{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train=pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/train.csv')\ntest=pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/test.csv')","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":"train.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.columns","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 = train.drop(['diagnosis','benign_malignant'], axis = 1)","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.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"car_feat = ['image_name', 'patient_id', 'sex', 'anatom_site_general_challenge']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['age_approx']=train['age_approx'].fillna((train['age_approx'].value_counts().index[0]))\ntrain['sex']=train['sex'].fillna((train['sex'].value_counts().index[0]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['anatom_site_general_challenge']=train['anatom_site_general_challenge'].fillna((train['anatom_site_general_challenge'].value_counts().index[0]))\ntest['anatom_site_general_challenge']=test['anatom_site_general_challenge'].fillna((test['anatom_site_general_challenge'].value_counts().index[0]))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import seaborn as sns\nsns.boxplot(x=train['age_approx'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# replace outliar from age column\ntrain['age_approx'] = train['age_approx'].replace(train['age_approx'].min(),train['age_approx'].median())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# seperate the features and target column\nX = train.drop('target', axis=1)\ny = train.target","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# specify the categorical columns list\ncategorical_features_indices = np.where(X.dtypes != np.float)[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# split the training dataset into train and validation datasets\nfrom sklearn.model_selection import train_test_split\n\nX_train, X_validation, y_train, y_validation = train_test_split(X, y, train_size=0.85, random_state=42, stratify=y)\n\nX_test = test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# import catboost library\nfrom catboost import CatBoostClassifier, Pool, cv","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = CatBoostClassifier(\n    eval_metric='AUC',\n    random_seed=42,\n    use_best_model=True,\n    verbose=1  \n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(\n    X_train, y_train,\n    cat_features=categorical_features_indices,\n    eval_set=(X_validation, y_validation),\n#     logging_level='Verbose',  uncomment this for text output\n    plot=False\n);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# make prediction on validation dataset\npredict = model.predict(X_validation)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# check AUC ROC score\nfrom sklearn.metrics import roc_auc_score\nscore = roc_auc_score(y_validation, predict)\nprint('ROC AUC %.3f' % score)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# check the important features\ntrain_pool = Pool(X_train, y_train, cat_features=categorical_features_indices)\nfeature_importances = model.get_feature_importance(train_pool)\nfeature_names = X_train.columns\nfor score, name in sorted(zip(feature_importances, feature_names), reverse=True):\n    print('{}: {}'.format(name, score))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict_proba(X_test)[:,1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/sample_submission.csv')\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({ 'image_name': test.image_name, 'target': predictions })\nsubmission.to_csv('Submission_catboost.csv', index=False)","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}