{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train=pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/train.csv\")\ntest=pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/test.csv\")\n\ntrain.iloc[:,4:22].head()\n#test.head()\n#train[\"ord_5\"].unique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train2=train.drop(\"id\",axis=1)\ntest2=test.drop(\"id\",axis=1)\n\n# ord1_dic\nord1_dic={\"Novice\":1, \"Contributor\":2, \"Expert\":3, \"Master\":4, \"Grandmaster\":5}\ntrain2[\"ord_1\"] = train2[\"ord_1\"].replace(ord1_dic)\ntest2[\"ord_1\"] = test2[\"ord_1\"].replace(ord1_dic)\n\n# ord2_dic\nord2_dic={\"Freezing\":1, \"Cold\":2, \"Warm\":3, \"Hot\":4, \"Lava Hot\":5, \"Boiling Hot\":6}\ntrain2[\"ord_2\"] = train2[\"ord_2\"].replace(ord2_dic)\ntest2[\"ord_2\"] = test2[\"ord_2\"].replace(ord2_dic)\n\n# apply lc\nfrom sklearn import preprocessing\nfor c in [\"bin_3\",\"bin_4\",\"nom_0\",\"nom_1\",\"nom_2\",\"nom_3\",\"nom_4\",\"nom_5\",\n          \"nom_6\",\"nom_7\",\"nom_8\",\"nom_9\",\"ord_3\",\"ord_4\",\"ord_5\"]:\n    le = preprocessing.LabelEncoder()\n    le.fit(pd.concat([train2[c].fillna(\"NA\"),test2[c].fillna(\"NA\")])) \n    train2[c] = le.transform(train2[c].fillna(\"NA\"))    \n    test2[c] = le.transform(test2[c].fillna(\"NA\"))\n    \ntrain2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# split to X and y\nlabel=\"target\"\ntrain_y = train2[label]\ntrain_X = train2.drop(label, axis=1)\ntest_X = test2\n\ntrain_X.head()\n#test2.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import lightgbm as lgb\nlgb=lgb.LGBMClassifier(random_state=334)\ngbm=lgb.fit(train_X,train_y)\ntest_y_lgb=gbm.predict_proba(test_X)[:,1]\n\nimport xgboost as xgb\nxgb = xgb.XGBClassifier(random_state=334)\ngbs = xgb.fit(train_X, train_y)\ntest_y_xgb = gbs.predict_proba(test_X)[:,1]\n\nw=0.8\ntest_y=w*test_y_lgb+(1-w)*test_y_xgb\nsubmission = pd.DataFrame({'id': test.id, 'target': test_y})\nsubmission.to_csv('submission_lxgb82_allattrs_ord12.csv', index=False)\nsubmission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sample=pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/sample_submission.csv\")\n#sample","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}