{"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":"2023-05-05T02:52:15.687788Z","iopub.execute_input":"2023-05-05T02:52:15.688182Z","iopub.status.idle":"2023-05-05T02:52:15.705295Z","shell.execute_reply.started":"2023-05-05T02:52:15.688153Z","shell.execute_reply":"2023-05-05T02:52:15.703958Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install memory_profiler\n%load_ext memory_profiler","metadata":{"execution":{"iopub.status.busy":"2023-05-05T02:52:17.898144Z","iopub.execute_input":"2023-05-05T02:52:17.898581Z","iopub.status.idle":"2023-05-05T02:52:30.465339Z","shell.execute_reply.started":"2023-05-05T02:52:17.898547Z","shell.execute_reply":"2023-05-05T02:52:30.464026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport gc\nfrom sklearn.model_selection import KFold, GroupKFold\nfrom xgboost import XGBClassifier\nfrom sklearn.metrics import f1_score\nfrom memory_profiler import memory_usage\n\n","metadata":{"execution":{"iopub.status.busy":"2023-05-05T02:52:48.763709Z","iopub.execute_input":"2023-05-05T02:52:48.764552Z","iopub.status.idle":"2023-05-05T02:52:48.769468Z","shell.execute_reply.started":"2023-05-05T02:52:48.764515Z","shell.execute_reply":"2023-05-05T02:52:48.768508Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# READ USER ID ONLY --> to get the row amount for creating chunk sizes.\n\n%time %memit tmp = pd.read_csv(\"/kaggle/input/predict-student-performance-from-game-play/train.csv\",usecols=[0])\ntmp = tmp.groupby('session_id').session_id.agg('count')\n\n# COMPUTE READS AND SKIPS\nPIECES = 10\nCHUNK = int( np.ceil(len(tmp)/PIECES) )\n\n# Here the data pieces are created\nreads = []\nskips = [0]\nfor k in range(PIECES):\n    a = k*CHUNK\n    b = (k+1)*CHUNK\n    if b>len(tmp): b=len(tmp)\n    r = tmp.iloc[a:b].sum()\n    reads.append(r)\n    skips.append(skips[-1]+r)\n    \nprint(f'To avoid memory error, we will read train in {PIECES} pieces of sizes:')\nprint(reads)","metadata":{"execution":{"iopub.status.busy":"2023-05-05T02:52:52.766377Z","iopub.execute_input":"2023-05-05T02:52:52.766804Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2023-05-05T02:47:12.061330Z","iopub.status.idle":"2023-05-05T02:47:12.061797Z","shell.execute_reply.started":"2023-05-05T02:47:12.061584Z","shell.execute_reply":"2023-05-05T02:47:12.061609Z"},"trusted":true},"execution_count":null,"outputs":[]}]}