{"cells":[{"metadata":{},"cell_type":"markdown","source":"This a simple baseline using the LGBM algorithm. This is a small modification to https://www.kaggle.com/lgreig/simple-lgbm-baseline.\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"import riiideducation\n# import dask.dataframe as dd\nimport pandas as pd\nimport numpy as np\nenv = riiideducation.make_env()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#note I also import the content_type_id to determine if I should filter out negative answered correctly\ntrain= pd.read_csv('/kaggle/input/riiid-test-answer-prediction/train.csv',\n                usecols=[1, 2, 3, 4, 7], dtype={'timestamp': 'int64', 'user_id': 'int64' ,'content_id': 'int16', 'content_type_id': 'bool', 'answered_correctly':'int8'}\n              )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Affirmatives (True) are only for those with a different type of content. Probably not real questions."},{"metadata":{"trusted":true},"cell_type":"code","source":"train = train[train.content_type_id == False]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Make a simple tree model and estimate score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#arrange by timestamp\n\ntrain = train.sort_values(['timestamp'], ascending=True).reset_index(drop = True)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.drop(['timestamp', 'content_type_id'], axis=1,   inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(list(set(train.iloc[0:90000000,:]['user_id']).intersection(set(train.iloc[90000000:99000000,:]['user_id']))))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_c = train.iloc[0:90000000,:][['content_id','answered_correctly']].groupby(['content_id']).agg(['mean'])\nresults_c.columns = [\"answered_correctly_content\"]\nresults_c.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_u = train.iloc[0:90000000,:][['user_id','answered_correctly']].groupby(['user_id']).agg(['mean', 'sum'])\nresults_u.columns = [\"answered_correctly_user\", 'sum']\nresults_u.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.iloc[90000000:99271299,:]\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = pd.merge(X, results_u, on=['user_id'], how=\"left\")\nX = pd.merge(X, results_c, on=['content_id'], how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X=X.sort_values(['user_id'])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y = X[[\"answered_correctly\"]]\nX = X.drop([\"answered_correctly\"], axis=1)\nX.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X[['answered_correctly_user', 'answered_correctly_content', 'sum']] \nX['answered_correctly_user'].fillna(0.5,  inplace=True)\nX['answered_correctly_content'].fillna(0.5,  inplace=True)\nX['sum'].fillna(0, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import lightgbm as lgb\n\nmodel = lgb.LGBMClassifier(num_leaves = 46, learning_rate = 0.11436513141203779, \n                           subsample_for_bin = 130000, min_child_samples = 470, \n                           reg_alpha = 0.5, reg_lambda = 0.26, subsample = 0.5, \n                           is_unbalance = False, n_estimators = 1000, \n                           objective = 'binary', random_state = 126)\n\nmodel.fit(X, Y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = model.predict_proba(X)[:, 1]\ny_true = np.array(Y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import roc_auc_score\nroc_auc_score(y_true, y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"###Make sure it works on the test set","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test =  pd.read_csv('/kaggle/input/riiid-test-answer-prediction/example_test.csv')\ntest.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.merge(test, results_u, on=['user_id'],  how=\"left\")\ntest = pd.merge(test, results_c, on=['content_id'],  how=\"left\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test[['answered_correctly_user', 'answered_correctly_content', 'sum']]\ntest['answered_correctly_user'].fillna(0.5, inplace=True)\ntest['answered_correctly_content'].fillna(0.5, inplace=True)\ntest['sum'].fillna(0, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = model.predict_proba(test[['answered_correctly_user', 'answered_correctly_content', 'sum']])[:, 1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test[[\"answered_correctly\"]] = y_pred\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#################","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Make preds\n\nresults_c = train[['content_id','answered_correctly']].groupby(['content_id']).agg(['mean'])\nresults_c.columns = [\"answered_correctly_content\"]\n\nresults_u = train[['user_id','answered_correctly']].groupby(['user_id']).agg(['mean', 'sum'])\nresults_u.columns = [\"answered_correctly_user\", 'sum']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results_c.head()","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 = pd.merge(test_df, results_u, on=['user_id'],  how=\"left\")\n    test_df = pd.merge(test_df, results_c, on=['content_id'],  how=\"left\")\n    test_df['answered_correctly_user'].fillna(0.5, inplace=True)\n    test_df['answered_correctly_content'].fillna(0.5, inplace=True)\n    test_df['sum'].fillna(0, inplace=True)\n    test_df['answered_correctly'] =  model.predict_proba(test_df[['answered_correctly_user', 'answered_correctly_content', 'sum']])[:, 1]\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":{"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}