{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ " *早早孕试纸机器学习算法验证*" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**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": [ "**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(\"light.csv\")\n", " data2 = pd.read_csv(\"nature_light.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": "markdown", "metadata": {}, "source": [ "**分析数据**" ] }, { "cell_type": "code", "execution_count": 3, "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 91301.000000 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 165.729696 134.358506 140.457706 178.764099 56.932838 \n", "std 30.728156 39.645554 35.580123 62.957946 28.703214 \n", "min 90.000000 51.000000 60.000000 7.000000 7.000000 \n", "25% 145.000000 103.000000 114.000000 143.000000 31.000000 \n", "50% 165.000000 135.000000 140.000000 202.000000 51.000000 \n", "75% 186.000000 165.000000 167.000000 228.000000 83.000000 \n", "max 247.000000 230.000000 233.000000 248.000000 119.000000 \n", "\n", " left_block_V left_block_l left_block_a left_block_b \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 166.771580 150.273458 140.877241 129.089342 \n", "std 31.214224 35.806975 7.556304 2.173696 \n", "min 90.000000 67.000000 124.000000 122.000000 \n", "25% 146.000000 124.000000 135.000000 128.000000 \n", "50% 166.000000 152.000000 141.000000 129.000000 \n", "75% 188.000000 177.000000 148.000000 131.000000 \n", "max 247.000000 231.000000 154.000000 135.000000 \n", "\n", " left_block_R_stddev ... right_grayHist right_grayMax \\\n", "count 91301.000000 ... 91301.000000 91301.000000 \n", "mean 11.584725 ... 124.195693 178.770342 \n", "std 8.180077 ... 30.525042 22.532460 \n", "min 0.000000 ... 49.000000 120.000000 \n", "25% 4.000000 ... 104.000000 162.000000 \n", "50% 11.000000 ... 122.000000 178.000000 \n", "75% 18.000000 ... 144.000000 194.000000 \n", "max 36.000000 ... 232.000000 251.000000 \n", "\n", " right_grayMin white_grayValue white_grayStddevValue white_grayHist \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 98.756312 192.484661 1.065191 193.134763 \n", "std 27.773504 24.373492 3.633961 24.401654 \n", "min 39.000000 102.000000 0.000000 0.000000 \n", "25% 78.000000 175.000000 0.000000 175.000000 \n", "50% 95.000000 194.000000 1.000000 195.000000 \n", "75% 115.000000 208.000000 1.000000 208.000000 \n", "max 196.000000 255.000000 52.000000 254.000000 \n", "\n", " white_grayMax white_grayMin whiteBalance index \n", "count 91301.000000 91301.000000 91301.0 91301.000000 \n", "mean 196.246043 189.544912 0.0 3.221476 \n", "std 22.966470 26.690282 0.0 1.891621 \n", "min 139.000000 49.000000 0.0 0.000000 \n", "25% 179.000000 172.000000 0.0 2.000000 \n", "50% 197.000000 192.000000 0.0 3.000000 \n", "75% 211.000000 206.000000 0.0 5.000000 \n", "max 255.000000 255.000000 0.0 6.000000 \n", "\n", "[8 rows x 152 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", "\n", "data1_0 = data1[data1[\"whiteBalance\"] == 0]\n", "data2_0 = data2[data2[\"whiteBalance\"] == 0]\n", "#data_test_0 = data_test\n", "\n", "data_all =data1_0.append(data2_0);\n", "#data_all =data1.append(data2);\n", "#data_all = data2\n", "whiteBlock_R_one = data_all[data_all[\"index\"] == 0 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_one = data_all[data_all[\"index\"] == 0 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_one = data_all[data_all[\"index\"] == 0 ][\"left_block_B_stddev\"]\n", "\n", "whiteBlock_R_two = data_all[data_all[\"index\"] == 1 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_two = data_all[data_all[\"index\"] == 1 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_two = data_all[data_all[\"index\"] == 1 ][\"left_block_B_stddev\"]\n", "\n", "whiteBlock_R_three = data_all[data_all[\"index\"] == 2 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_three = data_all[data_all[\"index\"] == 2 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_three = data_all[data_all[\"index\"] == 2 ][\"left_block_B_stddev\"]\n", "\n", "whiteBlock_R_four = data_all[data_all[\"index\"] == 3 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_four = data_all[data_all[\"index\"] == 3 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_four = data_all[data_all[\"index\"] == 3 ][\"left_block_B_stddev\"]\n", "\n", "\n", "whiteBlock_R_five = data_all[data_all[\"index\"] == 4 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_five = data_all[data_all[\"index\"] == 4 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_five = data_all[data_all[\"index\"] == 4 ][\"left_block_B_stddev\"]\n", "\n", "whiteBlock_R_six = data_all[data_all[\"index\"] == 5 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_six = data_all[data_all[\"index\"] == 5 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_six = data_all[data_all[\"index\"] == 5 ][\"left_block_B_stddev\"]\n", "\n", "whiteBlock_R_seven = data_all[data_all[\"index\"] == 6 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_seven = data_all[data_all[\"index\"] == 6 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_seven = data_all[data_all[\"index\"] == 6 ][\"left_block_B_stddev\"]\n", "\n", "whiteBlock_R_eghit = data_all[data_all[\"index\"] == 7 ][\"left_block_R_stddev\"]\n", "whiteBlock_G_eghit = data_all[data_all[\"index\"] == 7 ][\"left_block_G_stddev\"]\n", "whiteBlock_B_eghit = data_all[data_all[\"index\"] == 7 ][\"left_block_B_stddev\"]\n", "\n", "print(data_all.describe())\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['dateTime', 'left_block_R', 'left_block_G', 'left_block_B',\n", " 'left_block_H', 'left_block_S', 'left_block_V', 'left_block_l',\n", " 'left_block_a', 'left_block_b',\n", " ...\n", " 'right_grayHist', 'right_grayMax', 'right_grayMin', 'white_grayValue',\n", " 'white_grayStddevValue', 'white_grayHist', 'white_grayMax',\n", " 'white_grayMin', 'whiteBalance', 'index'],\n", " dtype='object', length=153)" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data_all.columns" ] }, { "cell_type": "markdown", "metadata": { "collapsed": true }, "source": [ "hsv max min hist value h值要去掉" ] }, { "cell_type": "code", "execution_count": 5, "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_grayValueright_grayStddevValueright_grayHistright_grayMaxright_grayMinwhite_grayValuewhite_grayStddevValuewhite_grayHistwhite_grayMaxwhite_grayMin
count91301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.000000...91301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.000000
mean165.729696134.358506140.457706178.76409956.932838166.771580150.273458140.877241129.08934211.584725...136.32823320.844142124.195693178.77034298.756312192.4846611.065191193.134763196.246043189.544912
std30.72815639.64555435.58012362.95794628.70321431.21422435.8069757.5563042.1736968.180077...25.5831884.95273030.52504222.53246027.77350424.3734923.63396124.40165422.96647026.690282
min90.00000051.00000060.0000007.0000007.00000090.00000067.000000124.000000122.0000000.000000...81.0000009.00000049.000000120.00000039.000000102.0000000.0000000.000000139.00000049.000000
25%145.000000103.000000114.000000143.00000031.000000146.000000124.000000135.000000128.0000004.000000...119.00000017.000000104.000000162.00000078.000000175.0000000.000000175.000000179.000000172.000000
50%165.000000135.000000140.000000202.00000051.000000166.000000152.000000141.000000129.00000011.000000...135.00000021.000000122.000000178.00000095.000000194.0000001.000000195.000000197.000000192.000000
