Upload catboost regressor.ipynb

catboost regressor.ipynb

@@ -0,0 +1,1011 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3723782b",
+   "metadata": {
+    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
+    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:09.644656Z",
+     "iopub.status.busy": "2022-09-05T13:02:09.643933Z",
+     "iopub.status.idle": "2022-09-05T13:02:09.657508Z",
+     "shell.execute_reply": "2022-09-05T13:02:09.656438Z"
+    },
+    "papermill": {
+     "duration": 0.023341,
+     "end_time": "2022-09-05T13:02:09.660113",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:09.636772",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/kaggle/input/nsutai/sample_submission.csv\n",
+      "/kaggle/input/nsutai/train.csv\n",
+      "/kaggle/input/nsutai/test.csv\n"
+     ]
+    }
+   ],
+   "source": [
+    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
+    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
+    "# For example, here's several helpful packages to load\n",
+    "\n",
+    "import numpy as np # linear algebra\n",
+    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
+    "\n",
+    "# Input data files are available in the read-only \"../input/\" directory\n",
+    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
+    "\n",
+    "import os\n",
+    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
+    "    for filename in filenames:\n",
+    "        print(os.path.join(dirname, filename))\n",
+    "\n",
+    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
+    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "909fe5b2",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:09.669974Z",
+     "iopub.status.busy": "2022-09-05T13:02:09.668381Z",
+     "iopub.status.idle": "2022-09-05T13:02:10.932568Z",
+     "shell.execute_reply": "2022-09-05T13:02:10.931603Z"
+    },
+    "papermill": {
+     "duration": 1.271004,
+     "end_time": "2022-09-05T13:02:10.934930",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:09.663926",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from catboost import CatBoostRegressor\n",
+    "from sklearn.model_selection import ShuffleSplit, GridSearchCV\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.model_selection import train_test_split, cross_val_score, cross_val_predict\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1462638a",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:10.943879Z",
+     "iopub.status.busy": "2022-09-05T13:02:10.943596Z",
+     "iopub.status.idle": "2022-09-05T13:02:11.394396Z",
+     "shell.execute_reply": "2022-09-05T13:02:11.393459Z"
+    },
+    "papermill": {
+     "duration": 0.457904,
+     "end_time": "2022-09-05T13:02:11.396743",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:10.938839",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv('../input/nsutai/train.csv')\n",
+    "# df = df.drop('name',axis=1)\n",
+    "# df = df.drop('sentry_object',axis=1)\n",
+    "df = df.drop('event',axis=1)\n",
+    "df = df.drop('id',axis=1)\n",
+    "terms = 0\n",
+    "total = 0\n",
+    "for i in df:\n",
+    "    df[i].fillna(value=df[i].mean(), inplace=True)\n",
+    "df['px12'] = df.px1 * df.px2\n",
+    "df['Q12'] = df.q1 * df.q2\n",
+    "df['phi12'] = df.phi1 * df.phi2\n",
+    "df['eta12'] = df.eta1 * df.eta2\n",
+    "df['pt12'] = df.pt1 * df.pt2\n",
+    "df['E12'] = df.e1 * df.e2\n",
+    "df['pz_diff'] = df.pz1 - df.pz2\n",
+    "df['eta_diff'] = df.eta1 - df.eta2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a9ed9929",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:11.405872Z",
