{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"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)\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":"2022-08-08T19:16:22.935217Z","iopub.execute_input":"2022-08-08T19:16:22.935710Z","iopub.status.idle":"2022-08-08T19:16:22.970553Z","shell.execute_reply.started":"2022-08-08T19:16:22.935607Z","shell.execute_reply":"2022-08-08T19:16:22.969531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### This notebook illustrates how to obtain a reasonably high score with an Explainable Boosting Machine. This algorithm often performs very well straight out of the box. Furthermore, the model is interpretable! For more information, take a look here: https://github.com/interpretml/interpret/. The notebook is purposely short; the aim is to show how 'easy' it is to obtain a decent model when data is in a good shape.","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/bankruptcy-risk-prediction/train.csv')\ndf_test = pd.read_csv('/kaggle/input/bankruptcy-risk-prediction/test.csv')","metadata":{"execution":{"iopub.status.busy":"2022-08-08T19:18:04.997150Z","iopub.execute_input":"2022-08-08T19:18:04.997583Z","iopub.status.idle":"2022-08-08T19:18:05.025277Z","shell.execute_reply.started":"2022-08-08T19:18:04.997546Z","shell.execute_reply":"2022-08-08T19:18:05.024160Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = df.drop(['id', 'bankruptcy'], axis=1)\nX_test = df_test.drop(['id'], axis=1)\ny = df['bankruptcy']","metadata":{"execution":{"iopub.status.busy":"2022-08-08T19:18:58.295496Z","iopub.execute_input":"2022-08-08T19:18:58.295931Z","iopub.status.idle":"2022-08-08T19:18:58.304846Z","shell.execute_reply.started":"2022-08-08T19:18:58.295897Z","shell.execute_reply":"2022-08-08T19:18:58.303653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip3 install interpret\nfrom interpret.glassbox import ExplainableBoostingClassifier\nebm = ExplainableBoostingClassifier()\nebm.fit(X, y)\npreds = ebm.predict_proba(X_test)[:, 1]","metadata":{"execution":{"iopub.status.busy":"2022-08-08T19:23:30.828495Z","iopub.execute_input":"2022-08-08T19:23:30.829056Z","iopub.status.idle":"2022-08-08T19:23:44.037713Z","shell.execute_reply.started":"2022-08-08T19:23:30.829015Z","shell.execute_reply":"2022-08-08T19:23:44.036536Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"final_submission = pd.concat([df_test['id'], pd.Series(preds, name='proba')], axis=1)\nfinal_submission.to_csv('results.csv', index=0)","metadata":{"execution":{"iopub.status.busy":"2022-08-08T19:28:17.996002Z","iopub.execute_input":"2022-08-08T19:28:17.996484Z","iopub.status.idle":"2022-08-08T19:28:18.008090Z","shell.execute_reply.started":"2022-08-08T19:28:17.996447Z","shell.execute_reply":"2022-08-08T19:28:18.006944Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}