admin/yola
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main
yola/pailuan/master/ov2019/ovulation-backup.ipynb
T
coco 85d885e008 a
2026-07-03 16:29:47 +08:00

1515 lines
77 KiB
Plaintext
Raw Permalink Blame History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
" *排卵试纸机器学习算法验证*"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**import moudle**"
]
},
{
"cell_type": "code",
"execution_count": null,
"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",
"\n",
"%matplotlib inline\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**load data**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"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(\"./newData/10_25.csv\")\n",
" data2 = pd.read_csv(\"./newData/5_10_25_50_70.csv\")\n",
" data_test1 = pd.read_csv(\"./newData/test.csv\")\n",
" data_test2 = pd.read_csv(\"./newData/nubia_test.csv\")\n",
" \n",
" print \"load data successful !!!!!\"\n",
"except :\n",
" print \"load data error !!!!!!!!!!\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"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(\"./10_25.csv\")\n",
" data2 = pd.read_csv(\"./0_5_10_50_70.csv\")\n",
" data3 = pd.read_csv(\"./5_10_25_50_70.csv\")\n",
" data4 = pd.read_csv(\"./25.csv\")\n",
" data_test1 = pd.read_csv(\"./test.csv\")\n",
" data_test2 = pd.read_csv(\"./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": null,
"metadata": {},
"outputs": [],
"source": [
"try :\n",
" data2020 = pd.read_csv(\"./ov_data_2020.csv\")\n",
" data2019 = pd.read_excel(\"./ov_data_2019.xlsx\")\n",
" print (\"load new data successful !!!!!\")\n",
"except :\n",
" print (\"load new data error !!!!!!!!!!\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"data_test = data_test1.append(data_test2)\n",
"data_test.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"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\"] == 1]\n",
"data2_0 = data2[data2[\"whiteBalance\"] == 1]\n",
"data_test_0 = data_test\n",
"\n",
"#data_all =data1_0.append(data2_0);\n",
"data_all =data1.append(data2);\n",
"#data_all = train_features_9\n",
"whiteBlock_R_one =data_all[data_all[\"index\"] == 0 ][\"right_block_l_min\"]\n",
"whiteBlock_G_one = data_all[data_all[\"index\"] == 0 ][\"right_block_a_min\"]\n",
"whiteBlock_B_one = data_all[data_all[\"index\"] == 0 ][\"right_block_b_min\"]\n",
"\n",
"whiteBlock_R_two = data_all[data_all[\"index\"] == 1 ][\"right_block_l_min\"]\n",
"whiteBlock_G_two = data_all[data_all[\"index\"] == 1 ][\"right_block_a_min\"]\n",
"whiteBlock_B_two = data_all[data_all[\"index\"] == 1 ][\"right_block_b_min\"]\n",
"\n",
"whiteBlock_R_three = data_all[data_all[\"index\"] == 2 ][\"right_block_l_min\"]\n",
"whiteBlock_G_three = data_all[data_all[\"index\"] == 2 ][\"right_block_a_min\"]\n",
"whiteBlock_B_three = data_all[data_all[\"index\"] == 2 ][\"right_block_b_min\"]\n",
"\n",
"whiteBlock_R_four = data_all[data_all[\"index\"] == 4 ][\"right_block_l_min\"]\n",
"whiteBlock_G_four = data_all[data_all[\"index\"] == 4 ][\"right_block_a_min\"]\n",
"whiteBlock_B_four = data_all[data_all[\"index\"] == 4 ][\"right_block_b_min\"]\n",
"\n",
"\n",
"whiteBlock_R_five = data_all[data_all[\"index\"] == 6 ][\"right_block_l_min\"]\n",
"whiteBlock_G_five = data_all[data_all[\"index\"] == 6 ][\"right_block_a_min\"]\n",
"whiteBlock_B_five = data_all[data_all[\"index\"] == 6 ][\"right_block_b_min\"]\n",
"\n",
"whiteBlock_R_six = data_all[data_all[\"index\"] == 7 ][\"right_block_l_min\"]\n",
"whiteBlock_G_six = data_all[data_all[\"index\"] == 7 ][\"right_block_a_min\"]\n",
"whiteBlock_B_six = data_all[data_all[\"index\"] == 7 ][\"right_block_b_min\"]\n",
"\n",
"data_all.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"whiteBlock_R_one.describe()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"\n",
"fig = plt.figure()\n",
"#plt.rcParams[\"figure.figsize\"] = 20,20\n",
"ax = Axes3D(fig)\n",
"\n",
"ax.set_xlim(0,255)\n",
"ax.set_ylim(0,255)\n",
"ax.set_zlim(0,255)\n",
"ax.set_xlabel('H')\n",
"ax.set_ylabel('S')\n",
"ax.set_zlabel('V')\n",
"ax.set_title('HSV colorspace OV right block max value')\n",
"# ax.scatter(whiteBlock_R_zero, whiteBlock_G_zero, whiteBlock_B_zero,s = 15,c='y')\n",
"ax.scatter(whiteBlock_R_one, whiteBlock_G_one, whiteBlock_B_one,s = 15,c='r')\n",
"\n",
"ax.scatter(whiteBlock_R_two, whiteBlock_G_two, whiteBlock_B_two,s = 15,c='g')\n",
"ax.scatter(whiteBlock_R_three, whiteBlock_G_three, whiteBlock_B_three,s = 15,c='b')\n",
"\n",
"ax.scatter(whiteBlock_R_four, whiteBlock_G_four, whiteBlock_B_four,s = 15,c='y')\n",
"ax.scatter(whiteBlock_R_five, whiteBlock_G_five, whiteBlock_B_five,s = 15,c='pink')\n",
"ax.scatter(whiteBlock_R_six, whiteBlock_G_six, whiteBlock_B_six,s = 15,c='c')\n",
"\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"*把档位从数据中分割出来，去掉蛋白质的标记*"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"\n",
"\n",
"# label_1 = data3[\"index\"]\n",
