{"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":54852,"databundleVersionId":5988920,"sourceType":"competition"},{"sourceId":7093304,"sourceType":"datasetVersion","datasetId":4087879}],"dockerImageVersionId":30587,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"I provide new training and test data that have been preprocessed by a few steps such as encoding nominal variables, mapping variables with many items into few items, filling missing values. Hopefully the data will help some of you to improve model efficiency.","metadata":{}},{"cell_type":"code","source":"import pandas as pd\ntrain_df = pd.read_csv('/kaggle/input/industrial-iot-challenge-fall-2023-prepocess-data/trainiot.csv')\ntest_df = pd.read_csv('/kaggle/input/industrial-iot-challenge-fall-2023-prepocess-data/testiot.csv')\nsubmission = pd.read_csv('/kaggle/input/cuboulder-iot-f23/sample_solution.csv')\ntrain_df.describe().T","metadata":{"execution":{"iopub.status.busy":"2023-12-01T16:46:53.440062Z","iopub.execute_input":"2023-12-01T16:46:53.441356Z","iopub.status.idle":"2023-12-01T16:47:25.374357Z","shell.execute_reply.started":"2023-12-01T16:46:53.441306Z","shell.execute_reply":"2023-12-01T16:47:25.373145Z"},"trusted":true},"execution_count":null,"outputs":[]}]}