{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## CatBoost HyperParameter Tuning with OPTUNA\n#### (For Beginners)","metadata":{}},{"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 loadss\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 20GB 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"full_train = pd.read_csv(\"/kaggle/input/riiid-test-answer-prediction/train.csv\",nrows=20000)\nquestions = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/questions.csv')\nlectures = pd.read_csv('/kaggle/input/riiid-test-answer-prediction/lectures.csv')","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"features = ['row_id', 'timestamp', 'user_id', 'content_id', 'content_type_id',\n       'task_container_id', 'user_answer',\n       'prior_question_elapsed_time']\ntarget = ['answered_correctly']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"full_train = full_train.dropna()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = full_train[features]\ny = full_train[target]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = np.array(X)\ny = np.array(y)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import catboost as cb\nimport optuna\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\ndef objective(trial):\n    train_x, valid_x, train_y, valid_y = train_test_split(X,y, test_size=0.3)\n\n    param = {\n        \"objective\": trial.suggest_categorical(\"objective\", [\"Logloss\", \"CrossEntropy\"]),\n        \"colsample_bylevel\": trial.suggest_float(\"colsample_bylevel\", 0.01, 0.1),\n        \"depth\": trial.suggest_int(\"depth\", 1, 12),\n        \"boosting_type\": trial.suggest_categorical(\"boosting_type\", [\"Ordered\", \"Plain\"]),\n        \"bootstrap_type\": trial.suggest_categorical(\n            \"bootstrap_type\", [\"Bayesian\", \"Bernoulli\", \"MVS\"]\n        ),\n        \"used_ram_limit\": \"3gb\",\n    }\n\n    if param[\"bootstrap_type\"] == \"Bayesian\":\n        param[\"bagging_temperature\"] = trial.suggest_float(\"bagging_temperature\", 0, 10)\n    elif param[\"bootstrap_type\"] == \"Bernoulli\":\n        param[\"subsample\"] = trial.suggest_float(\"subsample\", 0.1, 1)\n\n    gbm = cb.CatBoostClassifier(**param)\n\n    gbm.fit(train_x, train_y, eval_set=[(valid_x, valid_y)], verbose=0, early_stopping_rounds=100)\n\n    preds = gbm.predict(valid_x)\n    pred_labels = np.rint(preds)\n    accuracy = accuracy_score(valid_y, pred_labels)\n    return accuracy","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"study = optuna.create_study(direction=\"maximize\")\nstudy.optimize(objective, n_trials=50, timeout=600)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Number of finished trials: {}\".format(len(study.trials)))\n\nprint(\"Best trial:\")\ntrial = study.best_trial\n\nprint(\"  Value: {}\".format(trial.value))\n\nprint(\"  Params: \")\nfor key, value in trial.params.items():\n    print(\"    {}: {}\".format(key, value))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### You can use these parameters to increase the metric score","metadata":{}}]}