{"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":53666,"databundleVersionId":6589269,"sourceType":"competition"}],"dockerImageVersionId":30587,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport torch\n","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:51:05.108413Z","iopub.execute_input":"2023-11-20T12:51:05.108838Z","iopub.status.idle":"2023-11-20T12:51:09.034081Z","shell.execute_reply.started":"2023-11-20T12:51:05.108802Z","shell.execute_reply":"2023-11-20T12:51:09.032522Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"raw","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)\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"}},{"cell_type":"code","source":"train_event=pd.read_csv('/kaggle/input/child-mind-institute-detect-sleep-states/train_events.csv')\ntrain_series=pd.read_parquet('/kaggle/input/child-mind-institute-detect-sleep-states/train_series.parquet')","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:51:09.036079Z","iopub.execute_input":"2023-11-20T12:51:09.036581Z","iopub.status.idle":"2023-11-20T12:52:06.669908Z","shell.execute_reply.started":"2023-11-20T12:51:09.036552Z","shell.execute_reply":"2023-11-20T12:52:06.668445Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_event=train_event.dropna()\ntrain_event.head()","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:52:06.672033Z","iopub.execute_input":"2023-11-20T12:52:06.672863Z","iopub.status.idle":"2023-11-20T12:52:06.713546Z","shell.execute_reply.started":"2023-11-20T12:52:06.672767Z","shell.execute_reply":"2023-11-20T12:52:06.712469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_event['timestamp']=pd.to_datetime(train_event['timestamp'],utc=True)\ntrain_event['timestamp'].head()","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:52:06.715294Z","iopub.execute_input":"2023-11-20T12:52:06.716074Z","iopub.status.idle":"2023-11-20T12:52:06.782074Z","shell.execute_reply.started":"2023-11-20T12:52:06.716038Z","shell.execute_reply":"2023-11-20T12:52:06.780048Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_series.isnull().any().any()","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:52:06.786469Z","iopub.execute_input":"2023-11-20T12:52:06.786879Z","iopub.status.idle":"2023-11-20T12:52:14.378395Z","shell.execute_reply.started":"2023-11-20T12:52:06.786846Z","shell.execute_reply":"2023-11-20T12:52:14.377263Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"trainseries没有缺失数据","metadata":{}},{"cell_type":"code","source":"temp=train_event[:50]\n\ntemp.loc[(temp['series_id'] == '038441c925bb') & (temp['step'] >= 2), 'new_column'] = 10\ntemp","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:52:14.379750Z","iopub.execute_input":"2023-11-20T12:52:14.380208Z","iopub.status.idle":"2023-11-20T12:52:14.410423Z","shell.execute_reply.started":"2023-11-20T12:52:14.380170Z","shell.execute_reply":"2023-11-20T12:52:14.408900Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\n# create a series_id to index dictionary\nunique_ids=train_event['series_id'].unique()\nseries_id_to_idx={series_ids:idx for idx, series_ids in enumerate(unique_ids)}\n","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:52:14.412222Z","iopub.execute_input":"2023-11-20T12:52:14.413103Z","iopub.status.idle":"2023-11-20T12:52:14.420048Z","shell.execute_reply.started":"2023-11-20T12:52:14.413065Z","shell.execute_reply":"2023-11-20T12:52:14.418953Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ntrain_series['state']=None\n","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:52:14.421558Z","iopub.execute_input":"2023-11-20T12:52:14.421840Z","iopub.status.idle":"2023-11-20T12:52:15.318860Z","shell.execute_reply.started":"2023-11-20T12:52:14.421818Z","shell.execute_reply":"2023-11-20T12:52:15.316764Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#(onset，wakeup) =0, wakeup (前后半个小时) = 1, (wakeup, onset) =2, onset （前后半个小时） = 3. \nfrom tqdm import tqdm\nimport time\ni=0\nfor uid in tqdm(unique_ids,desc=\"Processing\", unit=\"item\"):\n    events=train_event[train_event['series_id']==uid]\n    for event in events.itertuples():\n        if event.event=='onset':\n            train_series.loc[(train_series['series_id']==uid) & ((event.step-360)<=train_series['step']) & (train_series['step']<=(event.step+360))]['state']=3\n            # 对onset前面的所有state为nan的，赋值为2\n            train_series.loc[(train_series['series_id']==uid) & (train_series['step']<(event.step-360)) & (train_series['state'].isnull())]['state']=2\n        elif event.event=='wakeup':\n            train_series.loc[(train_series['series_id']==uid) & ((event.step-360)<=train_series['step']) & (train_series['step']<=(event.step+360))]['state']=1\n            train_series.loc[(train_series['series_id']==uid) & (train_series['step']<(event.step-360)) & (train_series['state'].isnull())]['state']=0\n    i=i+1\n    print(i)\n        \n    ","metadata":{"execution":{"iopub.status.busy":"2023-11-20T12:52:15.321030Z","iopub.execute_input":"2023-11-20T12:52:15.321635Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}