{"cells":[{"metadata":{"_uuid":"6aa6c47ccf83cef6edbb05036455b1ca9859c518"},"cell_type":"markdown","source":"# Import data processing and plotting libraries"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d4eb4ed2fa9944b1a585121edf7cf30d5b8cedc6"},"cell_type":"markdown","source":"# Importing ML models and Evaluation metrics"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from sklearn.metrics import roc_curve, auc\nimport xgboost as xgb","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"fb24a3f1c7cb4bfed8e26cf52f896e1040eadd02"},"cell_type":"markdown","source":"#  Reading training data"},{"metadata":{"trusted":true,"_uuid":"6090ae36ba5f97274bd3368939a01b3c74a3155f"},"cell_type":"code","source":"print('Loading the training/test data using pandas...')\ntrain = pd.read_csv('../input/training.csv')\ntest = pd.read_csv('../input/test.csv')\ncheck_agreement = pd.read_csv('../input/check_agreement.csv')\ncheck_correlation = pd.read_csv('../input/check_correlation.csv')","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"ab619d19d690932dbb4d9861c8d4f9936f07d60f"},"cell_type":"markdown","source":"### 1. Define new potential features"},{"metadata":{"trusted":true,"_uuid":"8bc08931336d41c6a24729c33fe18697b176b48b"},"cell_type":"code","source":"def add_features(df):\n    # features from phunter\n    df['flight_dist_sig'] = df['FlightDistance']/df['FlightDistanceError']\n    df['flight_dist_sig2'] = (df['FlightDistance']/df['FlightDistanceError'])**2\n    df['NEW_IP_dira'] = df['IP']*df['dira']\n    df['p0p2_ip_ratio']=df['IP']/df['IP_p0p2']\n    df['p1p2_ip_ratio']=df['IP']/df['IP_p1p2']\n    df['DCA_MAX'] = df.loc[:, ['DOCAone', 'DOCAtwo', 'DOCAthree']].max(axis=1)\n    df['iso_bdt_min'] = df.loc[:, ['p0_IsoBDT', 'p1_IsoBDT', 'p2_IsoBDT']].min(axis=1)\n    df['iso_min'] = df.loc[:, ['isolationa', 'isolationb', 'isolationc','isolationd', 'isolatione', 'isolationf']].min(axis=1)\n    df['NEW_FD_LT']=df['FlightDistance']/df['LifeTime']\n    return df","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"3e74c10646744aaecd7dfbc8f432a35757260b07"},"cell_type":"markdown","source":"### 2. Add new potential features to datasets"},{"metadata":{"trusted":true,"_uuid":"753e2b8dd710dc023349809f5a261b6051a3f861"},"cell_type":"code","source":"train = add_features(train)\ntest = add_features(test)\ncheck_agreement = add_features(check_agreement)\ncheck_correlation = add_features(check_correlation)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"e4d0918464d5ec1a9ec6906af5aa1b5f16551480"},"cell_type":"markdown","source":"# Selecting features"},{"metadata":{"trusted":true,"_uuid":"b315f392a4154a0a3b65ce40b195848a61568fbb"},"cell_type":"code","source":"filter_out = ['id','min_ANNmuon', 'production', 'mass', 'signal', 'SPDhits', 'isolationb', 'isolationc', 'DOCAone', 'DOCAtwo', 'DOCAthree','CDF1', 'CDF2', 'CDF3']\n#filter_out = ['id', 'min_ANNmuon', 'production', 'mass', 'signal','SPDhits','p0_track_Chi2Dof','CDF1', 'CDF2', 'CDF3','isolationb', 'isolationc','p0_pt', 'p1_pt', 'p2_pt', 'p0_p', 'p1_p', 'p2_p', 'p0_eta', 'p1_eta', 'p2_eta','DOCAone', 'DOCAtwo', 'DOCAthree']\nfeatures = list(f for f in train.columns if f not in filter_out)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"62dd62aa02f6986f60ebf8a065e9f8f21a975ea9"},"cell_type":"markdown","source":"# Training XGBoost model"},{"metadata":{"trusted":true,"scrolled":true,"_uuid":"540d95ef53be58a72272ba37bf123c19b06bfca9"},"cell_type":"code","source":"print('Training XGBoost model...')\nmodel_xgb = xgb.XGBClassifier()\nparams ={'nthread': 4,\n         'objective': 'binary:logistic',\n         'max_depth' : 8,\n         'min_child_weight': 3,\n         'learning_rate' : 0.1, \n         'n_estimators' : 300, \n         'subsample' : 0.9, \n         'colsample_bytree' : 0.5,\n         'silent': 1}\nmodel_xgb.fit(train[features],train.signal)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"cf7ef2340903353f406d97405a06f0a9a70b3653"},"cell_type":"markdown","source":"# Predict test, create file for kaggle"},{"metadata":{"trusted":true,"_uuid":"8b358a50e5f4f9ddc44a39e2cbaa0fe64b2b8865"},"cell_type":"code","source":"pred_test = model_xgb.predict_proba(test[features])[:,1]\nresult = pd.DataFrame({'id': test.id})\nresult['prediction'] = pred_test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"994c45df62f4921d61ec3c4148ca9eb0f7f40adb"},"cell_type":"code","source":"result.to_csv('submission_nacho.csv', index=False, sep=',')","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}