{"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":59094,"databundleVersionId":7010844,"sourceType":"competition"},{"sourceId":7121955,"sourceType":"datasetVersion","datasetId":3948965}],"dockerImageVersionId":30587,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# What is about ? \n\nLate submits - compare/analyze various pyboosts blends.\n\nConclusions: \n    \n    1 Pyboost by AmbrosM (with t-scores) is much better on private LB, than other versions.\n    Its public is 0.572 (private 0.748), while another pyboost 0.574 (private - 0.768) - small difference in public score, big in private.\n\n\nVersions:\n    \n    1: Blend of three: 572 (AmrbosM) , 574, 577 - get: public 0.567, private - 0.751  \n    Correlations 0.85,0.83,0.9\n    \nCorrelations between these three: https://www.kaggle.com/code/alexandervc/op2-submits-correlations-and-analysis?scriptVersionId=153589440&cellId=11\n    \n    4 574+577: private: 0.759 ; public: 0.570\n    \n    \n    \n    # AmbrosM: # Private Score 0.748 Public Score 0.572\n    # 577: Private Score 0.768 Public Score 0.577\n    # 574: Private score 0.765 Public Score 0.574\n\n    \n","metadata":{}},{"cell_type":"code","source":"%%time\nimport numpy as np\nimport pandas as pd\n\nlist_df = []\n# fn = '/kaggle/input/open-problems-2-submits-collection/LB572_PyboostAmbrosMtscoreReTrainFull_openAfterEnd_nbV1.csv'\n# # Private Score 0.748 Public Score 0.572\n# print(fn)\n# df = pd.read_csv(fn, index_col = 'id')\n# print(df.shape)\n# display(df.head(2))\n# df1 = df.copy()\n# list_df.append(df)\n\nfn = '/kaggle/input/open-problems-2-submits-collection/LB577_PyboostCVRandom5_max_depth10_ntrees5000_lr001_subsample1_colsample035_n_components50_NikolenkoPubl.csv'\n# Private Score 0.768 Public Score 0.577\nprint(fn)\ndf = pd.read_csv(fn, index_col = 'id')\nprint(df.shape)\ndisplay(df.head(2))\ndf2 = df.copy()\nlist_df.append(df)\n\nfn = '/kaggle/input/open-problems-2-submits-collection/LB574_Pyboostmaxdepth12ntrees2000lr001subsample1colsample035ncomponents50T8T8b7t17_MadrisMillerBasedAlex_nbV8.csv'\n# Private score: 0.765 Public Score 0.574\nprint(fn)\ndf = pd.read_csv(fn, index_col = 'id')\nprint(df.shape)\ndisplay(df.head(2))\ndf2 = df.copy()\nlist_df.append(df)\n\n\nprint(); print()\nprint('--------------------------------------------------------------------------------------------')\nprint(); print();\n\n\ndf_blend = sum(list_df)\ndf_blend /= len(list_df)\n\ndisplay(df_blend.head(2) )\ndf_blend.to_csv('submission_Pyboosts_blend_574_577_late_submit.csv')","metadata":{"execution":{"iopub.status.busy":"2023-12-04T15:26:29.674262Z","iopub.execute_input":"2023-12-04T15:26:29.674982Z","iopub.status.idle":"2023-12-04T15:26:53.332772Z","shell.execute_reply.started":"2023-12-04T15:26:29.674930Z","shell.execute_reply":"2023-12-04T15:26:53.331951Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2023-12-04T15:21:47.266528Z","iopub.execute_input":"2023-12-04T15:21:47.266923Z","iopub.status.idle":"2023-12-04T15:21:47.701665Z","shell.execute_reply.started":"2023-12-04T15:21:47.266892Z","shell.execute_reply":"2023-12-04T15:21:47.700490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}