![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "id": "RQowCrZVSrRM"
+ },
+ "outputs": [],
+ "source": [
+ "import random\n",
+ "import os\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import gc\n",
+ "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
+ "from sklearn.ensemble import RandomForestClassifier\n",
+ "from sklearn.model_selection import train_test_split, GridSearchCV, StratifiedKFold\n",
+ "from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score, make_scorer\n",
+ "from xgboost import XGBClassifier"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "def seed_everything(seed):\n",
+ " random.seed(seed)\n",
+ " os.environ['PYTHONHASHSEED'] = str(seed)\n",
+ " np.random.seed(seed)\n",
+ "\n",
+ "seed_everything(42) # Fixed Seed\n",
+ "\n",
+ "def csv_to_parquet(csv_path, save_name):\n",
+ " df = pd.read_csv(csv_path)\n",
+ " df.to_parquet(f'./{save_name}.parquet')\n",
+ " del df\n",
+ " gc.collect()\n",
+ " print(save_name, 'Done.')"
+ ],
+ "metadata": {
+ "id": "SzoGNcLvSv8O"
+ },
+ "execution_count": 2,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# drive에 연결합니다.\n",
+ "from google.colab import drive\n",
+ "drive.mount('/content/drive', force_remount=True)\n",
+ "\n",
+ "# 현재 데이터가 있는 공간으로 작업 경로를 변경해줍니다.\n",
+ "%cd \"/content/drive/MyDrive/dacon/open_1\""
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "TYV5jX2yYkx1",
+ "outputId": "cff46d69-e744-49ca-d23e-76db3459a8ab"
+ },
+ "execution_count": 3,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Mounted at /content/drive\n",
+ "/content/drive/MyDrive/dacon/open_1\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "csv_to_parquet('train.csv', 'train')\n",
+ "csv_to_parquet('test.csv', 'test')\n",
+ "\n",
+ "train = pd.read_parquet('./train.parquet')\n",
+ "test = pd.read_parquet('./test.parquet')\n",
+ "sample_submission = pd.read_csv('sample_submission.csv', index_col = 0)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "uC9I13rAXf9L",
+ "outputId": "a5cb84f5-6690-4d1e-cdcd-ad07bdea267f"
+ },
+ "execution_count": 4,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "train Done.\n",
+ "test Done.\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#레이블(Delay)을 제외한 결측값이 존재하는 변수들을 학습 데이터의 최빈값으로 대체합니다\n",
+ "NaN_col = ['Origin_State','Destination_State','Airline','Estimated_Departure_Time', 'Estimated_Arrival_Time','Carrier_Code(IATA)','Carrier_ID(DOT)']\n",
+ "\n",
+ "for col in NaN_col:\n",
+ " mode = train[col].mode()[0]\n",
+ " train[col] = train[col].fillna(mode)\n",
+ "\n",
+ " if col in test.columns:\n",
+ " test[col] = test[col].fillna(mode)\n",
+ "print('Done.')"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "P_OEaI3qY6fU",
+ "outputId": "291b3be3-69fd-4330-a1fb-37f25574bbea"
+ },
+ "execution_count": 5,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Done.\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# cols = train.select_dtypes(include=['object'])\n",
+ "# le = LabelEncoder()\n",
+ "\n",
+ "# for col in cols:\n",
+ "# train[col] = le.fit_transform(train[col])\n",
+ "# test[col] = le.transform(test[col])"
+ ],
+ "metadata": {
+ "id": "b02EcTEfbeAX"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#질적 변수들을 수치화합니다\n",
+ "qual_col = ['Origin_Airport', 'Origin_State', 'Destination_Airport', 'Destination_State', 'Airline', 'Carrier_Code(IATA)', 'Tail_Number']\n",
+ "\n",
+ "for i in qual_col:\n",
+ " le = LabelEncoder()\n",
