{"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":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30648,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### Catboost on GPU with 5 folds and 2 r_seeds\nData Scientist with 10+ years of experience. Experienced in Retail Sales Forecast, RecSys, Banking, IT and Consulting. Open to interesting offers.\n\n\nData Pipeline from\nhttps://www.kaggle.com/code/greysky/home-credit-baseline","metadata":{}},{"cell_type":"code","source":"import os\nimport gc\nfrom glob import glob\nfrom pathlib import Path\nfrom datetime import datetime\n\nimport numpy as np\nimport pandas as pd\nimport polars as pl\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom sklearn.model_selection import train_test_split, StratifiedKFold, cross_val_score, GridSearchCV, cross_val_predict, KFold\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, ClassifierMixin\n\nimport lightgbm as lgb\n\nfrom catboost import CatBoostRegressor, Pool, cv, CatBoost\nimport catboost\nprint(catboost.__version__)\nfrom catboost import CatBoostClassifier\n\nimport itertools\n\nfrom sklearn.metrics import * \n\nimport warnings\nwarnings.simplefilter(action='ignore')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-03-16T15:40:19.379472Z","iopub.execute_input":"2024-03-16T15:40:19.380281Z","iopub.status.idle":"2024-03-16T15:40:24.809611Z","shell.execute_reply.started":"2024-03-16T15:40:19.380248Z","shell.execute_reply":"2024-03-16T15:40:24.808675Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pipeline","metadata":{}},{"cell_type":"code","source":"class Pipeline:\n    @staticmethod\n    def set_table_dtypes(df):\n        for col in df.columns:\n            if col in [\"case_id\", \"WEEK_NUM\", \"num_group1\", \"num_group2\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Int32))\n            elif col in [\"date_decision\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n            elif col[-1] in (\"P\", \"A\"):\n                df = df.with_columns(pl.col(col).cast(pl.Float64))\n            elif col[-1] in (\"M\",):\n                df = df.with_columns(pl.col(col).cast(pl.String))\n            elif col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col).cast(pl.Date))            \n\n        return df\n    \n    @staticmethod\n    def 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.with_columns(pl.col(col).cast(pl.Float32))\n                \n        df = df.drop(\"date_decision\", \"MONTH\")\n\n        return df\n    \n    @staticmethod\n    def filter_cols(df):\n        for col in df.columns:\n            if col not in [\"target\", \"case_id\", \"WEEK_NUM\"]:\n                isnull = df[col].is_null().mean()\n\n                if isnull > 0.95:\n                    df = df.drop(col)\n\n        for col in df.columns:\n            if (col not in [\"target\", \"case_id\", \"WEEK_NUM\"]) & (df[col].dtype == pl.String):\n                freq = df[col].n_unique()\n\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n\n        return df","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:24.811574Z","iopub.execute_input":"2024-03-16T15:40:24.812221Z","iopub.status.idle":"2024-03-16T15:40:24.824536Z","shell.execute_reply.started":"2024-03-16T15:40:24.812186Z","shell.execute_reply":"2024-03-16T15:40:24.823518Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Automatic Aggregation","metadata":{}},{"cell_type":"code","source":"class Aggregator:\n    @staticmethod\n    def num_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def date_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"D\",)]\n\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def str_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"M\",)]\n        \n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def other_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n        \n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\n        return expr_max\n    \n    @staticmethod\n    def count_expr(df):\n        cols = [col for col in df.columns if \"num_group\" in col]\n\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def get_exprs(df):\n        exprs = Aggregator.num_expr(df) + \\\n                Aggregator.date_expr(df) + \\\n                Aggregator.str_expr(df) + \\\n                Aggregator.other_expr(df) + \\\n                Aggregator.count_expr(df)\n\n        return exprs","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:24.825773Z","iopub.execute_input":"2024-03-16T15:40:24.826081Z","iopub.status.idle":"2024-03-16T15:40:24.852385Z","shell.execute_reply.started":"2024-03-16T15:40:24.826052Z","shell.execute_reply":"2024-03-16T15:40:24.851538Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Catboost Display","metadata":{}},{"cell_type":"code","source":"def display_importances_cat(feature_importance_df_):\n    cols = feature_importance_df_[[\"Feature