75%186.000000165.000000167.000000228.00000083.000000188.000000177.000000148.000000131.00000018.000000...153.00000024.000000144.000000194.000000115.000000208.0000001.000000208.000000211.000000206.000000
max247.000000230.000000233.000000248.000000119.000000247.000000231.000000154.000000135.00000036.000000...215.00000035.000000232.000000251.000000196.000000255.00000052.000000254.000000255.000000255.000000
\n", "

8 rows × 150 columns

\n", "
" ], "text/plain": [ " left_block_R left_block_G left_block_B left_block_H left_block_S \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 165.729696 134.358506 140.457706 178.764099 56.932838 \n", "std 30.728156 39.645554 35.580123 62.957946 28.703214 \n", "min 90.000000 51.000000 60.000000 7.000000 7.000000 \n", "25% 145.000000 103.000000 114.000000 143.000000 31.000000 \n", "50% 165.000000 135.000000 140.000000 202.000000 51.000000 \n", "75% 186.000000 165.000000 167.000000 228.000000 83.000000 \n", "max 247.000000 230.000000 233.000000 248.000000 119.000000 \n", "\n", " left_block_V left_block_l left_block_a left_block_b \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 166.771580 150.273458 140.877241 129.089342 \n", "std 31.214224 35.806975 7.556304 2.173696 \n", "min 90.000000 67.000000 124.000000 122.000000 \n", "25% 146.000000 124.000000 135.000000 128.000000 \n", "50% 166.000000 152.000000 141.000000 129.000000 \n", "75% 188.000000 177.000000 148.000000 131.000000 \n", "max 247.000000 231.000000 154.000000 135.000000 \n", "\n", " left_block_R_stddev ... right_grayValue \\\n", "count 91301.000000 ... 91301.000000 \n", "mean 11.584725 ... 136.328233 \n", "std 8.180077 ... 25.583188 \n", "min 0.000000 ... 81.000000 \n", "25% 4.000000 ... 119.000000 \n", "50% 11.000000 ... 135.000000 \n", "75% 18.000000 ... 153.000000 \n", "max 36.000000 ... 215.000000 \n", "\n", " right_grayStddevValue right_grayHist right_grayMax right_grayMin \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 20.844142 124.195693 178.770342 98.756312 \n", "std 4.952730 30.525042 22.532460 27.773504 \n", "min 9.000000 49.000000 120.000000 39.000000 \n", "25% 17.000000 104.000000 162.000000 78.000000 \n", "50% 21.000000 122.000000 178.000000 95.000000 \n", "75% 24.000000 144.000000 194.000000 115.000000 \n", "max 35.000000 232.000000 251.000000 196.000000 \n", "\n", " white_grayValue white_grayStddevValue white_grayHist white_grayMax \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 192.484661 1.065191 193.134763 196.246043 \n", "std 24.373492 3.633961 24.401654 22.966470 \n", "min 102.000000 0.000000 0.000000 139.000000 \n", "25% 175.000000 0.000000 175.000000 179.000000 \n", "50% 194.000000 1.000000 195.000000 197.000000 \n", "75% 208.000000 1.000000 208.000000 211.000000 \n", "max 255.000000 52.000000 254.000000 255.000000 \n", "\n", " white_grayMin \n", "count 91301.000000 \n", "mean 189.544912 \n", "std 26.690282 \n", "min 49.000000 \n", "25% 172.000000 \n", "50% 192.000000 \n", "75% 206.000000 \n", "max 255.000000 \n", "\n", "[8 rows x 150 columns]" ] }, "execution_count": 5, "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": [ "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": "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", "
left_block_Hleft_block_Sleft_block_Vleft_block_lleft_block_aleft_block_blelf_right_Hlelf_right_Slelf_right_Vlelf_right_l...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
count91301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.000000...91301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.00000091301.000000
mean178.76409956.932838166.771580150.273458140.877241129.089342-30.762193-11.3831392.2840288.190655...-1.4859097.07132516.983593-1.0593200.4021318.089287-3.90717511.5427322.55480217.138443