+     "iopub.status.busy": "2022-09-05T13:02:11.405576Z",
+     "iopub.status.idle": "2022-09-05T13:02:11.426360Z",
+     "shell.execute_reply": "2022-09-05T13:02:11.425332Z"
+    },
+    "papermill": {
+     "duration": 0.02842,
+     "end_time": "2022-09-05T13:02:11.429254",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:11.400834",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 69940 entries, 0 to 69939\n",
+      "Data columns (total 25 columns):\n",
+      " #   Column    Non-Null Count  Dtype  \n",
+      "---  ------    --------------  -----  \n",
+      " 0   e1        69940 non-null  float64\n",
+      " 1   px1       69940 non-null  float64\n",
+      " 2   py1       69940 non-null  float64\n",
+      " 3   pz1       69940 non-null  float64\n",
+      " 4   pt1       69940 non-null  float64\n",
+      " 5   eta1      69940 non-null  float64\n",
+      " 6   phi1      69940 non-null  float64\n",
+      " 7   q1        69940 non-null  int64  \n",
+      " 8   e2        69940 non-null  float64\n",
+      " 9   px2       69940 non-null  float64\n",
+      " 10  py2       69940 non-null  float64\n",
+      " 11  pz2       69940 non-null  float64\n",
+      " 12  pt2       69940 non-null  float64\n",
+      " 13  eta2      69940 non-null  float64\n",
+      " 14  phi2      69940 non-null  float64\n",
+      " 15  q2        69940 non-null  int64  \n",
+      " 16  mass      69940 non-null  float64\n",
+      " 17  px12      69940 non-null  float64\n",
+      " 18  Q12       69940 non-null  int64  \n",
+      " 19  phi12     69940 non-null  float64\n",
+      " 20  eta12     69940 non-null  float64\n",
+      " 21  pt12      69940 non-null  float64\n",
+      " 22  E12       69940 non-null  float64\n",
+      " 23  pz_diff   69940 non-null  float64\n",
+      " 24  eta_diff  69940 non-null  float64\n",
+      "dtypes: float64(22), int64(3)\n",
+      "memory usage: 13.3 MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ff7f9418",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:11.438260Z",
+     "iopub.status.busy": "2022-09-05T13:02:11.437997Z",
+     "iopub.status.idle": "2022-09-05T13:02:11.483587Z",
+     "shell.execute_reply": "2022-09-05T13:02:11.482534Z"
+    },
+    "papermill": {
+     "duration": 0.05382,
+     "end_time": "2022-09-05T13:02:11.487122",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:11.433302",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "Xn_data = np.array(df.drop('mass', axis = 1).values)\n",
+    "# Normalize X_data\n",
+    "X_data = (Xn_data - np.mean(Xn_data)) / np.std(Xn_data)\n",
+    "# y_data = np.log(np.array(df[\"mass\"]))\n",
+    "from sklearn.preprocessing import StandardScaler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "d33ee3a8",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:11.501842Z",
+     "iopub.status.busy": "2022-09-05T13:02:11.501512Z",
+     "iopub.status.idle": "2022-09-05T13:02:11.576250Z",
+     "shell.execute_reply": "2022-09-05T13:02:11.574558Z"
+    },
+    "papermill": {
+     "duration": 0.084845,
+     "end_time": "2022-09-05T13:02:11.580949",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:11.496104",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "X = df.drop('mass',axis=1)\n",
+    "# from sklearn.preprocessing import StandardScaler\n",
+    "# sc = StandardScaler()\n",
+    "# X = sc.fit_transform(X)\n",
+    "y = df['mass'].values\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_data,y,test_size=0.2,random_state=33)\n",
+    "ss = StandardScaler()\n",
+    "X_train = ss.fit_transform(X_train)\n",