"# feature_1 = data3.drop(\"dateTime\",axis=1)\n",
"# feature_1 = feature_1.drop(\"index\",axis=1)\n",
"\n",
"# feature_1 = feature_1.drop(\"right_block_R\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_G\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_B\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_H\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_S\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_V\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_l\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_a\",axis=1)\n",
"# feature_1 = feature_1.drop(\"right_block_b\",axis=1)\n",
"\n",
"\n",
"# label_2 = data4[\"index\"]\n",
"# feature_2 = data4.drop(\"dateTime\",axis=1)\n",
"# feature_2 = feature_2.drop(\"index\",axis=1)\n",
"\n",
"# feature_2 = feature_2.drop(\"left_block_R\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_G\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_B\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_H\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_S\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_V\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_l\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_a\",axis=1)\n",
"# feature_2 = feature_2.drop(\"left_block_b\",axis=1)\n",
"\n",
"# label_3 = data3[\"index\"]\n",
"# feature_3 = data3.drop(\"dateTime\",axis=1)\n",
"# feature_3 = feature_3.drop(\"index\",axis=1)\n",
"#sns.heatmap(feature_iphone6p)\n",
"\n",
"# feature_3.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"\n",
"\n",
"from sklearn.utils import shuffle\n",
"\n",
"\n",
"data_shuffle = shuffle(data_all)\n",
"#data_shuffle = data_all;\n",
"train_labels = data_shuffle[\"index\"]\n",
"train_features = data_shuffle.drop(\"dateTime\",axis=1)\n",
"train_features = train_features.drop(\"index\",axis=1)\n",
"train_features = train_features.drop(\"whiteBalance\",axis=1)\n",
"\n",
"data_shuffle_test = shuffle(data_test_0)\n",
"test_labels = data_shuffle_test[\"index\"]\n",
"test_features = data_shuffle_test.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",
"# 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",
"test_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": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"train_features_9 = pd.DataFrame()\n",
"train_features_9['lelf_right_R'] = train_features['left_block_R'] - train_features['right_block_R']\n",
"train_features_9['lelf_right_G'] = train_features['left_block_G'] - train_features['right_block_G']\n",
"train_features_9['lelf_right_B'] = train_features['left_block_B'] - train_features['right_block_B']\n",
"\n",
"train_features_9['lelf_right_H'] = train_features['left_block_H'] - train_features['right_block_H']\n",
"train_features_9['lelf_right_S'] = train_features['left_block_S'] - train_features['right_block_S']\n",
"train_features_9['lelf_right_V'] = train_features['left_block_V'] - train_features['right_block_V']\n",
"\n",
"train_features_9['lelf_right_l'] = train_features['left_block_l'] - train_features['right_block_l']\n",
"train_features_9['lelf_right_a'] = train_features['left_block_a'] - train_features['right_block_a']\n",
"train_features_9['lelf_right_b'] = train_features['left_block_b'] - train_features['right_block_b']\n",
"\n",
"train_features_9['lelf_right_R_stddev'] = train_features['left_block_R_stddev'] - train_features['right_block_R_stddev']\n",
"train_features_9['lelf_right_G_stddev'] = train_features['left_block_G_stddev'] - train_features['right_block_G_stddev']\n",
"train_features_9['lelf_right_B_stddev'] = train_features['left_block_B_stddev'] - train_features['right_block_B_stddev']\n",
"\n",
"train_features_9['lelf_right_H_stddev'] = train_features['left_block_H_stddev'] - train_features['right_block_H_stddev']\n",
"train_features_9['lelf_right_S_stddev'] = train_features['left_block_S_stddev'] - train_features['right_block_S_stddev']\n",
"train_features_9['lelf_right_V_stddev'] = train_features['left_block_V_stddev'] - train_features['right_block_V_stddev']\n",
"\n",
"train_features_9['lelf_right_l_stddev'] = train_features['left_block_l_stddev'] - train_features['right_block_l_stddev']\n",
"train_features_9['lelf_right_a_stddev'] = train_features['left_block_a_stddev'] - train_features['right_block_a_stddev']\n",
"train_features_9['lelf_right_b_stddev'] = train_features['left_block_b_stddev'] - train_features['right_block_b_stddev']\n",
"\n",
"train_features_9['lelf_right_R_hist'] = train_features['left_block_R_hist'] - train_features['right_block_R_hist']\n",
"train_features_9['lelf_right_G_hist'] = train_features['left_block_G_hist'] - train_features['right_block_G_hist']\n",
"train_features_9['lelf_right_B_hist'] = train_features['left_block_B_hist'] - train_features['right_block_B_hist']\n",
"\n",
"train_features_9['lelf_right_H_hist'] = train_features['left_block_H_hist'] - train_features['right_block_H_hist']\n",
