From babb31648c0b90541e27a4a8243be60d382cd466 Mon Sep 17 00:00:00 2001 From: klara Date: Sat, 8 Jun 2024 18:06:08 +0200 Subject: [PATCH] Annpassung --- notebooks/statistics.ipynb | 56 ++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 33 deletions(-) diff --git a/notebooks/statistics.ipynb b/notebooks/statistics.ipynb index aea6e93..80c6436 100644 --- a/notebooks/statistics.ipynb +++ b/notebooks/statistics.ipynb @@ -11,7 +11,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -29,27 +29,31 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Reading GSVT\n", - "Reading AFIB\n", - "Reading SR\n", - "Reading SB\n", - "Number of patients per category:\n", - "GSVT: 0\n", - "AFIB: 27\n", - "SR: 13\n", - "SB: 50\n" + "Reading GSVT\n" + ] + }, + { + "ename": "FileNotFoundError", + "evalue": "[Errno 2] No such file or directory: 'C:/Studium/dsa/data/GSVT.pkl'", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mFileNotFoundError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[3], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mdata_helper\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43monly_demographic\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[0;32m 3\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNumber of patients per category:\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m cat_name \u001b[38;5;129;01min\u001b[39;00m data\u001b[38;5;241m.\u001b[39mkeys():\n", + "File \u001b[1;32mc:\\Users\\klara\\projects\\DSA\\DSA_SS24\\notebooks\\../scripts\\data_helper.py:37\u001b[0m, in \u001b[0;36mload_data\u001b[1;34m(only_demographic, path_settings)\u001b[0m\n\u001b[0;32m 35\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m cat_name \u001b[38;5;129;01min\u001b[39;00m labels\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[0;32m 36\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mReading \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mcat_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m---> 37\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mpath_data\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m/\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mcat_name\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m.pkl\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mrb\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[0;32m 38\u001b[0m records \u001b[38;5;241m=\u001b[39m pickle\u001b[38;5;241m.\u001b[39mload(f)\n\u001b[0;32m 39\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m only_demographic:\n", + "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'C:/Studium/dsa/data/GSVT.pkl'" ] } ], "source": [ - "data = data_helper.load_data(only_demographic=False)\n", + "data = data_helper.load_data(only_demographic=True)\n", "\n", "print(\"Number of patients per category:\")\n", "for cat_name in data.keys():\n", @@ -58,37 +62,23 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 1, "metadata": {}, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "Reading GSVT\n", - "Reading AFIB\n", - "Reading SR\n", - "Reading SB\n" - ] - }, - { - "ename": "ValueError", - "evalue": "All arrays must be of the same length", + "ename": "NameError", + "evalue": "name 'data_helper' is not defined", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", - "Cell \u001b[1;32mIn[27], line 3\u001b[0m\n\u001b[0;32m 1\u001b[0m data_org \u001b[38;5;241m=\u001b[39m data_helper\u001b[38;5;241m.\u001b[39mload_data(only_demographic\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[1;32m----> 3\u001b[0m df_dgc \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mDataFrame\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata_org\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\pandas\\core\\frame.py:767\u001b[0m, in \u001b[0;36mDataFrame.__init__\u001b[1;34m(self, data, index, columns, dtype, copy)\u001b[0m\n\u001b[0;32m 761\u001b[0m mgr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_init_mgr(\n\u001b[0;32m 762\u001b[0m data, axes\u001b[38;5;241m=\u001b[39m{\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mindex\u001b[39m\u001b[38;5;124m\"\u001b[39m: index, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolumns\u001b[39m\u001b[38;5;124m\"\u001b[39m: columns}, dtype\u001b[38;5;241m=\u001b[39mdtype, copy\u001b[38;5;241m=\u001b[39mcopy\n\u001b[0;32m 763\u001b[0m )\n\u001b[0;32m 765\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(data, \u001b[38;5;28mdict\u001b[39m):\n\u001b[0;32m 766\u001b[0m \u001b[38;5;66;03m# GH#38939 de facto copy defaults to False only in non-dict cases\u001b[39;00m\n\u001b[1;32m--> 767\u001b[0m mgr \u001b[38;5;241m=\u001b[39m \u001b[43mdict_to_mgr\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtyp\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmanager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 768\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(data, ma\u001b[38;5;241m.\u001b[39mMaskedArray):\n\u001b[0;32m 769\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mnumpy\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mma\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m mrecords\n", - "File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\pandas\\core\\internals\\construction.py:503\u001b[0m, in \u001b[0;36mdict_to_mgr\u001b[1;34m(data, index, columns, dtype, typ, copy)\u001b[0m\n\u001b[0;32m 499\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 500\u001b[0m \u001b[38;5;66;03m# dtype check to exclude e.g. range objects, scalars\u001b[39;00m\n\u001b[0;32m 501\u001b[0m arrays \u001b[38;5;241m=\u001b[39m [x\u001b[38;5;241m.\u001b[39mcopy() \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(x, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdtype\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m x \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m arrays]\n\u001b[1;32m--> 503\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43marrays_to_mgr\u001b[49m\u001b[43m(\u001b[49m\u001b[43marrays\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtyp\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtyp\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mconsolidate\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\pandas\\core\\internals\\construction.py:114\u001b[0m, in \u001b[0;36marrays_to_mgr\u001b[1;34m(arrays, columns, index, dtype, verify_integrity, typ, consolidate)\u001b[0m\n\u001b[0;32m 111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m verify_integrity:\n\u001b[0;32m 112\u001b[0m \u001b[38;5;66;03m# figure out the index, if necessary\u001b[39;00m\n\u001b[0;32m 113\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m index \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m--> 114\u001b[0m index \u001b[38;5;241m=\u001b[39m \u001b[43m_extract_index\u001b[49m\u001b[43m(\u001b[49m\u001b[43marrays\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 115\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 116\u001b[0m index \u001b[38;5;241m=\u001b[39m ensure_index(index)\n", - "File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\pandas\\core\\internals\\construction.py:677\u001b[0m, in \u001b[0;36m_extract_index\u001b[1;34m(data)\u001b[0m\n\u001b[0;32m 675\u001b[0m lengths \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(\u001b[38;5;28mset\u001b[39m(raw_lengths))\n\u001b[0;32m 676\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(lengths) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m--> 677\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAll arrays must be of the same length\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 679\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m have_dicts:\n\u001b[0;32m 680\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 681\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mMixing dicts with non-Series may lead to ambiguous ordering.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 682\u001b[0m )\n", - "\u001b[1;31mValueError\u001b[0m: All arrays must be of the same length" + "\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[1;32mIn[1], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m data_org \u001b[38;5;241m=\u001b[39m \u001b[43mdata_helper\u001b[49m\u001b[38;5;241m.\u001b[39mload_data(only_demographic\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 3\u001b[0m df_dgc \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame(data_org)\n", + "\u001b[1;31mNameError\u001b[0m: name 'data_helper' is not defined" ] } ], "source": [ - "data_org = data_helper.load_data(only_demographic=False)\n", + "data_org = data_helper.load_data(only_demographic=True)\n", "\n", "df_dgc = pd.DataFrame(data_org)" ]