb | 166 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 166 insertions(+)
 create mode 100644 EDA/histogramms.ipynb

diff --git a/EDA/histogramms.ipynb b/EDA/histogramms.ipynb
new file mode 100644
index 0000000..e35055f
--- /dev/null
+++ b/EDA/histogramms.ipynb
@@ -0,0 +1,166 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1014c5e0",
+   "metadata": {},
+   "source": [
+    "Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e42f3011",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0a834496",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path =r\"C:\\Users\\micha\\FAUbox\\WS2526_Fahrsimulator_MSY (Celina Korzer)\\AU_dataset\\output_windowed.parquet\"\n",
+    "df = pd.read_parquet(path=path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aa4759fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "high_nback = df[\n",
+    "    (df[\"STUDY\"]==\"n-back\") &\n",
+    "    (df[\"LEVEL\"].isin([2, 3, 5, 6])) &\n",
+    "    (df[\"PHASE\"].isin([\"train\", \"test\"]))\n",
+    "]\n",
+    "high_nback.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a2aa0596",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "low_all = df[\n",
+    "    ((df[\"PHASE\"] == \"baseline\") |\n",
+    "     ((df[\"STUDY\"] == \"n-back\") & (df[\"PHASE\"] != \"baseline\") & (df[\"LEVEL\"].isin([1,4]))))\n",
+    "]\n",
+    "print(low_all.shape)\n",
+    "high_kdrive = df[\n",
+    "    (df[\"STUDY\"] == \"k-drive\") & (df[\"PHASE\"] != \"baseline\")\n",
+    "]\n",
+    "print(high_kdrive.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f7d446a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print((df.shape[0]==(high_kdrive.shape[0]+high_nback.shape[0]+low_all.shape[0])))\n",
+    "print(df.shape[0])\n",
+    "print((high_kdrive.shape[0]+high_nback.shape[0]+low_all.shape[0]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "474e144a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "high_all = pd.concat([high_nback, high_kdrive])\n",
+    "high_all.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5dd585c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0bd39d9f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get all columns that start with 'AU'\n",
+    "au_columns = [col for col in low_all.columns if col.startswith('AU')]\n",
+    "\n",
+    "# Calculate number of rows and columns for subplots\n",
+    "n_cols = len(au_columns)\n",
+    "n_rows = 4\n",
+    "n_cols_subplot = 5\n",
+    "\n",
+    "# Create figure with subplots\n",
+    "fig, axes = plt.subplots(n_rows, n_cols_subplot, figsize=(20, 16))\n",
+    "axes = axes.flatten()\n",
+    "fig.suptitle('Action Unit (AU) Distributions: Low vs High', fontsize=20, fontweight='bold', y=0.995)\n",
+    "\n",
+    "# Create histogram for each AU column\n",
+    "for idx, col in enumerate(au_columns):\n",
+    "    ax = axes[idx]\n",
+    "    \n",
+    "    # Plot overlapping histograms\n",
+    "    ax.hist(low_all[col].dropna(), bins=30, alpha=0.6, color='blue', label='low_all', edgecolor='black')\n",
+    "    ax.hist(high_all[col].dropna(), bins=30, alpha=0.6, color='red', label='high_all', edgecolor='black')\n",
+    "    \n",
+    "    # Set title and labels\n",
+    "    ax.set_title(col, fontsize=10, fontweight='bold')\n",
+    "    ax.set_xlabel('Value', fontsize=8)\n",
+    "    ax.set_ylabel('Frequency', fontsize=8)\n",
+    "    ax.legend(fontsize=8)\n",
+    "    ax.grid(True, alpha=0.3)\n",
+    "\n",
+    "# Hide any unused subplots\n",
+    "for idx in range(len(au_columns), len(axes)):\n",
+    "    axes[idx].set_visible(False)\n",
+    "\n",
+    "# Adjust layout\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}