{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 排卵试纸机器学习算法验证" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 1. **import moudle**" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd \n", "import seaborn as sns\n", "from IPython.display import display\n", "import matplotlib.pyplot as plt\n", "from mpl_toolkits.mplot3d import Axes3D\n", "import sklearn\n", "%matplotlib inline\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 2. **load data**" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "load data successful !!!!!\n" ] } ], "source": [ "try :\n", "# data_iphone6p_75_10 = pd.read_csv(\"20170912.pm.csv\")\n", "# data_iphone6p_1234 = pd.read_csv(\"20170920.pm.csv\")\n", "# data_iphone6p_5 = pd.read_csv(\"20170922.pm.csv\")\n", "# data_iphone6p_0 = pd.read_csv(\"20170925.am.csv\")\n", "# data_iphone6p_0_0 = pd.read_csv(\"20170925.pm.csv\")\n", "# data_iphone6p_246 = pd.read_csv(\"20171011.pm.csv\")\n", " \n", "# data1 = pd.read_csv(\"ovdata_reindex.csv\")\n", "# data2 = pd.read_csv(\"ovdataMore_reindex.csv\")\n", "# data3 = pd.read_csv(\"ov_data_2020_reindex.csv\")\n", " data1 = pd.read_csv(\"pregnancy_iphone.csv\")\n", " data2 = pd.read_csv(\"pregnancy_iphone1.csv\")\n", "\n", "# data4 = pd.read_csv(\"10_25_renew.csv\")\n", "\n", "# data_all = pd.read_csv(\"data_all_2019_2020_reindex.csv\")\n", "# data_all = pd.read_csv(\"ov_data_2020_reindex.csv\")\n", " \n", "# data1 = pd.read_csv(\"ovdata.csv\")\n", "# data2 = pd.read_csv(\"ovdataMore.csv\")\n", "# data3 = pd.read_csv(\"ov_data_2020.csv\")\n", "# data_test1 = pd.read_csv(\"./newData/test.csv\")\n", "# data_test2 = pd.read_csv(\"./newData/nubia_test.csv\")\n", " \n", " print (\"load data successful !!!!!\")\n", "except :\n", " print (\"load data error !!!!!!!!!!\")" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "data1.describe()\n", "data2.describe()\n", "data = data1.append(data2)\n", "data_all = data[data[\"whiteBalance\"] == 0]\n", "data0 = data_all[data_all[\"index\"] == 0]\n", "data5 = data_all[data_all[\"index\"] == 1]\n", "data10 = data_all[data_all[\"index\"] == 2]\n", "data25 = data_all[data_all[\"index\"] == 3]\n", "data40 = data_all[data_all[\"index\"] == 4]\n", "data50 = data_all[data_all[\"index\"] == 5]\n", "data75 = data_all[data_all[\"index\"] == 6]\n", "data100 = data_all[data_all[\"index\"] == 7]\n", "\n", "data0.to_csv('data0.csv')\n", "data5.to_csv('data5.csv')\n", "data10.to_csv('data10.csv')\n", "data25.to_csv('data25.csv')\n", "data40.to_csv('data40.csv')\n", "data50.to_csv('data50.csv')\n", "data75.to_csv('data75.csv')\n", "data100.to_csv('data100.csv')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 3. **分析数据**" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " left_block_R left_block_G left_block_B left_block_H left_block_S \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 180.289098 153.385590 160.582351 178.323906 44.126600 \n", "std 21.700504 35.551055 32.701433 78.575314 26.848687 \n", "min 58.000000 33.000000 34.000000 0.000000 0.000000 \n", "25% 162.000000 122.000000 134.000000 155.000000 18.000000 \n", "50% 181.000000 153.000000 159.000000 217.000000 45.000000 \n", "75% 198.000000 188.000000 190.000000 236.000000 68.000000 \n", "max 255.000000 255.000000 255.000000 250.000000 148.000000 \n", "\n", " left_block_V left_block_l left_block_a left_block_b \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 181.053984 167.856427 139.075259 127.747241 \n", "std 22.735616 30.366616 7.378973 3.389799 \n", "min 58.000000 41.000000 121.000000 114.000000 \n", "25% 163.000000 142.000000 133.000000 126.000000 \n", "50% 181.000000 169.000000 140.000000 128.000000 \n", "75% 198.000000 197.000000 146.000000 130.000000 \n", "max 255.000000 255.000000 154.000000 144.000000 \n", "\n", " left_block_R_stddev ... right_grayMax right_grayMin \\\n", "count 47662.000000 ... 47662.000000 47662.000000 \n", "mean 12.002476 ... 194.762725 122.369645 \n", "std 7.959948 ... 12.987519 18.713574 \n", "min 0.000000 ... 91.000000 24.000000 \n", "25% 4.000000 ... 189.000000 110.000000 \n", "50% 11.000000 ... 196.000000 120.000000 \n", "75% 19.000000 ... 202.000000 137.000000 \n", "max 32.000000 ... 255.000000 242.000000 \n", "\n", " white_grayValue white_grayStddevValue white_grayHist white_grayMax \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 201.867903 0.263627 202.181276 203.812240 \n", "std 13.437574 0.556166 14.096635 13.327305 \n", "min 102.000000 0.000000 0.000000 103.000000 \n", "25% 196.000000 0.000000 196.000000 198.000000 \n", "50% 202.000000 0.000000 202.000000 204.000000 \n", "75% 207.000000 0.000000 208.000000 209.000000 \n", "max 255.000000 17.000000 254.000000 255.000000 \n", "\n", " white_grayMin whiteBalance index Unnamed: 0 \n", "count 47662.000000 47662.0 47662.000000 5714.000000 \n", "mean 200.900340 0.0 2.187948 1289.203710 \n", "std 13.602098 0.0 1.380523 850.267883 \n", "min 101.000000 0.0 0.000000 0.000000 \n", "25% 194.000000 0.0 1.000000 570.250000 \n", "50% 201.000000 0.0 2.000000 1146.000000 \n", "75% 207.000000 0.0 4.000000 1981.500000 \n", "max 255.000000 0.0 4.000000 3226.000000 \n", "\n", "[8 rows x 153 columns]\n" ] } ], "source": [ "# data4 = data_iphone6p_246[data_iphone6p_246[\"whiteBalance\"] == 0]\n", "# data2= data_iphone6p_1234[data_iphone6p_1234[\"whiteBalance\"] == 0 ]\n", "# data1 = data_iphone6p_75_10[data_iphone6p_75_10[\"whiteBalance\"] == 0 ]\n", "# data3 = data_iphone6p_5[data_iphone6p_5[\"whiteBalance\"] == 0]\n", "# data0 = data_iphone6p_0[data_iphone6p_0[\"whiteBalance\"] == 0]\n", "# data0_0 = data_iphone6p_0_0[data_iphone6p_0_0[\"whiteBalance\"] == 0]\n", "\n", "\n", "#data_all = data2.append(data1[data1[\"index\"] == 5 ]).append(data3).append(data1[data1[\"index\"] == 7 ]).append(data1[data1[\"index\"] == 8 ]).append(data0).append(data0_0).append(data4)\n", "#data1['index'].replace(4,6,inplace=True)\n", "#data1['index'].replace(3,5,inplace=True)\n", "#data1['index'].replace(2,4,inplace=True)\n", "#data1['index'].replace(1,2,inplace=True)\n", "\n", "#data2['index'].replace(4,6,inplace=True)\n", "#data2['index'].replace(3,5,inplace=True)\n", "#data2['index'].replace(2,4,inplace=True)\n", "#data2['index'].replace(1,2,inplace=True)\n", "\n", "#data3['index'].replace(4,6,inplace=True)\n", "#data3['index'].replace(3,5,inplace=True)\n", "#data3['index'].replace(2,4,inplace=True)\n", "#data3['index'].replace(1,2,inplace=True)\n", "\n", "#data4['index'].replace(2,1,inplace=True)\n", "#data4['index'].replace(4,2,inplace=True)\n", "\n", "#data1_0 = data1[data1[\"whiteBalance\"] == 0]\n", "#data2_0 = data2[data2[\"whiteBalance\"] == 0]\n", "#data3_0 = data3[data3[\"whiteBalance\"] == 0]\n", "\n", "#data_test_0 = data_test\n", "\n", "#data_all =data1_0.append(data2_0);\n", "#data_all =data1.append(data2).append(data3);\n", "\n", "#data_all.to_csv('data_all_2019_2020_reindex.csv')\n", "#data1.to_csv('ovdata_modifed.csv')\n", "#data2.to_csv('ovdataMore_modifed.csv')\n", "#data3.to_csv('ov_data_2020_modifed.csv')\n", "#data4.to_csv('10_25_renew.csv')\n", "\n", "data =data1.append(data2).append(data3).append(data4)\n", "data_all = data[data[\"whiteBalance\"] == 0]\n", "print(data_all.describe())\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "whiteBlock_R_one =data_all[data_all[\"index\"] == 0 ][\"right_block_l_min\"]\n", "whiteBlock_G_one = data_all[data_all[\"index\"] == 0 ][\"right_block_a_min\"]\n", "whiteBlock_B_one = data_all[data_all[\"index\"] == 0 ][\"right_block_b_min\"]\n", "\n", "whiteBlock_R_two = data_all[data_all[\"index\"] == 1 ][\"right_block_l_min\"]\n", "whiteBlock_G_two = data_all[data_all[\"index\"] == 1 ][\"right_block_a_min\"]\n", "whiteBlock_B_two = data_all[data_all[\"index\"] == 1 ][\"right_block_b_min\"]\n", "\n", "whiteBlock_R_three = data_all[data_all[\"index\"] == 2 ][\"right_block_l_min\"]\n", "whiteBlock_G_three = data_all[data_all[\"index\"] == 2 ][\"right_block_a_min\"]\n", "whiteBlock_B_three = data_all[data_all[\"index\"] == 2 ][\"right_block_b_min\"]\n", "\n", "whiteBlock_R_four = data_all[data_all[\"index\"] == 4 ][\"right_block_l_min\"]\n", "whiteBlock_G_four = data_all[data_all[\"index\"] == 4 ][\"right_block_a_min\"]\n", "whiteBlock_B_four = data_all[data_all[\"index\"] == 4 ][\"right_block_b_min\"]\n", "\n", "\n", "whiteBlock_R_five = data_all[data_all[\"index\"] == 6 ][\"right_block_l_min\"]\n", "whiteBlock_G_five = data_all[data_all[\"index\"] == 6 ][\"right_block_a_min\"]\n", "whiteBlock_B_five = data_all[data_all[\"index\"] == 6 ][\"right_block_b_min\"]\n", "\n", "whiteBlock_R_six = data_all[data_all[\"index\"] == 7 ][\"right_block_l_min\"]\n", "whiteBlock_G_six = data_all[data_all[\"index\"] == 7 ][\"right_block_a_min\"]\n", "whiteBlock_B_six = data_all[data_all[\"index\"] == 7 ][\"right_block_b_min\"]\n", "\n", "fig = plt.figure()\n", "#plt.rcParams[\"figure.figsize\"] = 20,20\n", "ax = Axes3D(fig)\n", "\n", "ax.set_xlim(0,255)\n", "ax.set_ylim(0,255)\n", "ax.set_zlim(0,255)\n", "ax.set_xlabel('H')\n", "ax.set_ylabel('S')\n", "ax.set_zlabel('V')\n", "ax.set_title('HSV colorspace OV right block max value')\n", "# ax.scatter(whiteBlock_R_zero, whiteBlock_G_zero, whiteBlock_B_zero,s = 15,c='y')\n", "ax.scatter(whiteBlock_R_one, whiteBlock_G_one, whiteBlock_B_one,s = 15,c='r')\n", "\n", "ax.scatter(whiteBlock_R_two, whiteBlock_G_two, whiteBlock_B_two,s = 15,c='g')\n", "ax.scatter(whiteBlock_R_three, whiteBlock_G_three, whiteBlock_B_three,s = 15,c='b')\n", "\n", "ax.scatter(whiteBlock_R_four, whiteBlock_G_four, whiteBlock_B_four,s = 15,c='y')\n", "ax.scatter(whiteBlock_R_five, whiteBlock_G_five, whiteBlock_B_five,s = 15,c='pink')\n", "ax.scatter(whiteBlock_R_six, whiteBlock_G_six, whiteBlock_B_six,s = 15,c='c')\n", "\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "data_all.columns" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "hsv max min hist value h值要去掉" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 预处理数据" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
left_block_Rleft_block_Gleft_block_Bleft_block_Hleft_block_Sleft_block_Vleft_block_lleft_block_aleft_block_bleft_block_R_stddev...right_grayStddevValueright_grayHistright_grayMaxright_grayMinwhite_grayValuewhite_grayStddevValuewhite_grayHistwhite_grayMaxwhite_grayMinUnnamed: 0
