{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"!pip install xgboost\n\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.datasets import load_iris\nimport xgboost as xgb\nfrom sklearn.metrics import accuracy_score","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')\nsub   = pd.read_csv('../input/siim-isic-melanoma-classification/sample_submission.csv')\ntrain.head()\n\ntrain.target.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['sex'] = train['sex'].fillna('na')\ntrain['age_approx'] = train['age_approx'].fillna(0)\ntrain['anatom_site_general_challenge'] = train['anatom_site_general_challenge'].fillna('na')\n\ntest['sex'] = test['sex'].fillna('na')\ntest['age_approx'] = test['age_approx'].fillna(0)\ntest['anatom_site_general_challenge'] = test['anatom_site_general_challenge'].fillna('na')\ntrain['sex'] = train['sex'].astype(\"category\").cat.codes +1\ntrain['anatom_site_general_challenge'] = train['anatom_site_general_challenge'].astype(\"category\").cat.codes +1\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test['sex'] = test['sex'].astype(\"category\").cat.codes +1\ntest['anatom_site_general_challenge'] = test['anatom_site_general_challenge'].astype(\"category\").cat.codes +1\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = train[['sex', 'age_approx','anatom_site_general_challenge']]\ny_train = train['target']\n\n\nx_test = test[['sex', 'age_approx','anatom_site_general_challenge']]\n# y_train = test['target']\n\n\ntrain_DMatrix = xgb.DMatrix(x_train, label= y_train)\ntest_DMatrix = xgb.DMatrix(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf = xgb.XGBClassifier(n_estimators=2800, \n                        max_depth=18, \n                        objective='multi:softprob',\n                        seed=0,  \n                        nthread=-1, \n                        learning_rate=0.15, \n                        num_class = 2, \n                        scale_pos_weight = (32542/584))\n\nclf.fit(x_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf.predict_proba(x_test)[:,1]\n# clf.predict(x_test)\nsub.target = clf.predict_proba(x_test)[:,1]\nsub_tabular = sub.copy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub_new = pd.read_csv('../input/siimisic/sub-new.csv')\n# sub_public_merge = pd.read_csv('/kaggle/input/submission-9/submission_935.csv')\nsub_mean = pd.read_csv('/kaggle/input/siimisic/submission_mean.csv')\nsub.target = sub_mean.target *0.3 + sub_new.target *0.6 + sub_tabular.target *0.1\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv('submission.csv', index = False)","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}