"train_features_9['lelf_right_S_hist'] = train_features['left_block_S_hist'] - train_features['right_block_S_hist']\n",
"train_features_9['lelf_right_V_hist'] = train_features['left_block_V_hist'] - train_features['right_block_V_hist']\n",
"\n",
"train_features_9['lelf_right_l_hist'] = train_features['left_block_l_hist'] - train_features['right_block_l_hist']\n",
"train_features_9['lelf_right_a_hist'] = train_features['left_block_a_hist'] - train_features['right_block_a_hist']\n",
"train_features_9['lelf_right_b_hist'] = train_features['left_block_b_hist'] - train_features['right_block_b_hist']\n",
"\n",
"train_features_9['lelf_right_R_max'] = train_features['left_block_R_max'] - train_features['right_block_R_max']\n",
"train_features_9['lelf_right_G_max'] = train_features['left_block_G_max'] - train_features['right_block_G_max']\n",
"train_features_9['lelf_right_B_max'] = train_features['left_block_B_max'] - train_features['right_block_B_max']\n",
"\n",
"train_features_9['lelf_right_H_max'] = train_features['left_block_H_max'] - train_features['right_block_H_max']\n",
"train_features_9['lelf_right_S_max'] = train_features['left_block_S_max'] - train_features['right_block_S_max']\n",
"train_features_9['lelf_right_V_max'] = train_features['left_block_V_max'] - train_features['right_block_V_max']\n",
"\n",
"train_features_9['lelf_right_l_max'] = train_features['left_block_l_max'] - train_features['right_block_l_max']\n",
"train_features_9['lelf_right_a_max'] = train_features['left_block_a_max'] - train_features['right_block_a_max']\n",
"train_features_9['lelf_right_b_max'] = train_features['left_block_b_max'] - train_features['right_block_b_max']\n",
"\n",
"train_features_9['lelf_right_R_min'] = train_features['left_block_R_min'] - train_features['right_block_R_min']\n",
"train_features_9['lelf_right_G_min'] = train_features['left_block_G_min'] - train_features['right_block_G_min']\n",
"train_features_9['lelf_right_B_min'] = train_features['left_block_B_min'] - train_features['right_block_B_min']\n",
"\n",
"train_features_9['lelf_right_H_min'] = train_features['left_block_H_min'] - train_features['right_block_H_min']\n",
"train_features_9['lelf_right_S_min'] = train_features['left_block_S_min'] - train_features['right_block_S_min']\n",
"train_features_9['lelf_right_V_min'] = train_features['left_block_V_min'] - train_features['right_block_V_min']\n",
"\n",
"train_features_9['lelf_right_l_min'] = train_features['left_block_l_min'] - train_features['right_block_l_min']\n",
"train_features_9['lelf_right_a_min'] = train_features['left_block_a_min'] - train_features['right_block_a_min']\n",
"train_features_9['lelf_right_b_min'] = train_features['left_block_b_min'] - train_features['right_block_b_min']\n",
"\n",
"# train_features_9['left_grayValue']= train_features['left_grayValue'];\n",
"# train_features_9['left_grayStddevValue']= train_features['left_grayStddevValue'];\n",
"# train_features_9['left_grayHist']= train_features['left_grayHist'];\n",
"# train_features_9['left_grayMax']= train_features['left_grayMax'];\n",
"# train_features_9['left_grayMin']= train_features['left_grayMin'];\n",
"\n",
"# train_features_9['right_grayValue']= train_features['right_grayValue'];\n",
"# train_features_9['right_grayStddevValue']= train_features['right_grayStddevValue'];\n",
"# train_features_9['right_grayHist']= train_features['right_grayHist'];\n",
"# train_features_9['right_grayMax']= train_features['right_grayMax'];\n",
"# train_features_9['right_grayMin']= train_features['right_grayMin'];\n",
"\n",
"# train_features_9['lelf_R_stddev'] = train_features['left_block_R_stddev'] \n",
"# train_features_9['lelf_G_stddev'] = train_features['left_block_G_stddev'] \n",
"# train_features_9['lelf_B_stddev'] = train_features['left_block_B_stddev'] \n",
"\n",
"# train_features_9['left_block_R_min'] = train_features['left_block_R_min'] \n",
"# train_features_9['left_block_G_min'] = train_features['left_block_G_min'] \n",
"# train_features_9['left_block_B_min'] = train_features['left_block_B_min'] \n",
"\n",
"\n",
"train_features_9['lelf_right_gray_value'] = train_features['left_grayValue'] - train_features['right_grayValue']\n",
"train_features_9['lelf_right_gray_stddev'] = train_features['left_grayStddevValue'] - train_features['right_grayStddevValue']\n",
"train_features_9['lelf_right_gray_hist'] = train_features['left_grayHist'] - train_features['right_grayHist']\n",
"train_features_9['lelf_right_gray_max'] = train_features['left_grayMax'] - train_features['right_grayMax']\n",
"train_features_9['lelf_right_gray_min'] = train_features['left_grayMin'] - train_features['right_grayMin']\n",
"train_features_9['index'] = train_labels\n",