+ " le=le.fit(train[i])\n",
+ " train[i]=le.transform(train[i])\n",
+ "\n",
+ " for label in np.unique(test[i]):\n",
+ " if label not in le.classes_:\n",
+ " le.classes_ = np.append(le.classes_, label)\n",
+ " test[i]=le.transform(test[i])\n",
+ "print('Done.')"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "npCizVkPY8z0",
+ "outputId": "4ef74ffc-c836-447f-d3a8-84be8123d744"
+ },
+ "execution_count": 6,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Done.\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "#레이블이 없는 데이터들을 제거합니다\n",
+ "train = train.dropna()"
+ ],
+ "metadata": {
+ "id": "U_FNfAPicEDy"
+ },
+ "execution_count": 7,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "column_number = {}\n",
+ "for i, column in enumerate(sample_submission.columns):\n",
+ " column_number[column] = i\n",
+ "\n",
+ "def to_number(x, dic):\n",
+ " return dic[x]\n",
+ "\n",
+ "train.loc[:, 'Delay_num'] = train['Delay'].apply(lambda x: to_number(x, column_number))\n",
+ "print('Done.')"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "NwrUzHKtcEif",
+ "outputId": "ca472243-f309-43e3-d72c-62ea65d66f46"
+ },
+ "execution_count": 8,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Done.\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "train_x = train.drop(columns=['ID', 'Delay', 'Delay_num'])\n",
+ "train_y = train['Delay_num']\n",
+ "test_x = test.drop(columns=['ID'])"
+ ],
+ "metadata": {
+ "id": "BArQV8xycHhg"
+ },
+ "execution_count": 9,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "train_x, val_x, train_y, val_y = train_test_split(train_x, train_y, test_size=0.2, random_state=42)"
+ ],
+ "metadata": {
+ "id": "SAaBR2ledpbW"
+ },
+ "execution_count": 10,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "scaler = StandardScaler()\n",
+ "train_x = scaler.fit_transform(train_x)\n",
+ "val_x = scaler.transform(val_x)\n",
+ "test_x = scaler.transform(test_x)"
+ ],
+ "metadata": {
+ "id": "kPz2yfVedxwc"
+ },
+ "execution_count": 11,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from sklearn.tree import DecisionTreeClassifier\n",
+ "from sklearn.metrics import confusion_matrix, accuracy_score, recall_score, precision_score, f1_score, log_loss\n",
+ "\n",
+ "dt = DecisionTreeClassifier()\n",
+ "dt.fit(train_x, train_y)\n",
+ "pred_1 = dt.predict(val_x)\n",
+ "\n",
+ "accuracy = accuracy_score(val_y, pred_1)\n",
+ "f1 = f1_score(val_y, pred_1, average='weighted')\n",
+ "precision = precision_score(val_y, pred_1, average='weighted')\n",
+ "recall = recall_score(val_y, pred_1, average='weighted')\n",
+ "\n",
+ "print(f'Accuracy: {accuracy}')\n",
+ "print(f'F1 Score: {f1}')\n",
+ "print(f'Precision: {precision}')\n",
+ "print(f'Recall: {recall}')\n",
+ "\n",
+ "cm1 = confusion_matrix(val_y, pred_1)\n",
+ "print(cm1)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "QTdI1KxxcK0k",
+ "outputId": "24c24fab-ef94-413e-e570-a847fe8ac3ae"
+ },
+ "execution_count": 12,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Accuracy: 0.7101625458324347\n",
+ "F1 Score: 0.7157154247660936\n",
+ "Precision: 0.7216520312641815\n",
+ "Recall: 0.7101625458324347\n",
+ "[[34023 7869]\n",
+ " [ 6913 2196]]\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from sklearn.ensemble import RandomForestClassifier\n",
+ "rf = RandomForestClassifier(random_state=42)\n",
+ "\n",
+ "rf.fit(train_x, train_y)\n",
+ "pred_2 = rf.predict(val_x)\n",