count47662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.000000...47662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.0000005714.000000
mean180.289098153.385590160.582351178.32390644.126600181.053984167.856427139.075259127.74724112.002476...19.333809153.983719194.762725122.369645201.8679030.263627202.181276203.812240200.9003401289.203710
std21.70050435.55105532.70143378.57531426.84868722.73561630.3666167.3789733.3897997.959948...4.07141122.84810312.98751918.71357413.4375740.55616614.09663513.32730513.602098850.267883
min58.00000033.00000034.0000000.0000000.00000058.00000041.000000121.000000114.0000000.000000...1.00000028.00000091.00000024.000000102.0000000.0000000.000000103.000000101.0000000.000000
25%162.000000122.000000134.000000155.00000018.000000163.000000142.000000133.000000126.0000004.000000...16.000000139.000000189.000000110.000000196.0000000.000000196.000000198.000000194.000000570.250000
50%181.000000153.000000159.000000217.00000045.000000181.000000169.000000140.000000128.00000011.000000...19.000000151.000000196.000000120.000000202.0000000.000000202.000000204.000000201.0000001146.000000
75%198.000000188.000000190.000000236.00000068.000000198.000000197.000000146.000000130.00000019.000000...23.000000170.000000202.000000137.000000207.0000000.000000208.000000209.000000207.0000001981.500000
max255.000000255.000000255.000000250.000000148.000000255.000000255.000000154.000000144.00000032.000000...31.000000251.000000255.000000242.000000255.00000017.000000254.000000255.000000255.0000003226.000000
\n", "

8 rows × 151 columns

\n", "
" ], "text/plain": [ " left_block_R left_block_G left_block_B left_block_H left_block_S \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 180.289098 153.385590 160.582351 178.323906 44.126600 \n", "std 21.700504 35.551055 32.701433 78.575314 26.848687 \n", "min 58.000000 33.000000 34.000000 0.000000 0.000000 \n", "25% 162.000000 122.000000 134.000000 155.000000 18.000000 \n", "50% 181.000000 153.000000 159.000000 217.000000 45.000000 \n", "75% 198.000000 188.000000 190.000000 236.000000 68.000000 \n", "max 255.000000 255.000000 255.000000 250.000000 148.000000 \n", "\n", " left_block_V left_block_l left_block_a left_block_b \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 181.053984 167.856427 139.075259 127.747241 \n", "std 22.735616 30.366616 7.378973 3.389799 \n", "min 58.000000 41.000000 121.000000 114.000000 \n", "25% 163.000000 142.000000 133.000000 126.000000 \n", "50% 181.000000 169.000000 140.000000 128.000000 \n", "75% 198.000000 197.000000 146.000000 130.000000 \n", "max 255.000000 255.000000 154.000000 144.000000 \n", "\n", " left_block_R_stddev ... right_grayStddevValue right_grayHist \\\n", "count 47662.000000 ... 47662.000000 47662.000000 \n", "mean 12.002476 ... 19.333809 153.983719 \n", "std 7.959948 ... 4.071411 22.848103 \n", "min 0.000000 ... 1.000000 28.000000 \n", "25% 4.000000 ... 16.000000 139.000000 \n", "50% 11.000000 ... 19.000000 151.000000 \n", "75% 19.000000 ... 23.000000 170.000000 \n", "max 32.000000 ... 31.000000 251.000000 \n", "\n", " right_grayMax right_grayMin white_grayValue white_grayStddevValue \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 194.762725 122.369645 201.867903 0.263627 \n", "std 12.987519 18.713574 13.437574 0.556166 \n", "min 91.000000 24.000000 102.000000 0.000000 \n", "25% 189.000000 110.000000 196.000000 0.000000 \n", "50% 196.000000 120.000000 202.000000 0.000000 \n", "75% 202.000000 137.000000 207.000000 0.000000 \n", "max 255.000000 242.000000 255.000000 17.000000 \n", "\n", " white_grayHist white_grayMax white_grayMin Unnamed: 0 \n", "count 47662.000000 47662.000000 47662.000000 5714.000000 \n", "mean 202.181276 203.812240 200.900340 1289.203710 \n", "std 14.096635 13.327305 13.602098 850.267883 \n", "min 0.000000 103.000000 101.000000 0.000000 \n", "25% 196.000000 198.000000 194.000000 570.250000 \n", "50% 202.000000 204.000000 201.000000 1146.000000 \n", "75% 208.000000 209.000000 207.000000 1981.500000 \n", "max 254.000000 255.000000 255.000000 3226.000000 \n", "\n", "[8 rows x 151 columns]" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "\n", "train_labels = data_all[\"index\"]\n", "train_features = data_all.drop(\"dateTime\",axis=1)\n", "train_features = train_features.drop(\"index\",axis=1)\n", "train_features = train_features.drop(\"whiteBalance\",axis=1)\n", "\n", "\n", "\n", "train_features.describe()\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "#这一节的代码，不要执行\n", "\n", "train_features = train_features.drop(\"left_block_H\",axis=1)\n", "train_features = train_features.drop(\"left_block_S\",axis=1)\n", "train_features = train_features.drop(\"left_block_V\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H\",axis=1)\n", "train_features = train_features.drop(\"right_block_S\",axis=1)\n", "train_features = train_features.drop(\"right_block_V\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V\",axis=1)\n", "\n", "\n", "train_features = train_features.drop(\"left_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_hist\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_hist\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_hist\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_hist\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_min\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_min\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_min\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_min\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_min\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_min\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_min\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_min\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_min\",axis=1)\n", "\n", "\n", "\n", "train_features['lelf_right_R'] = train_features['left_block_R'] - train_features['right_block_R']\n", "train_features['lelf_right_G'] = train_features['left_block_G'] - train_features['right_block_G']\n", "train_features['lelf_right_B'] = train_features['left_block_B'] - train_features['right_block_B']\n", "\n", "# train_features['lelf_right_H'] = train_features['left_block_H'] - train_features['right_block_H']\n", "# train_features['lelf_right_S'] = train_features['left_block_S'] - train_features['right_block_S']\n", "# train_features['lelf_right_V'] = train_features['left_block_V'] - train_features['right_block_V']\n", "\n", "train_features['lelf_right_l'] = train_features['left_block_l'] - train_features['right_block_l']\n", "train_features['lelf_right_a'] = train_features['left_block_a'] - train_features['right_block_a']\n", "train_features['lelf_right_b'] = train_features['left_block_b'] - train_features['right_block_b']\n", "\n", "train_features['lelf_right_R_stddev'] = train_features['left_block_R_stddev'] - train_features['right_block_R_stddev']\n", "train_features['lelf_right_G_stddev'] = train_features['left_block_G_stddev'] - train_features['right_block_G_stddev']\n", "train_features['lelf_right_B_stddev'] = train_features['left_block_B_stddev'] - train_features['right_block_B_stddev']\n", "\n", "# train_features['lelf_right_H_stddev'] = train_features['left_block_H_stddev'] - train_features['right_block_H_stddev']\n", "# train_features['lelf_right_S_stddev'] = train_features['left_block_S_stddev'] - train_features['right_block_S_stddev']\n", "# train_features['lelf_right_V_stddev'] = train_features['left_block_V_stddev'] - train_features['right_block_V_stddev']\n", "\n", "train_features['lelf_right_l_stddev'] = train_features['left_block_l_stddev'] - train_features['right_block_l_stddev']\n", "train_features['lelf_right_a_stddev'] = train_features['left_block_a_stddev'] - train_features['right_block_a_stddev']\n", "train_features['lelf_right_b_stddev'] = train_features['left_block_b_stddev'] - train_features['right_block_b_stddev']\n", "\n", "train_features['lelf_right_R_hist'] = train_features['left_block_R_hist'] - train_features['right_block_R_hist']\n", "train_features['lelf_right_G_hist'] = train_features['left_block_G_hist'] - train_features['right_block_G_hist']\n", "train_features['lelf_right_B_hist'] = train_features['left_block_B_hist'] - train_features['right_block_B_hist']\n", "\n", "# train_features['lelf_right_H_hist'] = train_features['left_block_H_hist'] - train_features['right_block_H_hist']\n", "# train_features['lelf_right_S_hist'] = train_features['left_block_S_hist'] - train_features['right_block_S_hist']\n", "# train_features['lelf_right_V_hist'] = train_features['left_block_V_hist'] - train_features['right_block_V_hist']\n", "\n", "train_features['lelf_right_l_hist'] = train_features['left_block_l_hist'] - train_features['right_block_l_hist']\n", "train_features['lelf_right_a_hist'] = train_features['left_block_a_hist'] - train_features['right_block_a_hist']\n", "train_features['lelf_right_b_hist'] = train_features['left_block_b_hist'] - train_features['right_block_b_hist']\n", "\n", "train_features['lelf_right_R_max'] = train_features['left_block_R_max'] - train_features['right_block_R_max']\n", "train_features['lelf_right_G_max'] = train_features['left_block_G_max'] - train_features['right_block_G_max']\n", "train_features['lelf_right_B_max'] = train_features['left_block_B_max'] - train_features['right_block_B_max']\n", "\n", "# train_features['lelf_right_H_max'] = train_features['left_block_H_max'] - train_features['right_block_H_max']\n", "# train_features['lelf_right_S_max'] = train_features['left_block_S_max'] - train_features['right_block_S_max']\n", "# train_features['lelf_right_V_max'] = train_features['left_block_V_max'] - train_features['right_block_V_max']\n", "\n", "train_features['lelf_right_l_max'] = train_features['left_block_l_max'] - train_features['right_block_l_max']\n", "train_features['lelf_right_a_max'] = train_features['left_block_a_max'] - train_features['right_block_a_max']\n", "train_features['lelf_right_b_max'] = train_features['left_block_b_max'] - train_features['right_block_b_max']\n", "\n", "\n", "\n", "train_features['lelf_right_R_min'] = train_features['left_block