+    "X_test = ss.fit_transform(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "0fea2318",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:11.598458Z",
+     "iopub.status.busy": "2022-09-05T13:02:11.597860Z",
+     "iopub.status.idle": "2022-09-05T13:02:11.612775Z",
+     "shell.execute_reply": "2022-09-05T13:02:11.611552Z"
+    },
+    "papermill": {
+     "duration": 0.027089,
+     "end_time": "2022-09-05T13:02:11.616455",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:11.589366",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 1.54406036e-03,  5.00046796e-02,  9.72291485e-01, ...,\n",
+       "         3.46918585e-03, -4.15573889e-02, -7.97763559e-03],\n",
+       "       [ 1.94422910e-04, -3.33701351e-01, -1.21056344e+00, ...,\n",
+       "         3.65737676e-03, -1.13711783e-01,  2.60815651e-03],\n",
+       "       [ 2.38266960e-03,  5.19004764e-01,  8.78117565e-01, ...,\n",
+       "         2.62745940e-03,  8.97889389e-02, -2.15806071e-02],\n",
+       "       ...,\n",
+       "       [-1.40730483e-04, -1.79267428e-01,  1.03092574e+00, ...,\n",
+       "         3.74511846e-03, -2.07740905e+00,  7.78566082e-03],\n",
+       "       [-8.58332036e-04, -7.98378259e-01, -1.12113137e+00, ...,\n",
+       "         2.87497174e-03,  4.31631201e-01,  8.14307267e-04],\n",
+       "       [ 1.02554766e-03, -1.28674581e+00, -1.34946525e-01, ...,\n",
+       "         3.44007559e-03,  2.95152031e-03, -5.08424031e-04]])"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "79f26373",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:11.633832Z",
+     "iopub.status.busy": "2022-09-05T13:02:11.633551Z",
+     "iopub.status.idle": "2022-09-05T13:02:11.638935Z",
+     "shell.execute_reply": "2022-09-05T13:02:11.638026Z"
+    },
+    "papermill": {
+     "duration": 0.01656,
+     "end_time": "2022-09-05T13:02:11.641678",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:11.625118",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Location of categorical columns :  ['q1', 'q2', 'Q12']\n"
+     ]
+    }
+   ],
+   "source": [
+    "#List of categorical columns\n",
+    "# categoricalcolumns = X.select_dtypes(include=[\"object\"]).columns.tolist()\n",
+    "# print(\"Names of categorical columns : \", categoricalcolumns)\n",
+    "#Get location of categorical columns\n",
+    "cat_features = ['q1','q2','Q12']\n",
+    "print(\"Location of categorical columns : \",cat_features)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "255a87ee",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:11.651657Z",
+     "iopub.status.busy": "2022-09-05T13:02:11.651374Z",
+     "iopub.status.idle": "2022-09-05T13:02:12.403415Z",
+     "shell.execute_reply": "2022-09-05T13:02:12.402465Z"
+    },
+    "papermill": {
+     "duration": 0.760088,
+     "end_time": "2022-09-05T13:02:12.406197",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:11.646109",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# importing Pool\n",
+    "from catboost import Pool\n",
+    "#Creating pool object for train dataset. we give information of categorical fetures to parameter cat_fetaures\n",
+    "train_data = Pool(data=X_train,\n",
+    "                  label=y_train,\n",
+    "#                   cat_features=cat_features\n",
+    "                 )\n",
+    "#Creating pool object for test dataset\n",
+    "test_data = Pool(data=X_test,\n",
+    "                  label=y_test,\n",
+    "#                   cat_features=cat_features\n",
+    "                 )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "513ae7cc",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:12.420374Z",
+     "iopub.status.busy": "2022-09-05T13:02:12.420051Z",
