决策树完成叶子分类.ipynb · mlnt/machelearning2

1月18日，北京，聊聊2025如何加入技术开发？

forked from sdau20171754/machelearning2

加入 Gitee

与超过 1200万开发者一起发现、参与优秀开源项目，私有仓库也完全免费：）

免费加入

文件

该仓库未声明开源许可证文件（LICENSE），使用请关注具体项目描述及其代码上游依赖。

克隆/下载

决策树完成叶子分类.ipynb 23.82 KB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "train=pd.read_csv('train.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "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>id</th>\n",
       "      <th>species</th>\n",
       "      <th>margin1</th>\n",
       "      <th>margin2</th>\n",
       "      <th>margin3</th>\n",
       "      <th>margin4</th>\n",
       "      <th>margin5</th>\n",
       "      <th>margin6</th>\n",
       "      <th>margin7</th>\n",
       "      <th>margin8</th>\n",
       "      <th>...</th>\n",
       "      <th>texture55</th>\n",
       "      <th>texture56</th>\n",
       "      <th>texture57</th>\n",
       "      <th>texture58</th>\n",
       "      <th>texture59</th>\n",
       "      <th>texture60</th>\n",
       "      <th>texture61</th>\n",
       "      <th>texture62</th>\n",
       "      <th>texture63</th>\n",
       "      <th>texture64</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Acer_Opalus</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.011719</td>\n",
       "      <td>0.009766</td>\n",
       "      <td>0.027344</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.002930</td>\n",
       "      <td>0.002930</td>\n",
       "      <td>0.035156</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.004883</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.025391</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>Pterocarya_Stenoptera</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.031250</td>\n",
       "      <td>0.015625</td>\n",
       "      <td>0.025391</td>\n",
       "      <td>0.001953</td>\n",
       "      <td>0.019531</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.039062</td>\n",
       "      <td>0.022461</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>Quercus_Hartwissiana</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.009766</td>\n",
       "      <td>0.019531</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.068359</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.154300</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.020508</td>\n",
       "      <td>0.002930</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>5</td>\n",
       "      <td>Tilia_Tomentosa</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.021484</td>\n",
       "      <td>0.019531</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.020508</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.017578</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.047852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>Quercus_Variabilis</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.048828</td>\n",
       "      <td>0.009766</td>\n",
       "      <td>0.013672</td>\n",
       "      <td>0.015625</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.096680</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021484</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.031250</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 194 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   id                species   margin1   margin2   margin3   margin4  \\\n",
       "0   1            Acer_Opalus  0.007812  0.023438  0.023438  0.003906   \n",
       "1   2  Pterocarya_Stenoptera  0.005859  0.000000  0.031250  0.015625   \n",
       "2   3   Quercus_Hartwissiana  0.005859  0.009766  0.019531  0.007812   \n",
       "3   5        Tilia_Tomentosa  0.000000  0.003906  0.023438  0.005859   \n",
       "4   6     Quercus_Variabilis  0.005859  0.003906  0.048828  0.009766   \n",
       "\n",
       "    margin5   margin6   margin7  margin8    ...      texture55  texture56  \\\n",
       "0  0.011719  0.009766  0.027344      0.0    ...       0.007812   0.000000   \n",