+ "\n",
+ "accuracy = accuracy_score(val_y, pred_2)\n",
+ "f1 = f1_score(val_y, pred_2, average='weighted')\n",
+ "precision = precision_score(val_y, pred_2, average='weighted')\n",
+ "recall = recall_score(val_y, pred_2, average='weighted')\n",
+ "\n",
+ "print(f'Accuracy: {accuracy}')\n",
+ "print(f'F1 Score: {f1}')\n",
+ "print(f'Precision: {precision}')\n",
+ "print(f'Recall: {recall}')\n",
+ "\n",
+ "cm2 = confusion_matrix(val_y, pred_2)\n",
+ "print(cm2)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "FFFlTzfyep-e",
+ "outputId": "42cec3e3-24a2-475b-c8f2-c66567e624de"
+ },
+ "execution_count": 13,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Accuracy: 0.8181996431442521\n",
+ "F1 Score: 0.7489386921906548\n",
+ "Precision: 0.7463246276782165\n",
+ "Recall: 0.8181996431442521\n",
+ "[[41449 443]\n",
+ " [ 8829 280]]\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from xgboost import XGBClassifier\n",
+ "\n",
+ "xgb = XGBClassifier(random_state=42)\n",
+ "\n",
+ "xgb.fit(train_x, train_y)\n",
+ "pred_3 = xgb.predict(val_x)\n",
+ "\n",
+ "accuracy = accuracy_score(val_y, pred_3)\n",
+ "f1 = f1_score(val_y, pred_3, average='weighted')\n",
+ "precision = precision_score(val_y, pred_3, average='weighted')\n",
+ "recall = recall_score(val_y, pred_3, average='weighted')\n",
+ "\n",
+ "print(f'Accuracy: {accuracy}')\n",
+ "print(f'F1 Score: {f1}')\n",
+ "print(f'Precision: {precision}')\n",
+ "print(f'Recall: {recall}')\n",
+ "\n",
+ "cm3 = confusion_matrix(val_y, pred_3)\n",
+ "print(cm3)"
+ ],
+ "metadata": {
+ "id": "4jN9KiZSfaA6",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "f0b83813-4522-41e6-b5b2-dda8e5cd7169"
+ },
+ "execution_count": 15,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Accuracy: 0.8212976216152624\n",
+ "F1 Score: 0.7490495880677704\n",
+ "Precision: 0.7654504972612673\n",
+ "Recall: 0.8212976216152624\n",
+ "[[41655 237]\n",
+ " [ 8877 232]]\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from lightgbm import LGBMClassifier\n",
+ "\n",
+ "lgbm = LGBMClassifier()\n",
+ "lgbm.fit(train_x, train_y)\n",
+ "pred_4 = lgbm.predict(val_x)\n",
+ "\n",
+ "accuracy = accuracy_score(val_y, pred_4)\n",
+ "f1 = f1_score(val_y, pred_4, average='weighted')\n",
+ "precision = precision_score(val_y, pred_4, average='weighted')\n",
+ "recall = recall_score(val_y, pred_4, average='weighted')\n",
+ "\n",
+ "print(f'Accuracy: {accuracy}')\n",
+ "print(f'F1 Score: {f1}')\n",
+ "print(f'Precision: {precision}')\n",
+ "print(f'Recall: {recall}')\n",
+ "\n",
+ "cm4 = confusion_matrix(val_y, pred_4)\n",
+ "print(cm4)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "UviJ7wHzR-ul",
+ "outputId": "78723c7d-def0-4a8e-d0a8-6e102c00a467"
+ },
+ "execution_count": 18,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "[LightGBM] [Info] Number of positive: 35891, number of negative: 168109\n",
+ "[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.074233 seconds.\n",
+ "You can set `force_col_wise=true` to remove the overhead.\n",
+ "[LightGBM] [Info] Total Bins 2098\n",
+ "[LightGBM] [Info] Number of data points in the train set: 204000, number of used features: 15\n",
+ "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.175936 -> initscore=-1.544126\n",
+ "[LightGBM] [Info] Start training from score -1.544126\n",
+ "Accuracy: 0.8217682006235172\n",
+ "F1 Score: 0.7429650884383274\n",
