From c80e8808f2bd9fcad88c1ca467401141155a7c16 Mon Sep 17 00:00:00 2001
From: Michael <weigmi87303@th-nuernberg.de>
Date: Fri, 31 Oct 2025 16:37:08 +0100
Subject: [PATCH] restructured repo, fixed git ignore

---
 .gitignore                                    |  6 +-
 EDA.ipynb => EDA/EDA.ipynb                    |  6 +-
 owncloud.ipynb => EDA/owncloud.ipynb          |  2 +-
 .../create_feature_table.py                   |  0
 .../create_parquet_files.py                   |  0
 dataset_creation/open_parquet_test.ipynb      | 99 +++++++++++++++++++
 readme.md                                     |  1 -
 7 files changed, 107 insertions(+), 7 deletions(-)
 rename EDA.ipynb => EDA/EDA.ipynb (98%)
 rename owncloud.ipynb => EDA/owncloud.ipynb (97%)
 rename create_feature_table.py => dataset_creation/create_feature_table.py (100%)
 rename create_parquet_files.py => dataset_creation/create_parquet_files.py (100%)
 create mode 100644 dataset_creation/open_parquet_test.ipynb

diff --git a/.gitignore b/.gitignore
index 0a8e896..28bcfc7 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,4 +1,6 @@
 *
-!.py
-!.ipynb
+!*/
+!*.py
+!*.ipynb
+!*.md
 !.gitignore
diff --git a/EDA.ipynb b/EDA/EDA.ipynb
similarity index 98%
rename from EDA.ipynb
rename to EDA/EDA.ipynb
index f389458..76844a5 100644
--- a/EDA.ipynb
+++ b/EDA/EDA.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "7440a5b3",
    "metadata": {},
    "outputs": [],
@@ -237,7 +237,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "base",
    "language": "python",
    "name": "python3"
   },
@@ -251,7 +251,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.10"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,
diff --git a/owncloud.ipynb b/EDA/owncloud.ipynb
similarity index 97%
rename from owncloud.ipynb
rename to EDA/owncloud.ipynb
index 569ad16..8f6772a 100644
--- a/owncloud.ipynb
+++ b/EDA/owncloud.ipynb
@@ -59,7 +59,7 @@
    "outputs": [],
    "source": [
     "start = time.time()\n",
-    "df_4_col =  pd.read_hdf(\"tmp.h5\", \"SIGNALS\", mode=\"r\", columns=[\"STUDY\",\"LEVEL\", \"PHASE\", 'RAW_ECG_I'])\n",
+    "df_4_col =  pd.read_hdf(\"tmp.h5\", \"SIGNALS\", mode=\"r\", columns=[\"STUDY\",\"LEVEL\", \"PHASE\", ''])\n",
     "end = time.time()\n",
     "print(end - start)"
    ]
diff --git a/create_feature_table.py b/dataset_creation/create_feature_table.py
similarity index 100%
rename from create_feature_table.py
rename to dataset_creation/create_feature_table.py
diff --git a/create_parquet_files.py b/dataset_creation/create_parquet_files.py
similarity index 100%
rename from create_parquet_files.py
rename to dataset_creation/create_parquet_files.py
diff --git a/dataset_creation/open_parquet_test.ipynb b/dataset_creation/open_parquet_test.ipynb
new file mode 100644
index 0000000..2159704
--- /dev/null
+++ b/dataset_creation/open_parquet_test.ipynb
@@ -0,0 +1,99 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2b3fface",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74f1f5ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df= pd.read_parquet(\"cleaned_0000.parquet\")\n",
+    "print(df.shape)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "05775454",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "99e17328",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.tail()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0238d802",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "step2 = pd.read_parquet(\"output_windowed.parquet\")\n",
+    "step2.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1257c535",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "step2.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3754c664",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Zeigt alle Kombinationen mit Häufigkeit\n",
+    "step2[['STUDY', 'LEVEL', 'PHASE']].value_counts()"
+   ]
+  }
+ ],
+ "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
+}
diff --git a/readme.md b/readme.md
index d9dd48d..ac07ee7 100644
--- a/readme.md
+++ b/readme.md
@@ -2,4 +2,3 @@
 
 This repository contains the code for EDA, modell training and evaluation.
 To be continued.
-To be continued.
\ No newline at end of file