_R_min'] - train_features['right_block_R_min']\n", "train_features['lelf_right_G_min'] = train_features['left_block_G_min'] - train_features['right_block_G_min']\n", "train_features['lelf_right_B_min'] = train_features['left_block_B_min'] - train_features['right_block_B_min']\n", "\n", "# train_features['lelf_right_H_min'] = train_features['left_block_H_min'] - train_features['right_block_H_min']\n", "# train_features['lelf_right_S_min'] = train_features['left_block_S_min'] - train_features['right_block_S_min']\n", "# train_features['lelf_right_V_min'] = train_features['left_block_V_min'] - train_features['right_block_V_min']\n", "\n", "train_features['lelf_right_l_min'] = train_features['left_block_l_min'] - train_features['right_block_l_min']\n", "train_features['lelf_right_a_min'] = train_features['left_block_a_min'] - train_features['right_block_a_min']\n", "train_features['lelf_right_b_min'] = train_features['left_block_b_min'] - train_features['right_block_b_min']\n", "\n", "train_features['lelf_right_gray_value'] = train_features['left_grayValue'] - train_features['right_grayValue']\n", "train_features['lelf_right_gray_stddev'] = train_features['left_grayStddevValue'] - train_features['right_grayStddevValue']\n", "train_features['lelf_right_gray_hist'] = train_features['left_grayHist'] - train_features['right_grayHist']\n", "train_features['lelf_right_gray_max'] = train_features['left_grayMax'] - train_features['right_grayMax']\n", "train_features['lelf_right_gray_min'] = train_features['left_grayMin'] - train_features['right_grayMin']\n", "train_features.describe()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# train_features_9是真正的训练数据" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
lelf_right_Rlelf_right_Glelf_right_Blelf_right_Hlelf_right_Slelf_right_Vlelf_right_llelf_right_alelf_right_blelf_right_R_stddev...lelf_right_S_minlelf_right_V_minlelf_right_l_minlelf_right_a_minlelf_right_b_minlelf_right_gray_valuelelf_right_gray_stddevlelf_right_gray_histlelf_right_gray_maxlelf_right_gray_min
count47662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.000000...47662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.00000047662.000000
mean1.5246117.4143554.993936-29.645441-4.3005122.0483825.319017-2.4622550.554404-1.499895...-9.937833-0.31322612.762725-0.9569680.7408215.371596-2.692417-2.5818890.88021912.910872
std19.87769332.67659426.32020569.62818423.35777620.53950827.8179846.5658941.4981758.691766...41.7951046.60892043.9655072.2728742.20306928.07044111.11984246.1454299.52955143.804821
min-37.000000-52.000000-45.000000-242.000000-60.000000-37.000000-46.000000-17.000000-3.000000-21.000000...-124.000000-24.000000-74.000000-9.000000-5.000000-46.000000-27.000000-251.000000-28.000000-70.000000
25%-18.000000-25.000000-21.000000-41.000000-26.000000-18.000000-22.000000-9.000000-1.000000-8.000000...-47.000000-5.000000-28.000000-3.000000-1.000000-22.000000-12.000000-42.000000-6.000000-28.000000
50%2.0000008.0000007.000000-2.000000-7.0000002.0000006.000000-2.0000000.000000-3.000000...-13.000000-1.00000016.000000-1.0000000.0000006.000000-4.0000002.0000001.00000015.000000
75%21.00000041.00000031.0000006.00000018.00000022.00000034.0000004.0000002.0000006.000000...29.0000004.00000049.0000001.0000002.00000034.0000008.00000039.0000009.00000050.000000
max41.00000066.00000051.000000140.00000068.00000050.00000056.00000011.0000007.00000018.000000...138.00000029.000000101.0000007.00000010.00000056.00000020.000000101.00000039.000000100.000000
\n", "

8 rows × 50 columns

\n", "
" ], "text/plain": [ " lelf_right_R lelf_right_G lelf_right_B lelf_right_H lelf_right_S \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 1.524611 7.414355 4.993936 -29.645441 -4.300512 \n", "std 19.877693 32.676594 26.320205 69.628184 23.357776 \n", "min -37.000000 -52.000000 -45.000000 -242.000000 -60.000000 \n", "25% -18.000000 -25.000000 -21.000000 -41.000000 -26.000000 \n", "50% 2.000000 8.000000 7.000000 -2.000000 -7.000000 \n", "75% 21.000000 41.000000 31.000000 6.000000 18.000000 \n", "max 41.000000 66.000000 51.000000 140.000000 68.000000 \n", "\n", " lelf_right_V lelf_right_l lelf_right_a lelf_right_b \\\n", "count 47662.000000 47662.000000 47662.000000 47662.000000 \n", "mean 2.048382 5.319017 -2.462255 0.554404 \n", "std 20.539508 27.817984 6.565894 1.498175 \n", "min -37.000000 -46.000000 -17.000000 -3.000000 \n", "25% -18.000000 -22.000000 -9.000000 -1.000000 \n", "50% 2.000000 6.000000 -2.000000 0.000000 \n", "75% 22.000000 34.000000 4.000000 2.000000 \n", "max 50.000000 56.000000 11.000000 7.000000 \n", "\n", " lelf_right_R_stddev ... lelf_right_S_min lelf_right_V_min \\\n", "count 47662.000000 ... 47662.000000 47662.000000 \n", "mean -1.499895 ... -9.937833 -0.313226 \n", "std 8.691766 ... 41.795104 6.608920 \n", "min -21.000000 ... -124.000000 -24.000000 \n", "25% -8.000000 ... -47.000000 -5.000000 \n", "50% -3.000000 ... -13.000000 -1.000000 \n", "75% 6.000000 ... 29.000000 4.000000 \n", "max 18.000000 ... 138.000000 29.000000 \n", "\n", " lelf_right_l_min lelf_right_a_min lelf_right_b_min \\\n", "count 47662.000000 47662.000000 47662.000000 \n", "mean 12.762725 -0.956968 0.740821 \n", "std 43.965507 2.272874 2.203069 \n", "min -74.000000 -9.000000 -5.000000 \n", "25% -28.000000 -3.000000 -1.000000 \n", "50% 16.000000 -1.000000 0.000000 \n", "75% 49.000000 1.000000 2.000000 \n", "max 101.000000 7.000000 10.000000 \n", "\n", " lelf_right_gray_value lelf_right_gray_stddev lelf_right_gray_hist \\\n", "count 47662.000000 47662.000000 47662.000000 \n", "mean 5.371596 -2.692417 -2.581889 \n", "std 28.070441 11.119842 46.145429 \n", "min -46.000000 -27.000000 -251.000000 \n", "25% -22.000000 -12.000000 -42.000000 \n", "50% 6.000000 -4.000000 2.000000 \n", "75% 34.000000 8.000000 39.000000 \n", "max 56.000000 20.000000 101.000000 \n", "\n", " lelf_right_gray_max lelf_right_gray_min \n", "count 47662.000000 47662.000000 \n", "mean 0.880219 12.910872 \n", "std 9.529551 43.804821 \n", "min -28.000000 -70.000000 \n", "25% -6.000000 -28.000000 \n", "50% 1.000000 15.000000 \n", "75% 9.000000 50.000000 \n", "max 39.000000 100.000000 \n", "\n", "[8 rows x 50 columns]" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_features_9 = pd.DataFrame()\n", "train_features_9['lelf_right_R'] = train_features['left_block_R'] - train_features['right_block_R']\n", "train_features_9['lelf_right_G'] = train_features['left_block_G'] - train_features['right_block_G']\n", "train_features_9['lelf_right_B'] = train_features['left_block_B'] - train_features['right_block_B']\n", "\n", "train_features_9['lelf_right_H'] = train_features['left_block_H'] - train_features['right_block_H']\n", "train_features_9['lelf_right_S'] = train_features['left_block_S'] - train_features['right_block_S']\n", "train_features_9['lelf_right_V'] = train_features['left_block_V'] - train_features['right_block_V']\n", "\n", "train_features_9['lelf_right_l'] = train_features['left_block_l'] - train_features['right_block_l']\n", "train_features_9['lelf_right_a'] = train_features['left_block_a'] - train_features['right_block_a']\n", "train_features_9['lelf_right_b'] = train_features['left_block_b'] - train_features['right_block_b']\n", "\n", "train_features_9['lelf_right_R_stddev'] = train_features['left_block_R_stddev'] - train_features['right_block_R_stddev']\n", "train_features_9['lelf_right_G_stddev'] = train_features['left_block_G_stddev'] - train_features['right_block_G_stddev']\n", "train_features_9['lelf_right_B_stddev'] = train_features['left_block_B_stddev'] - train_features['right_block_B_stddev']\n", "\n", "train_features_9['lelf_right_H_stddev'] = train_features['left_block_H_stddev'] - train_features['right_block_H_stddev']\n", "train_features_9['lelf_right_S_stddev'] = train_features['left_block_S_stddev'] - train_features['right_block_S_stddev']\n", "train_features_9['lelf_right_V_stddev'] = train_features['left_block_V_stddev'] - train_features['right_block_V_stddev']\n", "\n", "train_features_9['lelf_right_l_stddev'] = train_features['left_block_l_stddev'] - train_features['right_block_l_stddev']\n", "train_features_9['lelf_right_a_stddev'] = train_features['left_block_a_stddev'] - train_features['right_block_a_stddev']\n", "train_features_9['lelf_right_b_stddev'] = train_features['left_block_b_stddev'] - train_features['right_block_b_stddev']\n", "\n", "train_features_9['lelf_right_R_hist'] = train_features['left_block_R_hist'] - train_features['right_block_R_hist']\n", "train_features_9['lelf_right_G_hist'] = train_features['left_block_G_hist'] - train_features['right_block_G_hist']\n", "train_features_9['lelf_right_B_hist'] = train_features['left_block_B_hist'] - train_features['right_block_B_hist']\n", "\n", "train_features_9['lelf_right_H_hist'] = train_features['left_block_H_hist'] - train_features['right_block_H_hist']\n", "train_features_9['lelf_right_S_hist'] = train_features['left_block_S_hist'] - train_features['right_block_S_hist']\n", "train_features_9['lelf_right_V_hist'] = train_features['left_block_V_hist'] - train_features['right_block_V_hist']\n", "\n", "train_features_9['lelf_right_l_hist'] = train_features['left_block_l_hist'] - train_features['right_block_l_hist']\n", "train_features_9['lelf_right_a_hist'] = train_features['left_block_a_hist'] - train_features['right_block_a_hist']\n", "train_features_9['lelf_right_b_hist'] = train_features['left_block_b_hist'] - train_features['right_block_b_hist']\n", "\n", "train_features_9['lelf_right_R_max'] = train_features['left_block_R_max'] - train_features['right_block_R_max']\n", "train_features_9['lelf_right_G_max'] = train_features['left_block_G_max'] - train_features['right_block_G_max']\n", "train_features_9['lelf_right_B_max'] = train_features['left_block_B_max'] - train_features['right_block_B_max']\n", "\n", "train_features_9['lelf_right_H_max'] = train_features['left_block_H_max'] - train_features['right_block_H_max']\n", "train_features_9['lelf_right_S_max'] = train_features['left_block_S_max'] - train_features['right_block_S_max']\n", "train_features_9['lelf_right_V_max'] = train_features['left_block_V_max'] - train_features['right_block_V_