+     "iopub.status.idle": "2022-09-05T13:02:12.423954Z",
+     "shell.execute_reply": "2022-09-05T13:02:12.423122Z"
+    },
+    "papermill": {
+     "duration": 0.015038,
+     "end_time": "2022-09-05T13:02:12.427807",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:12.412769",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# print(np.sqrt(error))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "f6829920",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T13:02:12.441091Z",
+     "iopub.status.busy": "2022-09-05T13:02:12.440796Z",
+     "iopub.status.idle": "2022-09-05T14:45:06.059945Z",
+     "shell.execute_reply": "2022-09-05T14:45:06.058899Z"
+    },
+    "papermill": {
+     "duration": 6173.62882,
+     "end_time": "2022-09-05T14:45:06.062699",
+     "exception": false,
+     "start_time": "2022-09-05T13:02:12.433879",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Learning rate set to 0.011444\n",
+      "0:\tlearn: 1.0109453\ttotal: 25.3ms\tremaining: 8m 25s\n",
+      "5000:\tlearn: 0.2627569\ttotal: 1m 41s\tremaining: 5m 3s\n",
+      "10000:\tlearn: 0.0976646\ttotal: 3m 22s\tremaining: 3m 22s\n",
+      "15000:\tlearn: 0.0396183\ttotal: 5m 4s\tremaining: 1m 41s\n",
+      "19999:\tlearn: 0.0169753\ttotal: 6m 44s\tremaining: 0us\n",
+      "Learning rate set to 0.008715\n",
+      "0:\tlearn: 1.0111765\ttotal: 32ms\tremaining: 10m 39s\n",
+      "5000:\tlearn: 0.5784365\ttotal: 12m 45s\tremaining: 38m 15s\n",
+      "10000:\tlearn: 0.5133532\ttotal: 25m 6s\tremaining: 25m 5s\n",
+      "15000:\tlearn: 0.4772074\ttotal: 37m 26s\tremaining: 12m 28s\n",
+      "19999:\tlearn: 0.4527199\ttotal: 49m 6s\tremaining: 0us\n",
+      "Learning rate set to 0.008715\n",
+      "0:\tlearn: 1.0070361\ttotal: 76.6ms\tremaining: 25m 31s\n",
+      "5000:\tlearn: 0.5676638\ttotal: 12m 51s\tremaining: 38m 33s\n",
+      "10000:\tlearn: 0.5046212\ttotal: 23m 32s\tremaining: 23m 32s\n",
+      "15000:\tlearn: 0.4696909\ttotal: 34m 21s\tremaining: 11m 26s\n",
+      "19999:\tlearn: 0.4463740\ttotal: 45m 11s\tremaining: 0us\n",
+      "0.8447744377236096\n"
+     ]
+    }
+   ],
+   "source": [
+    "catbr = CatBoostRegressor(verbose=5000,task_type='GPU',loss_function='RMSE',iterations = 20000,depth = 12).fit(X_train,y_train)\n",
+    "# R2CV = cross_val_score(catbr,X_test,y_test,cv=3,scoring=\"r2\").mean()\n",
+    "error = -cross_val_score(catbr,X_test,y_test,cv=2,scoring=\"neg_mean_squared_error\").mean()\n",
+    "# print(R2CV)\n",
+    "print(np.sqrt(error))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "96a52e15",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T14:45:06.074785Z",
+     "iopub.status.busy": "2022-09-05T14:45:06.074091Z",
+     "iopub.status.idle": "2022-09-05T14:45:06.077959Z",
+     "shell.execute_reply": "2022-09-05T14:45:06.077027Z"
+    },
+    "papermill": {
+     "duration": 0.011987,
+     "end_time": "2022-09-05T14:45:06.080009",
+     "exception": false,
+     "start_time": "2022-09-05T14:45:06.068022",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# params = {\n",
+    "    \n",
+    "#     \"depth\": [2, 3, 4, 5, 6],\n",
+    "#     \"learning_rate\": [0.1, 0.01, 0.5]\n",
+    "# }"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "58836338",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T14:45:06.091493Z",
+     "iopub.status.busy": "2022-09-05T14:45:06.091219Z",
+     "iopub.status.idle": "2022-09-05T14:45:06.095298Z",
+     "shell.execute_reply": "2022-09-05T14:45:06.094449Z"
+    },
+    "papermill": {
+     "duration": 0.012206,
+     "end_time": "2022-09-05T14:45:06.097198",
+     "exception": false,