Id\", \"Importances\"]].groupby(\"Feature Id\").mean().sort_values(by=\"Importances\", ascending=False)[:42].index\n    best_features = feature_importance_df_.loc[feature_importance_df_['Feature Id'].isin(cols)]\n    plt.figure(figsize=(8, 10))\n    sns.barplot(x=\"Importances\", y=\"Feature Id\", data=best_features.sort_values(by=\"Importances\", ascending=False))\n    plt.title('Catboost Features Importances (averaged)')\n    plt.tight_layout()\n    \n# Confusion matrix \ndef plot_confusion_matrix(cm, classes,\n                          normalize = False,\n                          title = 'Confusion matrix\"',\n                          cmap = plt.cm.Blues) :\n    plt.imshow(cm, interpolation = 'nearest', cmap = cmap)\n    plt.title(title)\n    plt.colorbar()\n    tick_marks = np.arange(len(classes))\n    plt.xticks(tick_marks, classes, rotation = 0)\n    plt.yticks(tick_marks, classes)\n \n    thresh = cm.max() / 2.\n    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])) :\n        plt.text(j, i, cm[i, j],\n                 horizontalalignment = 'center',\n                 color = 'white' if cm[i, j] > thresh else 'black')\n \n    plt.tight_layout()\n    plt.ylabel('True label')\n    plt.xlabel('Predicted label')","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:24.853908Z","iopub.execute_input":"2024-03-16T15:40:24.854176Z","iopub.status.idle":"2024-03-16T15:40:24.866344Z","shell.execute_reply.started":"2024-03-16T15:40:24.854154Z","shell.execute_reply":"2024-03-16T15:40:24.865475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### File I/O","metadata":{}},{"cell_type":"code","source":"def read_file(path, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    \n    if depth in [1, 2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n    \n    return df\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    for path in glob(str(regex_path)):\n        df = pl.read_parquet(path)\n        df = df.pipe(Pipeline.set_table_dtypes)\n        \n        if depth in [1, 2]:\n            df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n        \n        chunks.append(df)\n        \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    \n    return df","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:24.867534Z","iopub.execute_input":"2024-03-16T15:40:24.867849Z","iopub.status.idle":"2024-03-16T15:40:24.880047Z","shell.execute_reply.started":"2024-03-16T15:40:24.867821Z","shell.execute_reply":"2024-03-16T15:40:24.879315Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Engineering","metadata":{}},{"cell_type":"code","source":"def feature_eng(df_base, depth_0, depth_1, depth_2):\n    df_base = (\n        df_base\n        .with_columns(\n            month_decision = pl.col(\"date_decision\").dt.month(),\n            weekday_decision = pl.col(\"date_decision\").dt.weekday(),\n        )\n    )\n        \n    for i, df in enumerate(depth_0 + depth_1 + depth_2):\n        df_base = df_base.join(df, how=\"left\", on=\"case_id\", suffix=f\"_{i}\")\n        \n    df_base = df_base.pipe(Pipeline.handle_dates)\n    \n    return df_base","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:24.916743Z","iopub.execute_input":"2024-03-16T15:40:24.917000Z","iopub.status.idle":"2024-03-16T15:40:24.922375Z","shell.execute_reply.started":"2024-03-16T15:40:24.916979Z","shell.execute_reply":"2024-03-16T15:40:24.921597Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    \n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    \n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    \n    return df_data, cat_cols","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:25.434600Z","iopub.execute_input":"2024-03-16T15:40:25.435371Z","iopub.status.idle":"2024-03-16T15:40:25.440936Z","shell.execute_reply.started":"2024-03-16T15:40:25.435338Z","shell.execute_reply":"2024-03-16T15:40:25.439881Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Configuration","metadata":{}},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:26.874177Z","iopub.execute_input":"2024-03-16T15:40:26.874533Z","iopub.status.idle":"2024-03-16T15:40:26.879105Z","shell.execute_reply.started":"2024-03-16T15:40:26.874503Z","shell.execute_reply":"2024-03-16T15:40:26.878197Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Train Files Read & Feature Engineering","metadata":{}},{"cell_type":"code","source":"data_store = {\n    \"df_base\": read_file(TRAIN_DIR / \"train_base.parquet\"),\n    \"depth_0\": [\n        read_file(TRAIN_DIR / \"train_static_cb_0.parquet\"),\n        read_files(TRAIN_DIR / \"train_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_a_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_c_1.parquet\", 1),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_other_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_person_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_deposit_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", 2),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_2_*.parquet\", 2),\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:40:27.843705Z","iopub.execute_input":"2024-03-16T15:40:27.844486Z","iopub.status.idle":"2024-03-16T15:42:35.614903Z","shell.execute_reply.started":"2024-03-16T15:40:27.844453Z","shell.execute_reply":"2024-03-16T15:42:35.614066Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\n\nprint(\"train data shape:\\t\", df_train.