{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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)\nimport gc\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'):\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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_pickle('/kaggle/input/riiid-train-data-multiple-formats/riiid_train.pkl.gzip')\nquestions = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/questions.csv', dtype={'question_id':np.int16, 'bundle_id': np.int16, 'correct_answer': np.int8, 'part': np.int8, 'tags': np.str })\nlectures = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/lectures.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"user_stats = train[train['content_type_id'] == False].groupby(['user_id']).answered_correctly.agg(['count', 'sum'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"user_stats_dict = user_stats.to_dict()\nkeys_list = set(user_stats_dict['count'].keys())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def update_user_stats(df):\n    user_stats_temp = df[df['content_type_id'] == False].groupby(['user_id']).answered_correctly.agg(['count', 'sum'])\n    user_stats_temp_dict = user_stats_temp.to_dict()\n    user_stats_temp_dict_cnt = user_stats_temp_dict['count']\n    user_stats_temp_dict_sum = user_stats_temp_dict['sum']\n    for key, val in user_stats_temp_dict_cnt.items():\n        keys_list.add(key)\n        user_stats_dict['count'][key] = user_stats_temp_dict_cnt.get(key,0)+val\n    for key, val in user_stats_temp_dict_sum.items():\n        user_stats_dict['sum'][key] = user_stats_temp_dict_sum.get(key,0)+val","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def inference():\n    import riiideducation\n    import time\n    # You can only call make_env() once, so don't lose it!\n    env = riiideducation.make_env()\n    iter_test = env.iter_test()\n    previous_test_df = None\n    i = 0\n    print(\"Starting inference...\")\n    for (test_df, sample_prediction_df) in iter_test:\n        i+=1\n        curr_time = time.time()\n        if previous_test_df is not None:\n            previous_test_df['answered_correctly'] = eval(test_df[\"prior_group_answers_correct\"].iloc[0])\n            update_user_stats(previous_test_df)\n        previous_test_df = test_df.copy()\n        test_df = test_df[test_df['content_type_id'] == 0].reset_index(drop = True)\n\n        pred_list = []\n        for idx, row in test_df.iterrows():\n            if row['user_id'] not in keys_list:\n                pred_list.append(0.5)\n            else:\n                pred_list.append(user_stats_dict['sum'][row['user_id']] / user_stats_dict['count'][row['user_id']])\n        test_df = test_df.assign(answered_correctly = pred_list) \n        env.predict(test_df[['row_id', 'answered_correctly']])\n        print(\"Iteration took: \", time.time()-curr_time, \" seconds\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"inference()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}