{"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":7602123,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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":"2024-02-21T05:24:53.023526Z","iopub.execute_input":"2024-02-21T05:24:53.023943Z","iopub.status.idle":"2024-02-21T05:24:53.029551Z","shell.execute_reply.started":"2024-02-21T05:24:53.023913Z","shell.execute_reply":"2024-02-21T05:24:53.028473Z"},"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\"):\n            df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n\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":"2024-02-21T05:24:54.202213Z","iopub.execute_input":"2024-02-21T05:24:54.202582Z","iopub.status.idle":"2024-02-21T05:24:54.209276Z","shell.execute_reply.started":"2024-02-21T05:24:54.202554Z","shell.execute_reply":"2024-02-21T05:24:54.208588Z"},"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_2 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_2.csv\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:24:55.299913Z","iopub.execute_input":"2024-02-21T05:24:55.301450Z","iopub.status.idle":"2024-02-21T05:25:05.290278Z","shell.execute_reply.started":"2024-02-21T05:24:55.301398Z","shell.execute_reply":"2024-02-21T05:25:05.289442Z"},"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_2 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_2.csv\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:25:05.294966Z","iopub.execute_input":"2024-02-21T05:25:05.297306Z","iopub.status.idle":"2024-02-21T05:25:05.355747Z","shell.execute_reply.started":"2024-02-21T05:25:05.297268Z","shell.execute_reply":"2024-02-21T05:25:05.354304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 'lastapprcommoditytypec_5251766M','lastrejectcommodtypec_5251769M','mastercontrexist_109L'","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:14:05.103645Z","iopub.execute_input":"2024-02-21T05:14:05.105031Z","iopub.status.idle":"2024-02-21T05:14:05.114616Z","shell.execute_reply.started":"2024-02-21T05:14:05.104992Z","shell.execute_reply":"2024-02-21T05:14:05.113855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# train_static['opencred_647L'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-02-21T04:00:46.195137Z","iopub.execute_input":"2024-02-21T04:00:46.195626Z","iopub.status.idle":"2024-02-21T04:00:46.248502Z","shell.execute_reply.started":"2024-02-21T04:00:46.195591Z","shell.execute_reply":"2024-02-21T04:00:46.247492Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# test_static['opencred_647L'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-02-21T04:00:48.511710Z","iopub.execute_input":"2024-02-21T04:00:48.512047Z","iopub.status.idle":"2024-02-21T04:00:48.520834Z","shell.execute_reply.started":"2024-02-21T04:00:48.512021Z","shell.execute_reply":"2024-02-21T04:00:48.519289Z"},"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":"def custom_mode(series):\n    mode_values = series.mode()\n    if mode_values.len() > 1:\n        return mode_values[0]\n    else:\n        return mode_values[0]\n\n# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or \n# also num_group2 column.\ntrain_person_1_feats_1 = train_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\n# Here num_group1=0 has special meaning, it is the person who applied for the loan.