diff --git a/src/models/sofia_modelle/CNN.ipynb b/src/models/sofia_modelle/CNN.ipynb
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..b8fb945c12585107e0f43da88774f97c487a0c4f 100644
--- a/src/models/sofia_modelle/CNN.ipynb
+++ b/src/models/sofia_modelle/CNN.ipynb
@@ -0,0 +1,125 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# importe\n",
+ "from CNN import CNN\n",
+ "import sys\n",
+ "import pathlib\n",
+ "sys.path.append(str(pathlib.Path.absolute)+ '../../')\n",
+ "from src.utils.slidingWindows import find_length_rank\n",
+ "from src.run_model_wrapper import main"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "params = {\n",
+ " 'window_size': [50, 100, 150],\n",
+ " 'num_channel': [[32, 32, 40], [16, 32, 64]]\n",
+ " }"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def run_CNN(data_train, data_test, window_size=100, num_channel=[32, 32, 40], lr=0.0008, n_jobs=1):\n",
+ " clf = CNN(window_size=window_size, num_channel=num_channel, feats=data_test.shape[1], lr=lr, batch_size=128)\n",
+ " clf.fit(data_train)\n",
+ " score = clf.decision_function(data_test)\n",
+ " return score.ravel()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model = 'CNN'\n",
+ "output_path = '../../../docs/evaluation/'\n",
+ "\n",
+ "main(run_CNN,params,model,data_folders = '../../../data/', model_type='semi-supervised',output_dir = output_path)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os\n",
+ "data_empty = {\n",
+ " 'params':[],\n",
+ " 'file_name': [],\n",
+ " 'duration': [],\n",
+ " 'group': [],\n",
+ " 'point anomaly': [],\n",
+ " 'seq anomaly': [],\n",
+ " 'AUC-PR': [],\n",
+ " 'AUC-ROC': [],\n",
+ " 'VUS-PR': [],\n",
+ " 'VUS-ROC': [],\n",
+ " 'Standard-F1': [],\n",
+ " 'PA-F1': [],\n",
+ " 'Event-based-F1': [],\n",
+ " 'R-based-F1': [],\n",
+ " 'Affiliation-F': [],\n",
+ " 'Recall': [],\n",
+ " 'Precision': []\n",
+ "}\n",
+ "\n",
+ "df = pd.DataFrame(data_empty)\n",
+ "\n",
+ "path = '../../../docs/evaluation/'\n",
+ "model = 'CNN'\n",
+ "#concant all batch-files to big one\n",
+ "for file in os.listdir(path):\n",
+ " file_path = os.path.join(path,file_path)\n",
+ " #check if current file belongs to selected model and avoid overwriting existing model.csv data\n",
+ " if file.startswith(model) and file.split('.')[0] != model:\n",
+ " df_batch = pd.read_csv(file_path)\n",
+ " #join with dataframe with all data\n",
+ " df = pd.concat(df,df_batch)\n",
+ "\n",
+ "df.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.to_csv(output_path+model+'.csv')"
+ ]
+ }
+ ],
+ "metadata": {
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/src/models/sofia_modelle/IForest.ipynb b/src/models/sofia_modelle/IForest.ipynb
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..2de109e887e28e0194f819a1378524822aa109ab 100644
--- a/src/models/sofia_modelle/IForest.ipynb
+++ b/src/models/sofia_modelle/IForest.ipynb
@@ -0,0 +1,124 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# importe\n",
+ "from IForest import IForest\n",
+ "import sys\n",
+ "import pathlib\n",
+ "sys.path.append(str(pathlib.Path.absolute)+ '../../')\n",
+ "from src.utils.slidingWindows import find_length_rank\n",
+ "from src.run_model_wrapper import main"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "params = {\n",
+ " 'n_estimators': [25, 50, 100, 150, 200]\n",
+ " }"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def run_IForest(data, slidingWindow=100, n_estimators=100, max_features=1, n_jobs=1):\n",
+ " clf = IForest(slidingWindow=slidingWindow, n_estimators=n_estimators, max_features=max_features, n_jobs=n_jobs)\n",
+ " clf.fit(data)\n",
+ " score = clf.decision_scores_\n",
+ " return score.ravel()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model = 'IForest'\n",
+ "output_path = '../../../docs/evaluation/'\n",
+ "\n",