+     "start_time": "2022-09-05T14:45:06.084992",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# cv = GridSearchCV(catbr, params, cv=10, verbose=True).fit(X_train, y_train)\n",
+    "# print(cv.best_params_)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "81fb1672",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T14:45:06.107939Z",
+     "iopub.status.busy": "2022-09-05T14:45:06.107678Z",
+     "iopub.status.idle": "2022-09-05T14:45:06.111581Z",
+     "shell.execute_reply": "2022-09-05T14:45:06.110646Z"
+    },
+    "papermill": {
+     "duration": 0.011411,
+     "end_time": "2022-09-05T14:45:06.113552",
+     "exception": false,
+     "start_time": "2022-09-05T14:45:06.102141",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# catbrtuned = CatBoostRegressor(depth=5,learning_rate=0.01,verbose=False,task_type='GPU').fit(X_train,y_train)\n",
+    "\n",
+    "# # R2CVtuned = cross_val_score(catbrtuned,X_test,y_test,cv=15,scoring=\"r2\").mean()\n",
+    "# # print(R2CVtuned)\n",
+    "# errortuned = -cross_val_score(catbrtuned,X_test,y_test,cv=20,scoring=\"neg_mean_squared_error\").mean()\n",
+    "# print(np.sqrt(errortuned))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "9654095f",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T14:45:06.124164Z",
+     "iopub.status.busy": "2022-09-05T14:45:06.123909Z",
+     "iopub.status.idle": "2022-09-05T14:45:06.130345Z",
+     "shell.execute_reply": "2022-09-05T14:45:06.129490Z"
+    },
+    "papermill": {
+     "duration": 0.013934,
+     "end_time": "2022-09-05T14:45:06.132270",
+     "exception": false,
+     "start_time": "2022-09-05T14:45:06.118336",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 1.01680714e-02,  6.52076470e-01, -1.71361082e+00, ...,\n",
+       "         1.49118772e-03,  1.63726624e-01,  3.10255375e-03],\n",
+       "       [ 1.24653160e-02,  1.40030095e-01,  9.08963077e-01, ...,\n",
+       "         6.54264303e-04,  1.87932998e+00, -2.37996666e-02],\n",
+       "       [ 1.56609992e+00,  3.08161424e-01, -3.38753181e-01, ...,\n",
+       "        -4.62755342e-02,  1.25592922e+00, -1.43120765e-02],\n",
+       "       ...,\n",
+       "       [ 8.24693308e-03, -1.65144148e-01, -1.91790940e+00, ...,\n",
+       "         1.21247452e-04,  1.06549128e+00,  3.83478623e-03],\n",
+       "       [ 9.59390026e-05, -1.42118970e+00, -6.56800351e-01, ...,\n",
+       "         5.07400206e-04, -1.61068698e+00,  1.05205829e-03],\n",
+       "       [ 2.32941353e-03,  1.13598956e-01, -1.35239977e-01, ...,\n",
+       "         8.06554653e-04, -4.00680340e-01, -5.26439826e-03]])"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "0bb3dd56",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T14:45:06.143546Z",
+     "iopub.status.busy": "2022-09-05T14:45:06.143260Z",
+     "iopub.status.idle": "2022-09-05T14:45:06.354494Z",
+     "shell.execute_reply": "2022-09-05T14:45:06.353489Z"
+    },
+    "papermill": {
+     "duration": 0.219067,
+     "end_time": "2022-09-05T14:45:06.356593",
+     "exception": false,
+     "start_time": "2022-09-05T14:45:06.137526",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>e1</th>\n",
+       "      <th>px1</th>\n",
+       "      <th>py1</th>\n",
+       "      <th>pz1</th>\n",
+       "      <th>pt1</th>\n",
+       "      <th>eta1</th>\n",
+       "      <th>phi1</th>\n",
+       "      <th>q1</th>\n",
+       "      <th>e2</th>\n",
+       "      <th>px2</th>\n",
+       "      <th>py2</th>\n",
+       "      <th>pz2</th>\n",
+       "      <th>pt2</th>\n",
+       "      <th>eta2</th>\n",
+       "      <th>phi2</th>\n",
