{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","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":30664,"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":"2024-03-18T14:05:13.505699Z","iopub.execute_input":"2024-03-18T14:05:13.506843Z","iopub.status.idle":"2024-03-18T14:05:15.885987Z","shell.execute_reply.started":"2024-03-18T14:05:13.506804Z","shell.execute_reply":"2024-03-18T14:05:15.884834Z"},"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', 'bool']:\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":"2024-03-18T14:12:03.057833Z","iopub.execute_input":"2024-03-18T14:12:03.058278Z","iopub.status.idle":"2024-03-18T14:12:03.067584Z","shell.execute_reply.started":"2024-03-18T14:12:03.058245Z","shell.execute_reply":"2024-03-18T14:12:03.066632Z"},"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) \ntrain_prev_submission = pl.read_csv(dataPath + \"csv_files/train/train_applprev_1_1.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:12:05.623952Z","iopub.execute_input":"2024-03-18T14:12:05.624387Z","iopub.status.idle":"2024-03-18T14:12:28.221278Z","shell.execute_reply.started":"2024-03-18T14:12:05.624347Z","shell.execute_reply":"2024-03-18T14:12:28.220133Z"},"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) \ntest_prev_submission = pl.read_csv(dataPath + \"csv_files/test/test_applprev_1_1.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:12:28.223038Z","iopub.execute_input":"2024-03-18T14:12:28.224127Z","iopub.status.idle":"2024-03-18T14:12:28.273846Z","shell.execute_reply.started":"2024-03-18T14:12:28.224089Z","shell.execute_reply":"2024-03-18T14:12:28.272758Z"},"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":"train_prev_app = train_prev_submission.group_by(\"case_id\").agg(\n    pl.col(\"childnum_21L\").max().alias(\"num_of_children_beforE\"),\n    (pl.col(\"familystate_726L\") == 'MARRIED').max().alias(\"was_marrieD\"),\n    (pl.col(\"familystate_726L\") == 'SINGLE').max().alias(\"was_singlE\")   \n)\ntrain_person_1_feats_1 = train_person_1.group_by(\"case_id\").agg(\n    (pl.col(\"birth_259D\") > \"1990\").max().alias(\"is_an_adulT\"),\n    (pl.col(\"familystate_447L\") == \"SINGLE\").max().alias(\"is_singlE\"),\n    (pl.col(\"familystate_447L\") == \"MARRIED\").max().alias(\"is_marrieD\"),\n    pl.col(\"childnum_185L\").max().alias(\"num_children_noW\")\n\n\n)\n# We will process in this examples only A-type and M-type columns, so we need to select them.\nselected_static_cols = []\nfor col in train_static.columns:\n    if col[-1] in (\"A\", \"M\"):\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\"):\n        selected_static_cb_cols.append(col)\nprint(selected_static_cb_cols)\n\n# Join all tables together.\ndata = train_basetable.join(\n    train_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    train_prev_app, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:12:28.275390Z","iopub.execute_input":"2024-03-18T14:12:28.275735Z","iopub.status.idle":"2024-03-18T14:12:31.816445Z","shell.execute_reply.started":"2024-03-18T14:12:28.275672Z","shell.execute_reply":"2024-03-18T14:12:31.815573Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_prev_app = test_prev_submission.group_by(\"case_id\").agg(\n    pl.col(\"childnum_21L\").max().alias(\"num_of_children_beforE\"),\n    (pl.col(\"familystate_726L\") == 'MARRIED').max().alias(\"was_marrieD\"),\n    (pl.col(\"familystate_726L\") == 'SINGLE').max().alias(\"was_singlE\")   \n)\ntest_person_1_feats_1 = test_person_1.group_by(\"case_id\").agg(\n    (pl.col(\"birth_259D\") > \"1990\").max().alias(\"is_an_adulT\"),\n    (pl.col(\"familystate_447L\") == \"SINGLE\").max().alias(\"is_singlE\"),\n    (pl.col(\"familystate_447L\") == \"MARRIED\").max().alias(\"is_marrieD\"),\n    pl.col(\"childnum_185L\").max().alias(\"num_children_noW\")\n\n\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_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    