{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":66052,"databundleVersionId":7275866,"sourceType":"competition"}],"dockerImageVersionId":30615,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport random\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-13T20:22:29.315174Z","iopub.execute_input":"2023-12-13T20:22:29.315531Z","iopub.status.idle":"2023-12-13T20:22:29.761217Z","shell.execute_reply.started":"2023-12-13T20:22:29.315500Z","shell.execute_reply":"2023-12-13T20:22:29.760424Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Read the Data","metadata":{}},{"cell_type":"code","source":"raw_train_data = pd.read_csv('/kaggle/input/ai-serving-grid-stability/train.csv', index_col='id', parse_dates=['Datum_Uhrzeit_CET'])\nraw_test_data = pd.read_csv('/kaggle/input/ai-serving-grid-stability/test.csv', index_col='id', parse_dates=['Datum_Uhrzeit_CET'])","metadata":{"execution":{"iopub.status.busy":"2023-12-13T20:22:29.762809Z","iopub.execute_input":"2023-12-13T20:22:29.763404Z","iopub.status.idle":"2023-12-13T20:23:06.121476Z","shell.execute_reply.started":"2023-12-13T20:22:29.763372Z","shell.execute_reply":"2023-12-13T20:23:06.120625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Explore the Data","metadata":{}},{"cell_type":"code","source":"# The Dataset contains data from two different control areas. Make sure to separate them when handling the data ;-)\ncontrol_area_1 = raw_train_data[raw_train_data['controlArea']==1]\ncontrol_area_2 = raw_train_data[raw_train_data['controlArea']==2]\n\ncontrol_area_1[['correctedDemand', 'aFRRactivation', 'aFRRrequest']][1000:2000].plot()\ncontrol_area_2[['correctedDemand', 'aFRRactivation', 'aFRRrequest']][1000:2000].plot()","metadata":{"execution":{"iopub.status.busy":"2023-12-13T20:23:06.122689Z","iopub.execute_input":"2023-12-13T20:23:06.123064Z","iopub.status.idle":"2023-12-13T20:23:07.504437Z","shell.execute_reply.started":"2023-12-13T20:23:06.123031Z","shell.execute_reply":"2023-12-13T20:23:07.503296Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# The test dataset is split into multiple data segments\nraw_test_data['test_data_segment_id'].unique()","metadata":{"execution":{"iopub.status.busy":"2023-12-13T20:23:07.507316Z","iopub.execute_input":"2023-12-13T20:23:07.507664Z","iopub.status.idle":"2023-12-13T20:23:07.517051Z","shell.execute_reply.started":"2023-12-13T20:23:07.507631Z","shell.execute_reply":"2023-12-13T20:23:07.515879Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# All test data segments have the same length\nraw_test_data.groupby('test_data_segment_id').size()","metadata":{"execution":{"iopub.status.busy":"2023-12-13T20:23:07.518421Z","iopub.execute_input":"2023-12-13T20:23:07.518873Z","iopub.status.idle":"2023-12-13T20:23:07.533792Z","shell.execute_reply.started":"2023-12-13T20:23:07.518832Z","shell.execute_reply":"2023-12-13T20:23:07.532614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Each Data Segment belongs to one of the both control Areas\nraw_test_data.groupby('test_data_segment_id').mean()['controlArea']","metadata":{"execution":{"iopub.status.busy":"2023-12-13T20:23:07.535059Z","iopub.execute_input":"2023-12-13T20:23:07.536222Z","iopub.status.idle":"2023-12-13T20:23:07.556977Z","shell.execute_reply.started":"2023-12-13T20:23:07.536156Z","shell.execute_reply":"2023-12-13T20:23:07.555855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Create a Model to Detect Anomalies","metadata":{}},{"cell_type":"code","source":"class RandomModel():\n    \"\"\"\n    A random model just to showcase the basic handling of data\n    \"\"\"\n    def train(self, train_data):\n        print(\"training the model...\")\n    \n    def predict(self, test_data):\n        # Make random predictions just to showcase how a model could look like\n        return [random.choice([0, 1]) for _ in range(len(test_data))]\n    \nmodel = RandomModel()\nmodel.train(raw_train_data)","metadata":{"execution":{"iopub.status.busy":"2023-12-13T20:24:39.879768Z","iopub.execute_input":"2023-12-13T20:24:39.880263Z","iopub.status.idle":"2023-12-13T20:24:39.888686Z","shell.execute_reply.started":"2023-12-13T20:24:39.880228Z","shell.execute_reply":"2023-12-13T20:24:39.887601Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Detect Anomalies in Test Data Using the Radom Model","metadata":{}},{"cell_type":"code","source":"dataset_ids = raw_test_data['test_data_segment_id'].unique()\n\nsubmission = np.array([])\n\nfor dataset_id in dataset_ids:\n    sample = raw_test_data[raw_test_data['test_data_segment_id'] == dataset_id]\n    classifications = model.predict(sample)\n    submission = np.append(submission, classifications)\n    \nsubmission = pd.DataFrame({'anomaly': submission})\nsubmission.index.name = 'id'","metadata":{"execution":{"iopub.status.busy":"2023-12-13T20:24:40.721249Z","iopub.execute_input":"2023-12-13T20:24:40.721620Z","iopub.status.idle":"2023-12-13T20:24:40.798962Z","shell.execute_reply.started":"2023-12-13T20:24:40.721590Z","shell.execute_reply":"2023-12-13T20:24:40.797878Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submit Using this Notebook","metadata":{}},{"cell_type":"code","source":"# save as submission.csv in order to submit via this kaggle notebook\nsubmission.to_csv('submission.csv')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Happy Hacking\n\n![Alt Text](https://media.giphy.com/media/o0vwzuFwCGAFO/giphy.gif)","metadata":{}}]}