max']\n", "\n", "train_features_9['lelf_right_l_max'] = train_features['left_block_l_max'] - train_features['right_block_l_max']\n", "train_features_9['lelf_right_a_max'] = train_features['left_block_a_max'] - train_features['right_block_a_max']\n", "train_features_9['lelf_right_b_max'] = train_features['left_block_b_max'] - train_features['right_block_b_max']\n", "\n", "train_features_9['lelf_right_R_min'] = train_features['left_block_R_min'] - train_features['right_block_R_min']\n", "train_features_9['lelf_right_G_min'] = train_features['left_block_G_min'] - train_features['right_block_G_min']\n", "train_features_9['lelf_right_B_min'] = train_features['left_block_B_min'] - train_features['right_block_B_min']\n", "\n", "train_features_9['lelf_right_H_min'] = train_features['left_block_H_min'] - train_features['right_block_H_min']\n", "train_features_9['lelf_right_S_min'] = train_features['left_block_S_min'] - train_features['right_block_S_min']\n", "train_features_9['lelf_right_V_min'] = train_features['left_block_V_min'] - train_features['right_block_V_min']\n", "\n", "train_features_9['lelf_right_l_min'] = train_features['left_block_l_min'] - train_features['right_block_l_min']\n", "train_features_9['lelf_right_a_min'] = train_features['left_block_a_min'] - train_features['right_block_a_min']\n", "train_features_9['lelf_right_b_min'] = train_features['left_block_b_min'] - train_features['right_block_b_min']\n", "\n", "# train_features_9['left_grayValue']= train_features['left_grayValue'];\n", "# train_features_9['left_grayStddevValue']= train_features['left_grayStddevValue'];\n", "# train_features_9['left_grayHist']= train_features['left_grayHist'];\n", "# train_features_9['left_grayMax']= train_features['left_grayMax'];\n", "# train_features_9['left_grayMin']= train_features['left_grayMin'];\n", "\n", "# train_features_9['right_grayValue']= train_features['right_grayValue'];\n", "# train_features_9['right_grayStddevValue']= train_features['right_grayStddevValue'];\n", "# train_features_9['right_grayHist']= train_features['right_grayHist'];\n", "# train_features_9['right_grayMax']= train_features['right_grayMax'];\n", "# train_features_9['right_grayMin']= train_features['right_grayMin'];\n", "\n", "# train_features_9['lelf_R_stddev'] = train_features['left_block_R_stddev'] \n", "# train_features_9['lelf_G_stddev'] = train_features['left_block_G_stddev'] \n", "# train_features_9['lelf_B_stddev'] = train_features['left_block_B_stddev'] \n", "\n", "# train_features_9['left_block_R_min'] = train_features['left_block_R_min'] \n", "# train_features_9['left_block_G_min'] = train_features['left_block_G_min'] \n", "# train_features_9['left_block_B_min'] = train_features['left_block_B_min'] \n", "\n", "\n", "train_features_9['lelf_right_gray_value'] = train_features['left_grayValue'] - train_features['right_grayValue']\n", "train_features_9['lelf_right_gray_stddev'] = train_features['left_grayStddevValue'] - train_features['right_grayStddevValue']\n", "train_features_9['lelf_right_gray_hist'] = train_features['left_grayHist'] - train_features['right_grayHist']\n", "train_features_9['lelf_right_gray_max'] = train_features['left_grayMax'] - train_features['right_grayMax']\n", "train_features_9['lelf_right_gray_min'] = train_features['left_grayMin'] - train_features['right_grayMin']\n", "#train_features_9['index'] = train_labels\n", "train_features_9.describe()\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**去掉左边块的方差和白块和右边块的特征**" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": false }, "outputs": [], "source": [ "# train_features = train_features.drop(\"left_block_R\",axis=1)\n", "# train_features = train_features.drop(\"left_block_G\",axis=1)\n", "# train_features = train_features.drop(\"left_block_B\",axis=1)\n", "\n", "# train_features = train_features.drop(\"left_block_R_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_G_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_B_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_B_stddev\",axis=1)\n", "\n", "# train_features = train_features.drop(\"left_block_R_max\",axis=1)\n", "# train_features = train_features.drop(\"left_block_G_max\",axis=1)\n", "# train_features = train_features.drop(\"left_block_B_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H\",axis=1)\n", "train_features = train_features.drop(\"left_block_S\",axis=1)\n", "train_features = train_features.drop(\"left_block_V\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_hist\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_hist\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_l\",axis=1)\n", "train_features = train_features.drop(\"left_block_a\",axis=1)\n", "train_features = train_features.drop(\"left_block_b\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_l_hist\",axis=1)\n", "train_features = train_features.drop(\"left_block_a_hist\",axis=1)\n", "train_features = train_features.drop(\"left_block_b_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_l_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_a_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_b_max\",axis=1)\n", "##################################################################\n", "\n", "# train_features = train_features.drop(\"right_block_R\",axis=1)\n", "# train_features = train_features.drop(\"right_block_G\",axis=1)\n", "# train_features = train_features.drop(\"right_block_B\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_B_stddev\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_R_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_G_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_B_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_R_max\",axis=1)\n", "# train_features = train_features.drop(\"right_block_G_max\",axis=1)\n", "# train_features = train_features.drop(\"right_block_B_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H\",axis=1)\n", "train_features = train_features.drop(\"right_block_S\",axis=1)\n", "train_features = train_features.drop(\"right_block_V\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_hist\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_hist\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_l\",axis=1)\n", "train_features = train_features.drop(\"right_block_a\",axis=1)\n", "train_features = train_features.drop(\"right_block_b\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_l_hist\",axis=1)\n", "train_features = train_features.drop(\"right_block_a_hist\",axis=1)\n", "train_features = train_features.drop(\"right_block_b_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_l_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_a_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_b_max\",axis=1)\n", "\n", "####################################################################\n", "\n", "train_features = train_features.drop(\"whiteBlock_R\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_G\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_B\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_B_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_R_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_G_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_B_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_R_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_G_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_B_max\",axis=1)\n", "\n", "\n", "train_features = train_features.drop(\"whiteBlock_H\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_max\",axis=1)\n", "\n", "\n", "\n", "train_features = train_features.drop(\"whiteBlock_l\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_a\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_b\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_l_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_a_hist\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_b_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_l_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_a_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_b_max\",axis=1)\n", "\n", "##################################################################\n", "\n", "\n", "\n", "train_features.describe()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**去掉所有块的方差特征**" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "\n", "train_features = train_features.drop(\"left_block_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_B_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_B_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_B_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_b_stddev\",axis=1)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# train_features = train_features.drop(\"left_block_R\",axis=1)\n", "# train_features = train_features.drop(\"left_block_G\",axis=1)\n", "# train_features = train_features.drop(\"left_block_B\",axis=1)\n", "\n", "# train_features = train_features.drop(\"left_block_H\",axis=1)\n", "# train_features = train_features.drop(\"left_block_S\",axis=1)\n", "# train_features = train_features.drop(\"left_block_V\",axis=1)\n", "\n", "# train_features = train_features.drop(\"left_block_l\",axis=1)\n", "# train_features = train_features.drop(\"left_block_a\",axis=1)\n", "# train_features = train_features.drop(\"left_block_b\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_R\",axis=1)\n", "# train_features = train_features.drop(\"right_block_G\",axis=1)\n", "# train_features = train_features.drop(\"right_block_B\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_H\",axis=1)\n", "# train_features = train_features.drop(\"right_block_S\",axis=1)\n", "# train_features = train_features.drop(\"right_block_V\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_l\",axis=1)\n", "# train_features = train_features.drop(\"right_block_a\",axis=1)\n", "# train_features = train_features.drop(\"right_block_b\",axis=1)\n", "\n", "# train_features = train_features.drop(\"whiteBlock_R\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_G\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_B\",axis=1)\n", "\n", "# train_features = train_features.drop(\"whiteBlock_H\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_S\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_V\",axis=1)\n", "\n", "# train_features = train_features.drop(\"whiteBlock_l\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_a\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_b\",axis=1)\n", "\n", "# train_features = train_features.drop(\"left_block_R_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_G_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_B_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"left_block_H_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_S_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_V_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"left_block_l_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_a_hist\",axis=1)\n", "# train_features = train_features.drop(\"left_block_b_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_R_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_G_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_B_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_H_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_S_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_V_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"right_block_l_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_a_hist\",axis=1)\n", "# train_features = train_features.drop(\"right_block_b_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"whiteBlock_R_hist\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_G_hist\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_B_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"whiteBlock_H_hist\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_S_hist\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_V_hist\",axis=1)\n", "\n", "# train_features = train_features.drop(\"whiteBlock_l_hist\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_a_hist\",axis=1)\n", "# train_features = train_features.drop(\"whiteBlock_b_hist\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_B_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"left_block_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_B_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"right_block_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_R_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_G_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_B_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_l_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_a_stddev\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_b_stddev\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_R_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_G_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_B_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_H_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_S_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"left_block_l_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_a_max\",axis=1)\n", "train_features = train_features.drop(\"left_block_b_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_R_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_G_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_B_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_H_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_S_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"right_block_l_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_a_max\",axis=1)\n", "train_features = train_features.drop(\"right_block_b_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_R_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_G_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_B_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_H_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_S_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_V_max\",axis=1)\n", "\n", "train_features = train_features.drop(\"whiteBlock_l_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_a_max\",axis=1)\n", "train_features = train_features.drop(\"whiteBlock_b_max\",axis=1)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": true }, "outputs": [], "source": [ "train_features.describe()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# svc支持向量机算法" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "#from sklearn.model_selection import KFold\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import accuracy_score\n", "from sklearn.svm import SVC\n", "from sklearn.metrics import f1_score\n", "from sklearn.metrics import precision_score\n", "from sklearn.metrics import recall_score\n", "#集成学习(Ensemble Learning) \n", "from sklearn.ensemble import ExtraTreesClassifier\n", "from sklearn.ensemble import AdaBoostClassifier\n", "\n", "#报错：ModuleNotFoundError: No module named 'sklearn.cross_validation'\n", "#原因：当前 sklearn 版本中 cross_validation 已经替换成了 model_selection，但其中的函数功能并没有变化\n", "#from sklearn.cross_validation import train_test_split\n", "from sklearn.model_selection import train_test_split\n", "X_train ,X_test,y_train,y_test = train_test_split(train_features_9,train_labels,test_size = 0.3, random_state = 20)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "##fit_transform,fit,transform区别和作用详解\n", "###fit和transform没有任何关系，仅仅是数据处理的两个不同环节，之所以出来fit_transform这个函数名，仅仅是为了写代码方便，会高效一点。\n", "###sklearn里的封装好的各种算法使用前都要fit，fit相对于整个代码而言，为后续API服务。fit之后，然后调用各种API方法,transform只是其中一个API方法，所以当你调用transform之外的方法，也必须要先fit。\n", "###fit原义指的是安装、使适合的意思，其实有点train的含义，但是和train不同的是，它并不是一个训练的过程，而是一个适配的过程，过程都是确定的，最后得到一个可用于转换的有价值的信息。\n", "###https://blog.csdn.net/weixin_38278334/article/details/82971752\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": true }, "outputs": [], "source": [ "##这个不需要了！\n", "X = train_features.values\n", "y = train_labels.values\n", "\n", "kf = KFold(n_splits=5)\n", "kf.get_n_splits(X)\n", "\n", "print(kf) \n", "\n", "for train_index, test_index in kf.split(X):\n", " print(\"TRAIN:\", train_index, \"TEST:\", test_index)\n", " X_train, X_test = X[train_index], X[test_index]\n", " y_train, y_test = y[train_index], y[test_index]\n", " \n", " \n", " from datetime import datetime\n", " trarining_start_time = datetime.now()\n", "\n", " clf_svm_linear = SVC(kernel = 'linear',gamma=0.00001,C=0.1)\n", " clf_svm_linear = clf_svm_linear.fit(X_train, y_train)\n", " pred = clf_svm_linear.predict(X_test)\n", " print \"svm linear accuracy score:\" , accuracy_score(y_test,pred)\n", " print \"f1 score:\" , f1_score(y_test,pred,average='micro')\n", "\n", "\n", " training_stop_time = datetime.now()\n", "\n", " print \"runing time:\",(training_stop_time - trarining_start_time)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import StratifiedKFold #交叉验证\n", "from sklearn.model_selection import GridSearchCV #网格搜索\n", "from sklearn.model_selection import train_test_split #将数据集分开成训练集和测试集\n", "from xgboost import XGBClassifier #xgboost\n", "\n", "#这个不需要了！\n", "model = XGBClassifier()\n", "learning_rate = [0.0001,0.001,0.01,0.1,0.2,0.3] #学习率\n", "gamma = [1, 0.1, 0.01, 0.001]\n", "param_grid = dict(learning_rate = learning_rate,gamma = gamma)#转化为字典格式，网络搜索要求\n", "kflod = StratifiedKFold(n_splits=10, shuffle = True,random_state=7)#将训练/测试数据集划分10个互斥子集，\n", "grid_search = GridSearchCV(model,param_grid,scoring = 'neg_log_loss',n_jobs = -1,cv = kflod)\n", "#scoring指定损失函数类型，n_jobs指定全部cpu跑，cv指定交叉验证\n", "grid_result = grid_search.fit(X_train, y_train) #运行网格搜索\n", "print(\"Best: %f using %s\" % (grid_result.best_score_,grid_search.best_params_))\n", "#grid_scores_：给出不同参数情况下的评价结果。best_params_：描述了已取得最佳结果的参数的组合\n", "#best_score_：成员提供优化过程期间观察到的最好的评分\n", "#具有键作为列标题和值作为列的dict，可以导入到DataFrame中。\n", "#注意，“params”键用于存储所有参数候选项的参数设置列表。\n", "means = grid_result.cv_results_['mean_test_score']\n", "params = grid_result.cv_results_['params']\n", "for mean,param in zip(means,params):\n", " print(\"%f with: %r\" % (mean,param))\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import StratifiedKFold #交叉验证\n", "from sklearn.model_selection import GridSearchCV #网格搜索\n", "from sklearn.model_selection import GridSearchCV\n", "from sklearn import metrics \n", "#https://blog.csdn.net/WJWFighting/article/details/80983022\n", "thresholds=np.linspace(0,0.1,20)#设置gamma参数列表,生成等差数列\n", "thresholds\n", "param_grid={'gamma':thresholds}\n", "clf=GridSearchCV(SVC(kernel='rbf'),param_grid,cv=5)\n", "clf.fit(X_train, y_train)\n", "\n", "print(\"best param: {0}\\nbest score: {1}\".format(clf.best_params_, clf.best_score_))\n", "\n", "y_pred = clf.predict(X_test)\n", "\n", "print(\"查准率：\",metrics.precision_score(y_pred, y_test))\n", "print(\"召回率：\",metrics.recall_score(y_pred, y_test))\n", "print(\"F1：\",metrics.f1_score(y_pred, y_test))\n", "\n", "print(\"最佳效果：%0.3f\"% clf.best_score_)\n", "print(\"最优参数组合：\")\n", "best_parameters=clf.best_estimator_.get_params()\n", "for param_name in sorted(param_grid.keys()):\n", " print('\\t%s:%r' %(param_name,best_parameters[param_name]))\n", "\n", "#print(\"训练集评分：\",clf.score(x_train,y_train))\n", "#print(\"测试集评分：\",clf.score(x_test,y_test))\n", "\n", "\"\"\"\n", "SVC方法。常用的参数如下：\n", "C：默认为1.0，是对于错误的惩罚项。\n", "kernel：指定算法的核函数，默认为'rbf'，常用的有'linear'，'poly'，'rbf'，'sigmoid'，'precomputed'。\n", "degree：多项式核函数的次数（'poly'），默认为3。 其他核函数会将其忽略。\n", "gamma：'rbf'，'poly'和'sigmoid'的核系数。 如果gamma是'auto'，那么将使用1 / n_features。