diff --git a/src/models/sofia_modelle/KNN.ipynb b/src/models/sofia_modelle/KNN.ipynb
index 14680774dd7154b50494807b2d51ace2ae8f1089..800bbb1b67778fa5feafa4a0706f03d4fa17fbbd 100644
--- a/src/models/sofia_modelle/KNN.ipynb
+++ b/src/models/sofia_modelle/KNN.ipynb
@@ -40,21 +40,9 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 3,
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'filename' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[7], line 7\u001b[0m\n\u001b[1;32m 5\u001b[0m score \u001b[38;5;241m=\u001b[39m clf\u001b[38;5;241m.\u001b[39mdecision_scores_\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m score\u001b[38;5;241m.\u001b[39mravel()\n\u001b[0;32m----> 7\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[43mfilename\u001b[49m)\n",
- "\u001b[0;31mNameError\u001b[0m: name 'filename' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"def run_Sub_KNN(data, n_neighbors=10, method='largest', periodicity=1, n_jobs=1):\n",
" slidingWindow = find_length_rank(data, rank=periodicity)\n",
@@ -66,21 +54,9 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 4,
"metadata": {},
- "outputs": [
- {
- "ename": "NameError",
- "evalue": "name 'filename' is not defined",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[6], line 7\u001b[0m\n\u001b[1;32m 5\u001b[0m score \u001b[38;5;241m=\u001b[39m clf\u001b[38;5;241m.\u001b[39mdecision_scores_\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m score\u001b[38;5;241m.\u001b[39mravel()\n\u001b[0;32m----> 7\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[43mfilename\u001b[49m)\n",
- "\u001b[0;31mNameError\u001b[0m: name 'filename' is not defined"
- ]
- }
- ],
+ "outputs": [],
"source": [
"# util wrapper def\n",
"def run_KNN(data, slidingWindow=100, n_neighbors=10, method='largest', n_jobs=1): #,leaf_size = 30\n",
@@ -92,7 +68,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
@@ -103,32 +79,161 @@
]
},
{
- "ename": "UnicodeDecodeError",
- "evalue": "'utf-8' codec can't decode byte 0xaa in position 1077: invalid start byte",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mUnicodeDecodeError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[0;32mIn[5], line 5\u001b[0m\n\u001b[1;32m 2\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSub_KNN\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m 3\u001b[0m output_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m../../../docs/evaluation/\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m----> 5\u001b[0m \u001b[43mmain\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrun_Sub_KNN\u001b[49m\u001b[43m,\u001b[49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43mdata_folders\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43m../../../data/\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43munsupervised\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43moutput_dir\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43moutput_path\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m~/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/run_model_wrapper.py:253\u001b[0m, in \u001b[0;36mmain\u001b[0;34m(run_model, hyperparams, model_name, data_folders, model_type, output_dir)\u001b[0m\n\u001b[1;32m 251\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mStart Processing files\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 252\u001b[0m \u001b[38;5;66;03m#reutrns [{file_name:str,train_data:list,data:list, label:list, sliding_window:int}]\u001b[39;00m\n\u001b[0;32m--> 253\u001b[0m file_data_dict_list \u001b[38;5;241m=\u001b[39m \u001b[43mpreprocess_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath_data_all\u001b[49m\u001b[43m)\u001b[49m \n\u001b[1;32m 255\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mStart Hyperparameter Tuning\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 256\u001b[0m \u001b[38;5;66;03m#find hyperparametrs for each file:\u001b[39;00m\n",
- "File \u001b[0;32m~/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/run_model_wrapper.py:160\u001b[0m, in \u001b[0;36mpreprocess_data\u001b[0;34m(data_path)\u001b[0m\n\u001b[1;32m 158\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m filename \u001b[38;5;129;01min\u001b[39;00m os\u001b[38;5;241m.\u001b[39mlistdir(data_path):\n\u001b[1;32m 159\u001b[0m file_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(data_path, filename)\n\u001b[0;32m--> 160\u001b[0m df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_csv\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile_path\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mdropna()\n\u001b[1;32m 161\u001b[0m data \u001b[38;5;241m=\u001b[39m df\u001b[38;5;241m.\u001b[39miloc[:, \u001b[38;5;241m0\u001b[39m:\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\u001b[38;5;241m.\u001b[39mvalues\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mfloat\u001b[39m)\n\u001b[1;32m 162\u001b[0m label \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mLabel\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mint\u001b[39m)\u001b[38;5;241m.\u001b[39mto_numpy()\n",