std62.95794628.70321431.21422435.8069757.5563042.17369664.43292135.02915829.07589838.617100...8.28117144.60871453.4774323.8004652.22257338.23671712.01834151.66631214.25411152.269917
min7.0000007.00000090.00000067.000000124.000000122.000000-222.000000-84.000000-52.000000-56.000000...-38.000000-71.000000-65.000000-12.000000-9.000000-57.000000-31.000000-126.000000-33.000000-65.000000
25%143.00000031.000000146.000000124.000000135.000000128.000000-76.000000-43.000000-26.000000-30.000000...-7.000000-38.000000-37.000000-4.000000-1.000000-30.000000-16.000000-40.000000-10.000000-35.000000
50%202.00000051.000000166.000000152.000000141.000000129.000000-7.000000-20.00000012.00000019.000000...-1.00000018.00000027.000000-1.0000000.00000019.000000-5.00000020.0000005.00000027.000000
75%228.00000083.000000188.000000177.000000148.000000131.00000018.00000022.00000029.00000044.000000...4.00000051.00000069.0000002.0000002.00000044.0000008.00000056.00000015.00000069.000000
max248.000000119.000000247.000000231.000000154.000000135.000000152.00000046.00000060.00000080.000000...35.00000093.000000127.00000011.00000010.00000080.00000019.000000120.00000050.000000127.000000
\n", "

8 rows × 41 columns

\n", "
" ], "text/plain": [ " left_block_H left_block_S left_block_V left_block_l left_block_a \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 178.764099 56.932838 166.771580 150.273458 140.877241 \n", "std 62.957946 28.703214 31.214224 35.806975 7.556304 \n", "min 7.000000 7.000000 90.000000 67.000000 124.000000 \n", "25% 143.000000 31.000000 146.000000 124.000000 135.000000 \n", "50% 202.000000 51.000000 166.000000 152.000000 141.000000 \n", "75% 228.000000 83.000000 188.000000 177.000000 148.000000 \n", "max 248.000000 119.000000 247.000000 231.000000 154.000000 \n", "\n", " left_block_b lelf_right_H lelf_right_S lelf_right_V lelf_right_l \\\n", "count 91301.000000 91301.000000 91301.000000 91301.000000 91301.000000 \n", "mean 129.089342 -30.762193 -11.383139 2.284028 8.190655 \n", "std 2.173696 64.432921 35.029158 29.075898 38.617100 \n", "min 122.000000 -222.000000 -84.000000 -52.000000 -56.000000 \n", "25% 128.000000 -76.000000 -43.000000 -26.000000 -30.000000 \n", "50% 129.000000 -7.000000 -20.000000 12.000000 19.000000 \n", "75% 131.000000 18.000000 22.000000 29.000000 44.000000 \n", "max 135.000000 152.000000 46.000000 60.000000 80.000000 \n", "\n", " ... lelf_right_S_min lelf_right_V_min \\\n", "count ... 91301.000000 91301.000000 \n", "mean ... -1.485909 7.071325 \n", "std ... 8.281171 44.608714 \n", "min ... -38.000000 -71.000000 \n", "25% ... -7.000000 -38.000000 \n", "50% ... -1.000000 18.000000 \n", "75% ... 4.000000 51.000000 \n", "max ... 35.000000 93.000000 \n", "\n", " lelf_right_l_min lelf_right_a_min lelf_right_b_min \\\n", "count 91301.000000 91301.000000 91301.000000 \n", "mean 16.983593 -1.059320 0.402131 \n", "std 53.477432 3.800465 2.222573 \n", "min -65.000000 -12.000000 -9.000000 \n", "25% -37.000000 -4.000000 -1.000000 \n", "50% 27.000000 -1.000000 0.000000 \n", "75% 69.000000 2.000000 2.000000 \n", "max 127.000000 11.000000 10.000000 \n", "\n", " lelf_right_gray_value lelf_right_gray_stddev lelf_right_gray_hist \\\n", "count 91301.000000 91301.000000 91301.000000 \n", "mean 8.089287 -3.907175 11.542732 \n", "std 38.236717 12.018341 51.666312 \n", "min -57.000000 -31.000000 -126.000000 \n", "25% -30.000000 -16.000000 -40.000000 \n", "50% 19.000000 -5.000000 20.000000 \n", "75% 44.000000 8.000000 56.000000 \n", "max 80.000000 19.000000 120.000000 \n", "\n", " lelf_right_gray_max lelf_right_gray_min \n", "count 91301.000000 91301.000000 \n", "mean 2.554802 17.138443 \n", "std 14.254111 52.269917 \n", "min -33.000000 -65.000000 \n", "25% -10.000000 -35.000000 \n", "50% 5.000000 27.000000 \n", "75% 15.000000 