{"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 \nimport sys\nimport os\nimport warnings\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport numpy as np # linear algebra \nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom sklearn.model_selection import train_test_split\nimport pydicom ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Read the data\ntest = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')\ntrain = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['sex'].fillna('unknown', inplace=True)\ntest['sex'].fillna('unknown', inplace=True)\n\ntrain['age_approx'].fillna(train['age_approx'].mode().values[0], inplace=True)\ntest['age_approx'].fillna(test['age_approx'].mode().values[0], inplace=True)\n\ntrain['anatom_site_general_challenge'].fillna('unknown', inplace=True)\ntest['anatom_site_general_challenge'].fillna('unknown', inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nenc = LabelEncoder()\n\ntrain['sex_enc'] = enc.fit_transform(train.sex.astype('str'))\ntest['sex_enc'] = enc.transform(test.sex.astype('str'))\n\ntrain['age_enc'] = enc.fit_transform(train.age_approx.astype('str'))\ntest['age_enc'] = enc.transform(test.age_approx.astype('str'))\n\ntrain['anatom_enc'] = enc.fit_transform(train.anatom_site_general_challenge.astype('str'))\ntest['anatom_enc'] = enc.transform(test.anatom_site_general_challenge.astype('str'))","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['age_enc'] = train['age_enc'] / np.mean(train['age_enc'])\ntest['age_enc'] = test['age_enc'] / np.mean(test['age_enc'])\n\ntrain['anatom_enc'] = train['anatom_enc'] / np.mean(train['anatom_enc'])\ntest['anatom_enc'] = test['anatom_enc'] / np.mean(test['anatom_enc'])\n\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"features = [\n            'sex_enc',\n            'age_enc',\n            'anatom_enc'\n]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = train[features]\ny_train = train['target']\n\nx_test = test[features]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# model tuning\n\nfrom xgboost import XGBRegressor\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.model_selection import RandomizedSearchCV\nimport time\nfrom sklearn.metrics import roc_auc_score\n\n# A parameter grid for XGBoost\nparams = {\n    'n_estimators':[500],\n    'min_child_weight':[4,5], \n    'gamma':[i/10.0 for i in range(3,6)],  \n    'subsample':[i/10.0 for i in range(6,11)],\n    'colsample_bytree':[i/10.0 for i in range(6,11)], \n    'max_depth': [2,3,4,6,7],\n    'objective': ['binary:logistic'],\n    'booster': ['gbtree', 'gblinear'],\n    'eval_metric': ['rmse'],\n    'eta': [i/10.0 for i in range(3,6)],\n}\n\nreg = XGBRegressor(n_jobs=-1, nthread=-1)\n\n# run randomized search\nn_iter_search = 100\nrandom_search = RandomizedSearchCV(reg, param_distributions=params,\n                                   n_iter=n_iter_search, cv=5, iid=False, scoring='roc_auc')\n\nstart = time.time()\nrandom_search.fit(X_train, y_train)\nprint(\"RandomizedSearchCV took %.2f seconds for %d candidates\"\n      \" parameter settings.\" % ((time.time() - start), n_iter_search))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"best_regressor = random_search.best_estimator_\npreds = best_regressor.predict(x_test)","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.head()\nsample_submission['target'] = preds\nsample_submission.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}