minor fixes to new paths / dataset with all columns

EDA/histogramms.ipynb

@@ -1,5 +1,13 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cc08936c",
+   "metadata": {},
+   "source": [
+    "## Insights into the dataset with histogramms and scatter plots"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "1014c5e0",
@@ -17,7 +25,8 @@
    "source": [
     "import pandas as pd\n",
     "import numpy as np\n",
-    "import matplotlib.pyplot as plt"
+    "import matplotlib.pyplot as plt\n",
+    "from pathlib import Path"
    ]
   },
   {
@@ -27,7 +36,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "path =r\"C:\\Users\\micha\\FAUbox\\WS2526_Fahrsimulator_MSY (Celina Korzer)\\AU_dataset\\output_windowed.parquet\"\n",
+    "path  = Path(r\"/home/jovyan/data-paulusjafahrsimulator-gpu/new_datasets/50s_25Hz_dataset.parquet\")\n",
     "df = pd.read_parquet(path=path)"
    ]
   },
@@ -104,21 +113,27 @@
    "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",
+    "face_au_cols = [c for c in low_all.columns if c.startswith(\"FACE_AU\")]\n",
+    "eye_cols =  ['Fix_count_short_66_150', 'Fix_count_medium_300_500',\n",
+    "       'Fix_count_long_gt_1000', 'Fix_count_100', 'Fix_mean_duration',\n",
+    "       'Fix_median_duration', 'Sac_count', 'Sac_mean_amp', 'Sac_mean_dur',\n",
+    "       'Sac_median_dur', 'Blink_count', 'Blink_mean_dur', 'Blink_median_dur',\n",
+    "       'Pupil_mean', 'Pupil_IPA']\n",
+    "\n",
+    "cols = face_au_cols+eye_cols\n",
     "\n",
     "# Calculate number of rows and columns for subplots\n",
-    "n_cols = len(au_columns)\n",
-    "n_rows = 4\n",
+    "n_cols = len(cols)\n",
+    "n_rows = 7\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",
+    "fig.suptitle('Feature 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",
+    "for idx, col in enumerate(cols):\n",
     "    ax = axes[idx]\n",
     "    \n",
     "    # Plot overlapping histograms\n",
@@ -133,18 +148,48 @@
     "    ax.grid(True, alpha=0.3)\n",
     "\n",
     "# Hide any unused subplots\n",
-    "for idx in range(len(au_columns), len(axes)):\n",
+    "for idx in range(len(cols), len(axes)):\n",
     "    axes[idx].set_visible(False)\n",
     "\n",
     "# Adjust layout\n",
     "plt.tight_layout()\n",
     "plt.show()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6cd53cdb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create figure with subplots\n",
+    "fig, axes = plt.subplots(n_rows, n_cols_subplot, figsize=(20, 16))\n",
+    "axes = axes.flatten()\n",
+    "fig.suptitle('Feature Scatter: Low vs High', fontsize=20, fontweight='bold', y=0.995)\n",
+    "\n",
+    "for idx, col in enumerate(cols):\n",
+    "    ax = axes[idx]\n",
+    "\n",
+    "    # Scatterplots\n",
+    "    ax.scatter(range(len(low_all[col])), low_all[col], alpha=0.6, color='blue', label='low_all', s=10)\n",
+    "    ax.scatter(range(len(high_all[col])), high_all[col], alpha=0.6, color='red', label='high_all', s=10)\n",
+    "\n",
+    "    ax.set_title(col, fontsize=10, fontweight='bold')\n",
+    "    ax.set_xlabel('Sample index', fontsize=8)\n",
+    "    ax.set_ylabel('Value', fontsize=8)\n",
+    "    ax.legend(fontsize=8)\n",
+    "    ax.grid(True, alpha=0.3)\n",
+    "\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "base",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -158,7 +203,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.12.10"
   }
  },
  "nbformat": 4,