69.000000 \n", "max 50.000000 127.000000 \n", "\n", "[8 rows x 41 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['left_block_H'] = train_features['left_block_H']\n", "train_features_9['left_block_S'] = train_features['left_block_S']\n", "train_features_9['left_block_V'] = train_features['left_block_V']\n", "train_features_9['left_block_l'] = train_features['left_block_l']\n", "train_features_9['left_block_a'] = train_features['left_block_a']\n", "train_features_9['left_block_b'] = train_features['left_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": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "d:\\Anaconda3\\lib\\site-packages\\sklearn\\ensemble\\weight_boosting.py:29: DeprecationWarning: numpy.core.umath_tests is an internal NumPy module and should not be imported. It will be removed in a future NumPy release.\n", " from numpy.core.umath_tests import inner1d\n", "d:\\Anaconda3\\lib\\site-packages\\sklearn\\cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n", " \"This module will be removed in 0.20.\", DeprecationWarning)\n" ] } ], "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.cross_validation import train_test_split\n", "X_train ,X_test,y_train,y_test = train_test_split(train_features_9,train_labels,test_size = 0.5, random_state = 0)\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": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "-----------classification_report----------------------\n", "\n", " precision recall f1-score support\n", "\n", " 0 0.00 0.00 0.00 7138\n", " 1 0.00 0.00 0.00 0\n", " 2 0.00 0.00 0.00 0\n", " 5 0.73 0.99 0.84 4133\n", " 6 0.99 0.78 0.87 6989\n", "\n", "avg / total 0.54 0.52 0.52 18260\n", "\n", "-----------cm----------------------\n", "\n", "[[ 0 7097 41 0 0]\n", " [ 0 0 0 0 0]\n", " [ 0 0 0 0 0]\n", " [ 0 0 0 4072 61]\n", " [ 0 0 0 1524 5465]]\n", "---------------------------------\n", "\n", "Accuracy of prediction: 0.0\n", "---------------------------------\n", "\n", "DecisionTree accuracy score: 0.522289156626506\n", "f1 score: 0.522289156626506\n", "precision_score: 0.522289156626506\n", "recall_score: 0.522289156626506\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "d:\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1135: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "d:\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1137: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples.\n", " 'recall', 'true', average, warn_for)\n" ] } ], "source": [ "from sklearn.tree import DecisionTreeClassifier\n", "from sklearn.metrics import classification_report,confusion_matrix\n", "\n", "dtree = DecisionTreeClassifier(criterion='gini',max_depth=None)\n", "dtree.fit(X_train,y_train)\n", "predictions = dtree.predict(X_test)\n", "\n", "print(\"-----------classification_report----------------------\\n\")\n", "print(classification_report(y_test,predictions))\n", "print(\"-----------cm----------------------\\n\")\n", "cm=confusion_matrix(y_test,predictions)\n", "print(cm)\n", "print(\"---------------------------------\\n\")\n", "print (\"Accuracy of prediction:\",round((cm[0,0]+cm[1,1])/cm.sum(),3))\n", "print(\"---------------------------------\\n\")\n", "print (\"DecisionTree accuracy score:\" , accuracy_score(y_test,predictions))\n", "print (\"f1 score:\" , f1_score(y_test,predictions,average='micro'))\n", "print (\"precision_score:\" , precision_score(y_test,predictions,average='micro'))\n", "print (\"recall_score:\" , recall_score(y_test,predictions,average='micro'))" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.00 0.00 0.00 7138\n", " 1 0.00 0.00 0.00 0\n", " 2 0.00 0.00 0.00 0\n", " 5 0.73 0.99 0.84 4133\n", " 6 0.99 0.78 0.87 6989\n", "\n", "avg / total 0.54 0.52 0.52 18260\n", "\n", "[[ 