+       "      <th>q2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3.900910</td>\n",
+       "      <td>24.920700</td>\n",
+       "      <td>-1.102674</td>\n",
+       "      <td>0.702628</td>\n",
+       "      <td>24.98810</td>\n",
+       "      <td>-42.967949</td>\n",
+       "      <td>-0.073422</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>0.726854</td>\n",
+       "      <td>0.715108</td>\n",
+       "      <td>-0.374241</td>\n",
+       "      <td>-1.351969</td>\n",
+       "      <td>-0.654767</td>\n",
+       "      <td>0.674536</td>\n",
+       "      <td>-0.987639</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>-3.401169</td>\n",
+       "      <td>-7.007870</td>\n",
+       "      <td>0.581511</td>\n",
+       "      <td>0.321741</td>\n",
+       "      <td>8.03705</td>\n",
+       "      <td>-0.162631</td>\n",
+       "      <td>2.629960</td>\n",
+       "      <td>1</td>\n",
+       "      <td>36.603944</td>\n",
+       "      <td>0.698290</td>\n",
+       "      <td>0.936158</td>\n",
+       "      <td>-0.772930</td>\n",
+       "      <td>0.828964</td>\n",
+       "      <td>0.647576</td>\n",
+       "      <td>-0.532239</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0.804254</td>\n",
+       "      <td>-1.219560</td>\n",
+       "      <td>1.557146</td>\n",
+       "      <td>0.949164</td>\n",
+       "      <td>12.61310</td>\n",
+       "      <td>0.337772</td>\n",
+       "      <td>-1.667640</td>\n",
+       "      <td>1</td>\n",
+       "      <td>-25.401295</td>\n",
+       "      <td>0.615361</td>\n",
+       "      <td>0.550970</td>\n",
+       "      <td>0.397435</td>\n",
+       "      <td>-0.525276</td>\n",
+       "      <td>0.723704</td>\n",
+       "      <td>0.481615</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1.073530</td>\n",
+       "      <td>-2.721070</td>\n",
+       "      <td>1.258642</td>\n",
+       "      <td>0.268368</td>\n",
+       "      <td>2.75403</td>\n",
+       "      <td>3.670449</td>\n",
+       "      <td>-2.986720</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>-42.101333</td>\n",
+       "      <td>0.741327</td>\n",
+       "      <td>0.236630</td>\n",
+       "      <td>-0.151015</td>\n",
+       "      <td>0.472083</td>\n",
+       "      <td>0.974790</td>\n",
+       "      <td>0.356768</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.704689</td>\n",
+       "      <td>16.055100</td>\n",
+       "      <td>1.471738</td>\n",
+       "      <td>-0.863552</td>\n",
+       "      <td>17.32390</td>\n",
+       "      <td>2.430194</td>\n",
+       "      <td>0.385110</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>-1.048602</td>\n",
+       "      <td>0.958089</td>\n",
+       "      <td>0.268982</td>\n",
+       "      <td>-0.264064</td>\n",
+       "      <td>-0.969478</td>\n",
+       "      <td>0.554407</td>\n",
+       "      <td>-0.101867</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29970</th>\n",
+       "      <td>-0.258829</td>\n",
+       "      <td>-10.658000</td>\n",
+       "      <td>-0.507161</td>\n",
+       "      <td>0.228920</td>\n",
+       "      <td>11.84330</td>\n",
+       "      <td>0.296608</td>\n",
+       "      <td>2.690370</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>-4.251468</td>\n",
+       "      <td>0.813939</td>\n",
+       "      <td>73.667501</td>\n",
+       "      <td>1.158823</td>\n",
+       "      <td>-0.148324</td>\n",
+       "      <td>0.954442</td>\n",
+       "      <td>0.388798</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29971</th>\n",
+       "      <td>-0.405636</td>\n",
+       "      <td>7.854990</td>\n",