       "1  0.025391  0.001953  0.019531      0.0    ...       0.000977   0.000000   \n",
       "2  0.003906  0.005859  0.068359      0.0    ...       0.154300   0.000000   \n",
       "3  0.021484  0.019531  0.023438      0.0    ...       0.000000   0.000977   \n",
       "4  0.013672  0.015625  0.005859      0.0    ...       0.096680   0.000000   \n",
       "\n",
       "   texture57  texture58  texture59  texture60  texture61  texture62  \\\n",
       "0   0.002930   0.002930   0.035156        0.0        0.0   0.004883   \n",
       "1   0.000000   0.000977   0.023438        0.0        0.0   0.000977   \n",
       "2   0.005859   0.000977   0.007812        0.0        0.0   0.000000   \n",
       "3   0.000000   0.000000   0.020508        0.0        0.0   0.017578   \n",
       "4   0.021484   0.000000   0.000000        0.0        0.0   0.000000   \n",
       "\n",
       "   texture63  texture64  \n",
       "0   0.000000   0.025391  \n",
       "1   0.039062   0.022461  \n",
       "2   0.020508   0.002930  \n",
       "3   0.000000   0.047852  \n",
       "4   0.000000   0.031250  \n",
       "\n",
       "[5 rows x 194 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(990, 194)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "99"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(train.species.unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[ 3 49 65 94 84 40 54 78 53 89 98 16 74 50 58 31 43  4 75 44 83 84 13 66\n",
      " 15  6 73 22 73 31 36 27 94 88 12 28 21 25 20 60 84 65 69 58 23 76 18 52\n",
      " 54  9 48 47 64 81 83 36 58 21 81 20 62 88 34 92 79 82 20 32  4 84 36 35\n",
      " 72 60 71 72 52 50 54 11 51 18 47  5  8 37 97 20 33  1 59  1 56  1  9 57\n",
      " 20 79 29 16 32 54 93 10 46 59 84 76 15 10 15  0 69  4 51 51 94 36 39 62\n",
      "  2 24 26 35 25 87  0 55 34 38  1 45  7 93 56 38 21 51 75 81 74 33 20 37\n",
      "  9 40 60 31 83 50 71 67 30 66  1 43 61 23 65 84 87 46 57 16  2 28 12 96\n",
      " 44 76 29 75 41 87 67 61 30  5 12 62  3 83 81  6 85  4 37 57 84 39 71 61\n",
      "  6 76 14 31 98 40 17 51 16 42 63 86 37 69 86 71 80 78 14 35 25  5 39  8\n",
      "  9 26 44 60 13 14 77 13 80 87 18 60 78 92 51 45 78 41 51 30 14 35 46 21\n",
      "  8  6 92 38 40 15 32 17 93 71 92 27 78 15 19 60 21 38 36 49 74 67 95 31\n",
      " 82 45 16 83 63 80 42 22 74 53 15 44 47 57 94 76 17 32 24 15 93 24 80 59\n",
      " 46 12 51 77 79 70 69 16  2 63 83 55 12 53  1 67  0  2 36 42 10  9 52 59\n",
      "  6 22 86 31 51 37 43 75 90 24 86 96 45 32 98 36 66 48 73 73 79 56 41 21\n",
      " 25 27 97 18 44 45 40 80 63 20 35  0  8 27 25 35 59 61 21 37 29  6 19 78\n",
      " 50 54 37 93 33 46 79 59 29 43  0 23 17 38 66 38 89 17 25 31 65 10 26 86\n",
      " 58 42 46 24 95 93  8 53 32 14 10 94  8  8 64 44 74 30 97 22 11 68 56 90\n",
      " 96 16 43 57 91 24 28 82 90 64 61 92 28 84 70 45 85 34  7 88 89 61 26 88\n",
      " 41 46  8 91 41 14 98 28 26 36 70 74  7 52 70 42 66 22 13 44 91 53 22 16\n",
      " 40 40 28 70  6 60 95 23 16 50 29 49  9 18 55 63 60 19 28 30 31 85 66 88\n",
      " 63 83 64 96 13 34 27 95 36 72 29 91 22 65 71 66 11 32  2 75 39  5 37 67\n",
      " 81 55 61 57 81 82 63 55 54 35 86 25 24 96 10 58 59 28 89 54 52 85 68 69\n",
      "  8 39 95 39 82 48 74 52 74 55  9 47 84 91 12 96 82 64  7 40 73 77 11 36\n",
      " 68 23 28 46 75 43  2 11 47 53 56 62 62 80 56 30  3 88 37 33 73 76 21  5\n",
      " 76 87 68 83 62 57 47 19 88 96 42 23 44 87 82 49 63 24 94 69 54  5 79 43\n",
      " 12 50  5 52 92  4 84  1 33 49 26 18 44 13 24 73 89 78 67 41 11 46 47 69\n",
      "  0 18 98 44 85 29 53  1 45  3  9 13  2 66 59 79  6 17 43 83 26  1 12 49\n",
      " 71 89 58 93 39 42 15 38 55 15 93  4 90 88 55 40 55 17 34 94 57 92 81 26\n",
      " 60 89 49 89 30 65 58  4 19  4 76 74 71 21 54 13 16 72 68 62 61 25 72  7\n",
      " 12 18 77 90 62 14  3 78 65 37 27 50 95 98 60 72 58 38 87 93 19  7 83 50\n",
      "  3 91 77  7 64 61 69 23 76 65 48 41 92 20 91 18 70  9  9 29 85 67  0 35\n",