"train_features_9.describe()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**去掉左边块的方差和白块和右边块的特征**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"# train_features = train_features.drop(\"left_block_R\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_G\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_B\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"left_block_R_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_G_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_B_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_B_stddev\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"left_block_R_max\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_G_max\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_B_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_H\",axis=1)\n",
"train_features = train_features.drop(\"left_block_S\",axis=1)\n",
"train_features = train_features.drop(\"left_block_V\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_H_hist\",axis=1)\n",
"train_features = train_features.drop(\"left_block_S_hist\",axis=1)\n",
"train_features = train_features.drop(\"left_block_V_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_H_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_S_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_V_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_l\",axis=1)\n",
"train_features = train_features.drop(\"left_block_a\",axis=1)\n",
"train_features = train_features.drop(\"left_block_b\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_l_hist\",axis=1)\n",
"train_features = train_features.drop(\"left_block_a_hist\",axis=1)\n",
"train_features = train_features.drop(\"left_block_b_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_l_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_a_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_b_max\",axis=1)\n",
"##################################################################\n",
"\n",
"# train_features = train_features.drop(\"right_block_R\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_G\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_B\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_B_stddev\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_R_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_G_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_B_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_R_max\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_G_max\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_B_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_H\",axis=1)\n",
"train_features = train_features.drop(\"right_block_S\",axis=1)\n",
"train_features = train_features.drop(\"right_block_V\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_H_hist\",axis=1)\n",
"train_features = train_features.drop(\"right_block_S_hist\",axis=1)\n",
"train_features = train_features.drop(\"right_block_V_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_H_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_S_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_V_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_l\",axis=1)\n",
"train_features = train_features.drop(\"right_block_a\",axis=1)\n",
"train_features = train_features.drop(\"right_block_b\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_l_hist\",axis=1)\n",
"train_features = train_features.drop(\"right_block_a_hist\",axis=1)\n",
"train_features = train_features.drop(\"right_block_b_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_l_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_a_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_b_max\",axis=1)\n",
"\n",
"####################################################################\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_R\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_G\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_B\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_B_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_R_hist\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_G_hist\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_B_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_R_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_G_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_B_max\",axis=1)\n",
"\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_H\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_S\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_V\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_H_hist\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_S_hist\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_V_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_H_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_S_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_V_max\",axis=1)\n",
"\n",