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:42:35.616532Z","iopub.execute_input":"2024-03-16T15:42:35.616827Z","iopub.status.idle":"2024-03-16T15:42:48.088300Z","shell.execute_reply.started":"2024-03-16T15:42:35.616801Z","shell.execute_reply":"2024-03-16T15:42:48.087321Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Test Files Read & Feature Engineering","metadata":{}},{"cell_type":"code","source":"data_store = {\n    \"df_base\": read_file(TEST_DIR / \"test_base.parquet\"),\n    \"depth_0\": [\n        read_file(TEST_DIR / \"test_static_cb_0.parquet\"),\n        read_files(TEST_DIR / \"test_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TEST_DIR / \"test_applprev_1_*.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_a_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_c_1.parquet\", 1),\n        read_files(TEST_DIR / \"test_credit_bureau_a_1_*.parquet\", 1),\n        read_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_other_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_person_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_deposit_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", 2),\n        read_files(TEST_DIR / \"test_credit_bureau_a_2_*.parquet\", 2),\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:42:48.089693Z","iopub.execute_input":"2024-03-16T15:42:48.090461Z","iopub.status.idle":"2024-03-16T15:42:48.669864Z","shell.execute_reply.started":"2024-03-16T15:42:48.090426Z","shell.execute_reply":"2024-03-16T15:42:48.669034Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\n\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:42:48.671950Z","iopub.execute_input":"2024-03-16T15:42:48.672259Z","iopub.status.idle":"2024-03-16T15:42:48.712574Z","shell.execute_reply.started":"2024-03-16T15:42:48.672233Z","shell.execute_reply":"2024-03-16T15:42:48.711765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Elimination","metadata":{}},{"cell_type":"code","source":"df_train = df_train.pipe(Pipeline.filter_cols)\ndf_test = df_test.select([col for col in df_train.columns if col != \"target\"])\n\nprint(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:42:48.713510Z","iopub.execute_input":"2024-03-16T15:42:48.713787Z","iopub.status.idle":"2024-03-16T15:42:51.482910Z","shell.execute_reply.started":"2024-03-16T15:42:48.713764Z","shell.execute_reply":"2024-03-16T15:42:51.481936Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pandas Conversion","metadata":{}},{"cell_type":"code","source":"train_df, cat_feats = to_pandas(df_train)\ntest_df, cat_feats = to_pandas(df_test, cat_feats)","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:42:51.483887Z","iopub.execute_input":"2024-03-16T15:42:51.484160Z","iopub.status.idle":"2024-03-16T15:43:10.169496Z","shell.execute_reply.started":"2024-03-16T15:42:51.484126Z","shell.execute_reply":"2024-03-16T15:43:10.168584Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Garbage Collection","metadata":{}},{"cell_type":"code","source":"del data_store, df_train, df_test\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:43:10.170744Z","iopub.execute_input":"2024-03-16T15:43:10.171114Z","iopub.status.idle":"2024-03-16T15:43:10.582211Z","shell.execute_reply.started":"2024-03-16T15:43:10.171084Z","shell.execute_reply":"2024-03-16T15:43:10.581180Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training & Prediction","metadata":{}},{"cell_type":"code","source":"target = 'target'\n\nremove_features = [\"target\", \"case_id\", \"WEEK_NUM\"]\nfeatures = [x for x in train_df.columns if x not in remove_features]\n\n","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:43:10.583332Z","iopub.execute_input":"2024-03-16T15:43:10.583615Z","iopub.status.idle":"2024-03-16T15:43:10.594269Z","shell.execute_reply.started":"2024-03-16T15:43:10.583591Z","shell.execute_reply":"2024-03-16T15:43:10.593324Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for col in cat_feats:\n    train_df[col] = train_df[col].cat.add_categories('Missing').fillna('Missing')\n    test_df[col] = test_df[col].cat.add_categories('Missing').fillna('Missing')","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:43:10.595266Z","iopub.execute_input":"2024-03-16T15:43:10.595493Z","iopub.status.idle":"2024-03-16T15:43:10.895774Z","shell.execute_reply.started":"2024-03-16T15:43:10.595473Z","shell.execute_reply":"2024-03-16T15:43:10.894961Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n# CatBoostClassifier