{"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\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\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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"building=pd.read_csv(\"../input/ashrae-energy-prediction/building_metadata.csv\")\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train=pd.read_csv(\"../input/ashrae-energy-prediction/train.csv\")\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nbuilding_train=pd.merge(building,train,on=\"building_id\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"    data=building_train.iloc[:,:7]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"    dummy_primaryuse=pd.get_dummies(data[\"primary_use\"])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ddata=data.merge(dummy_primaryuse,left_index=True,right_index=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"del ddata[\"primary_use\"]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data=ddata","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label=building_train.iloc[:,8]\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x, test_x, train_y, test_y = train_test_split(data, label, random_state=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import xgboost as xgb\ndtrain=xgb.DMatrix(train_x,label=train_y)\ndtest=xgb.DMatrix(test_x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"params={'booster':'gbtree',\n    'objective': 'reg:linear',\n    'eval_metric': 'auc',\n    'max_depth':4,\n    'lambda':10,\n    'subsample':0.75,\n    'colsample_bytree':0.75,\n    'min_child_weight':2,\n    'eta': 0.025,\n    'seed':0,\n    'nthread':8,\n     'silent':1}\n\nwatchlist = [(dtrain,'train')]\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bst=xgb.train(params,dtrain,num_boost_round=5,evals=watchlist)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ypred=bst.predict(dtest)\n\n\ny_pred = (ypred >= 0.5)*1\n\nfrom sklearn import metrics\nprint 'AUC: %.4f' % metrics.roc_auc_score(test_y,ypred)\nprint 'ACC: %.4f' % metrics.accuracy_score(test_y,y_pred)\nprint 'Recall: %.4f' % metrics.recall_score(test_y,y_pred)\nprint 'F1-score: %.4f' %metrics.f1_score(test_y,y_pred)\nprint 'Precesion: %.4f' %metrics.precision_score(test_y,y_pred)\nmetrics.confusion_matrix(test_y,y_pred)\n","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}