+       "      <td>1.024085</td>\n",
+       "      <td>-0.860718</td>\n",
+       "      <td>17.05020</td>\n",
+       "      <td>-0.456347</td>\n",
+       "      <td>1.092010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>-1.616737</td>\n",
+       "      <td>0.550067</td>\n",
+       "      <td>1.162549</td>\n",
+       "      <td>-0.311051</td>\n",
+       "      <td>-0.897992</td>\n",
+       "      <td>0.772986</td>\n",
+       "      <td>-0.527932</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29972</th>\n",
+       "      <td>1.719597</td>\n",
+       "      <td>-3.273500</td>\n",
+       "      <td>1.397346</td>\n",
+       "      <td>0.577056</td>\n",
+       "      <td>3.28801</td>\n",
+       "      <td>-1.215898</td>\n",
+       "      <td>-3.047630</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0.628021</td>\n",
+       "      <td>0.542946</td>\n",
+       "      <td>0.143970</td>\n",
+       "      <td>-0.731390</td>\n",
+       "      <td>-0.307851</td>\n",
+       "      <td>0.734795</td>\n",
+       "      <td>-0.766423</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29973</th>\n",
+       "      <td>1.764202</td>\n",
+       "      <td>11.352600</td>\n",
+       "      <td>0.815074</td>\n",
+       "      <td>0.930537</td>\n",
+       "      <td>16.43280</td>\n",
+       "      <td>-0.126448</td>\n",
+       "      <td>0.808132</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>-1.111305</td>\n",
+       "      <td>0.932663</td>\n",
+       "      <td>-0.063397</td>\n",
+       "      <td>-0.153664</td>\n",
+       "      <td>-0.999193</td>\n",
+       "      <td>0.545050</td>\n",
+       "      <td>0.121883</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29974</th>\n",
+       "      <td>4.601752</td>\n",
+       "      <td>0.886162</td>\n",
+       "      <td>0.556092</td>\n",
+       "      <td>0.994464</td>\n",
+       "      <td>5.55010</td>\n",
+       "      <td>-2.074547</td>\n",
+       "      <td>1.410440</td>\n",
+       "      <td>1</td>\n",
+       "      <td>-3.578146</td>\n",
+       "      <td>0.628637</td>\n",
+       "      <td>-9.284831</td>\n",
+       "      <td>0.425168</td>\n",
+       "      <td>0.147698</td>\n",
+       "      <td>0.555115</td>\n",
+       "      <td>0.964454</td>\n",
+       "      <td>-1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>29975 rows × 16 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             e1        px1       py1       pz1       pt1       eta1      phi1  \\\n",
+       "0      3.900910  24.920700 -1.102674  0.702628  24.98810 -42.967949 -0.073422   \n",
+       "1     -3.401169  -7.007870  0.581511  0.321741   8.03705  -0.162631  2.629960   \n",
+       "2      0.804254  -1.219560  1.557146  0.949164  12.61310   0.337772 -1.667640   \n",
+       "3      1.073530  -2.721070  1.258642  0.268368   2.75403   3.670449 -2.986720   \n",
+       "4      0.704689  16.055100  1.471738 -0.863552  17.32390   2.430194  0.385110   \n",
+       "...         ...        ...       ...       ...       ...        ...       ...   \n",
+       "29970 -0.258829 -10.658000 -0.507161  0.228920  11.84330   0.296608  2.690370   \n",
+       "29971 -0.405636   7.854990  1.024085 -0.860718  17.05020  -0.456347  1.092010   \n",
+       "29972  1.719597  -3.273500  1.397346  0.577056   3.28801  -1.215898 -3.047630   \n",
+       "29973  1.764202  11.352600  0.815074  0.930537  16.43280  -0.126448  0.808132   \n",
+       "29974  4.601752   0.886162  0.556092  0.994464   5.55010  -2.074547  1.410440   \n",
+       "\n",
+       "       q1         e2       px2        py2       pz2       pt2      eta2  \\\n",