      " 98 91 90 31 53 39 24 85 96 17  7 11 96 39 56 90 79 45 64 97 41 19 74 11\n",
      " 10 62 95 28 96 10  7 68  7 93 34 42 68 41 14 22 58 12 71 27 98 72 91  3\n",
      " 43 19 61 75 20 81 63 67 56 26 47 11 31 57 62 66 19 75 97 94 13 75 95 32\n",
      " 50 97 52 87 32  3 47 77 48 33 73 64 49 68 43 94 77 68 47 82  2 30 23 33\n",
      " 34 66 33 35 88 68 27 87 54 79 34 67 65 18  4 26 30 52 86  0 29 80 67 95\n",
      " 39 25 70 58 35 27 17 38 91 13 23 77 79 77 22 49 98 48 46 48  5 63 97 80\n",
      " 53 20 25 78 10 65 33 41 85 90 98 97 71 95 52  3 29 69 51 70 27 22 34  6\n",
      " 48 72 21 89 17 97 72 80 10 57 64 92 38 15 73 87 73 48 42 82 33 56  3 42\n",
      "  1 53 55 90 19  6 30 86 64 49  2  8 45 76 92  0 23 69 59 80 90 32  5 59\n",
      " 85 89 94 45 48 86 81 14  4 77 56 82  2 85 70 88  0 75 14 86 81 97 70 72\n",
      " 34 40  5 11 78 50]\n"
     ]
    }
   ],
   "source": [
    "lb=LabelEncoder()\n",
    "labels=lb.fit_transform(train.species)\n",
    "print(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "data=train.drop(['species','id'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "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>margin1</th>\n",
       "      <th>margin2</th>\n",
       "      <th>margin3</th>\n",
       "      <th>margin4</th>\n",
       "      <th>margin5</th>\n",
       "      <th>margin6</th>\n",
       "      <th>margin7</th>\n",
       "      <th>margin8</th>\n",
       "      <th>margin9</th>\n",
       "      <th>margin10</th>\n",
       "      <th>...</th>\n",
       "      <th>texture55</th>\n",
       "      <th>texture56</th>\n",
       "      <th>texture57</th>\n",
       "      <th>texture58</th>\n",
       "      <th>texture59</th>\n",
       "      <th>texture60</th>\n",
       "      <th>texture61</th>\n",
       "      <th>texture62</th>\n",
       "      <th>texture63</th>\n",
       "      <th>texture64</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.011719</td>\n",
       "      <td>0.009766</td>\n",
       "      <td>0.027344</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.001953</td>\n",
       "      <td>0.033203</td>\n",
       "      <td>...</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.002930</td>\n",
       "      <td>0.002930</td>\n",
       "      <td>0.035156</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.004883</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.025391</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.031250</td>\n",
       "      <td>0.015625</td>\n",
       "      <td>0.025391</td>\n",
       "      <td>0.001953</td>\n",
       "      <td>0.019531</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.039062</td>\n",
       "      <td>0.022461</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.009766</td>\n",
       "      <td>0.019531</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.068359</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.044922</td>\n",
       "      <td>...</td>\n",
       "      <td>0.154300</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.007812</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.020508</td>\n",
       "      <td>0.002930</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.021484</td>\n",
       "      <td>0.019531</td>\n",
       "      <td>0.023438</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.013672</td>\n",
       "      <td>0.017578</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000977</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.020508</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.017578</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.047852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.003906</td>\n",
       "      <td>0.048828</td>\n",
       "      <td>0.009766</td>\n",
       "      <td>0.013672</td>\n",
       "      <td>0.015625</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.005859</td>\n",
       "      <td>...</td>\n",
