{"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":"markdown","source":"### Imports and environment variables","metadata":{}},{"cell_type":"code","source":"import pandas as pd\n\ndatapath=\"../input/birdclef-2022\"","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-03-02T07:54:01.859971Z","iopub.execute_input":"2022-03-02T07:54:01.860227Z","iopub.status.idle":"2022-03-02T07:54:01.864185Z","shell.execute_reply.started":"2022-03-02T07:54:01.860198Z","shell.execute_reply":"2022-03-02T07:54:01.86332Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Prepare testing data","metadata":{}},{"cell_type":"code","source":"submission=pd.read_csv(datapath+'/'+'sample_submission.csv')","metadata":{"execution":{"iopub.status.busy":"2022-03-02T07:54:04.940269Z","iopub.execute_input":"2022-03-02T07:54:04.940548Z","iopub.status.idle":"2022-03-02T07:54:04.949801Z","shell.execute_reply.started":"2022-03-02T07:54:04.94052Z","shell.execute_reply":"2022-03-02T07:54:04.949005Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Load model","metadata":{}},{"cell_type":"code","source":"def naive(row_id):\n    return True","metadata":{"execution":{"iopub.status.busy":"2022-03-02T07:54:33.740021Z","iopub.execute_input":"2022-03-02T07:54:33.740455Z","iopub.status.idle":"2022-03-02T07:54:33.744784Z","shell.execute_reply.started":"2022-03-02T07:54:33.740419Z","shell.execute_reply":"2022-03-02T07:54:33.744187Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Update target using pd.apply()","metadata":{}},{"cell_type":"code","source":"submission['target']=submission.apply(\n    lambda row: naive(row.row_id) , axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-03-02T07:54:37.521202Z","iopub.execute_input":"2022-03-02T07:54:37.521635Z","iopub.status.idle":"2022-03-02T07:54:37.527057Z","shell.execute_reply.started":"2022-03-02T07:54:37.521601Z","shell.execute_reply":"2022-03-02T07:54:37.526549Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Write csv","metadata":{}},{"cell_type":"code","source":"submission.to_csv('submission.csv',header=True, index=False)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Conclusion\nYou get .48 returning all values to False (same as just saving sample_submission.csv as it is)\n\nInterestingly you get .51 by returning all values to True\n\nIt seems to me this is the intended way to proceed, I share because it was unclear to me","metadata":{}}]}