+       "0      -1   0.726854  0.715108  -0.374241 -1.351969 -0.654767  0.674536   \n",
+       "1       1  36.603944  0.698290   0.936158 -0.772930  0.828964  0.647576   \n",
+       "2       1 -25.401295  0.615361   0.550970  0.397435 -0.525276  0.723704   \n",
+       "3      -1 -42.101333  0.741327   0.236630 -0.151015  0.472083  0.974790   \n",
+       "4      -1  -1.048602  0.958089   0.268982 -0.264064 -0.969478  0.554407   \n",
+       "...    ..        ...       ...        ...       ...       ...       ...   \n",
+       "29970  -1  -4.251468  0.813939  73.667501  1.158823 -0.148324  0.954442   \n",
+       "29971   1  -1.616737  0.550067   1.162549 -0.311051 -0.897992  0.772986   \n",
+       "29972   1   0.628021  0.542946   0.143970 -0.731390 -0.307851  0.734795   \n",
+       "29973  -1  -1.111305  0.932663  -0.063397 -0.153664 -0.999193  0.545050   \n",
+       "29974   1  -3.578146  0.628637  -9.284831  0.425168  0.147698  0.555115   \n",
+       "\n",
+       "           phi2  q2  \n",
+       "0     -0.987639  -1  \n",
+       "1     -0.532239  -1  \n",
+       "2      0.481615   1  \n",
+       "3      0.356768  -1  \n",
+       "4     -0.101867  -1  \n",
+       "...         ...  ..  \n",
+       "29970  0.388798   1  \n",
+       "29971 -0.527932   1  \n",
+       "29972 -0.766423  -1  \n",
+       "29973  0.121883   1  \n",
+       "29974  0.964454  -1  \n",
+       "\n",
+       "[29975 rows x 16 columns]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test=pd.read_csv(\"../input/nsutai/test.csv\")\n",
+    "\n",
+    "X_test=test.drop('id',axis=1)\n",
+    "X_test = X_test.drop('event',axis=1)\n",
+    "# X_test = X_test.drop('id',axis=1)\n",
+    "\n",
+    "X_test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "46a97231",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2022-09-05T14:45:06.371027Z",
+     "iopub.status.busy": "2022-09-05T14:45:06.369496Z",
+     "iopub.status.idle": "2022-09-05T14:45:10.555987Z",
+     "shell.execute_reply": "2022-09-05T14:45:10.554972Z"
+    },
+    "papermill": {
+     "duration": 4.195275,
+     "end_time": "2022-09-05T14:45:10.558397",
+     "exception": false,
+     "start_time": "2022-09-05T14:45:06.363122",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "X_test['px12'] = X_test.px1 * X_test.px2\n",
+    "X_test['Q12'] = X_test.q1 * X_test.q2\n",
+    "X_test['phi12'] = X_test.phi1 * X_test.phi2\n",
+    "X_test['eta12'] = X_test.eta1 * X_test.eta2\n",
+    "X_test['pt12'] = X_test.pt1 * X_test.pt2\n",
+    "X_test['E12'] = X_test.e1 * X_test.e2\n",
+    "X_test['pz_diff'] = X_test.pz1 - X_test.pz2\n",
+    "X_test['eta_diff'] = X_test.eta1 - X_test.eta2\n",
+    "y_pred=catbr.predict(X_test)\n",
+    "sample_submission=pd.read_csv(\"../input/nsutai/sample_submission.csv\")\n",
+    "sample_submission['mass']=y_pred\n",
+    "sample_submission.to_csv('submission.csv',index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b5dfc088",
+   "metadata": {
+    "papermill": {
+     "duration": 0.005294,
+     "end_time": "2022-09-05T14:45:10.569668",
+     "exception": false,
+     "start_time": "2022-09-05T14:45:10.564374",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.12"
+  },
+  "papermill": {
+   "default_parameters": {},
+   "duration": 6189.341373,
+   "end_time": "2022-09-05T14:45:11.404111",
+   "environment_variables": {},
+   "exception": null,
+   "input_path": "__notebook__.ipynb",
+   "output_path": "__notebook__.ipynb",
+   "parameters": {},
+   "start_time": "2022-09-05T13:02:02.062738",
+   "version": "2.3.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}