{"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":"df_train = pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/train.csv\")\ndf_test = pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split, StratifiedKFold, GridSearchCV\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.linear_model import LogisticRegression\nfrom category_encoders import *\nfrom xgboost import XGBClassifier\n\nX = df_train.drop([\"id\", \"target\"], axis=1)\ny = df_train['target']\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=1993)\ncols = list(X_train.columns)\n\nencoder = TargetEncoder(cols=cols)\nlr_est = LogisticRegression()\n\npipeline = Pipeline([\n    (\"Encoder\", encoder),\n    (\"Estimator\", lr_est)\n])\n\nparams = {\n    \"Encoder__smoothing\" : [0.1, 0.3, 0.9],\n    \"Encoder__min_samples_leaf\" : [10,20,100],\n}\n\nsearch = GridSearchCV(pipeline, params, verbose=1,cv=StratifiedKFold(n_splits=5).get_n_splits([X_train, y_train]))\nsearch.fit(X_train, y_train)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_results = pd.DataFrame(search.cv_results_)\ndf_results","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pipeline = Pipeline([\n    (\"Encoder\", encoder),\n    (\"Estimator\", lr_est)\n])\n\nparams = {\n    \"Encoder__smoothing\" : [0.1],\n    \"Encoder__min_samples_leaf\" : [100],\n    \"Estimator__C\": [0.1, 0.5, 1.0],\n    \"Estimator__solver\": [\"lbfgs\", \"liblinear\"]\n}\n\nsearch = GridSearchCV(pipeline, params, verbose=1,cv=3)\nsearch.fit(X_train, y_train)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_results = pd.DataFrame(search.cv_results_)\ndf_results","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"final_pipeline = Pipeline([\n    (\"Encoder\", TargetEncoder(cols=cols, smoothing=0.1, min_samples_leaf=100)),\n    (\"Estimator\", LogisticRegression(solver=\"liblinear\"))\n])\n\nfinal_pipeline.fit(X_train, y_train)\ntrain_preds = final_pipeline.predict_proba(X_train)[:,1]\ntest_preds = final_pipeline.predict_proba(X_test)[:,1]\n\ntrain_roc = roc_auc_score(y_train, train_preds)\ntest_roc = roc_auc_score(y_test, test_preds)\nprint(\"Train ROC = {:.3f}\".format(train_roc))\nprint(\"Test ROC = {:.3f}\".format(test_roc))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"final_pipeline.fit(X, y)\nfinal_preds = final_pipeline.predict_proba(df_test.drop('id', axis=1))[:,1]\ndf_preds = pd.DataFrame({'id': df_test['id'], 'target': final_preds})\ndf_preds.to_csv(\"LogReg_TargetEnc_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":1}