{"cells":[{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_kg_hide-input":true,"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","execution":{"iopub.execute_input":"2020-12-17T09:47:55.277252Z","iopub.status.busy":"2020-12-17T09:47:55.276489Z","iopub.status.idle":"2020-12-17T09:47:56.374948Z","shell.execute_reply":"2020-12-17T09:47:56.373872Z"},"papermill":{"duration":1.184028,"end_time":"2020-12-17T09:47:56.375118","exception":false,"start_time":"2020-12-17T09:47:55.19109","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport matplotlib.style as style\nstyle.use('fivethirtyeight')\nimport seaborn as sns\nimport os\nfrom matplotlib.ticker import FuncFormatter\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn import preprocessing\nimport lightgbm as lgb\nimport gc\nimport riiideducation\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input/riiid-test-answer-prediction'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:47:56.683953Z","iopub.status.busy":"2020-12-17T09:47:56.68318Z","iopub.status.idle":"2020-12-17T09:48:41.917755Z","shell.execute_reply":"2020-12-17T09:48:41.918344Z"},"papermill":{"duration":45.316915,"end_time":"2020-12-17T09:48:41.918495","exception":false,"start_time":"2020-12-17T09:47:56.60158","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"%%time\ncols_to_load = ['row_id', 'user_id', 'answered_correctly', 'content_id', 'prior_question_had_explanation', 'prior_question_elapsed_time']\ntrain = pd.read_pickle(\"../input/riiid-train-data-multiple-formats/riiid_train.pkl.gzip\")[cols_to_load]\ntrain['prior_question_had_explanation'] = train['prior_question_had_explanation'].astype('boolean')\n\nprint(\"Train size:\", train.shape)","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-12-17T09:49:02.314821Z","iopub.status.busy":"2020-12-17T09:49:02.307832Z","iopub.status.idle":"2020-12-17T09:49:02.319877Z","shell.execute_reply":"2020-12-17T09:49:02.319188Z"},"papermill":{"duration":20.158522,"end_time":"2020-12-17T09:49:02.319994","exception":false,"start_time":"2020-12-17T09:48:42.161472","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"%%time\n\nquestions = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/questions.csv')\nlectures = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/lectures.csv')\nexample_test = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/example_test.csv')\nexample_sample_submission = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/example_sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-12-17T09:49:02.483865Z","iopub.status.busy":"2020-12-17T09:49:02.483137Z","iopub.status.idle":"2020-12-17T09:49:02.489613Z","shell.execute_reply":"2020-12-17T09:49:02.488839Z"},"papermill":{"duration":0.095582,"end_time":"2020-12-17T09:49:02.489794","exception":false,"start_time":"2020-12-17T09:49:02.394212","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-12-17T09:49:13.821693Z","iopub.status.busy":"2020-12-17T09:49:13.820922Z","iopub.status.idle":"2020-12-17T09:49:34.910989Z","shell.execute_reply":"2020-12-17T09:49:34.911584Z"},"papermill":{"duration":32.19594,"end_time":"2020-12-17T09:49:34.911773","exception":false,"start_time":"2020-12-17T09:49:02.715833","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:35.225102Z","iopub.status.busy":"2020-12-17T09:49:35.224395Z","iopub.status.idle":"2020-12-17T09:49:35.271272Z","shell.execute_reply":"2020-12-17T09:49:35.272088Z"},"papermill":{"duration":0.132324,"end_time":"2020-12-17T09:49:35.272284","exception":false,"start_time":"2020-12-17T09:49:35.13996","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"#adding user features\nuser_df = train[train.answered_correctly != -1].groupby('user_id').agg({'answered_correctly': ['count', 'mean']}).reset_index()\nuser_df.columns = ['user_id', 'user_questions', 'user_mean']\n\nuser_lect = train.groupby([\"user_id\", \"answered_correctly\"]).size().unstack()\nuser_lect.columns = ['Lecture', 'Wrong', 'Right']\nuser_lect = user_lect[['Lecture']].fillna(0).astype('int8')\n#user_lect = user_lect.astype('int8')\nuser_lect['watches_lecture'] = np.where(user_lect.Lecture > 0, 1, 0)\nuser_lect = user_lect.reset_index()\nuser_lect = user_lect[['user_id', 'watches_lecture']]\n\nuser_df = user_df.merge(user_lect, on = \"user_id\", how = \"left\")\ndel user_lect\nuser_df.head()","execution_count":null,"outputs":[]},{"metadata":{"execution":{"iopub.execute_input":"2020-12-17T09:49:35.579207Z","iopub.status.busy":"2020-12-17T09:49:35.578482Z","iopub.status.idle":"2020-12-17T09:49:35.598707Z","shell.execute_reply":"2020-12-17T09:49:35.598136Z"},"papermill":{"duration":0.097864,"end_time":"2020-12-17T09:49:35.598829","exception":false,"start_time":"2020-12-17T09:49:35.500965","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"%%time\n#adding content features\ncontent_df = train[train.answered_correctly != -1].groupby('content_id').agg({'answered_correctly': ['count', 'mean']}).reset_index()\ncontent_df.columns = ['content_id', 'content_questions', 'content_mean']\ncontent_df.head()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:35.770016Z","iopub.status.busy":"2020-12-17T09:49:35.769116Z","iopub.status.idle":"2020-12-17T09:49:36.603831Z","shell.execute_reply":"2020-12-17T09:49:36.603097Z"},"papermill":{"duration":0.914477,"end_time":"2020-12-17T09:49:36.603953","exception":false,"start_time":"2020-12-17T09:49:35.689476","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"%%time\n#using one of the validation sets composed by tito\ncv2_train = pd.read_pickle(\"../input/riiid-cross-validation-files/cv2_train.pickle\")['row_id']\ncv2_valid = pd.read_pickle(\"../input/riiid-cross-validation-files/cv2_valid.pickle\")['row_id']","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:36.919736Z","iopub.status.busy":"2020-12-17T09:49:36.918997Z","iopub.status.idle":"2020-12-17T09:49:37.690938Z","shell.execute_reply":"2020-12-17T09:49:37.691935Z"},"papermill":{"duration":0.856267,"end_time":"2020-12-17T09:49:37.69222","exception":false,"start_time":"2020-12-17T09:49:36.835953","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"train = train[train.answered_correctly != -1]\n\n#save mean before splitting\n#please be aware that there is an issues with train.prior_question_elapsed_time.mean()\n#see https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/195032\nmean_prior = train.prior_question_elapsed_time.astype(\"float64\").mean()\n\nvalidation = train[train.row_id.isin(cv2_valid)]\ntrain = train[train.row_id.isin(cv2_train)]\n\nvalidation = validation.drop(columns = \"row_id\")\ntrain = train.drop(columns = \"row_id\")","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:38.064307Z","iopub.status.busy":"2020-12-17T09:49:38.063608Z","iopub.status.idle":"2020-12-17T09:49:46.995901Z","shell.execute_reply":"2020-12-17T09:49:46.996562Z"},"papermill":{"duration":9.014258,"end_time":"2020-12-17T09:49:46.996737","exception":false,"start_time":"2020-12-17T09:49:37.982479","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"label_enc = preprocessing.LabelEncoder()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:47.157471Z","iopub.status.busy":"2020-12-17T09:49:47.156735Z","iopub.status.idle":"2020-12-17T09:49:51.381475Z","shell.execute_reply":"2020-12-17T09:49:51.380799Z"},"papermill":{"duration":4.30588,"end_time":"2020-12-17T09:49:51.381593","exception":false,"start_time":"2020-12-17T09:49:47.075713","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"train = train.sample(n=10000000, random_state = 1)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:51.701468Z","iopub.status.busy":"2020-12-17T09:49:51.700057Z","iopub.status.idle":"2020-12-17T09:49:52.575777Z","shell.execute_reply":"2020-12-17T09:49:52.575169Z"},"papermill":{"duration":0.960111,"end_time":"2020-12-17T09:49:52.575894","exception":false,"start_time":"2020-12-17T09:49:51.615783","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"train = train.merge(user_df, on = \"user_id\", how = \"left\")\ntrain = train.merge(content_df, on = \"content_id\", how = \"left\")\ntrain['content_questions'].fillna(0, inplace = True)\ntrain['content_mean'].fillna(0.5, inplace = True)\ntrain['watches_lecture'].fillna(0, inplace = True)\ntrain['user_questions'].fillna(0, inplace = True)\ntrain['user_mean'].fillna(0.5, inplace = True)\ntrain['prior_question_elapsed_time'].fillna(mean_prior, inplace = True)\ntrain['prior_question_had_explanation'].fillna(False, inplace = True)\nlabel_enc.fit(train['prior_question_had_explanation'])\ntrain['prior_question_had_explanation'] = label_enc.transform(train['prior_question_had_explanation'])\ntrain[['content_questions', 'user_questions']] = train[['content_questions', 'user_questions']].astype(int)\ntrain.sample(5)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:52.95259Z","iopub.status.busy":"2020-12-17T09:49:52.951233Z","iopub.status.idle":"2020-12-17T09:49:53.747695Z","shell.execute_reply":"2020-12-17T09:49:53.747087Z"},"papermill":{"duration":0.880937,"end_time":"2020-12-17T09:49:53.747823","exception":false,"start_time":"2020-12-17T09:49:52.866886","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"validation = validation.merge(user_df, on = \"user_id\", how = \"left\")\nvalidation = validation.merge(content_df, on = \"content_id\", how = \"left\")\nvalidation['content_questions'].fillna(0, inplace = True)\nvalidation['content_mean'].fillna(0.5, inplace = True)\nvalidation['watches_lecture'].fillna(0, inplace = True)\nvalidation['user_questions'].fillna(0, inplace = True)\nvalidation['user_mean'].fillna(0.5, inplace = True)\nvalidation['prior_question_elapsed_time'].fillna(mean_prior, inplace = True)\nvalidation['prior_question_had_explanation'].fillna(False, inplace = True)\nvalidation['prior_question_had_explanation'] = label_enc.transform(validation['prior_question_had_explanation'])\nvalidation[['content_questions', 'user_questions']] = validation[['content_questions', 'user_questions']].astype(int)\nvalidation.sample(5)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"execution":{"iopub.execute_input":"2020-12-17T09:49:54.095527Z","iopub.status.busy":"2020-12-17T09:49:54.093838Z","iopub.status.idle":"2020-12-17T09:50:08.348311Z","shell.execute_reply":"2020-12-17T09:50:08.347556Z"},"papermill":{"duration":14.35882,"end_time":"2020-12-17T09:50:08.348441","exception":false,"start_time":"2020-12-17T09:49:53.989621","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"features = ['user_questions', 'user_mean', 'content_questions', 'content_mean', 'prior_question_elapsed_time']\n\ny_train = train['answered_correctly']\ntrain = train[features]\n\ny_val = validation['answered_correctly']\nvalidation = validation[features]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"params = {'objective': 'binary',\n          'metric': 'auc',\n          'seed': 2020,\n          'learning_rate': 0.1, #default\n          \"boosting_type\": \"gbdt\" #default\n         }","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lgb_train = lgb.Dataset(train, y_train, categorical_feature = None)\nlgb_eval = lgb.Dataset(validation, y_val, categorical_feature = None)\ndel train, y_train, validation, y_val\ngc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nmodel = lgb.train(\n    params, lgb_train,\n    valid_sets=[lgb_train, lgb_eval],\n    verbose_eval=50,\n    num_boost_round=10000,\n    early_stopping_rounds=8\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lgb.plot_importance(model)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"env = riiideducation.make_env()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"iter_test = env.iter_test()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for (test_df, sample_prediction_df) in iter_test:\n    test_df = test_df.merge(user_df, on = \"user_id\", how = \"left\")\n    test_df = test_df.merge(content_df, on = \"content_id\", how = \"left\")\n    test_df['content_questions'].fillna(0, inplace = True)\n    test_df['content_mean'].fillna(0.5, inplace = True)\n    test_df['watches_lecture'].fillna(0, inplace = True)\n    test_df['user_questions'].fillna(0, inplace = True)\n    test_df['user_mean'].fillna(0.5, inplace = True)\n    test_df['prior_question_elapsed_time'].fillna(mean_prior, inplace = True)\n    test_df['prior_question_had_explanation'].fillna(False, inplace = True)\n    test_df['prior_question_had_explanation'] = label_enc.transform(test_df['prior_question_had_explanation'])\n    test_df[['content_questions', 'user_questions']] = test_df[['content_questions', 'user_questions']].astype(int)\n    test_df['answered_correctly'] =  model.predict(test_df[features])\n    env.predict(test_df.loc[test_df['content_type_id'] == 0, ['row_id', 'answered_correctly']])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}