\ntrain_person_1_feats_2 = train_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\n\n# train_person_1_feats_3 = train_person_1.select(['case_id','mainoccupationinc_384A'])\n\n# feat_4 = train_person_1.select(['case_id', 'incometype_1044T'])\ntrain_person_1_feats_4 = train_person_1.select(['case_id', 'incometype_1044T','num_group1']).filter(\n  pl.col('num_group1')==0 \n).drop('num_group1')\n\n# train_person_1_feats_4 = train_person_1.groupby(\"case_id\").agg(pl.col(\"incometype_1044T\").mode()\n# )\n\n# feat_5 = train_person_1.select(['case_id', 'language1_981M'])\n# train_person_1_feats_5 = train_person_1.groupby(\"case_id\").agg(pl.col(\"language1_981M\").apply(custom_mode).alias(\"language1_981M_mode\")\n# )\ntrain_person_1_feats_5 = train_person_1.select(['case_id', 'language1_981M','num_group1']).filter(\n  pl.col('num_group1')==0\n).drop('num_group1')\n\n# Here we have num_goup1 and num_group2, so we need to aggregate again.\n# train_credit_bureau_b_2_feats = 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# )\n\n# We will process in this examples only A-type and M-type columns, so we need to select them.\n# 이지만 D빼고 다할거임 \nselected_static_cols = []\ndrop_static_cols = [\n    'lastst_736L',\n    'opencred_647L',\n    'paytype1st_925L',\n    'paytype_783L',\n    'price_1097A',\n    'commnoinclast6m_3546845L',\n#     'maxdpdfrom6mto36m_3546853P',\n#     'lastapplicationdate_877D',\n]\nconstant_imbalance_cols =[\n    'bankacctype_710L',\n    'commnoinclast6m_3546845L',\n    'deferredmnthsnum_166L',\n    'interestrategrace_34L',\n    'isdebitcard_729L',\n    'lastapprcommoditytypec_5251766M',\n    'lastrejectcommodtypec_5251769M',\n    'mastercontrelectronic_519L',\n    'mastercontrexist_109L',\n    'paytype1st_925L',\n    'paytype_783L',\n    'typesuite_864L',\n    'equalitydataagreement_891L',\n    'equalityempfrom_62L',\n    'isbidproductrequest_292L',\n    'opencred_647L'\n]\n\nfor col in train_static.columns:\n    if col[-1] in (\"A\"):\n        selected_static_cols.append(col)\n    if col[-1] in ('M','L') and col in constant_imbalance_cols:\n        selected_static_cols.append(col)\nprint(selected_static_cols)\n\nselected_static_cb_cols = []\nfor col in train_static_cb.columns:\n    if col[-1] in (\"A\",'M','L'):\n        selected_static_cb_cols.append(col)\nprint(selected_static_cb_cols)\n\n\ndata = train_basetable.join(\n    train_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_4, how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_5, how=\"left\", on=\"case_id\"\n)\n# join(\n#     train_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n# ).\n# .join(\n#     train_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n#)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:25:06.698069Z","iopub.execute_input":"2024-02-21T05:25:06.698437Z","iopub.status.idle":"2024-02-21T05:25:07.825294Z","shell.execute_reply.started":"2024-02-21T05:25:06.698411Z","shell.execute_reply":"2024-02-21T05:25:07.824435Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# train_person_1.shape","metadata":{"execution":{"iopub.status.busy":"2024-02-20T04:24:03.678070Z","iopub.execute_input":"2024-02-20T04:24:03.678668Z","iopub.status.idle":"2024-02-20T04:24:03.684938Z","shell.execute_reply.started":"2024-02-20T04:24:03.678637Z","shell.execute_reply":"2024-02-20T04:24:03.683922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#  train_person_1_feats_4['case_id'].is_duplicated","metadata":{"execution":{"iopub.status.busy":"2024-02-20T04:24:07.792609Z","iopub.execute_input":"2024-02-20T04:24:07.792977Z","iopub.status.idle":"2024-02-20T04:24:07.797172Z","shell.execute_reply.started":"2024-02-20T04:24:07.792947Z","shell.execute_reply":"2024-02-20T04:24:07.796359Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# data['cntincpaycont9m_3716944L']","metadata":{"execution":{"iopub.status.busy":"2024-02-20T10:13:29.581036Z","iopub.execute_input":"2024-02-20T10:13:29.581420Z","iopub.status.idle":"2024-02-20T10:13:29.589973Z","shell.execute_reply.started":"2024-02-20T10:13:29.581392Z","shell.execute_reply":"2024-02-20T10:13:29.588958Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#train_person_1_feats_6","metadata":{"execution":{"iopub.status.busy":"2024-02-20T04:55:35.319389Z","iopub.execute_input":"2024-02-20T04:55:35.320447Z","iopub.status.idle":"2024-02-20T04:55:35.327228Z","shell.execute_reply.started":"2024-02-20T04:55:35.320416Z","shell.execute_reply":"2024-02-20T04:55:35.326363Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_person_1_feats_1 = test_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\ntest_person_1_feats_2 = test_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\n# test_person_1_feats_3 = test_person_1.select(['case_id','mainoccupationinc_384A'])\n\nfeat_4 = test_person_1.select(['case_id', 'incometype_1044T'])\n# test_person_1_feats_4 = test_person_1.groupby(\"case_id\").agg(pl.col(\"incometype_1044T\").mode()\n# )\n\ntest_person_1_feats_4 = test_person_1.select(['case_id', 'incometype_1044T','num_group1']).filter(\n  pl.col('num_group1')==0\n).drop('num_group1')\n\n# feat_5 = test_person_1.select(['case_id', 'language1_981M'])\n# test_person_1_feats_5 = test_person_1.groupby(\"case_id\").agg(pl.col(\"language1_981M\").mode()\n# )\ntest_person_1_feats_5 = test_person_1.select(['case_id', 'language1_981M','num_group1']).filter(\n  pl.col('num_group1')==0\n).drop('num_group1')\n\n\n# test_credit_bureau_b_2_feats = 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\")\n# )\n\ndata_submission = test_basetable.join(\n    test_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_4, how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_5, how=\"left\", on=\"case_id\"\n)\n# .join(\n#     test_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n# )\n# .join(\n#     test_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n# )","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:25:13.701771Z","iopub.execute_input":"2024-02-21T05:25:13.702176Z","iopub.status.idle":"2024-02-21T05:25:13.717924Z","shell.execute_reply.started":"2024-02-21T05:25:13.702147Z","shell.execute_reply":"2024-02-21T05:25:13.716682Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#test_person_1_feats_7","metadata":{"execution":{"iopub.status.busy":"2024-02-20T09:19:37.329965Z","iopub.execute_input":"2024-02-20T09:19:37.330376Z","iopub.status.idle":"2024-02-20T09:19:37.335726Z","shell.execute_reply.started":"2024-02-20T09:19:37.330343Z","shell.execute_reply":"2024-02-20T09:19:37.334560Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# test_person_1_feats_1","metadata":{"execution":{"iopub.status.busy":"2024-02-19T08:08:22.606652Z","iopub.execute_input":"2024-02-19T08:08:22.607152Z","iopub.status.idle":"2024-02-19T08:08:22.617774Z","shell.execute_reply.started":"2024-02-19T08:08:22.607104Z","shell.execute_reply":"2024-02-19T08:08:22.616759Z"},"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#     if col == 'mainoccupationinc_384A_max':\n#         cols_pred.append(col)\n#     if col == 'mainoccupationinc_384A_any_selfemployed':\n#         cols_pred.append(col)\n#     if col == 'person_housetype':\n#         cols_pred.append(col)\n\n# 'mainoccupationinc_384A_max',\n#  'mainoccupationinc_384A_any_selfemployed',\n#  'person_housetype',\n#  'language1_981M_P10_39_147',\n#  'language1_981M_a55475b1',\n#  'language1_981M_P209_127_106'\n\n# print(len(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)\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:25:17.668173Z","iopub.execute_input":"2024-02-21T05:25:17.668531Z","iopub.status.idle":"2024-02-21T05:25:22.216499Z","shell.execute_reply.started":"2024-02-21T05:25:17.668505Z","shell.execute_reply":"2024-02-21T05:25:22.215174Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df.dtypes","metadata":{"execution":{"iopub.status.busy":"2024-02-21T02:07:01.998150Z","iopub.execute_input":"2024-02-21T02:07:01.998537Z","iopub.status.idle":"2024-02-21T02:07:02.008661Z","shell.execute_reply.started