"\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_l\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_a\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_b\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_l_hist\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_a_hist\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_b_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_l_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_a_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_b_max\",axis=1)\n",
"\n",
"##################################################################\n",
"\n",
"\n",
"\n",
"train_features.describe()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**去掉所有块的方差特征**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"train_features = train_features.drop(\"left_block_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_B_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_B_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_B_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_b_stddev\",axis=1)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# train_features = train_features.drop(\"left_block_R\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_G\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_B\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"left_block_H\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_S\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_V\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"left_block_l\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_a\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_b\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_R\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_G\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_B\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_H\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_S\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_V\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_l\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_a\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_b\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"whiteBlock_R\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_G\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_B\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"whiteBlock_H\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_S\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_V\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"whiteBlock_l\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_a\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_b\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"left_block_R_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_G_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_B_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"left_block_H_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_S_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_V_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"left_block_l_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_a_hist\",axis=1)\n",
"# train_features = train_features.drop(\"left_block_b_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_R_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_G_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_B_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_H_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_S_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_V_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"right_block_l_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_a_hist\",axis=1)\n",
"# train_features = train_features.drop(\"right_block_b_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"whiteBlock_R_hist\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_G_hist\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_B_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"whiteBlock_H_hist\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_S_hist\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_V_hist\",axis=1)\n",
"\n",
"# train_features = train_features.drop(\"whiteBlock_l_hist\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_a_hist\",axis=1)\n",
"# train_features = train_features.drop(\"whiteBlock_b_hist\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_B_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"left_block_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_B_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"right_block_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_R_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_G_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_B_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_H_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_S_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_V_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_l_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_a_stddev\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_b_stddev\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_R_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_G_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_B_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_H_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_S_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_V_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"left_block_l_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_a_max\",axis=1)\n",