- "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1026\u001b[0m, in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m 1013\u001b[0m kwds_defaults \u001b[38;5;241m=\u001b[39m _refine_defaults_read(\n\u001b[1;32m 1014\u001b[0m dialect,\n\u001b[1;32m 1015\u001b[0m delimiter,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1022\u001b[0m dtype_backend\u001b[38;5;241m=\u001b[39mdtype_backend,\n\u001b[1;32m 1023\u001b[0m )\n\u001b[1;32m 1024\u001b[0m kwds\u001b[38;5;241m.\u001b[39mupdate(kwds_defaults)\n\u001b[0;32m-> 1026\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_read\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:620\u001b[0m, in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 617\u001b[0m _validate_names(kwds\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnames\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m))\n\u001b[1;32m 619\u001b[0m \u001b[38;5;66;03m# Create the parser.\u001b[39;00m\n\u001b[0;32m--> 620\u001b[0m parser \u001b[38;5;241m=\u001b[39m \u001b[43mTextFileReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath_or_buffer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 622\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m chunksize \u001b[38;5;129;01mor\u001b[39;00m iterator:\n\u001b[1;32m 623\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m parser\n",
- "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1620\u001b[0m, in \u001b[0;36mTextFileReader.__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m 1617\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moptions[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhas_index_names\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n\u001b[1;32m 1619\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles: IOHandles \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1620\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_make_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n",
- "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/readers.py:1898\u001b[0m, in \u001b[0;36mTextFileReader._make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m 1895\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(msg)\n\u001b[1;32m 1897\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1898\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mmapping\u001b[49m\u001b[43m[\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m]\u001b[49m\u001b[43m(\u001b[49m\u001b[43mf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1899\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[1;32m 1900\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandles \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
- "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pandas/io/parsers/c_parser_wrapper.py:93\u001b[0m, in \u001b[0;36mCParserWrapper.__init__\u001b[0;34m(self, src, **kwds)\u001b[0m\n\u001b[1;32m 90\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwds[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdtype_backend\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 91\u001b[0m \u001b[38;5;66;03m# Fail here loudly instead of in cython after reading\u001b[39;00m\n\u001b[1;32m 92\u001b[0m import_optional_dependency(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 93\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reader \u001b[38;5;241m=\u001b[39m \u001b[43mparsers\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTextReader\u001b[49m\u001b[43m(\u001b[49m\u001b[43msrc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 95\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39munnamed_cols \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_reader\u001b[38;5;241m.\u001b[39munnamed_cols\n\u001b[1;32m 97\u001b[0m \u001b[38;5;66;03m# error: Cannot determine type of 'names'\u001b[39;00m\n",
- "File \u001b[0;32mparsers.pyx:574\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader.__cinit__\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32mparsers.pyx:663\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader._get_header\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32mparsers.pyx:874\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader._tokenize_rows\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32mparsers.pyx:891\u001b[0m, in \u001b[0;36mpandas._libs.parsers.TextReader._check_tokenize_status\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32mparsers.pyx:2053\u001b[0m, in \u001b[0;36mpandas._libs.parsers.raise_parser_error\u001b[0;34m()\u001b[0m\n",
- "File \u001b[0;32m<frozen codecs>:322\u001b[0m, in \u001b[0;36mdecode\u001b[0;34m(self, input, final)\u001b[0m\n",
