{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n# INSTALL RAPIDS WITH CONDA. TAKES 6 MINUTES :-(\nimport sys\n!conda create -n rapids -c rapidsai/label/xgboost -c rapidsai -c nvidia -c conda-forge rapids=0.11 python=3.6 cudatoolkit=10.1 --yes\nsys.path = [\"/opt/conda/envs/rapids/lib\"] + [\"/opt/conda/envs/rapids/lib/python3.6\"] + [\"/opt/conda/envs/rapids/lib/python3.6/site-packages\"] + sys.path\n!cp /opt/conda/envs/rapids/lib/libxgboost.so /opt/conda/lib/","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from sklearn.model_selection import KFold\nfrom sklearn.metrics import accuracy_score, roc_auc_score\nimport cudf, cuml\nimport cupy as cp\nfrom cuml.linear_model import LogisticRegression\nimport numpy as np\n#from cuml.metrics import accuracy_score\n\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\nimport gc\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from cuml.neighbors import KNeighborsClassifier, NearestNeighbors\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = cudf.read_csv('../input/multi-cat-encodings/X_train_te.csv')\ntest = cudf.read_csv('../input/multi-cat-encodings/X_test_te.csv')\nsample_submission = cudf.read_csv('../input/cat-in-the-dat-ii/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_oof = cp.zeros((train.shape[0],))\ntest_preds = 0\ntrain_oof.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cupy as cp\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def auc_cp(y_true,y_pred):\n  y_true = y_true.astype('float32')\n  ids = np.argsort(-y_pred) # we want descedning order\n  y_true = y_true[ids.values]\n  y_pred = y_pred[ids.values]\n  zero = 1 - y_true\n  acc_one = cp.cumsum(y_true)\n  acc_zero = cp.cumsum(zero)\n  sum_one = cp.sum(y_true)\n  sum_zero = cp.sum(zero)\n  tpr = acc_one/sum_one\n  fpr = acc_zero/sum_zero\n  return calculate_area(fpr,tpr)\n\ndef calculate_area(fpr,tpr):\n  return cp.sum((fpr[1:]-fpr[:-1])*(tpr[1:]+tpr[:-1]))/2\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = test.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nn_splits = 5\nkf = KFold(n_splits=n_splits, random_state=137)\n\nfor jj, (train_index, val_index) in enumerate(kf.split(train)):\n    print(\"Fitting fold\", jj+1)\n    train_features = train.loc[train['fold_column'] != jj][features]\n    train_target = train.loc[train['fold_column'] != jj]['target'].values.astype(float)\n    \n    val_features = train.loc[train['fold_column'] == jj][features]\n    val_target = train.loc[train['fold_column'] == jj]['target'].values.astype(float)\n    \n    model = KNeighborsClassifier(n_neighbors=400)\n    model.fit(train_features, train_target)\n    val_pred = model.predict_proba(val_features)[1]\n    train_oof[val_index] = val_pred\n    val_target = cp.asarray(val_target)\n    print(\"Fold AUC:\", auc_cp(val_target, val_pred))\n    test_preds += model.predict_proba(test)[1].values/n_splits\n    del train_features, train_target, val_features, val_target\n    gc.collect()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission['target'] = test_preds\nsample_submission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cp.save('test_preds', test_preds)\ncp.save('train_oof', train_oof)","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":1}