+ "main(run_IForest,params,model,data_folders = '../../../data/', model_type='unsupervised',output_dir = output_path)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os\n",
+ "data_empty = {\n",
+ " 'params':[],\n",
+ " 'file_name': [],\n",
+ " 'duration': [],\n",
+ " 'group': [],\n",
+ " 'point anomaly': [],\n",
+ " 'seq anomaly': [],\n",
+ " 'AUC-PR': [],\n",
+ " 'AUC-ROC': [],\n",
+ " 'VUS-PR': [],\n",
+ " 'VUS-ROC': [],\n",
+ " 'Standard-F1': [],\n",
+ " 'PA-F1': [],\n",
+ " 'Event-based-F1': [],\n",
+ " 'R-based-F1': [],\n",
+ " 'Affiliation-F': [],\n",
+ " 'Recall': [],\n",
+ " 'Precision': []\n",
+ "}\n",
+ "\n",
+ "df = pd.DataFrame(data_empty)\n",
+ "\n",
+ "path = '../../../docs/evaluation/'\n",
+ "model = 'IForest'\n",
+ "#concant all batch-files to big one\n",
+ "for file in os.listdir(path):\n",
+ " file_path = os.path.join(path,file_path)\n",
+ " #check if current file belongs to selected model and avoid overwriting existing model.csv data\n",
+ " if file.startswith(model) and file.split('.')[0] != model:\n",
+ " df_batch = pd.read_csv(file_path)\n",
+ " #join with dataframe with all data\n",
+ " df = pd.concat(df,df_batch)\n",
+ "\n",
+ "df.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.to_csv(output_path+model+'.csv')"
+ ]
+ }
+ ],
+ "metadata": {
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/src/models/sofia_modelle/KNN.ipynb b/src/models/sofia_modelle/KNN.ipynb
index 4b34ef00372d9c01eb5a314036145108951bce8d..800bbb1b67778fa5feafa4a0706f03d4fa17fbbd 100644
--- a/src/models/sofia_modelle/KNN.ipynb
+++ b/src/models/sofia_modelle/KNN.ipynb
@@ -2,9 +2,18 @@
"cells": [
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "CUDA available: False\n",
+ "cuDNN version: None\n"
+ ]
+ }
+ ],
"source": [
"# importe\n",
"from KNN import KNN\n",
@@ -17,7 +26,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@@ -31,7 +40,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -45,7 +54,7 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@@ -61,10 +70,174 @@
"cell_type": "code",
"execution_count": null,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Start Processing files\n"
+ ]
+ },
+ {
+ "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",
- "main(run_Sub_KNN,params,'Sub_KNN',data_folders = '../../../data/', model_type='unsupervised',output_dir = '../../../docs/evaluation/')"
+ "# find . -name \"*.DS_Store\" -type f -delete\n",
+ "model = 'Sub_KNN'\n",
+ "output_path = '../../../docs/evaluation/'\n",
+ "\n",
+ "main(run_Sub_KNN,params,model,data_folders = '../../../data/', model_type='unsupervised',output_dir = output_path)"
]
},
{
@@ -74,9 +247,40 @@
"outputs": [],
"source": [
"import pandas as pd\n",
+ "import os\n",
+ "data_empty = {\n",
+ " 'params':[],\n",
+ " 'file_name': [],\n",
+ " 'duration': [],\n",
+ " 'group': [],\n",
+ " 'point anomaly': [],\n",
+ " 'seq anomaly': [],\n",
+ " 'AUC-PR': [],\n",
+ " 'AUC-ROC': [],\n",
+ " 'VUS-PR': [],\n",
+ " 'VUS-ROC': [],\n",
+ " 'Standard-F1': [],\n",
+ " 'PA-F1': [],\n",
+ " 'Event-based-F1': [],\n",
+ " 'R-based-F1': [],\n",
+ " 'Affiliation-F': [],\n",
+ " 'Recall': [],\n",
+ " 'Precision': []\n",
+ "}\n",
+ "\n",
+ "df = pd.DataFrame(data_empty)\n",
+ "\n",
+ "path = '../../../docs/evaluation/'\n",
+ "#concant all batch-files to big one\n",
+ "for file in os.listdir(path):\n",
+ " file_path = os.path.join(path,file_path)\n",
+ " #check if current file belongs to selected model and avoid overwriting existing model.csv data\n",
+ " if file.startswith(model) and file.split('.')[0] != model:\n",
+ " df_batch = pd.read_csv(file_path)\n",
+ " #join with dataframe with all data\n",
+ " df = pd.concat(df,df_batch)\n",
"\n",
- "path = '../../../docs/evaluation/Sub_KNN.csv'\n",
- "df = pd.read_csv(path)"
+ "df.shape"
]
},
{
@@ -87,11 +291,34 @@
"source": [
"df.head()"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df.to_csv(output_path+model+'.csv')"
+ ]
}
],
"metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