+ "Precision: 0.7845486323828018\n",
+ "Recall: 0.8217682006235172\n",
+ "[[41859 33]\n",
+ " [ 9057 52]]\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from sklearn.metrics import log_loss\n",
+ "\n",
+ "logloss_1 = log_loss(val_y, pred_1)\n",
+ "logloss_2 = log_loss(val_y, pred_2)\n",
+ "logloss_3 = log_loss(val_y, pred_3)\n",
+ "logloss_4 = log_loss(val_y, pred_4)\n",
+ "\n",
+ "f1_1 = f1_score(val_y, pred_1, average='weighted')\n",
+ "f1_2 = f1_score(val_y, pred_2, average='weighted')\n",
+ "f1_3 = f1_score(val_y, pred_3, average='weighted')\n",
+ "f1_4 = f1_score(val_y, pred_4, average='weighted')\n",
+ "\n",
+ "# 결과 출력\n",
+ "print(f'F1_1 Score: {f1_1}')\n",
+ "print(f'F1_2 Score: {f1_2}')\n",
+ "print(f'F1_3 Score: {f1_3}')\n",
+ "print(f'F1_4 Score: {f1_4}')\n",
+ "\n",
+ "print(f\"Log Loss_1: {logloss_1}\")\n",
+ "print(f\"Log Loss_1: {logloss_2}\")\n",
+ "print(f\"Log Loss_3: {logloss_3}\")\n",
+ "print(f\"Log Loss_4: {logloss_4}\")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "uCr3tkmYShCm",
+ "outputId": "a3524f5d-b682-4fbf-e3af-7c7c32a008a1"
+ },
+ "execution_count": 20,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "F1_1 Score: 0.7157154247660936\n",
+ "F1_2 Score: 0.7489386921906548\n",
+ "F1_3 Score: 0.7490495880677704\n",
+ "F1_4 Score: 0.7429650884383274\n",
+ "Log Loss_1: 10.446800737199853\n",
+ "Log Loss_1: 6.552749048526386\n",
+ "Log Loss_3: 6.441086586310341\n",
+ "Log Loss_4: 6.424125199644614\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)"
+ ],
+ "metadata": {
+ "id": "KpF0bhFET-wg"
+ },
+ "execution_count": 21,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "param_grid = {\n",
+ " 'learning_rate': [0.01, 0.1],\n",
+ " 'max_depth': [3, 5 ,8],\n",
+ " 'n_estimators': [100, 200],\n",
+ "}"
+ ],
+ "metadata": {
+ "id": "SInHwUomVelh"
+ },
+ "execution_count": 27,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "grid = GridSearchCV(xgb,\n",
+ " param_grid,\n",
+ " cv=cv,\n",
+ " scoring='accuracy',\n",
+ " n_jobs=-1,\n",
+ " verbose=1)"
+ ],
+ "metadata": {
+ "id": "bh_xTcuSVfsv"
+ },
+ "execution_count": 28,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "grid.fit(train_x,train_y)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 192
+ },
+ "id": "QeFgvLUrVobH",
+ "outputId": "be47ea4b-ee66-4d61-f2a6-e65436647ea4"
+ },
+ "execution_count": 29,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Fitting 5 folds for each of 12 candidates, totalling 60 fits\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "/usr/local/lib/python3.10/dist-packages/joblib/externals/loky/process_executor.py:752: UserWarning: A worker stopped while some jobs were given to the executor. This can be caused by a too short worker timeout or by a memory leak.\n",
+ " warnings.warn(\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=42, shuffle=True),\n",
+ " estimator=XGBClassifier(base_score=None, booster=None,\n",
+ " callbacks=None, colsample_bylevel=None,\n",
+ " colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None,\n",
+ " early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None,\n",
+ " feature_types=None, gamma=None,\n",
+ " grow_policy=None, importance_typ...\n",
+ " max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None,\n",
+ " max_leaves=None, min_child_weight=None,\n",
+ " missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=None,\n",
+ " n_jobs=None, num_parallel_tree=None,\n",