       "      <td>0.096680</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021484</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.031250</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 192 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    margin1   margin2   margin3   margin4   margin5   margin6   margin7  \\\n",
       "0  0.007812  0.023438  0.023438  0.003906  0.011719  0.009766  0.027344   \n",
       "1  0.005859  0.000000  0.031250  0.015625  0.025391  0.001953  0.019531   \n",
       "2  0.005859  0.009766  0.019531  0.007812  0.003906  0.005859  0.068359   \n",
       "3  0.000000  0.003906  0.023438  0.005859  0.021484  0.019531  0.023438   \n",
       "4  0.005859  0.003906  0.048828  0.009766  0.013672  0.015625  0.005859   \n",
       "\n",
       "   margin8   margin9  margin10    ...      texture55  texture56  texture57  \\\n",
       "0      0.0  0.001953  0.033203    ...       0.007812   0.000000   0.002930   \n",
       "1      0.0  0.000000  0.007812    ...       0.000977   0.000000   0.000000   \n",
       "2      0.0  0.000000  0.044922    ...       0.154300   0.000000   0.005859   \n",
       "3      0.0  0.013672  0.017578    ...       0.000000   0.000977   0.000000   \n",
       "4      0.0  0.000000  0.005859    ...       0.096680   0.000000   0.021484   \n",
       "\n",
       "   texture58  texture59  texture60  texture61  texture62  texture63  texture64  \n",
       "0   0.002930   0.035156        0.0        0.0   0.004883   0.000000   0.025391  \n",
       "1   0.000977   0.023438        0.0        0.0   0.000977   0.039062   0.022461  \n",
       "2   0.000977   0.007812        0.0        0.0   0.000000   0.020508   0.002930  \n",
       "3   0.000000   0.020508        0.0        0.0   0.017578   0.000000   0.047852  \n",
       "4   0.000000   0.000000        0.0        0.0   0.000000   0.000000   0.031250  \n",
       "\n",
       "[5 rows x 192 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 3, 49, 65, 94, 84], dtype=int64)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "labels[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train,x_test,y_train,y_test=train_test_split(data,labels,test_size=0.3,stratify=labels,random_state=20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tree=DecisionTreeClassifier()\n",
    "tree.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6397306397306397"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tree.score(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tree.score(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=70,\n",
      "            max_features=None, max_leaf_nodes=None,\n",
      "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
      "            min_samples_leaf=2, min_samples_split=2,\n",
      "            min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
      "            splitter='best')\n"
     ]
    }
   ],
   "source": [
    "#网格搜索\n",
    "#max_depth 树的最大深度\n",
    "#min_samples_split 内部节点再划分所需的最小样本数\n",
    "#min_samples_leaf 叶子结点最小样本数\n",
    "param_grid={'max_depth':[30,40,50,60,70],\n",
    "            'min_samples_split':[2,3,4,5,6],\n",
    "            'min_samples_leaf':[1,2,3,4]\n",
    "           }\n",
    "model=GridSearchCV(DecisionTreeClassifier(),param_grid,cv=3)#切分成3份\n",
    "model.fit(x_train,y_train)\n",
    "print(model.best_estimator_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6464646464646465"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.score(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "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
}

一键复制编辑原始数据按行查看历史

提交于 2020-02-04 21:37 . 机器学习2

马建仓 AI 助手

尝试更多

代码解读

代码找茬

代码优化

https://gitee.com/mlnt/machelearning2.git

git@gitee.com:mlnt/machelearning2.git

mlnt

machelearning2

master

mlnt/machelearning2

简介

发行版

贡献者

近期动态

mlnt/machelearning2 .gitee-modal { width: 500px !important; }

简介

发行版

贡献者

近期动态

搜索帮助

mlnt/machelearning2