- "\u001b[0;31mUnicodeDecodeError\u001b[0m: 'utf-8' codec can't decode byte 0xaa in position 1077: invalid start byte"
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Start Hyperparameter Tuning\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/threadpoolctl.py:1214: RuntimeWarning: \n",
+ "Found Intel OpenMP ('libiomp') and LLVM OpenMP ('libomp') loaded at\n",
+ "the same time. Both libraries are known to be incompatible and this\n",
+ "can cause random crashes or deadlocks on Linux when loaded in the\n",
+ "same Python program.\n",
+ "Using threadpoolctl may cause crashes or deadlocks. For more\n",
+ "information and possible workarounds, please see\n",
+ " https://github.com/joblib/threadpoolctl/blob/master/multiple_openmp.md\n",
+ "\n",
+ " warnings.warn(msg, RuntimeWarning)\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "File: 806_YAHOO_id_256_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 40, 'method': 'largest'}\n",
+ "File: 811_Exathlon_id_2_Facility_tr_10766_1st_12590.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 780_YAHOO_id_230_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 30, 'method': 'largest'}\n",
+ "File: 734_YAHOO_id_184_WebService_tr_500_1st_768.csv, best hyperparameter: {'n_neighbors': 50, 'method': 'largest'}\n",
+ "File: 555_YAHOO_id_5_WebService_tr_500_1st_730.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 814_Exathlon_id_5_Facility_tr_10766_1st_12590.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 658_YAHOO_id_108_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'largest'}\n",
+ "File: 723_YAHOO_id_173_WebService_tr_500_1st_1214.csv, best hyperparameter: {'n_neighbors': 50, 'method': 'largest'}\n",
+ "File: 818_Exathlon_id_9_Facility_tr_11665_1st_13484.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 549_SMAP_id_19_Sensor_tr_1998_1st_2098.csv, best hyperparameter: {'n_neighbors': 40, 'method': 'largest'}\n",
+ "File: 603_YAHOO_id_53_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 570_YAHOO_id_20_Synthetic_tr_500_1st_658.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'median'}\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "File: 813_Exathlon_id_4_Facility_tr_10766_1st_12590.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 810_Exathlon_id_1_Facility_tr_10766_1st_12590.csv, best hyperparameter: {'n_neighbors': 50, 'method': 'largest'}\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n",
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "File: 817_Exathlon_id_8_Facility_tr_10766_1st_12590.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 724_YAHOO_id_174_WebService_tr_500_1st_1030.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'largest'}\n",
+ "File: 701_YAHOO_id_151_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'median'}\n",
+ "File: 815_Exathlon_id_6_Facility_tr_10766_1st_12590.csv, best hyperparameter: {'n_neighbors': 30, 'method': 'mean'}\n",
+ "File: 672_YAHOO_id_122_WebService_tr_500_1st_857.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'largest'}\n",
+ "File: 680_YAHOO_id_130_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 821_Exathlon_id_12_Facility_tr_6985_1st_7085.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 649_YAHOO_id_99_WebService_tr_500_1st_1386.csv, best hyperparameter: {'n_neighbors': 30, 'method': 'median'}\n",
+ "File: 819_Exathlon_id_10_Facility_tr_10766_1st_12590.csv, best hyperparameter: {'n_neighbors': 50, 'method': 'largest'}\n",
+ "File: 568_YAHOO_id_18_WebService_tr_500_1st_333.csv, best hyperparameter: {'n_neighbors': 50, 'method': 'median'}\n",
+ "File: 762_YAHOO_id_212_WebService_tr_500_1st_1055.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 657_YAHOO_id_107_WebService_tr_500_1st_1260.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 552_YAHOO_id_2_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'largest'}\n",
+ "File: 755_YAHOO_id_205_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 558_YAHOO_id_8_WebService_tr_500_1st_1125.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'median'}\n",
+ "File: 788_YAHOO_id_238_WebService_tr_500_1st_973.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'largest'}\n",
+ "File: 643_YAHOO_id_93_WebService_tr_500_1st_1038.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'mean'}\n",
+ "File: 551_YAHOO_id_1_Synthetic_tr_500_1st_893.csv, best hyperparameter: {'n_neighbors': 10, 'method': 'median'}\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/sofiawuckert/Desktop/master_bioinformatik/übungen/2_Semester/data_mining_maschinelles_lernen/data-mining/src/utils/utility.py:30: RuntimeWarning: invalid value encountered in divide\n",
+ " res = ((a - np.expand_dims(mns, axis=axis)) /\n"
]
}
],
"source": [
- "# main run model wrapper\n",
+ "# find . -name \"*.DS_Store\" -type f -delete\n",
"model = 'Sub_KNN'\n",
"output_path = '../../../docs/evaluation/'\n",
"\n",