"language_info": {
- "name": "python"
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.12.3"
}
},
"nbformat": 4,
diff --git a/src/models/sofia_modelle/call_cnn.py b/src/models/sofia_modelle/call_cnn.py
new file mode 100644
index 0000000000000000000000000000000000000000..99536904dc49a13f97335418a79544839f2e32a1
--- /dev/null
+++ b/src/models/sofia_modelle/call_cnn.py
@@ -0,0 +1,27 @@
+from CNN import CNN
+import sys
+import pathlib
+sys.path.append(str(pathlib.Path.absolute)+ '../../')
+from src.utils.slidingWindows import find_length_rank
+from src.run_model_wrapper import main
+
+#optimal hyperparameters from autors: 'POLY': {'periodicity': 1, 'power': 4}
+params = {
+ 'window_size': [50, 100, 150],
+ 'num_channel': [[32, 32, 40], [16, 32, 64]]
+ }
+
+def run_CNN(data_train, data_test, window_size=100, num_channel=[32, 32, 40], lr=0.0008, n_jobs=1):
+ clf = CNN(window_size=window_size, num_channel=num_channel, feats=data_test.shape[1], lr=lr, batch_size=128)
+ clf.fit(data_train)
+ score = clf.decision_function(data_test)
+ return score.ravel()
+
+model = 'CNN'
+output_path = '../../../docs/evaluation/'
+
+#writes results in .csv
+main(run_CNN,params,model,data_folders = '../../../data/', model_type='semi-supervised',output_dir = output_path)
+
+#pip3 install -r requirements.txt
+# python src/models/desi/call_poly.py
\ No newline at end of file
diff --git a/src/models/sofia_modelle/call_iforest.py b/src/models/sofia_modelle/call_iforest.py
new file mode 100644
index 0000000000000000000000000000000000000000..50631433019223c5b60f3280ca0b6f465777e9b4
--- /dev/null
+++ b/src/models/sofia_modelle/call_iforest.py
@@ -0,0 +1,26 @@
+from IForest import IForest
+import sys
+import pathlib
+sys.path.append(str(pathlib.Path.absolute)+ '../../')
+from src.utils.slidingWindows import find_length_rank
+from src.run_model_wrapper import main
+
+#optimal hyperparameters from autors: 'POLY': {'periodicity': 1, 'power': 4}
+params = {
+ 'n_estimators': [25, 50, 100, 150, 200]
+ }
+
+def run_IForest(data, slidingWindow=100, n_estimators=100, max_features=1, n_jobs=1):
+ clf = IForest(slidingWindow=slidingWindow, n_estimators=n_estimators, max_features=max_features, n_jobs=n_jobs)
+ clf.fit(data)
+ score = clf.decision_scores_
+ return score.ravel()
+
+model = 'IForest'
+output_path = '../../../docs/evaluation/'
+
+#writes results in .csv
+main(run_IForest,params,model,data_folders = '../../../data/', model_type='unsupervised',output_dir = output_path)
+
+#pip3 install -r requirements.txt
+# python src/models/desi/call_poly.py
\ No newline at end of file
diff --git a/src/models/sofia_modelle/call_knn.py b/src/models/sofia_modelle/call_knn.py
new file mode 100644
index 0000000000000000000000000000000000000000..efa40fadcf7cbcecf779bf44b36107bd369549b2
--- /dev/null
+++ b/src/models/sofia_modelle/call_knn.py
@@ -0,0 +1,28 @@
+from KNN import KNN
+import sys
+import pathlib
+sys.path.append(str(pathlib.Path.absolute)+ '../../')
+from src.utils.slidingWindows import find_length_rank
+from src.run_model_wrapper import main
+
+#optimal hyperparameters from autors: 'POLY': {'periodicity': 1, 'power': 4}
+params = {
+ 'n_neighbors': [10, 20, 30, 40, 50],
+ 'method': ['largest', 'mean', 'median']
+ }
+
+def run_Sub_KNN(data, n_neighbors=10, method='largest', periodicity=1, n_jobs=1):
+ slidingWindow = find_length_rank(data, rank=periodicity)
+ clf = KNN(slidingWindow=slidingWindow, n_neighbors=n_neighbors,method=method, n_jobs=n_jobs)
+ clf.fit(data)
+ score = clf.decision_scores_
+ return score.ravel()
+
+model = 'Sub_KNN'
+output_path = '../../../docs/evaluation/'
+
+#writes results in .csv
+main(run_Sub_KNN,params,model,data_folders = '../../../data/', model_type='unsupervised',output_dir = output_path)
+
+#pip3 install -r requirements.txt
+# python src/models/desi/call_poly.py
\ No newline at end of file