"train_features = train_features.drop(\"left_block_b_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_R_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_G_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_B_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_H_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_S_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_V_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"right_block_l_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_a_max\",axis=1)\n",
"train_features = train_features.drop(\"right_block_b_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_R_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_G_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_B_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_H_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_S_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_V_max\",axis=1)\n",
"\n",
"train_features = train_features.drop(\"whiteBlock_l_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_a_max\",axis=1)\n",
"train_features = train_features.drop(\"whiteBlock_b_max\",axis=1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"train_features.describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.model_selection import KFold\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.svm import SVC\n",
"from sklearn.metrics import f1_score\n",
"from sklearn.metrics import precision_score\n",
"from sklearn.metrics import recall_score\n",
"\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,train_labels,test_size = 0.002, random_state = 20)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"\n",
"\n",
"X = train_features.values\n",
"y = train_labels.values\n",
"\n",
"kf = KFold(n_splits=5)\n",
"kf.get_n_splits(X)\n",
"\n",
"print(kf) \n",
"\n",
"for train_index, test_index in kf.split(X):\n",
" print(\"TRAIN:\", train_index, \"TEST:\", test_index)\n",
" X_train, X_test = X[train_index], X[test_index]\n",
" y_train, y_test = y[train_index], y[test_index]\n",
" \n",
" \n",
" from datetime import datetime\n",
" trarining_start_time = datetime.now()\n",
"\n",
" clf_svm_linear = SVC(kernel = 'linear',gamma=0.00001,C=0.1)\n",
" clf_svm_linear = clf_svm_linear.fit(X_train, y_train)\n",
" pred = clf_svm_linear.predict(X_test)\n",
" print \"svm linear accuracy score:\" , accuracy_score(y_test,pred)\n",
" print \"f1 score:\" , f1_score(y_test,pred,average='micro')\n",
"\n",
"\n",
" training_stop_time = datetime.now()\n",
"\n",
" print \"runing time:\",(training_stop_time - trarining_start_time)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"X_train = train_features_9\n",
"y_train = train_labels\n",
"\n",
"# X_test = test_features\n",
"# y_test = test_labels\n",
"\n",
"#clf_svm_linear = SVC(kernel = 'linear',gamma=0.00001,C=0.01)\n",
"clf_svm_linear = SVC(kernel = 'linear',gamma=0.00001,C=0.01)\n",
"\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')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"pred = clf_svm_linear.predict(X_train)\n",
"print \"svm linear accuracy score:\" , accuracy_score(y_train,pred)"
]
},
{
"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='micro')\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_45features_201710119.txt\",'wb')\n",
"#f = open(\"clf_svm_linear_125100_low_feature_data.txt\",'wb')\n",
"f.write(porter_clf_svm_linear)\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": [
"**参数选择**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn import svm, datasets\n",
"from sklearn.model_selection import GridSearchCV\n",
"\n",
"parameters = {'n_estimators':[15,16,17,18], 'max_features':[8,9,10,11],\\\n",
" 'min_samples_split':[3,4,5,6,7],\\\n",
" 'max_depth':[7,8,9,10,11,12,13,14,15]\n",
" }\n",
"clf = RandomForestClassifier(random_state=10)\n",
"\n",
"from datetime import datetime\n",
"trarining_start_time = datetime.now()\n",
"clf_grid = GridSearchCV(clf, parameters)\n",
"training_stop_time = datetime.now()\n",
"print \"runing time:\",(training_stop_time - trarining_start_time)\n",
"\n",
"clf_grid.fit(X_train, y_train)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print clf_grid.best_estimator_"
]
},
{
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue View Git Blame Copy Permalink