Split
" + ] + }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 17, + "id": "24675f41-d48f-4e27-a3d8-e303556ee7d1", + "metadata": {}, + "outputs": [], + "source": [ + "df['goal'] = df['goal'].replace({0: 0, 1: 1, 2: 1, 3: 1, 4: 1})" + ] + }, + { + "cell_type": "code", + "execution_count": 23, "id": "d7bf2c46-7885-4dfe-a4e7-8b8439cf0434", "metadata": {}, "outputs": [], "source": [ "# save 'cleaned' dataset as csv file for further processing\n", + "import os\n", + "os.makedirs('data', exist_ok=True)\n", "df.to_csv('./data/dataset_cleaned.csv', index=False)" ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "ce134731-e15e-4a2a-aa4e-a28de45fd3af", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -261,7 +290,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.7" + "version": "3.11.5" } }, "nbformat": 4, diff --git a/Experiments.ipynb b/Experiments.ipynb index 9cff778..c6ae8cd 100644 --- a/Experiments.ipynb +++ b/Experiments.ipynb @@ -609,6 +609,188 @@ "avg_accuracy = sum(accuracies) / len(accuracies)\n", "print(f'Avg accuracy {avg_accuracy:.3%}')" ] + }, + { + "cell_type": "markdown", + "id": "15b73e96-8b24-4087-b491-f9248577a886", + "metadata": {}, + "source": [ + "### Clustering and PCA\n", + "Um zu analysieren, ob ähnliche Merkmale auch zur gleichen Diagnose führen, wird zuerst ein k-Means Clustering angewandt." + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "id": "79631688-07cb-450d-9958-8d8341722d7d", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "KMeans(n_clusters=2, n_init='auto', random_state=42)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
KMeans(n_clusters=2, n_init='auto', random_state=42)