{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## <span style=\"color:green\"> **ДЗ2 по соревновательному анализу данных** </span>\n### <span style=\"color:green\"> **Марченко Мария 204** </span>\n\n<span style=\"color:green\"> Этот ноутбук - форк отсюда -> https://www.kaggle.com/code/jetakow/home-credit-2024-starter-notebook </span>\n\n* <span style=\"color:green\"> Было:                                 0.3 </span>\n\n* <span style=\"color:green\"> Стало:         0.492 </span>","metadata":{"execution":{"iopub.status.busy":"2024-03-17T13:43:39.597629Z","iopub.execute_input":"2024-03-17T13:43:39.598080Z","iopub.status.idle":"2024-03-17T13:43:39.605454Z","shell.execute_reply.started":"2024-03-17T13:43:39.598046Z","shell.execute_reply":"2024-03-17T13:43:39.604208Z"}}},{"cell_type":"markdown","source":"### <span style=\"color:green\"> Изменения в соревновании: </span>\n\n* <span style=\"color:green\"> Метрика штрафует за падение качества при росте WEEK_NUM, а также за дисперсию этого качества. </span>\n    \n* <span style=\"color:green\"> Поэтому можно было написать такую модель, которая специально бы хуже работала на маленьких значениях WEEK_NUM, за счет чего немного потерять в AUC части, но зато избежать штрафа за падение качества. Такое \"улучшение\" модели было не на руку спонсорам соревнования, поэтому в перезапущенном соревновании из тестовой выборки WEEK_NUM и MONTH сделали константным, чтобы участники не могли подобным образом модифицировать поведении модели. </span>\n\n\n### <span style=\"color:green\"> Feature engineering: </span>\n* <span style=\"color:green\"> Добавим признаки с самым большим весом из этого EDA -> https://www.kaggle.com/code/liamhealy/lightgbm-feature-importance-all-datasets#Static-0 </span> \n\n* <span style=\"color:green\"> Поскольку у признаков из debit_card и deposit AUC score там же 0.5, их не добавляем </span>\n\n* <span style=\"color:green\"> Из вот этого EDA -> https://www.kaggle.com/code/sergiosaharovskiy/home-credit-crms-2024-eda-and-submission  видно, что в credit_bureau_a... много null и они весят несколько ГБ. Не добавляем их тоже, тк это приведет к нестабильному и долгообучающемуся решению</span>\n\n### <span style=\"color:green\"> Гиперпараметры и другое: </span>\n* <span style=\"color:green\"> Добавила перебор гиперпараметров для LightGBM </span>\n* <span style=\"color:green\"> Попробовала настроить CatBoost вместо LightGBM на GPU, тоже лучше не стало </span>\n* <span style=\"color:green\"> Попробовала добавить unbalanced = True, поскольку классы не сбалансированы, качество не изменилось </span>","metadata":{}},{"cell_type":"markdown","source":"# Example Notebook\n\nWelcome to the example notebook for the Home Credit Kaggle competition. The goal of this competition is to determine how likely a customer is going to default on an issued loan. The main difference between the [first](https://www.kaggle.com/c/home-credit-default-risk) and this competition is that now your submission will be scored with a custom metric that will take into account how well the model performs in future. A decline in performance will be penalized. The goal is to create a model that is stable and performs well in the future.\n\nIn this notebook you will see how to:\n* Load the data\n* Join tables with Polars - a DataFrame library implemented in Rust language, designed to be blazingy fast and memory efficient.  \n* Create simple aggregation features\n* Train a LightGBM model\n* Create a submission table\n\n## Load the data","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score \n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:55:53.963706Z","iopub.execute_input":"2024-03-17T20:55:53.964148Z","iopub.status.idle":"2024-03-17T20:55:53.971588Z","shell.execute_reply.started":"2024-03-17T20:55:53.964113Z","shell.execute_reply":"2024-03-17T20:55:53.970039Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n    # implement here all desired dtypes for tables\n    # the following is just an example\n    for col in df.columns:\n        # last letter of column name will help you determine the type\n        if col[-1] in (\"P\", \"A\", \"L\"):\n            try:\n                df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n            except:\n                pass\n    return df\n\ndef convert_strings(df: pd.DataFrame) -> pd.DataFrame:\n    for col in df.columns:  \n        if df[col].dtype.name in ['object', 'string']:\n            