training & test prediction on GPU (5 folds & 2 r_seeds)\n\nnfold = 5\nr_seeds = [777, 888, 42, 22, 7]\nsteps = len(r_seeds) * nfold\nweeks = train_df[\"WEEK_NUM\"]\nskf = StratifiedGroupKFold(n_splits=nfold, shuffle=False)\n \noof = np.zeros(len(train_df))\npredictions = np.zeros(len(test_df))\ncms= []\ny_real = []\ny_proba = []\nrecalls = []\nroc_aucs = []\nf1_scores = []\naccuracies = []\nprecisions = []\n\nfeature_importance_df = pd.DataFrame()\n\nstep = 0\nfor r_seed in r_seeds:\n    i = 0\n    model = CatBoostClassifier(iterations=1000, loss_function='Logloss', task_type=\"GPU\", \n                               random_state=r_seed)\n    cats = [x for x in features if x in cat_feats]\n    for train_idx, valid_idx in skf.split(train_df, train_df[target].values, groups=weeks):\n        print(\"\\nr_seed {0} fold {1}\".format(r_seed, i))\n\n        trn_data = Pool(data=train_df.iloc[train_idx][features], \n                           label=train_df.iloc[train_idx][target].values, cat_features=cats)\n        val_data = Pool(data=train_df.iloc[valid_idx][features], label=train_df.iloc[valid_idx][target].values, cat_features=cats)\n\n        model.fit(trn_data, eval_set=val_data, use_best_model=True, verbose=False)\n                  \n        oof[valid_idx] += model.predict_proba(train_df.iloc[valid_idx][features])[:,1] / len(r_seeds)\n\n        predictions += model.predict_proba(test_df[features])[:,1] / steps\n\n        \n\n        oof_2 = (oof[valid_idx] * 1).round()\n        oof_2[oof_2 > 1] = 1 \n        # Confusion matrix by folds\n        cms.append(confusion_matrix(train_df.iloc[valid_idx][target].values, oof_2))\n\n        # Features imp\n        fold_importance_df =  model.get_feature_importance(Pool(data=train_df.iloc[train_idx][features], \n                                                                   label=train_df.iloc[train_idx][target].values, cat_features=cats)\n                                                           ,type='FeatureImportance',prettified=True)\n        fold_importance_df[\"step\"] = step \n        feature_importance_df = pd.concat([feature_importance_df, fold_importance_df], axis=0)\n        \n        step = step + 1\n        i = i + 1\n        del trn_data, val_data\n        gc.collect()\n\n\nprint('OOF Gini:')\nprint((roc_auc_score(train_df[target].values, oof) * 2 - 1))","metadata":{"execution":{"iopub.status.busy":"2024-03-16T15:52:57.028313Z","iopub.execute_input":"2024-03-16T15:52:57.029027Z","iopub.status.idle":"2024-03-16T17:30:53.012605Z","shell.execute_reply.started":"2024-03-16T15:52:57.028996Z","shell.execute_reply":"2024-03-16T17:30:53.011599Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Confusion maxtrix\nplt.rcParams[\"axes.grid\"] = False\ncm = np.average(cms, axis=0)\nclass_names = [0,1]\nplt.figure()\nplot_confusion_matrix(cm, \n                      classes=class_names, \n                      title= 'Catboost Confusion matrix [averaged/steps]')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-03-16T17:30:53.014579Z","iopub.execute_input":"2024-03-16T17:30:53.015267Z","iopub.status.idle":"2024-03-16T17:30:53.233316Z","shell.execute_reply.started":"2024-03-16T17:30:53.015229Z","shell.execute_reply":"2024-03-16T17:30:53.232378Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Feature importance\ndisplay_importances_cat(feature_importance_df)","metadata":{"execution":{"iopub.status.busy":"2024-03-16T17:30:53.234556Z","iopub.execute_input":"2024-03-16T17:30:53.234912Z","iopub.status.idle":"2024-03-16T17:30:55.130327Z","shell.execute_reply.started":"2024-03-16T17:30:53.234878Z","shell.execute_reply":"2024-03-16T17:30:55.129382Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{}},{"cell_type":"code","source":"df_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\ndf_subm[\"score\"] = predictions","metadata":{"execution":{"iopub.status.busy":"2024-03-16T17:39:01.966260Z","iopub.execute_input":"2024-03-16T17:39:01.966993Z","iopub.status.idle":"2024-03-16T17:39:01.980057Z","shell.execute_reply.started":"2024-03-16T17:39:01.966963Z","shell.execute_reply":"2024-03-16T17:39:01.979204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())\n\ndf_subm.head()","metadata":{"execution":{"iopub.status.busy":"2024-03-16T17:39:03.013556Z","iopub.execute_input":"2024-03-16T17:39:03.014330Z","iopub.status.idle":"2024-03-16T17:39:03.028265Z","shell.execute_reply.started":"2024-03-16T17:39:03.014296Z","shell.execute_reply":"2024-03-16T17:39:03.027083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-16T17:39:05.059470Z","iopub.execute_input":"2024-03-16T17:39:05.060173Z","iopub.status.idle":"2024-03-16T17:39:05.067194Z","shell.execute_reply.started":"2024-03-16T17:39:05.060127Z","shell.execute_reply":"2024-03-16T17:39:05.066405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}