\n", "\"\"\"" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": true }, "outputs": [], "source": [ "#X_train = train_features_9\n", "#y_train = train_labels\n", "# X_test = test_features\n", "# y_test = test_labels\n", "#clf_svm_linear = SVC(kernel = 'linear',gamma=0.00001,C=0.01)\n", "#clf_svm_linear = SVC(kernel = 'linear',gamma=0.01,C=0.01)\n", "#svm linear accuracy score: 0.9746101835242169\n", "clf_svm_linear = SVC(kernel = 'linear',C=0.1)\n", "#svm linear accuracy score: 0.974885004599816\n", "clf_svm_linear = clf_svm_linear.fit(X_train, y_train)\n", "# pred = clf_svm_linear.predict(X_test)\n", "# print \"svm linear accuracy score:\" , accuracy_score(y_test,pred)\n", "# print \"f1 score:\" , f1_score(y_test,pred,average='micro')\n", "pred = clf_svm_linear.predict(X_test)\n", "print (\"svm linear accuracy score:\" , accuracy_score(y_test,pred))\n", "print (\"f1 score :\" , f1_score(y_test,pred,average=None))\n", "print (\"precision_score:\" , precision_score(y_test,pred,average=None))\n", "print (\"recall_score :\" , recall_score(y_test,pred,average=None))\n", "print(\"preds:\",pred[:10])\n", "print('trues:\\n',y_test[:10])\n", "print(\"\\n\")\n", "###针对同一份数据，\n", "clf_svc_poly = SVC(kernel='poly',degree=3,gamma=0.001,C=0.1)\n", "#clf_svc_poly = SVC(kernel='poly',degree=3,gamma=0.00001,C=0.1)\n", "\n", "##svm polynomial accuracy score: 0.37460901563937443\n", "clf_svc_poly.fit(X_train, y_train)\n", "pred_poly = clf_svc_poly.predict(X_test)\n", "print (\"svm polynomial accuracy score:\" , accuracy_score(y_test,pred_poly))\n", "print (\"f1 score :\" , f1_score(y_test,pred_poly,average=None))\n", "print (\"precision_score:\" , precision_score(y_test,pred_poly,average=None))\n", "print (\"recall_score :\" , recall_score(y_test,pred_poly,average=None))\n", "\n", "clf_svc_rbf = SVC(kernel='rbf', gamma=0.05,C=0.1)\n", "##svm rbf accuracy score: 0.284360625574977\n", "clf_svc_rbf.fit(X_train, y_train)\n", "pred_rbf = clf_svc_rbf.predict(X_test)\n", "print (\"svm rbf accuracy score:\" , accuracy_score(y_test,pred_rbf))\n", "print (\"f1 score :\" , f1_score(y_test,pred_rbf,average=None))\n", "print (\"precision_score:\" , precision_score(y_test,pred_rbf,average=None))\n", "print (\"recall_score :\" , recall_score(y_test,pred_rbf,average=None))\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sklearn_porter import Porter\n", "\n", "porter_clf_svm_linear = Porter(clf_svm_linear, language='c').export()\n", "#porter_clf_svm_poly = Porter(clf_svm_poly, language='c').export()\n", "# porter_clf_forest = Porter(clf_randomForest, language='c').export()\n", "#porter_clf_extra_forest = Porter(clf_extra_forest, language='c').export()\n", "\n", "#print(porter_clf_svm_linear)\n", "f = open(\"clf/clf_svm_linear_50features_2020.cpp\",'wb')\n", "#f = open(\"clf/clf_svm_linear_50features_20171207.txt\",'wb')\n", "#f = open(\"clf_svm_linear_125100_low_feature_data.txt\",'wb')\n", "f.write(porter_clf_svm_linear.encode())\n", "f.close()\n", "#f = open(\"clf_svm_poly_2457100_data.txt\",'wb')\n", "#f.write(porter_clf_svm_poly)\n", "#f.close()\n", "# f = open(\"clf/clf_randomForest_27features_stddev_c_0_01.txt\",'wb')\n", "# f.write(porter_clf_forest)\n", "# f.close()\n", "# f = open(\"oclf_extra_forest_2457100_data_0824.txt\",'wb')\n", "# f.write(porter_clf_extra_forest)\n", "# f.close()\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# 随机森林算法" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "#from sklearn.model_selection import KFold\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import accuracy_score\n", "from sklearn.svm import SVC\n", "from sklearn.metrics import f1_score\n", "from sklearn.metrics import precision_score\n", "from sklearn.metrics import recall_score\n", "\n", "\n", "from sklearn.ensemble import ExtraTreesClassifier\n", "from sklearn.ensemble import AdaBoostClassifier\n", "\n", "from sklearn.model_selection import train_test_split\n", "X_train ,X_test,y_train,y_test = train_test_split(train_features_9,train_labels,test_size = 0.3, random_state = 20)\n", "#X_train ,X_test,y_train,y_test = train_test_split(train_features_9,train_labels,test_size = 0.2, random_state = 20)\n" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.99 0.98 0.99 1698\n", " 1 0.99 0.99 0.99 3791\n", " 2 0.99 0.99 0.99 2548\n", " 3 0.96 0.97 0.96 2693\n", " 4 0.98 0.97 0.97 3569\n", "\n", " accuracy 0.98 14299\n", " macro avg 0.98 0.98 0.98 14299\n", "weighted avg 0.98 0.98 0.98 14299\n", "\n", "[[1663 33 1 1 0]\n", " [ 11 3760 19 1 0]\n", " [ 1 11 2531 5 0]\n", " [ 0 0 6 2612 75]\n", " [ 0 0 0 104 3465]]\n", "---------------------------------\n", "\n", "Accuracy of prediction: 0.379\n", "RandomForest accuracy score: 0.9812574305895517\n", "---------------------------------\n", "\n", "f1 score: 0.9812574305895517\n", "precision_score: 0.9812574305895517\n", "recall_score: 0.9812574305895517\n" ] } ], "source": [ "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import classification_report\n", "from sklearn.metrics import classification_report,confusion_matrix\n", "from sklearn.metrics import f1_score\n", "from sklearn.metrics import precision_score\n", "from sklearn.metrics import recall_score\n", "\n", "#rfc = RandomForestClassifier(n_estimators=600)\n", "\n", "#rfc = RandomForestClassifier(n_estimators=50)\n", "#RandomForest accuracy score: 0.9955591300090916\n", "\n", "rfc = RandomForestClassifier(n_estimators=50,min_samples_leaf=20)\n", "#RandomForest accuracy score: 0.9772012028813204/0.9803133086229806/0.9811874956290649/0.9852786908175397\n", "\n", "#rfc = RandomForestClassifier(n_estimators=50)\n", "#RandomForest accuracy score: 0.9955940974893349\n", "\n", "#rfc = RandomForestClassifier(n_estimators=100,min_samples_leaf=50)\n", "#RandomForest accuracy score: 0.97688649555913\n", "\n", "#rfc = RandomForestClassifier(n_estimators=50,min_samples_leaf=100)\n", "#RandomForest accuracy score: 0.9669906986502552\n", "\n", "\n", "rfc.fit(X_train, y_train)\n", "rfc_pred = rfc.predict(X_test)\n", "cr = classification_report(y_test,rfc_pred)\n", "print(cr)\n", "cm = confusion_matrix(y_test,rfc_pred)\n", "print(cm)\n", "\n", "print(\"---------------------------------\\n\")\n", "print (\"Accuracy of prediction:\",round((cm[0,0]+cm[1,1])/cm.sum(),3))\n", "print (\"RandomForest accuracy score:\" , accuracy_score(y_test,rfc_pred))\n", "print(\"---------------------------------\\n\")\n", "print (\"f1 score:\" , f1_score(y_test,rfc_pred,average='micro'))\n", "print (\"precision_score:\" , precision_score(y_test,rfc_pred,average='micro'))\n", "print (\"recall_score:\" , recall_score(y_test,rfc_pred,average='micro'))" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [], "source": [ "from sklearn_porter import Porter\n", "\n", "porter_clf_rfc = Porter(rfc, language='c').export()\n", "#porter_clf_svm_poly = Porter(clf_svm_poly, language='c').export()\n", "# porter_clf_forest = Porter(clf_randomForest, language='c').export()\n", "#porter_clf_extra_forest = Porter(clf_extra_forest, language='c').export()\n", "\n", "#print(porter_clf_svm_linear)\n", "f = open(\"clf/ov_rtree50_f20_2020428.cpp\",'wb')\n", "#f = open(\"clf/clf_svm_linear_50features_20171207.txt\",'wb')\n", "#f = open(\"clf_svm_linear_125100_low_feature_data.txt\",'wb')\n", "f.write(porter_clf_rfc.encode())\n", "f.close()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import KFold\n", "\n", "X = train_features_9.values\n", "y = train_labels.values\n", "\n", "kf = KFold(n_splits=5)\n", "kf.get_n_splits(X)\n", "\n", "print(kf) \n", "\n", "for train_index, test_index in kf.split(X):\n", " print(\"TRAIN:\", train_index, \"TEST:\", test_index)\n", " X_train, X_test = X[train_index], X[test_index]\n", " y_train, y_test = y[train_index], y[test_index]\n", " \n", " \n", " from datetime import datetime\n", " trarining_start_time = datetime.now()\n", "\n", " rfc = RandomForestClassifier(n_estimators=600)\n", " rfc.fit(X_train, y_train)\n", " rfc_pred = rfc.predict(X_test) \n", " print (\"svm linear accuracy score:\" , accuracy_score(y_test,rfc_pred))\n", " print (\"f1 score:\" , f1_score(y_test,rfc_pred,average='micro'))\n", " print (\"precision_score:\" , precision_score(y_test,rfc_pred,average='micro'))\n", " print (\"recall_score:\" , recall_score(y_test,rfc_pred,average='micro'))\n", "\n", " training_stop_time = datetime.now()\n", "\n", " print (\"runing time:\",(training_stop_time - trarining_start_time))\n", " print(\"\\n\\n\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "nsimu = 21\n", "accuracy=[0]*nsimu\n", "ntree = [0]*nsimu\n", "for i in range(1,nsimu):\n", " rfc = RandomForestClassifier(n_estimators=i*5,min_samples_split=10,max_depth=None,criterion='gini')\n", " rfc.fit(X_train, y_train)\n", " rfc_pred = rfc.predict(X_test)\n", " cm = confusion_matrix(y_test,rfc_pred)\n", " accuracy[i] = (cm[0,0]+cm[1,1])/cm.sum()\n", " ntree[i]=i*5\n", "\n", " print (\"RandomForest accuracy score:\" , accuracy_score(y_test,rfc_pred))\n", " print (\"f1 score:\" , f1_score(y_test,rfc_pred,average='micro')) \n", " print (\"Accuracy of prediction:\",round((cm[0,0]+cm[1,1])/cm.sum(),3))\n", "\n", " \n", "plt.figure(figsize=(10,6))\n", "plt.scatter(x=ntree[1:nsimu],y=accuracy[1:nsimu],s=60,c='red')\n", "plt.title(\"Number of trees in the Random Forest vs. prediction accuracy (criterion: 'gini')\", fontsize=18)\n", "plt.xlabel(\"Number of trees\", fontsize=15)\n", "plt.ylabel(\"Prediction accuracy from confusion matrix\", fontsize=15)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": true }, "outputs": [], "source": [ "from sklearn.utils import shuffle\n", "\n", "\n", "# data_shuffle1 = shuffle(data1)\n", "# #data_shuffle = data_all;\n", "# test_labels = data_shuffle1[\"index\"]\n", "# test_features = data_shuffle1.drop(\"dateTime\",axis=1)\n", "# test_features = test_features.drop(\"index\",axis=1)\n", "# test_features = test_features.drop(\"whiteBalance\",axis=1)\n", "\n", "\n", "# test_features = test_features.drop(\"left_block_R_stddev\",axis=1)\n", "# test_features = test_features.drop(\"left_block_G_stddev\",axis=1)\n", "# test_features = test_features.drop(\"left_block_B_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"left_block_H_stddev\",axis=1)\n", "# test_features = test_features.drop(\"left_block_S_stddev\",axis=1)\n", "# test_features = test_features.drop(\"left_block_V_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"left_block_l_stddev\",axis=1)\n", "# test_features = test_features.drop(\"left_block_a_stddev\",axis=1)\n", "# test_features = test_features.drop(\"left_block_b_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"right_block_R_stddev\",axis=1)\n", "# test_features = test_features.drop(\"right_block_G_stddev\",axis=1)\n", "# test_features = test_features.drop(\"right_block_B_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"right_block_H_stddev\",axis=1)\n", "# test_features = test_features.drop(\"right_block_S_stddev\",axis=1)\n", "# test_features = test_features.drop(\"right_block_V_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"right_block_l_stddev\",axis=1)\n", "# test_features = test_features.drop(\"right_block_a_stddev\",axis=1)\n", "# test_features = test_features.drop(\"right_block_b_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"whiteBlock_R_stddev\",axis=1)\n", "# test_features = test_features.drop(\"whiteBlock_G_stddev\",axis=1)\n", "# test_features = test_features.drop(\"whiteBlock_B_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"whiteBlock_H_stddev\",axis=1)\n", "# test_features = test_features.drop(\"whiteBlock_S_stddev\",axis=1)\n", "# test_features = test_features.drop(\"whiteBlock_V_stddev\",axis=1)\n", "\n", "# test_features = test_features.drop(\"whiteBlock_l_stddev\",axis=1)\n", "# test_features = test_features.drop(\"whiteBlock_a_stddev\",axis=1)\n", "# test_features = test_features.drop(\"whiteBlock_b_stddev\",axis=1)\n", "\n", "train_features_10 = pd.DataFrame()\n", "train_features_10['lelf_right_R'] = test_features['left_block_R'] - test_features['right_block_R']\n", "train_features_10['lelf_right_G'] = test_features['left_block_G'] - test_features['right_block_G']\n", "train_features_10['lelf_right_B'] = test_features['left_block_B'] - test_features['right_block_B']\n", "\n", "train_features_10['lelf_right_H'] = test_features['left_block_H'] - test_features['right_block_H']\n", "# train_features_10['lelf_right_S'] = test_features['left_block_S'] - test_features['right_block_S']\n", "train_features_10['lelf_right_V'] = test_features['left_block_V'] - test_features['right_block_V']\n", "\n", "train_features_10['lelf_right_l'] = test_features['left_block_l'] - test_features['right_block_l']\n", "train_features_10['lelf_right_a'] = test_features['left_block_a'] - test_features['right_block_a']\n", "train_features_10['lelf_right_b'] = test_features['left_block_b'] - test_features['right_block_b']\n", "\n", "train_features_10['lelf_right_R_stddev'] = test_features['left_block_R_stddev'] - test_features['right_block_R_stddev']\n", "train_features_10['lelf_right_G_stddev'] = test_features['left_block_G_stddev'] - test_features['right_block_G_stddev']\n", "train_features_10['lelf_right_B_stddev'] = test_features['left_block_B_stddev'] - test_features['right_block_B_stddev']\n", "\n", "train_features_10['lelf_right_H_stddev'] = test_features['left_block_H_stddev'] - test_features['right_block_H_stddev']\n", "# train_features_10['lelf_right_S_stddev'] = test_features['left_block_S_stddev'] - test_features['right_block_S_stddev']\n", "train_features_10['lelf_right_V_stddev'] = test_features['left_block_V_stddev'] - test_features['right_block_V_stddev']\n", "\n", "train_features_10['lelf_right_l_stddev'] = test_features['left_block_l_stddev'] - test_features['right_block_l_stddev']\n", "train_features_10['lelf_right_a_stddev'] = test_features['left_block_a_stddev'] - test_features['right_block_a_stddev']\n", "train_features_10['lelf_right_b_stddev'] = test_features['left_block_b_stddev'] - test_features['right_block_b_stddev']\n", "\n", "train_features_10['lelf_right_R_hist'] = test_features['left_block_R_hist'] - test_features['right_block_R_hist']\n", "train_features_10['lelf_right_G_hist'] = test_features['left_block_G_hist'] - test_features['right_block_G_hist']\n", "train_features_10['lelf_right_B_hist'] = test_features['left_block_B_hist'] - test_features['right_block_B_hist']\n", "\n", "train_features_10['lelf_right_H_hist'] = test_features['left_block_H_hist'] - test_features['right_block_H_hist']\n", "# train_features_10['lelf_right_S_hist'] = test_features['left_block_S_hist'] - test_features['right_block_S_hist']\n", "train_features_10['lelf_right_V_hist'] = test_features['left_block_V_hist'] - test_features['right_block_V_hist']\n", "\n", "train_features_10['lelf_right_l_hist'] = test_features['left_block_l_hist'] - test_features['right_block_l_hist']\n", "train_features_10['lelf_right_a_hist'] = test_features['left_block_a_hist'] - test_features['right_block_a_hist']\n", "train_features_10['lelf_right_b_hist'] = test_features['left_block_b_hist'] - test_features['right_block_b_hist']\n", "\n", "train_features_10['lelf_right_R_max'] = test_features['left_block_R_max'] - test_features['right_block_R_max']\n", "train_features_10['lelf_right_G_max'] = test_features['left_block_G_max'] - test_features['right_block_G_max']\n", "train_features_10['lelf_right_B_max'] = test_features['left_block_B_max'] - test_features['right_block_B_max']\n", "\n", "train_features_10['lelf_right_H_max'] = test_features['left_block_H_max'] - test_features['right_block_H_max']\n", "# train_features_10['lelf_right_S_max'] = test_features['left_block_S_max'] - test_features['right_block_S_max']\n", "train_features_10['lelf_right_V_max'] = test_features['left_block_V_max'] - test_features['right_block_V_max']\n", "\n", "train_features_10['lelf_right_l_max'] = test_features['left_block_l_max'] - test_features['right_block_l_max']\n", "train_features_10['lelf_right_a_max'] = test_features['left_block_a_max'] - test_features['right_block_a_max']\n", "train_features_10['lelf_right_b_max'] = test_features['left_block_b_max'] - test_features['right_block_b_max']\n", "\n", "\n", "train_features_10['lelf_right_R_min'] = test_features['left_block_R_min'] - test_features['right_block_R_min']\n", "train_features_10['lelf_right_G_min'] = test_features['left_block_G_min'] - test_features['right_block_G_min']\n", "train_features_10['lelf_right_B_min'] = test_features['left_block_B_min'] - test_features['right_block_B_min']\n", "\n", "train_features_10['lelf_right_H_min'] = test_features['left_block_H_min'] - test_features['right_block_H_min']\n", "# train_features_10['lelf_right_S_min'] = test_features['left_block_S_min'] - test_features['right_block_S_min']\n", "train_features_10['lelf_right_V_min'] = test_features['left_block_V_min'] - test_features['right_block_V_min']\n", "\n", "train_features_10['lelf_right_l_min'] = test_features['left_block_l_min'] - test_features['right_block_l_min']\n", "train_features_10['lelf_right_a_min'] = test_features['left_block_a_min'] - test_features['right_block_a_min']\n", "train_features_10['lelf_right_b_min'] = test_features['left_block_b_min'] - test_features['right_block_b_min']\n", "\n", "# train_features_10['left_grayValue']= test_features['left_grayValue'];\n", "# train_features_10['left_grayStddevValue']= test_features['left_grayStddevValue'];\n", "# train_features_10['left_grayHist']= test_features['left_grayHist'];\n", "# train_features_10['left_grayMax']= test_features['left_grayMax'];\n", "# train_features_10['left_grayMin']= test_features['left_grayMin'];\n", "\n", "# train_features_10['right_grayValue']= test_features['right_grayValue'];\n", "# train_features_10['right_grayStddevValue']= test_features['right_grayStddevValue'];\n", "# train_features_10['right_grayHist']= test_features['right_grayHist'];\n", "# train_features_10['right_grayMax']= test_features['right_grayMax'];\n", "# train_features_10['right_grayMin']= test_features['right_grayMin'];\n", "\n", "# train_features_10['lelf_R_stddev'] = test_features['left_block_R_stddev'] \n", "# train_features_10['lelf_G_stddev'] = test_features['left_block_G_stddev'] \n", "# train_features_10['lelf_B_stddev'] = test_features['left_block_B_stddev'] \n", "\n", "# train_features_10['left_block_R_min'] = test_features['left_block_R_min'] \n", "# train_features_10['left_block_G_min'] = test_features['left_block_G_min'] \n", "# train_features_10['left_block_B_min'] = test_features['left_block_B_min'] \n", "\n", "\n", "\n", "train_features_10['lelf_right_gray_value'] = test_features['left_grayValue'] - test_features['right_grayValue']\n", "train_features_10['lelf_right_gray_stddev'] = test_features['left_grayStddevValue'] - test_features['right_grayStddevValue']\n", "train_features_10['lelf_right_gray_hist'] = test_features['left_grayHist'] - test_features['right_grayHist']\n", "train_features_10['lelf_right_gray_max'] = test_features['left_grayMax'] - test_features['right_grayMax']\n", "train_features_10['lelf_right_gray_min'] = test_features['left_grayMin'] - test_features['right_grayMin']\n", "\n", "train_features_10.describe()\n", "\n", "\n", "# feature = feature.drop(\"left_block_H_hist\",axis=1)\n", "# feature = feature.drop(\"right_block_H_hist\",axis=1)\n", "# feature = feature.drop(\"whiteBlock_H_hist\",axis=1)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ " \n", "test_features = test_features.drop(\"left_block_H\",axis=1)\n", "test_features = test_features.drop(\"left_block_S\",axis=1)\n", "test_features = test_features.drop(\"left_block_V\",axis=1)\n", "\n", "test_features = test_features.drop(\"right_block_H\",axis=1)\n", "test_features = test_features.drop(\"right_block_S\",axis=1)\n", "test_features = test_features.drop(\"right_block_V\",axis=1)\n", "\n", "test_features = test_features.drop(\"whiteBlock_H\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_S\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_V\",axis=1)\n", "\n", "\n", "test_features = test_features.drop(\"left_block_H_stddev\",axis=1)\n", "test_features = test_features.drop(\"left_block_S_stddev\",axis=1)\n", "test_features = test_features.drop(\"left_block_V_stddev\",axis=1)\n", "\n", "test_features = test_features.drop(\"right_block_H_stddev\",axis=1)\n", "test_features = test_features.drop(\"right_block_S_stddev\",axis=1)\n", "test_features = test_features.drop(\"right_block_V_stddev\",axis=1)\n", "\n", "test_features = test_features.drop(\"whiteBlock_H_stddev\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_S_stddev\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_V_stddev\",axis=1)\n", "\n", "test_features = test_features.drop(\"left_block_H_hist\",axis=1)\n", "test_features = test_features.drop(\"left_block_S_hist\",axis=1)\n", "test_features = test_features.drop(\"left_block_V_hist\",axis=1)\n", "\n", "test_features = test_features.drop(\"right_block_H_hist\",axis=1)\n", "test_features = test_features.drop(\"right_block_S_hist\",axis=1)\n", "test_features = test_features.drop(\"right_block_V_hist\",axis=1)\n", "\n", "test_features = test_features.drop(\"whiteBlock_H_hist\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_S_hist\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_V_hist\",axis=1)\n", "\n", "test_features = test_features.drop(\"left_block_H_max\",axis=1)\n", "test_features = test_features.drop(\"left_block_S_max\",axis=1)\n", "test_features = test_features.drop(\"left_block_V_max\",axis=1)\n", "\n", "test_features = test_features.drop(\"right_block_H_max\",axis=1)\n", "test_features = test_features.drop(\"right_block_S_max\",axis=1)\n", "test_features = test_features.drop(\"right_block_V_max\",axis=1)\n", "\n", "test_features = test_features.drop(\"whiteBlock_H_max\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_S_max\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_V_max\",axis=1)\n", "\n", "test_features = test_features.drop(\"left_block_H_min\",axis=1)\n", "test_features = test_features.drop(\"left_block_S_min\",axis=1)\n", "test_features = test_features.drop(\"left_block_V_min\",axis=1)\n", "\n", "test_features = test_features.drop(\"right_block_H_min\",axis=1)\n", "test_features = test_features.drop(\"right_block_S_min\",axis=1)\n", "test_features = test_features.drop(\"right_block_V_min\",axis=1)\n", "\n", "test_features = test_features.drop(\"whiteBlock_H_min\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_S_min\",axis=1)\n", "test_features = test_features.drop(\"whiteBlock_V_min\",axis=1)\n", " \n", " \n", "test_features['lelf_right_R'] = test_features['left_block_R'] - test_features['right_block_R']\n", "test_features['lelf_right_G'] = test_features['left_block_G'] - test_features['right_block_G']\n", "test_features['lelf_right_B'] = test_features['left_block_B'] - test_features['right_block_B']\n", "\n", "# test_features['lelf_right_H'] = test_features['left_block_H'] - test_features['right_block_H']\n", "# test_features['lelf_right_S'] = test_features['left_block_S'] - test_features['right_block_S']\n", "# test_features['lelf_right_V'] = test_features['left_block_V'] - test_features['right_block_V']\n", "\n", "# test_features['lelf_right_l'] = test_features['left_block_l'] - test_features['right_block_l']\n", "# test_features['lelf_right_a'] = test_features['left_block_a'] - test_features['right_block_a']\n", "# test_features['lelf_right_b'] = test_features['left_block_b'] - test_features['right_block_b']\n", "\n", "# test_features['lelf_right_R_stddev'] = test_features['left_block_R_stddev'] - test_features['right_block_R_stddev']\n", "# test_features['lelf_right_G_stddev'] = test_features['left_block_G_stddev'] - test_features['right_block_G_stddev']\n", "# test_features['lelf_right_B_stddev'] = test_features['left_block_B_stddev'] - test_features['right_block_B_stddev']\n", "\n", "# test_features['lelf_right_H_stddev'] = test_features['left_block_H_stddev'] - test_features['right_block_H_stddev']\n", "# test_features['lelf_right_S_stddev'] = test_features['left_block_S_stddev'] - test_features['right_block_S_stddev']\n", "# test_features['lelf_right_V_stddev'] = test_features['left_block_V_stddev'] - test_features['right_block_V_stddev']\n", "\n", "# test_features['lelf_right_l_stddev'] = test_features['left_block_l_stddev'] - test_features['right_block_l_stddev']\n", "# test_features['lelf_right_a_stddev'] = test_features['left_block_a_stddev'] - test_features['right_block_a_stddev']\n", "# test_features['lelf_right_b_stddev'] = test_features['left_block_b_stddev'] - test_features['right_block_b_stddev']\n", "\n", "# test_features['lelf_right_R_hist'] = test_features['left_block_R_hist'] - test_features['right_block_R_hist']\n", "# test_features['lelf_right_G_hist'] = test_features['left_block_G_hist'] - test_features['right_block_G_hist']\n", "# test_features['lelf_right_B_hist'] = test_features['left_block_B_hist'] - test_features['right_block_B_hist']\n", "\n", "# test_features['lelf_right_H_hist'] = test_features['left_block_H_hist'] - test_features['right_block_H_hist']\n", "# test_features['lelf_right_S_hist'] = test_features['left_block_S_hist'] - test_features['right_block_S_hist']\n", "# test_features['lelf_right_V_hist'] = test_features['left_block_V_hist'] - test_features['right_block_V_hist']\n", "\n", "# test_features['lelf_right_l_hist'] = test_features['left_block_l_hist'] - test_features['right_block_l_hist']\n", "# test_features['lelf_right_a_hist'] = test_features['left_block_a_hist'] - test_features['right_block_a_hist']\n", "# test_features['lelf_right_b_hist'] = test_features['left_block_b_hist'] - test_features['right_block_b_hist']\n", "\n", "# test_features['lelf_right_R_max'] = test_features['left_block_R_max'] - test_features['right_block_R_max']\n", "# test_features['lelf_right_G_max'] = test_features['left_block_G_max'] - test_features['right_block_G_max']\n", "# test_features['lelf_right_B_max'] = test_features['left_block_B_max'] - test_features['right_block_B_max']\n", "\n", "# test_features['lelf_right_H_max'] = test_features['left_block_H_max'] - test_features['right_block_H_max']\n", "# test_features['lelf_right_S_max'] = test_features['left_block_S_max'] - test_features['right_block_S_max']\n", "# test_features['lelf_right_V_max'] = test_features['left_block_V_max'] - test_features['right_block_V_max']\n", "\n", "# test_features['lelf_right_l_max'] = test_features['left_block_l_max'] - test_features['right_block_l_max']\n", "# test_features['lelf_right_a_max'] = test_features['left_block_a_max'] - test_features['right_block_a_max']\n", "# test_features['lelf_right_b_max'] = test_features['left_block_b_max'] - test_features['right_block_b_max']\n", "\n", "\n", "\n", "# test_features['lelf_right_R_min'] = test_features['left_block_R_min'] - test_features['right_block_R_min']\n", "# test_features['lelf_right_G_min'] = test_features['left_block_G_min'] - test_features['right_block_G_min']\n", "# test_features['lelf_right_B_min'] = test_features['left_block_B_min'] - test_features['right_block_B_min']\n", "\n", "# test_features['lelf_right_H_min'] = test_features['left_block_H_min'] - test_features['right_block_H_min']\n", "# test_features['lelf_right_S_min'] = test_features['left_block_S_min'] - test_features['right_block_S_min']\n", "# test_features['lelf_right_V_min'] = test_features['left_block_V_min'] - test_features['right_block_V_min']\n", "\n", "# test_features['lelf_right_l_min'] = test_features['left_block_l_min'] - test_features['right_block_l_min']\n", "# test_features['lelf_right_a_min'] = test_features['left_block_a_min'] - test_features['right_block_a_min']\n", "# test_features['lelf_right_b_min'] = test_features['left_block_b_min'] - test_features['right_block_b_min']\n", "\n", "test_features['lelf_right_gray_value'] = test_features['left_grayValue'] - test_features['right_grayValue']\n", "test_features['lelf_right_gray_stddev'] = test_features['left_grayStddevValue'] - test_features['right_grayStddevValue']\n", "test_features['lelf_right_gray_hist'] = test_features['left_grayHist'] - test_features['right_grayHist']\n", "test_features['lelf_right_gray_max'] = test_features['left_grayMax'] - test_features['right_grayMax']\n", "test_features['lelf_right_gray_min'] = test_features['left_grayMin'] - test_features['right_grayMin']\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "pred = clf_svm_linear.predict(train_features_10)\n", "test_features_gray_stddev = test_features['left_grayStddevValue']\n", "test_features_np = np.ndarray(test_features_gray_stddev.shape,dtype = np.float32)\n", "\n", "test_features_np = test_features_gray_stddev.values\n", "print \"svm linear accuracy score:\" , accuracy_score(test_labels,pred)\n", "print \"f1 score:\" , f1_score(test_labels,pred,average='micro')\n", "print \"recall_score :\" , recall_score(test_labels,pred,average='micro')\n", "print \"precision_score :\" , precision_score(test_labels,pred,average='micro')\n", "\n", "for i in range(0, len(test_features_np)):\n", " if test_features_np[i] < 3:\n", " pred[i] =0\n", "print \"svm linear accuracy score:\" , accuracy_score(test_labels,pred)\n", "print \"f1 score:\" , f1_score(test_labels,pred,average='micro')\n", "print \"recall_score :\" , recall_score(test_labels,pred,average='micro')\n", "print \"precision_score :\" , precision_score(test_labels,pred,average='micro')\n", "\n", "\n", "print(\"preds:\",pred[120:130])\n", "print('trues:\\n',test_labels[120:130])\n", "test_labels_np = np.ndarray(test_labels.shape,dtype= np.int32)\n", "test_labels_np = test_labels.values\n", "print(test_labels_np[0])\n", "all_counter = 0\n", "counter = 0\n", "for i in range(0 ,len(pred) ):\n", " if (pred[i] == 4 or (pred[i] == 4 and test_labels_np[i] ==4 )or test_labels_np[i] ==4 ) :\n", " all_counter = all_counter + 1\n", " if pred[i] != test_labels_np[i] :\n", " counter = counter+1\n", " print(pred[i] , test_labels_np[i])\n", "print(len(pred),all_counter, counter) \n", "all_counter = 0\n", "counter = 0\n", "for i in range(0 ,len(pred) ):\n", " if pred[i] != test_labels_np[i] :\n", " counter = counter+1\n", " print(pred[i] , test_labels_np[i])\n", "print(len(pred),all_counter, counter) \n", "\n", "# print \"svm linear accuracy score:\" , accuracy_score(test_labels,pred)\n", "# print \"f1 score:\" , f1_score(test_labels,pred,average='micro')\n", "# print \"recall_score :\" , recall_score(test_labels,pred,average='micro')\n", "# print \"precision_score :\" , precision_score(test_labels,pred,average='micro')\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## from sklearn.metrics import recall_score\n", "from sklearn.metrics import precision_score\n", "print \"accuracy score:\" , accuracy_score(y_test,pred)\n", "print \"recall_score :\" , recall_score(y_test,pred,average='macro')\n", "print \"precision_score :\" , precision_score(y_test,pred,average='macro')\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sklearn_porter import Porter\n", "\n", "porter_java = Porter(clf_svm, language='java').export()\n", "porter_c = Porter(clf_svm, language='c').export()\n", "\n", "f = open(\"Protein_c.txt\",'wb')\n", "f.write(porter_c)\n", "f.close()\n", "\n", "f = open(\"Protein_svm_java.txt\",'wb')\n", "f.write(porter_java)\n", "f.close()" ] } ], "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": "3.7.6" } }, "nbformat": 4, "nbformat_minor": 2 }