":"2024-02-21T02:07:01.998500Z","shell.execute_reply":"2024-02-21T02:07:02.007529Z"},"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":"2024-02-21T05:25:22.217666Z","iopub.execute_input":"2024-02-21T05:25:22.217903Z","iopub.status.idle":"2024-02-21T05:25:22.224321Z","shell.execute_reply.started":"2024-02-21T05:25:22.217881Z","shell.execute_reply":"2024-02-21T05:25:22.223292Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# X_train.columns\n# X_valid.columns","metadata":{"execution":{"iopub.status.busy":"2024-02-20T10:04:57.780676Z","iopub.execute_input":"2024-02-20T10:04:57.781009Z","iopub.status.idle":"2024-02-20T10:04:57.788391Z","shell.execute_reply.started":"2024-02-20T10:04:57.780982Z","shell.execute_reply":"2024-02-20T10:04:57.786896Z"},"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    \"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}\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":"2024-02-21T05:25:28.796786Z","iopub.execute_input":"2024-02-21T05:25:28.797195Z","iopub.status.idle":"2024-02-21T05:26:41.857191Z","shell.execute_reply.started":"2024-02-21T05:25:28.797152Z","shell.execute_reply":"2024-02-21T05:26:41.855930Z"},"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":"2024-02-21T05:26:41.858970Z","iopub.execute_input":"2024-02-21T05:26:41.859295Z","iopub.status.idle":"2024-02-21T05:27:01.805206Z","shell.execute_reply.started":"2024-02-21T05:26:41.859269Z","shell.execute_reply":"2024-02-21T05:27:01.804470Z"},"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":"2024-02-21T05:27:01.806235Z","iopub.execute_input":"2024-02-21T05:27:01.807087Z","iopub.status.idle":"2024-02-21T05:27:02.596791Z","shell.execute_reply.started":"2024-02-21T05:27:01.807053Z","shell.execute_reply":"2024-02-21T05:27:02.595909Z"},"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":"# # 데이터 타입 일치 여부 확인\n# dtype_match = X_train.dtypes == X_submission.dtypes\n\n# if dtype_match.all():\n#     print(\"데이터 타입이 일치합니다.\")\n# else:\n#     print(\"데이터 타입이 일치하지 않습니다.\")\n    \n#     # 불일치한 열과 데이터 타입 출력\n#     mismatched_cols = X_train.columns[~dtype_match].tolist()\n#     for col in mismatched_cols:\n#         print(f\"데이터 타입 불일치 - 열: {col}, 훈련 데이터셋: {X_train[col].dtype}, 제출 데이터셋: {X_submission[col].dtype}\")","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:19:46.315296Z","iopub.execute_input":"2024-02-21T05:19:46.315964Z","iopub.status.idle":"2024-02-21T05:19:46.324025Z","shell.execute_reply.started":"2024-02-21T05:19:46.315925Z","shell.execute_reply":"2024-02-21T05:19:46.322448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\ndtype_match = X_train.dtypes == X_submission.dtypes\n # 불일치한 열과 데이터 타입 출력\nmismatched_cols = X_train.columns[~dtype_match].tolist()\n    \n    # 불일치한 열에 대해 pd.to_numeric 적용\nfor col in mismatched_cols:\n    if X_submission[col].dtype == 'category':\n            # 'object' 타입인 경우에만 pd.to_numeric 적용\n        X_submission[col] = pd.to_numeric(X_submission[col], errors='coerce')\n\n# X_submission['language1_981M']= pd.to_numeric(X_submission['language1_981M'], errors='coerce')                                \ny_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-02-21T05:27:02.598314Z","iopub.execute_input":"2024-02-21T05:27:02.598552Z","iopub.status.idle":"2024-02-21T05:27:02.670733Z","shell.execute_reply.started":"2024-02-21T05:27:02.598531Z","shell.execute_reply":"2024-02-21T05:27:02.669461Z"},"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":"2024-02-21T05:27:02.672467Z","iopub.execute_input":"2024-02-21T05:27:02.672932Z","iopub.status.idle":"2024-02-21T05:27:02.682327Z","shell.execute_reply.started":"2024-02-21T05:27:02.672889Z","shell.execute_reply":"2024-02-21T05:27:02.680683Z"},"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":{}}]}