0 7138 0 0]\n", " [ 0 0 0 0]\n", " [ 0 0 4090 43]\n", " [ 0 0 1967 5022]]\n", "---------------------------------\n", "\n", "Accuracy of prediction: 0.0\n", "RandomForest accuracy score: 0.49901423877327494\n", "---------------------------------\n", "\n", "f1 score: 0.49901423877327494\n", "precision_score: 0.49901423877327494\n", "recall_score: 0.49901423877327494\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "d:\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1135: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n", " 'precision', 'predicted', average, warn_for)\n", "d:\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1137: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples.\n", " 'recall', 'true', average, warn_for)\n" ] } ], "source": [ "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import classification_report\n", "\n", "rfc = RandomForestClassifier(n_estimators=600)\n", "rfc.fit(X_train, y_train)\n", "rfc_pred = rfc.predict(X_test)\n", "cr = classification_report(y_test,predictions)\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": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "KFold(n_splits=5, random_state=None, shuffle=False)\n", "TRAIN: [18261 18262 18263 ... 91298 91299 91300] TEST: [ 0 1 2 ... 18258 18259 18260]\n", "svm linear accuracy score: 0.8475987076282788\n", "f1 score: 0.8475987076282787\n", "precision_score: 0.8475987076282788\n", "recall_score: 0.8475987076282788\n", "runing time: 0:00:41.736420\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 91298 91299 91300] TEST: [18261 18262 18263 ... 36518 36519 36520]\n", "svm linear accuracy score: 0.6246987951807229\n", "f1 score: 0.6246987951807229\n", "precision_score: 0.6246987951807229\n", "recall_score: 0.6246987951807229\n", "runing time: 0:00:44.495668\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 91298 91299 91300] TEST: [36521 36522 36523 ... 54778 54779 54780]\n", "svm linear accuracy score: 0.6128148959474261\n", "f1 score: 0.6128148959474261\n", "precision_score: 0.6128148959474261\n", "recall_score: 0.6128148959474261\n", "runing time: 0:00:37.768042\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 91298 91299 91300] TEST: [54781 54782 54783 ... 73038 73039 73040]\n", "svm linear accuracy score: 0.6917853231106244\n", "f1 score: 0.6917853231106244\n", "precision_score: 0.6917853231106244\n", "recall_score: 0.6917853231106244\n", "runing time: 0:00:40.198486\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 73038 73039 73040] TEST: [73041 73042 73043 ... 91298 91299 91300]\n", "svm linear accuracy score: 0.512157721796276\n", "f1 score: 0.512157721796276\n", "precision_score: 0.512157721796276\n", "recall_score: 0.512157721796276\n", "runing time: 0:00:37.209128\n", "\n", "\n", "\n" ] } ], "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": [ "\n", "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)\n", "\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "KFold(n_splits=5, random_state=None, shuffle=False)\n", "TRAIN: [18261 18262 18263 ... 91298 91299 91300] TEST: [ 0 1 2 ... 18258 18259 18260]\n", "svm linear accuracy score: 0.9905810196593834\n", "f1 score: 0.9905810196593834\n", "precision_score: 0.9905810196593834\n", "recall_score: 0.9905810196593834\n", "runing time: 0:00:01.629664\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 91298 91299 91300] TEST: [18261 18262 18263 ... 36518 36519 36520]\n", "svm linear accuracy score: 0.6089813800657174\n", "f1 score: 0.6089813800657174\n", "precision_score: 0.6089813800657174\n", "recall_score: 0.6089813800657174\n", "runing time: 0:00:01.333435\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 91298 91299 91300] TEST: [36521 36522 36523 ... 