test_prev_app, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:12:31.818667Z","iopub.execute_input":"2024-03-18T14:12:31.818999Z","iopub.status.idle":"2024-03-18T14:12:31.837241Z","shell.execute_reply.started":"2024-03-18T14:12:31.818971Z","shell.execute_reply":"2024-03-18T14:12:31.836075Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"set(data.columns) - set(data_submission.columns)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:12:31.841596Z","iopub.execute_input":"2024-03-18T14:12:31.843707Z","iopub.status.idle":"2024-03-18T14:12:31.852479Z","shell.execute_reply.started":"2024-03-18T14:12:31.843672Z","shell.execute_reply":"2024-03-18T14:12:31.851655Z"},"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)\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:12:55.801416Z","iopub.execute_input":"2024-03-18T14:12:55.801796Z","iopub.status.idle":"2024-03-18T14:13:08.538181Z","shell.execute_reply.started":"2024-03-18T14:12:55.801767Z","shell.execute_reply":"2024-03-18T14:13:08.537239Z"},"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":"2024-03-18T14:13:08.539959Z","iopub.execute_input":"2024-03-18T14:13:08.540664Z","iopub.status.idle":"2024-03-18T14:13:08.547351Z","shell.execute_reply.started":"2024-03-18T14:13:08.540632Z","shell.execute_reply":"2024-03-18T14:13:08.546100Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Тут были графички на которых я смотрел разницу между эстимейтами и распределение таргетов на трейне по некоторым фичам, я их выпилил из сабмита когда дебагал проверку на закрытом тесте","metadata":{}},{"cell_type":"code","source":"# sns.scatterplot(data=X_train, x='disbursedcredamount_1113A', y='currdebt_22A', hue=y_train,alpha=0.3)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:13:08.548733Z","iopub.execute_input":"2024-03-18T14:13:08.549094Z","iopub.status.idle":"2024-03-18T14:13:08.562245Z","shell.execute_reply.started":"2024-03-18T14:13:08.549065Z","shell.execute_reply":"2024-03-18T14:13:08.561299Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import matplotlib.pyplot as plt\n# plt.yscale('log')\n# sns.histplot(X_train['sumoutstandtotalest_4493215A'][y_train == 1] - X_train['currdebt_22A'][y_train == 1],bins=100)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:13:08.564892Z","iopub.execute_input":"2024-03-18T14:13:08.565762Z","iopub.status.idle":"2024-03-18T14:13:08.573848Z","shell.execute_reply.started":"2024-03-18T14:13:08.565721Z","shell.execute_reply":"2024-03-18T14:13:08.572717Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import matplotlib.pyplot as plt\n# plt.yscale('log')\n# sns.histplot(X_train['sumoutstandtotalest_4493215A'][y_train == 0] - X_train['currdebt_22A'][y_train == 0],bins=100)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:13:08.575129Z","iopub.execute_input":"2024-03-18T14:13:08.575655Z","iopub.status.idle":"2024-03-18T14:13:08.584108Z","shell.execute_reply.started":"2024-03-18T14:13:08.575625Z","shell.execute_reply":"2024-03-18T14:13:08.583081Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# sns.scatterplot(data=X_train, x='currdebt_22A', y='maxdebt4_972A', hue=y_train,alpha=0.3)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:13:08.585540Z","iopub.execute_input":"2024-03-18T14:13:08.586008Z","iopub.status.idle":"2024-03-18T14:13:08.593592Z","shell.execute_reply.started":"2024-03-18T14:13:08.585970Z","shell.execute_reply":"2024-03-18T14:13:08.592768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Тут значит добавили фичей\nСодержательных мыслей было две: оценка текущего долга из одной какой-то таблички и из другой расходятся и когда расходятся есть сигнал какой-то\nИ вторая идея что когда люди разводятся/женятся/заводят новых детей у них меняется способность к выплате больше чем если они просто не были женаты/были женаты/имели детей","metadata":{}},{"cell_type":"code","source":"\ndef add_custom_features(df):\n    try:\n        df['cur_to_max_ratio'] = df['currdebt_22A'] / df['maxdebt4_972A']\n    except:\n        df['cur_to_max_ratio'] = np.nan\n    try:\n        df['est_delta'] = df['sumoutstandtotalest_4493215A'] - df['currdebt_22A']\n    except:\n        df['est_delta'] = np.nan\n    try:\n        df['got_married'] = (df['was_singlE'] == True) & (df['is_marrieD'] == True)\n    except:\n        df['got_married'] = np.nan\n    try:\n        df['children_increment'] = df['num_children_noW'] - df['num_of_children_beforE']\n    except:\n        df['children_increment'] = np.nan\n    try:\n        df['got_divorced'] = (df['was_marrieD'] == True) & (df['is_singlE'] == True)        \n    except:\n        df['got_divorced'] = np.nan\n\n\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:13:08.594969Z","iopub.execute_input":"2024-03-18T14:13:08.596034Z","iopub.status.idle":"2024-03-18T14:13:08.606172Z","shell.execute_reply.started":"2024-03-18T14:13:08.595995Z","shell.execute_reply":"2024-03-18T14:13:08.605073Z"},"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":"for