{"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nfrom sklearn.svm import SVC\nfrom sklearn.decomposition import PCA\n\nfrom sklearn.model_selection import KFold\nfrom sklearn.metrics import roc_auc_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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"../input/siim-isic-melanoma-classification/train.csv\")\ntest = pd.read_csv(\"../input/siim-isic-melanoma-classification/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train_32 = np.load('../input/siimisic-melanoma-resized-images/x_train_32.npy')\nx_test_32 = np.load('../input/siimisic-melanoma-resized-images/x_test_32.npy')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train_32 = x_train_32.reshape((x_train_32.shape[0], 32*32*3))\nx_train_32.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_test_32 = x_test_32.reshape((x_test_32.shape[0], 32*32*3))\nx_test_32.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\npca = PCA(n_components=0.99,whiten=True)\nx_train_32 = pca.fit_transform(x_train_32)\nx_test_32 = pca.transform(x_test_32)\nprint(x_train_32.shape)\nprint(x_test_32.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"NUM_FOLDS = 5\nkf = KFold(n_splits=NUM_FOLDS, shuffle=True, random_state=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_oof = np.zeros(train.shape[0])\ny_test = np.zeros(test.shape[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train['target'].values\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nfor f, (train_ind, val_ind) in enumerate(kf.split(train, train)):\n    print(f)\n    train_, val_ = x_train_32[train_ind].astype('float32'), x_train_32[val_ind].astype('float32')\n    y_tr, y_vl = y[train_ind].astype('float32'), y[val_ind].astype('float32')\n    \n        \n    model = SVC(kernel='rbf',C=1, probability=True)\n    model.fit(train_, y_tr)\n    \n    val_pred = model.predict_proba(val_)[:,1]\n    y_oof[val_ind] = val_pred\n    \n    y_test += model.predict_proba(x_test_32.astype('float32'))[:,1]/NUM_FOLDS\n    \n    print(\"Fold AUC:\", roc_auc_score(y_vl, val_pred))\n    \n    \n\n\nprint(\"Total AUC:\", roc_auc_score(y, y_oof))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv('../input/siim-isic-melanoma-classification/sample_submission.csv')\nsample_submission['target'] = y_test\nsample_submission.to_csv('submission_32x32_svc.csv', index=False)\nsample_submission.head()","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}