54778 54779 54780]\n", "svm linear accuracy score: 0.7424424972617744\n", "f1 score: 0.7424424972617744\n", "precision_score: 0.7424424972617744\n", "recall_score: 0.7424424972617744\n", "runing time: 0:00:01.253643\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 91298 91299 91300] TEST: [54781 54782 54783 ... 73038 73039 73040]\n", "svm linear accuracy score: 0.7694414019715224\n", "f1 score: 0.7694414019715224\n", "precision_score: 0.7694414019715224\n", "recall_score: 0.7694414019715224\n", "runing time: 0:00:01.432155\n", "\n", "\n", "\n", "TRAIN: [ 0 1 2 ... 73038 73039 73040] TEST: [73041 73042 73043 ... 91298 91299 91300]\n", "svm linear accuracy score: 0.5460021905805038\n", "f1 score: 0.5460021905805038\n", "precision_score: 0.5460021905805038\n", "recall_score: 0.5460021905805038\n", "runing time: 0:00:01.428182\n", "\n", "\n", "\n" ] } ], "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", " clf_svm_linear = SVC(kernel='linear', gamma=0.02, C=1)\n", " clf_svm_linear = clf_svm_linear.fit(X_train, y_train)\n", " #print(clf_svm_linear.predict(X_test))\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", " print (\"precision_score:\" , precision_score(y_test,pred,average='micro'))\n", " print (\"recall_score:\" , recall_score(y_test,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\")\n" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "svm linear accuracy score: 0.9999342840244464\n", "f1 score: 0.9999342840244464\n", "precision_score: 0.9999342840244464\n", "recall_score: 0.9999342840244464\n", "runing clf_svm_linear time: 0:00:01.601394\n" ] } ], "source": [ "#X_train = train_features_9\n", "#y_train = train_labels\n", "\n", "# X_test = test_features\n", "# y_test = test_labels\n", "\n", "from datetime import datetime\n", "trarining_start_time = datetime.now()\n", " \n", "#clf_svm_linear = SVC(kernel = 'linear',gamma=0.00001,C=0.01)\n", "clf_svm_linear = SVC(kernel = 'linear',gamma=0.02,C=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", "#print (\"precision_score:\" , precision_score(y_test,pred,average=None))\n", "#print (\"recall_score :\" , recall_score(y_test,pred,average=None))\n", "print (\"svm linear accuracy score:\" , accuracy_score(y_test,pred))\n", "print (\"f1 score:\" , f1_score(y_test,pred,average='micro'))\n", "print (\"precision_score:\" , precision_score(y_test,pred,average='micro'))\n", "print (\"recall_score:\" , recall_score(y_test,pred,average='micro'))\n", "\n", "training_stop_time = datetime.now()\n", "print (\"runing clf_svm_linear time:\",(training_stop_time - trarining_start_time))\n" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [], "source": [ "from sklearn_porter import Porter\n", "\n", "porter_clf_svm_liner = 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_20181221.txt\",'wb')\n", "#f = open(\"clf_svm_linear_125100_low_feature_data.txt\",'wb')\n", "f.write(porter_clf_svm_liner.encode())\n", "f.close()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "from sklearn_porter import Porter\n", "\n", "porter_clf_svm_liner = Porter(clf_svm_linear, language='js').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_41features_js_20181221.js\",'wb')\n", "#f = open(\"clf_svm_linear_125100_low_feature_data.txt\",'wb')\n", "f.write(porter_clf_svm_liner.encode())\n", "f.close()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "scrolled": false }, "outputs": [], "source": [ "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", "\n", "print(\"preds:\",pred[:10])\n", "print('trues:\\n',y_test[:10])\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_20181207.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": "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": "3.7.0" } }, "nbformat": 4, "nbformat_minor": 2 }