df[col] = df[col].astype(\"string\").astype('category')\n            current_categories = df[col].cat.categories\n            new_categories = current_categories.to_list() + [\"Unknown\"]\n            new_dtype = pd.CategoricalDtype(categories=new_categories, ordered=True)\n            df[col] = df[col].astype(new_dtype)\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:55:53.974856Z","iopub.execute_input":"2024-03-17T20:55:53.975394Z","iopub.status.idle":"2024-03-17T20:55:53.988749Z","shell.execute_reply.started":"2024-03-17T20:55:53.975344Z","shell.execute_reply":"2024-03-17T20:55:53.987227Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_basetable = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\ntrain_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_1.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntrain_static_cb = pl.read_csv(dataPath + \"csv_files/train/train_static_cb_0.csv\").pipe(set_table_dtypes)\ntrain_person_1 = pl.read_csv(dataPath + \"csv_files/train/train_person_1.csv\").pipe(set_table_dtypes) \ntrain_credit_bureau_b_1 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_1.csv\").pipe(set_table_dtypes)\ntrain_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_2.csv\").pipe(set_table_dtypes) \ntrain_credit_debit_card_1 = pl.read_csv(dataPath + \"csv_files/train/train_debitcard_1.csv\").pipe(set_table_dtypes) \ntrain_credit_deposit_1 = pl.read_csv(dataPath + \"csv_files/train/train_deposit_1.csv\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:55:53.990855Z","iopub.execute_input":"2024-03-17T20:55:53.991373Z","iopub.status.idle":"2024-03-17T20:56:13.123068Z","shell.execute_reply.started":"2024-03-17T20:55:53.991324Z","shell.execute_reply":"2024-03-17T20:56:13.122187Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_basetable = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\ntest_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_1.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_2.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntest_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\ntest_person_1 = pl.read_csv(dataPath + \"csv_files/test/test_person_1.csv\").pipe(set_table_dtypes) \ntest_credit_bureau_b_1 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_1.csv\").pipe(set_table_dtypes)\ntest_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_2.csv\").pipe(set_table_dtypes) \ntest_credit_debit_card_1 = pl.read_csv(dataPath + \"csv_files/test/test_debitcard_1.csv\").pipe(set_table_dtypes) \ntest_credit_deposit_1 = pl.read_csv(dataPath + \"csv_files/test/test_deposit_1.csv\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:13.124908Z","iopub.execute_input":"2024-03-17T20:56:13.126389Z","iopub.status.idle":"2024-03-17T20:56:13.235926Z","shell.execute_reply.started":"2024-03-17T20:56:13.126340Z","shell.execute_reply":"2024-03-17T20:56:13.234643Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature engineering\n\nIn this part, we can see a simple example of joining tables via `case_id`. Here the loading and joining is done with polars library. Polars library is blazingly fast and has much smaller memory footprint than pandas. ","metadata":{}},{"cell_type":"code","source":"person_important = [\"registaddr_district_1083M\",\n                    \"education_927M\",\n                    \"mainoccupationinc_384A\", \n                    #\"incometype_1044T\",\n                    \"empladdr_district_926M\"]\n\ntrain_person_fin = train_person_1.select([\"case_id\", \"num_group1\"] + person_important).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\")\n\ntest_person_fin = test_person_1.select([\"case_id\", \"num_group1\"] + person_important).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\")","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:13.238058Z","iopub.execute_input":"2024-03-17T20:56:13.239007Z","iopub.status.idle":"2024-03-17T20:56:13.376082Z","shell.execute_reply.started":"2024-03-17T20:56:13.238926Z","shell.execute_reply":"2024-03-17T20:56:13.375073Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cb_important = [#\"dateofbirth_337D\",\n               \"pmtssum_45A\",\n               \"education_1103M\",\n               #\"riskassesment_940T\",\n               \"pmtaverage_3A\",\n               \"pmtaverage_4527227A\",\n               \"days30_165L\",\n               \"days360_512L\",\n               \"days180_256L\"]\n               #\"responsedate_4527233D\"]\ntrain_cb_fin = train_static_cb.select([\"case_id\"]+cb_important)\ntest_cb_fin = test_static_cb.select([\"case_id\"]+cb_important)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:13.378061Z","iopub.execute_input":"2024-03-17T20:56:13.379039Z","iopub.status.idle":"2024-03-17T20:56:13.401329Z","shell.execute_reply.started":"2024-03-17T20:56:13.378987Z","shell.execute_reply":"2024-03-17T20:56:13.399918Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"static_important = ['price_1097A',\n 'mobilephncnt_593L',\n 'pmtnum_254L',\n 'avgdpdtolclosure24_3658938P',\n 'numrejects9m_859L',\n 'cntpmts24_3658933L',\n 'numinstunpaidmax_3546851L',\n 'eir_270L',\n 'numinstlsallpaid_934L',\n #'lastdelinqdate_224D',\n 'maxdbddpdtollast12m_3658940P',\n 'numincomingpmts_3546848L',\n 'pctinstlsallpaidlate1d_3546856L',\n 'maxdpdlast3m_392P',\n 'monthsannuity_845L',\n #'datelastinstal40dpd_247D',\n 'lastrejectreason_759M']\ntrain_static_fin = train_static.select([\"case_id\"]+static_important)\ntest_static_fin = test_static.select([\"case_id\"]+static_important)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:13.403361Z","iopub.execute_input":"2024-03-17T20:56:13.403870Z","iopub.status.idle":"2024-03-17T20:56:13.430657Z","shell.execute_reply.started":"2024-03-17T20:56:13.403821Z","shell.execute_reply":"2024-03-17T20:56:13.429441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_bureau_fin = train_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\"))\n\ntest_bureau_fin = test_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\"))","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:13.434695Z","iopub.execute_input":"2024-03-17T20:56:13.435141Z","iopub.status.idle":"2024-03-17T20:56:13.476539Z","shell.execute_reply.started":"2024-03-17T20:56:13.435102Z","shell.execute_reply":"2024-03-17T20:56:13.475472Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''\ndef handle_dates(df):\n    for col in df.columns:\n        if col[-1] in (\"D\",):\n            df = df.with_columns(pl.col(col) - pl.col(\"date_decision\"))\n            df = df.with_columns(pl.col(col).dt.total_days())\n    df = df.drop(\"date_decision\", \"MONTH\")\n    return df\n'''","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:13.481806Z","iopub.execute_input":"2024-03-17T20:56:13.482220Z","iopub.status.idle":"2024-03-17T20:56:13.489052Z","shell.execute_reply.started":"2024-03-17T20:56:13.482186Z","shell.execute_reply":"2024-03-17T20:56:13.487653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = train_basetable.join(\n    train_static_fin, how=\"left\", on=\"case_id\"\n).join(\n    train_cb_fin, how=\"left\", on=\"case_id\"\n).join(\n    train_person_fin, how=\"left\", on=\"case_id\"\n).join(\n    train_bureau_fin, how=\"left\", on=\"case_id\"\n)#.join(\n#    train_credit_debit_card_1, how=\"left\", on=\"case_id\"\n#)#.join(\n#    train_credit_deposit_1, how=\"left\", on=\"case_id\"\n#)\n\ndata_submission = test_basetable.join(\n    test_static_fin, how=\"left\", on=\"case_id\"\n).join(\n    test_cb_fin, how=\"left\", on=\"case_id\"\n).join(\n    test_person_fin, how=\"left\", on=\"case_id\"\n).join(\n    test_bureau_fin, how=\"left\", on=\"case_id\"\n)#.join(\n#    test_credit_debit_card_1, how=\"left\", on=\"case_id\"\n#)#.join(\n#    test_credit_deposit_1, how=\"left\", on=\"case_id\"\n#)\n\n#data = data.pipe(handle_dates)\n#data_submission = data_submission.pipe(handle_dates)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:13.491228Z","iopub.execute_input":"2024-03-17T20:56:13.492175Z","iopub.status.idle":"2024-03-17T20:56:14.432206Z","shell.execute_reply.started":"2024-03-17T20:56:13.492125Z","shell.execute_reply":"2024-03-17T20:56:14.431256Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:14.433182Z","iopub.execute_input":"2024-03-17T20:56:14.433501Z","iopub.status.idle":"2024-03-17T20:56:14.461091Z","shell.execute_reply.started":"2024-03-17T20:56:14.433473Z","shell.execute_reply":"2024-03-17T20:56:14.460062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_ids = data[\"case_id\"].unique().shuffle(seed=1)\ncase_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.6, random_state=1)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)\n\ncols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)\n\nprint(cols_pred)\n\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    return (\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\n    )\n\nbase_train, X_train, y_train = from_polars_to_pandas(case_ids_train)\nbase_valid, X_valid, y_valid = from_polars_to_pandas(case_ids_valid)\nbase_test, X_test, y_test = from_polars_to_pandas(case_ids_test)\ncbflag = False\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:14.462373Z","iopub.execute_input":"2024-03-17T20:56:14.463432Z","iopub.status.idle":"2024-03-17T20:56:23.880104Z","shell.execute_reply.started":"2024-03-17T20:56:14.463390Z","shell.execute_reply":"2024-03-17T20:56:23.874490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:23.885846Z","iopub.execute_input":"2024-03-17T20:56:23.889283Z","iopub.status.idle":"2024-03-17T20:56:24.855600Z","shell.execute_reply.started":"2024-03-17T20:56:23.889089Z","shell.execute_reply":"2024-03-17T20:56:24.852142Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:24.859779Z","iopub.execute_input":"2024-03-17T20:56:24.860882Z","iopub.status.idle":"2024-03-17T20:56:24.881496Z","shell.execute_reply.started":"2024-03-17T20:56:24.860735Z","shell.execute_reply":"2024-03-17T20:56:24.877607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training LightGBM\n\nMinimal example of LightGBM training is shown below.","metadata":{}},{"cell_type":"code","source":"lgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n'''\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    #\"is_unbalance\": True,\n    \"metric\": \"auc\",\n    \"max_depth\": 3,\n    \"num_leaves\": 31,\n    \"learning_rate\": 0.05,\n    \"feature_fraction\": 0.9,\n    \"bagging_fraction\": 0.8,\n    \"bagging_freq\": 5,\n    \"n_estimators\": 1000,\n    \"verbose\": -1,\n    #\"device\": \"gpu\",\n    #'gpu_platform_id': 0,\n    #'gpu_device_id': 0,\n}\n\ngbm = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,\n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n)\n'''","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:24.886859Z","iopub.execute_input":"2024-03-17T20:56:24.888217Z","iopub.status.idle":"2024-03-17T20:56:24.915875Z","shell.execute_reply.started":"2024-03-17T20:56:24.888103Z","shell.execute_reply":"2024-03-17T20:56:24.911762Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import optuna\n\ndef objective(trial):\n    params = {\n        \"objective\": \"binary\",\n        \"metric\": \"auc\",\n        \"n_estimators\": 1000,\n        \"verbosity\": -1,\n        \"max_depth\": trial.suggest_int(\"max_depth\", 3, 6),\n        \"num_leaves\": trial.suggest_int(\"num_leaves\", 15, 50),\n        \"learning_rate\": trial.suggest_float(\"learning_rate\", 0.001, 0.1),\n        \"feature_fraction\": 0.9,\n        \"bagging_fraction\": 0.8,\n        \"bagging_freq\": 5,\n    }\n\n    gbm = lgb.train(\n        params,\n        lgb_train,\n        valid_sets=lgb_valid,\n        callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n    )\n    \n    predictions = gbm.predict(X_valid, num_iteration=gbm.best_iteration)\n    return roc_auc_score(base_valid[\"target\"], predictions)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:24.921734Z","iopub.execute_input":"2024-03-17T20:56:24.923451Z","iopub.status.idle":"2024-03-17T20:56:24.951102Z","shell.execute_reply.started":"2024-03-17T20:56:24.923342Z","shell.execute_reply":"2024-03-17T20:56:24.948036Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# study = optuna.create_study(direction='maximize')\n# study.optimize(objective, n_trials=20)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:24.955981Z","iopub.execute_input":"2024-03-17T20:56:24.957270Z","iopub.status.idle":"2024-03-17T20:56:24.969919Z","shell.execute_reply.started":"2024-03-17T20:56:24.957201Z","shell.execute_reply":"2024-03-17T20:56:24.967092Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# print('Best hyperparameters:', study.best_params)\n# print('Best AUC:', study.best_value)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:24.974561Z","iopub.execute_input":"2024-03-17T20:56:24.975907Z","iopub.status.idle":"2024-03-17T20:56:24.988791Z","shell.execute_reply.started":"2024-03-17T20:56:24.975832Z","shell.execute_reply":"2024-03-17T20:56:24.985144Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"params = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    #\"is_unbalance\": True,\n    \"metric\": \"auc\",\n    \"max_depth\": 3,\n    \"num_leaves\": 30,\n    \"learning_rate\": 0.05,\n    \"feature_fraction\": 0.9,\n    \"bagging_fraction\": 0.8,\n    \"bagging_freq\": 5,\n    \"n_estimators\": 1000,\n    \"verbose\": -1,\n    #\"device\": \"gpu\",\n    #'gpu_platform_id': 0,\n    #'gpu_device_id': 0,\n}\n\ngbm = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,\n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:56:24.993553Z","iopub.execute_input":"2024-03-17T20:56:24.995356Z","iopub.status.idle":"2024-03-17T20:57:52.311771Z","shell.execute_reply.started":"2024-03-17T20:56:24.995105Z","shell.execute_reply":"2024-03-17T20:57:52.310254Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lgb.plot_importance(gbm, max_num_features=50, height=0.8)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:57:52.314008Z","iopub.execute_input":"2024-03-17T20:57:52.314890Z","iopub.status.idle":"2024-03-17T20:57:53.153347Z","shell.execute_reply.started":"2024-03-17T20:57:52.314840Z","shell.execute_reply":"2024-03-17T20:57:53.151921Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Evaluation with AUC and then comparison with the stability metric is shown below.","metadata":{}},{"cell_type":"code","source":"for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = gbm.predict(X, num_iteration=gbm.best_iteration)\n    base[\"score\"] = y_pred\n\nprint(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}') \nprint(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}') \nprint(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:57:53.155253Z","iopub.execute_input":"2024-03-17T20:57:53.156159Z","iopub.status.idle":"2024-03-17T20:58:17.122290Z","shell.execute_reply.started":"2024-03-17T20:57:53.156109Z","shell.execute_reply":"2024-03-17T20:58:17.120976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def gini_stability(base, w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", \"score\"]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", \"score\"]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[\"score\"])-1).tolist()\n    \n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n\nstability_score_train = gini_stability(base_train)\nstability_score_valid = gini_stability(base_valid)\nstability_score_test = gini_stability(base_test)\n\nprint(f'The stability score on the train set is: {stability_score_train}') \nprint(f'The stability score on the valid set is: {stability_score_valid}') \nprint(f'The stability score on the test set is: {stability_score_test}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:58:17.123699Z","iopub.execute_input":"2024-03-17T20:58:17.124062Z","iopub.status.idle":"2024-03-17T20:58:18.250023Z","shell.execute_reply.started":"2024-03-17T20:58:17.124031Z","shell.execute_reply":"2024-03-17T20:58:18.248738Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission\n\nScoring the submission dataset is below, we need to take care of new categories. Then we save the score as a last step. ","metadata":{}},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\n\nfor col in categorical_cols:\n    train_categories = set(X_train[col].cat.categories)\n    submission_categories = set(X_submission[col].cat.categories)\n    new_categories = submission_categories - train_categories\n    X_submission.loc[X_submission[col].isin(new_categories), col] = \"Unknown\"\n    new_dtype = pd.CategoricalDtype(categories=train_categories, ordered=True)\n    X_train[col] = X_train[col].astype(new_dtype)\n    X_submission[col] = X_submission[col].astype(new_dtype)\n\ny_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:58:18.254092Z","iopub.execute_input":"2024-03-17T20:58:18.254463Z","iopub.status.idle":"2024-03-17T20:58:18.312222Z","shell.execute_reply.started":"2024-03-17T20:58:18.254432Z","shell.execute_reply":"2024-03-17T20:58:18.311221Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"case_id\": data_submission[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:58:18.316658Z","iopub.execute_input":"2024-03-17T20:58:18.317041Z","iopub.status.idle":"2024-03-17T20:58:18.329273Z","shell.execute_reply.started":"2024-03-17T20:58:18.317004Z","shell.execute_reply":"2024-03-17T20:58:18.328148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"execution":{"iopub.status.busy":"2024-03-17T20:58:18.330875Z","iopub.execute_input":"2024-03-17T20:58:18.331223Z","iopub.status.idle":"2024-03-17T20:58:18.342163Z","shell.execute_reply.started":"2024-03-17T20:58:18.331194Z","shell.execute_reply":"2024-03-17T20:58:18.341328Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Best of luck, and most importantly, enjoy the process of learning and discovery! \n\n<img src=\"https://i.imgur.com/obVWIBh.png\" alt=\"Image\" width=\"700\"/>","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}