Add files via upload

Author: luwill

charpter13_LightGBM/lightgbm.ipynb

@@ -0,0 +1,122 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1]\tvalid_0's multi_logloss: 1.02277\n",
+      "Training until validation scores don't improve for 5 rounds\n",
+      "[2]\tvalid_0's multi_logloss: 0.943765\n",
+      "[3]\tvalid_0's multi_logloss: 0.873274\n",
+      "[4]\tvalid_0's multi_logloss: 0.810478\n",
+      "[5]\tvalid_0's multi_logloss: 0.752973\n",
+      "[6]\tvalid_0's multi_logloss: 0.701621\n",
+      "[7]\tvalid_0's multi_logloss: 0.654982\n",
+      "[8]\tvalid_0's multi_logloss: 0.611268\n",
+      "[9]\tvalid_0's multi_logloss: 0.572202\n",
+      "[10]\tvalid_0's multi_logloss: 0.53541\n",
+      "[11]\tvalid_0's multi_logloss: 0.502582\n",
+      "[12]\tvalid_0's multi_logloss: 0.472856\n",
+      "[13]\tvalid_0's multi_logloss: 0.443853\n",
+      "[14]\tvalid_0's multi_logloss: 0.417764\n",
+      "[15]\tvalid_0's multi_logloss: 0.393613\n",
+      "[16]\tvalid_0's multi_logloss: 0.370679\n",
+      "[17]\tvalid_0's multi_logloss: 0.349936\n",
+      "[18]\tvalid_0's multi_logloss: 0.330669\n",
+      "[19]\tvalid_0's multi_logloss: 0.312805\n",
+      "[20]\tvalid_0's multi_logloss: 0.296973\n",
+      "Did not meet early stopping. Best iteration is:\n",
+      "[20]\tvalid_0's multi_logloss: 0.296973\n",
+      "Accuracy of lightgbm: 1.0\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# 导入相关模块\n",
+    "import lightgbm as lgb\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.datasets import load_iris\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import matplotlib.pyplot as plt\n",
+    "# 导入iris数据集\n",
+    "iris = load_iris()\n",
+    "data = iris.data\n",
+    "target = iris.target\n",
+    "# 数据集划分\n",
+    "X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=43)\n",
+    "# 创建lightgbm分类模型\n",
+    "gbm = lgb.LGBMClassifier(objective='multiclass',\n",
+    "                         num_class=3,\n",
+    "                         num_leaves=31,\n",
+    "                         learning_rate=0.05,\n",
+    "                         n_estimators=20)\n",
+    "# 模型训练\n",
+    "gbm.fit(X_train, y_train, eval_set=[(X_test, y_test)], early_stopping_rounds=5)\n",
+    "# 预测测试集\n",
+    "y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration_)\n",
+    "# 模型评估\n",
+    "print('Accuracy of lightgbm:', accuracy_score(y_test, y_pred))\n",
+    "lgb.plot_importance(gbm)\n",
+    "plt.show();"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "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": "3.7.3"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}