{"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":{"execution":{"iopub.status.busy":"2022-11-13T22:06:01.482529Z","iopub.execute_input":"2022-11-13T22:06:01.483172Z","iopub.status.idle":"2022-11-13T22:06:01.618844Z","shell.execute_reply.started":"2022-11-13T22:06:01.483022Z","shell.execute_reply":"2022-11-13T22:06:01.617574Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nfn = '/kaggle/input/data2-multimodal-singlecell-integration/submit_average4models.csv'\nfn = '/kaggle/input/data2-multimodal-singlecell-integration/submit_average19models.csv'\nfn = '/kaggle/input/data2-multimodal-singlecell-integration/submit_averageTop4GroupsModels.csv'\nresult = pd.read_csv(fn ,  index_col = 0)\n\nresult","metadata":{"execution":{"iopub.status.busy":"2022-11-13T22:06:02.588806Z","iopub.execute_input":"2022-11-13T22:06:02.589287Z","iopub.status.idle":"2022-11-13T22:06:05.921016Z","shell.execute_reply.started":"2022-11-13T22:06:02.589247Z","shell.execute_reply":"2022-11-13T22:06:05.919804Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n# Normally that part works Wall time: 1min 11s - however sometimes Kaggle system does not work correctly and it never stops\nif 1:# (flag_prepare_submission) and (Y.shape[1] == constant_number_of_original_targets):\n    mode_subm = 'USE: sskknts MSCI CITEseq Keras Quickstart + Dropout' # 'put_zeros_to_multiome_part'\n\n    if mode_subm == 'USE: sskknts MSCI CITEseq Keras Quickstart + Dropout' :\n        fn_loc = '/kaggle/input/msci-citeseq-keras-quickstart-dropout/submission.csv'\n        fn_loc = '/kaggle/input/solutions-for-multimodal-singlecell-integration/msci-citeseq-keras-quickstart-dropout_submission.csv'\n        fn_loc = '../input/all-in-one-citeseq-multiome-with-keras/submission_lolo_total_ensembling.csv'\n        df_submission_full = pd.read_csv(fn_loc,\n                                 index_col='row_id', squeeze=True)\n        df_submission_full = df_submission_full.to_frame()\n    elif mode_subm == 'put_zeros_to_multiome_part':\n        df_submission_full = pd.DataFrame(index = range(65_744_180), columns = ['target'], data = np.zeros(65_744_180) )\n        df_submission_full.index.name = 'row_id'\n\n    display(df_submission_full.info() )\n    print()\n    display(df_submission_full.head(10))","metadata":{"execution":{"iopub.status.busy":"2022-11-13T22:06:13.136459Z","iopub.execute_input":"2022-11-13T22:06:13.136908Z","iopub.status.idle":"2022-11-13T22:07:46.597360Z","shell.execute_reply.started":"2022-11-13T22:06:13.136873Z","shell.execute_reply":"2022-11-13T22:07:46.596210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"    df_submission_full['target'].iloc[:6_812_820] = result.values.ravel()\n    display(df_submission_full.head(20))\n    display(df_submission_full.tail(20))\n    ","metadata":{"execution":{"iopub.status.busy":"2022-11-13T22:08:08.524147Z","iopub.execute_input":"2022-11-13T22:08:08.525398Z","iopub.status.idle":"2022-11-13T22:08:08.587089Z","shell.execute_reply.started":"2022-11-13T22:08:08.525339Z","shell.execute_reply":"2022-11-13T22:08:08.586018Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n#submit_filename_postfix = 'average19models'\ndf_submission_full.to_csv('full_'+fn.split('/')[-1])# 'submission_'+submit_filename_postfix +'.csv')","metadata":{"execution":{"iopub.status.busy":"2022-11-13T22:08:57.740361Z","iopub.execute_input":"2022-11-13T22:08:57.740771Z","iopub.status.idle":"2022-11-13T22:11:40.705857Z","shell.execute_reply.started":"2022-11-13T22:08:57.740738Z","shell.execute_reply":"2022-11-13T22:11:40.704597Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# %%time\n# df_submission_full.to_csv('submission' +'.csv')","metadata":{"execution":{"iopub.status.busy":"2022-11-11T22:23:26.648403Z","iopub.execute_input":"2022-11-11T22:23:26.648746Z","iopub.status.idle":"2022-11-11T22:25:27.145217Z","shell.execute_reply.started":"2022-11-11T22:23:26.648718Z","shell.execute_reply":"2022-11-11T22:25:27.143563Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}