df in [X_train, X_valid, X_test]:\n    df = add_custom_features(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:13:11.601692Z","iopub.execute_input":"2024-03-18T14:13:11.602495Z","iopub.status.idle":"2024-03-18T14:13:11.642741Z","shell.execute_reply.started":"2024-03-18T14:13:11.602451Z","shell.execute_reply":"2024-03-18T14:13:11.641665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import GridSearchCV\nfrom sklearn.model_selection import KFold","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:13:12.437611Z","iopub.execute_input":"2024-03-18T14:13:12.438003Z","iopub.status.idle":"2024-03-18T14:13:12.443186Z","shell.execute_reply.started":"2024-03-18T14:13:12.437974Z","shell.execute_reply":"2024-03-18T14:13:12.441793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Тут значит гиперпараметры перебирались грид серчем, но я не стал это запихивать в сабмит: слишком долго считается, поэтому просто захардкодил те, которые выбрались (честно-честно)\n","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\nparam_grid = {\n    'num_leaves': [15, 31],\n    'min_data_in_leaf': [30, 300],\n    \n    \"boosting_type\": [\"gbdt\"],\n    \"objective\": [\"binary\"],\n    \"metric\": [\"auc\"],\n    \"max_depth\": [3, 5, 7],\n    \"learning_rate\": [0.05],\n    \"feature_fraction\": [0.9],\n    \"bagging_fraction\": [0.8],\n    \"bagging_freq\": [5],\n    \"n_estimators\": [50, 100]\n    }\n# я не хочу перебор гиперпараметров запихивать в сабмит\n# но я перебрал на этих и потом довалидировался по количеству деревьев\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    'num_leaves' : 15,\n    \"metric\": \"auc\",\n    'min_data_in_leaf':30,\n    \"max_depth\": 7,\n    \"learning_rate\": 0.05,\n    \"feature_fraction\": 0.9,\n    \"bagging_fraction\": 0.8,\n    \"bagging_freq\": 5,\n    \"n_estimators\": 1000\n}\n\nmodel =lgb.LGBMClassifier()","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:34:28.824843Z","iopub.execute_input":"2024-03-18T14:34:28.825275Z","iopub.status.idle":"2024-03-18T14:34:28.835532Z","shell.execute_reply.started":"2024-03-18T14:34:28.825232Z","shell.execute_reply":"2024-03-18T14:34:28.834119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\nmodel_stupid = lgb.LGBMClassifier(**params)\nmodel_stupid.fit(X_train, y_train,eval_set=[(X_valid, y_valid)],callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)])","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:34:30.654841Z","iopub.execute_input":"2024-03-18T14:34:30.655266Z","iopub.status.idle":"2024-03-18T14:38:10.678401Z","shell.execute_reply.started":"2024-03-18T14:34:30.655228Z","shell.execute_reply":"2024-03-18T14:38:10.677581Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = model_stupid.predict_proba(X)[:,1]\n    base[\"score\"] = y_pred.copy()\n    \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":"2024-03-18T14:38:10.680100Z","iopub.execute_input":"2024-03-18T14:38:10.680825Z","iopub.status.idle":"2024-03-18T14:39:11.662864Z","shell.execute_reply.started":"2024-03-18T14:38:10.680794Z","shell.execute_reply":"2024-03-18T14:39:11.661646Z"},"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":"2024-03-18T14:39:11.664385Z","iopub.execute_input":"2024-03-18T14:39:11.664709Z","iopub.status.idle":"2024-03-18T14:39:12.773404Z","shell.execute_reply.started":"2024-03-18T14:39:11.664681Z","shell.execute_reply":"2024-03-18T14:39:12.772068Z"},"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()\n\n\nX_submission = convert_strings(X_submission)\n\n\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\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\nX_submission = add_custom_features(X_submission)\n\n\ny_submission_pred = model_stupid.predict_proba(X_submission)[:,1]","metadata":{"execution":{"iopub.status.busy":"2024-03-18T14:39:12.779001Z","iopub.execute_input":"2024-03-18T14:39:12.779385Z","iopub.status.idle":"2024-03-18T14:39:12.924558Z","shell.execute_reply.started":"2024-03-18T14:39:12.779354Z","shell.execute_reply":"2024-03-18T14:39:12.923405Z"},"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":"2024-03-18T14:39:12.926304Z","iopub.execute_input":"2024-03-18T14:39:12.926755Z","iopub.status.idle":"2024-03-18T14:39:12.936531Z","shell.execute_reply.started":"2024-03-18T14:39:12.926714Z","shell.execute_reply":"2024-03-18T14:39:12.935400Z"},"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":[]}]}