|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "code", |
| 5 | + "execution_count": 21, |
| 6 | + "metadata": {}, |
| 7 | + "outputs": [], |
| 8 | + "source": [ |
| 9 | + "#import library\n", |
| 10 | + "\n", |
| 11 | + "from sklearn.datasets import load_boston\n", |
| 12 | + "import xgboost as xgb\n", |
| 13 | + "from sklearn.metrics import mean_squared_error\n", |
| 14 | + "import pandas as pd\n", |
| 15 | + "import numpy as np" |
| 16 | + ] |
| 17 | + }, |
| 18 | + { |
| 19 | + "cell_type": "code", |
| 20 | + "execution_count": 22, |
| 21 | + "metadata": {}, |
| 22 | + "outputs": [ |
| 23 | + { |
| 24 | + "name": "stdout", |
| 25 | + "output_type": "stream", |
| 26 | + "text": [ |
| 27 | + "dict_keys(['data', 'target', 'feature_names', 'DESCR', 'filename'])\n" |
| 28 | + ] |
| 29 | + } |
| 30 | + ], |
| 31 | + "source": [ |
| 32 | + "#load Data\n", |
| 33 | + "boston = load_boston()\n", |
| 34 | + "print(boston.keys())" |
| 35 | + ] |
| 36 | + }, |
| 37 | + { |
| 38 | + "cell_type": "code", |
| 39 | + "execution_count": 23, |
| 40 | + "metadata": {}, |
| 41 | + "outputs": [ |
| 42 | + { |
| 43 | + "name": "stdout", |
| 44 | + "output_type": "stream", |
| 45 | + "text": [ |
| 46 | + "(506, 13)\n", |
| 47 | + "['CRIM' 'ZN' 'INDUS' 'CHAS' 'NOX' 'RM' 'AGE' 'DIS' 'RAD' 'TAX' 'PTRATIO'\n", |
| 48 | + " 'B' 'LSTAT']\n" |
| 49 | + ] |
| 50 | + } |
| 51 | + ], |
| 52 | + "source": [ |
| 53 | + "print(boston.data.shape)\n", |
| 54 | + "print(boston.feature_names)" |
| 55 | + ] |
| 56 | + }, |
| 57 | + { |
| 58 | + "cell_type": "code", |
| 59 | + "execution_count": 24, |
| 60 | + "metadata": {}, |
| 61 | + "outputs": [], |
| 62 | + "source": [ |
| 63 | + "#covert data into DataFrame\n", |
| 64 | + "data = pd.DataFrame(boston.data)\n", |
| 65 | + "data.columns = boston.feature_names" |
| 66 | + ] |
| 67 | + }, |
| 68 | + { |
| 69 | + "cell_type": "code", |
| 70 | + "execution_count": 25, |
| 71 | + "metadata": {}, |
| 72 | + "outputs": [], |
| 73 | + "source": [ |
| 74 | + "#set depend and predictor\n", |
| 75 | + "data['PRICE'] = boston.target\n", |
| 76 | + "data.describe()\n", |
| 77 | + "X, y = data.iloc[:,:-1],data.iloc[:,-1]" |
| 78 | + ] |
| 79 | + }, |
| 80 | + { |
| 81 | + "cell_type": "code", |
| 82 | + "execution_count": 26, |
| 83 | + "metadata": {}, |
| 84 | + "outputs": [ |
| 85 | + { |
| 86 | + "name": "stderr", |
| 87 | + "output_type": "stream", |
| 88 | + "text": [ |
| 89 | + "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/xgboost/core.py:587: FutureWarning: Series.base is deprecated and will be removed in a future version\n", |
| 90 | + " if getattr(data, 'base', None) is not None and \\\n", |
| 91 | + "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/xgboost/core.py:588: FutureWarning: Series.base is deprecated and will be removed in a future version\n", |
| 92 | + " data.base is not None and isinstance(data, np.ndarray) \\\n" |
| 93 | + ] |
| 94 | + } |
| 95 | + ], |
| 96 | + "source": [ |
| 97 | + "#xgb model\n", |
| 98 | + "data_dmatrix = xgb.DMatrix(data=X,label=y)" |
| 99 | + ] |
| 100 | + }, |
| 101 | + { |
| 102 | + "cell_type": "code", |
| 103 | + "execution_count": 27, |
| 104 | + "metadata": {}, |
| 105 | + "outputs": [], |
| 106 | + "source": [ |
| 107 | + "#spilt data\n", |
| 108 | + "from sklearn.model_selection import train_test_split\n", |
| 109 | + "\n", |
| 110 | + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=123)" |
| 111 | + ] |
| 112 | + }, |
| 113 | + { |
| 114 | + "cell_type": "code", |
| 115 | + "execution_count": 28, |
| 116 | + "metadata": {}, |
| 117 | + "outputs": [], |
| 118 | + "source": [ |
| 119 | + "#XGBRegressor model\n", |
| 120 | + "xg_reg = xgb.XGBRegressor(objective ='reg:linear', colsample_bytree = 0.3, learning_rate = 0.1,\n", |
| 121 | + " max_depth = 5, alpha = 10, n_estimators = 10)" |
| 122 | + ] |
| 123 | + }, |
| 124 | + { |
| 125 | + "cell_type": "code", |
| 126 | + "execution_count": 29, |
| 127 | + "metadata": {}, |
| 128 | + "outputs": [ |
| 129 | + { |
| 130 | + "name": "stdout", |
| 131 | + "output_type": "stream", |
| 132 | + "text": [ |
| 133 | + "[16:18:05] WARNING: src/objective/regression_obj.cu:152: reg:linear is now deprecated in favor of reg:squarederror.\n" |
| 134 | + ] |
| 135 | + } |
| 136 | + ], |
| 137 | + "source": [ |
| 138 | + "#fit model\n", |
| 139 | + "xg_reg.fit(X_train,y_train)\n", |
| 140 | + "\n", |
| 141 | + "preds = xg_reg.predict(X_test)" |
| 142 | + ] |
| 143 | + }, |
| 144 | + { |
| 145 | + "cell_type": "code", |
| 146 | + "execution_count": 30, |
| 147 | + "metadata": {}, |
| 148 | + "outputs": [ |
| 149 | + { |
| 150 | + "name": "stdout", |
| 151 | + "output_type": "stream", |
| 152 | + "text": [ |
| 153 | + "RMSE: 10.397587\n" |
| 154 | + ] |
| 155 | + } |
| 156 | + ], |
| 157 | + "source": [ |
| 158 | + "#check error\n", |
| 159 | + "rmse = np.sqrt(mean_squared_error(y_test, preds))\n", |
| 160 | + "print(\"RMSE: %f\" % (rmse))" |
| 161 | + ] |
| 162 | + } |
| 163 | + ], |
| 164 | + "metadata": { |
| 165 | + "kernelspec": { |
| 166 | + "display_name": "Python 3", |
| 167 | + "language": "python", |
| 168 | + "name": "python3" |
| 169 | + }, |
| 170 | + "language_info": { |
| 171 | + "codemirror_mode": { |
| 172 | + "name": "ipython", |
| 173 | + "version": 3 |
| 174 | + }, |
| 175 | + "file_extension": ".py", |
| 176 | + "mimetype": "text/x-python", |
| 177 | + "name": "python", |
| 178 | + "nbconvert_exporter": "python", |
| 179 | + "pygments_lexer": "ipython3", |
| 180 | + "version": "3.7.7" |
| 181 | + } |
| 182 | + }, |
| 183 | + "nbformat": 4, |
| 184 | + "nbformat_minor": 4 |
| 185 | +} |
0 commit comments