+ " random_state=42, ...),\n",
+ " n_jobs=-1,\n",
+ " param_grid={'learning_rate': [0.01, 0.1], 'max_depth': [3, 5, 8],\n",
+ " 'n_estimators': [100, 200]},\n",
+ " scoring='accuracy', verbose=1)"
+ ],
+ "text/html": [
+ "GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=42, shuffle=True),\n",
+ " estimator=XGBClassifier(base_score=None, booster=None,\n",
+ " callbacks=None, colsample_bylevel=None,\n",
+ " colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None,\n",
+ " early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None,\n",
+ " feature_types=None, gamma=None,\n",
+ " grow_policy=None, importance_typ...\n",
+ " max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None,\n",
+ " max_leaves=None, min_child_weight=None,\n",
+ " missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=None,\n",
+ " n_jobs=None, num_parallel_tree=None,\n",
+ " random_state=42, ...),\n",
+ " n_jobs=-1,\n",
+ " param_grid={'learning_rate': [0.01, 0.1], 'max_depth': [3, 5, 8],\n",
+ " 'n_estimators': [100, 200]},\n",
+ " scoring='accuracy', verbose=1)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. GridSearchCV(cv=StratifiedKFold(n_splits=5, random_state=42, shuffle=True),\n",
+ " estimator=XGBClassifier(base_score=None, booster=None,\n",
+ " callbacks=None, colsample_bylevel=None,\n",
+ " colsample_bynode=None,\n",
+ " colsample_bytree=None, device=None,\n",
+ " early_stopping_rounds=None,\n",
+ " enable_categorical=False, eval_metric=None,\n",
+ " feature_types=None, gamma=None,\n",
+ " grow_policy=None, importance_typ...\n",
+ " max_cat_to_onehot=None,\n",
+ " max_delta_step=None, max_depth=None,\n",
+ " max_leaves=None, min_child_weight=None,\n",
+ " missing=nan, monotone_constraints=None,\n",
+ " multi_strategy=None, n_estimators=None,\n",
+ " n_jobs=None, num_parallel_tree=None,\n",
+ " random_state=42, ...),\n",
+ " n_jobs=-1,\n",
+ " param_grid={'learning_rate': [0.01, 0.1], 'max_depth': [3, 5, 8],\n",
+ " 'n_estimators': [100, 200]},\n",
+ " scoring='accuracy', verbose=1)XGBClassifier(base_score=None, booster=None, callbacks=None,\n", + " colsample_bylevel=None, colsample_bynode=None,\n", + " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", + " enable_categorical=False, eval_metric=None, feature_types=None,\n", + " gamma=None, grow_policy=None, importance_type=None,\n", + " interaction_constraints=None, learning_rate=None, max_bin=None,\n", + " max_cat_threshold=None, max_cat_to_onehot=None,\n", + " max_delta_step=None, max_depth=None, max_leaves=None,\n", + " min_child_weight=None, missing=nan, monotone_constraints=None,\n", + " multi_strategy=None, n_estimators=None, n_jobs=None,\n", + " num_parallel_tree=None, random_state=42, ...)
XGBClassifier(base_score=None, booster=None, callbacks=None,\n", + " colsample_bylevel=None, colsample_bynode=None,\n", + " colsample_bytree=None, device=None, early_stopping_rounds=None,\n", + " enable_categorical=False, eval_metric=None, feature_types=None,\n", + " gamma=None, grow_policy=None, importance_type=None,\n", + " interaction_constraints=None, learning_rate=None, max_bin=None,\n", + " max_cat_threshold=None, max_cat_to_onehot=None,\n", + " max_delta_step=None, max_depth=None, max_leaves=None,\n", + " min_child_weight=None, missing=nan, monotone_constraints=None,\n", + " multi_strategy=None, n_estimators=None, n_jobs=None,\n", + " num_parallel_tree=None, random_state=42, ...)