Mercurial > hg > plosone_underreview

comparison notebooks/sensitivity_experiment.ipynb @ 59:444041185ba9 branch-tests

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
changes in sensitivity experiment
author mpanteli <m.x.panteli@gmail.com>
date Thu, 21 Sep 2017 15:23:05 +0100
parents 98cd5317e504
children 402f43d5b7ad
comparison
equal deleted inserted replaced
55:98cd5317e504 59:444041185ba9
1 { 1 {
2 "cells": [ 2 "cells": [
3 { 3 {
4 "cell_type": "code", 4 "cell_type": "code",
5 "execution_count": 1, 5 "execution_count": 20,
6 "metadata": {}, 6 "metadata": {},
7 "outputs": [ 7 "outputs": [
8 { 8 {
9 "name": "stderr", 9 "name": "stdout",
10 "output_type": "stream", 10 "output_type": "stream",
11 "text": [ 11 "text": [
12 "/homes/mp305/anaconda/lib/python2.7/site-packages/librosa/core/audio.py:33: UserWarning: Could not import scikits.samplerate. Falling back to scipy.signal\n", 12 "The autoreload extension is already loaded. To reload it, use:\n",
13 " warnings.warn('Could not import scikits.samplerate. '\n" 13 " %reload_ext autoreload\n"
14 ] 14 ]
15 } 15 }
16 ], 16 ],
17 "source": [ 17 "source": [
18 "import numpy as np\n", 18 "import numpy as np\n",
4545 ] 4545 ]
4546 }, 4546 },
4547 { 4547 {
4548 "cell_type": "code", 4548 "cell_type": "code",
4549 "execution_count": null, 4549 "execution_count": null,
4550 "metadata": {}, 4550 "metadata": {
4551 "collapsed": true
4552 },
4551 "outputs": [], 4553 "outputs": [],
4552 "source": [ 4554 "source": [
4553 "MAPPER_OUTPUT_FILES = mapper.OUTPUT_FILES\n", 4555 "MAPPER_OUTPUT_FILES = mapper.OUTPUT_FILES\n",
4554 "for n in range(n_iters):\n", 4556 "for n in range(n_iters):\n",
4555 " print \"iteration %d\" % n\n", 4557 " print \"iteration %d\" % n\n",
4570 "## Classification only - assuming mapper files are exported " 4572 "## Classification only - assuming mapper files are exported "
4571 ] 4573 ]
4572 }, 4574 },
4573 { 4575 {
4574 "cell_type": "code", 4576 "cell_type": "code",
4575 "execution_count": 19, 4577 "execution_count": 21,
4576 "metadata": {}, 4578 "metadata": {},
4577 "outputs": [ 4579 "outputs": [
4578 { 4580 {
4579 "name": "stdout", 4581 "name": "stdout",
4580 "output_type": "stream", 4582 "output_type": "stream",
4786 "74 Czech Republic 0.024390 41 1\n", 4788 "74 Czech Republic 0.024390 41 1\n",
4787 "13 Germany 0.040000 100 4\n", 4789 "13 Germany 0.040000 100 4\n",
4788 "31 Afghanistan 0.041667 24 1\n", 4790 "31 Afghanistan 0.041667 24 1\n",
4789 "105 Sudan 0.045455 66 3\n", 4791 "105 Sudan 0.045455 66 3\n",
4790 "120 Kazakhstan 0.045455 88 4\n", 4792 "120 Kazakhstan 0.045455 88 4\n",
4793 "writing file\n",
4794 "iteration 7\n"
4795 ]
4796 },
4797 {
4798 "name": "stdout",
4799 "output_type": "stream",
4800 "text": [
4801 "classifying...\n",
4802 "/import/c4dm-04/mariap/train_data_melodia_8_7.pickle\n",
4803 "0.179777654473\n",
4804 "detecting outliers...\n",
4805 "most outliers \n",
4806 " Country Outliers N_Country N_Outliers\n",
4807 "136 Botswana 0.636364 88 56\n",
4808 "95 Chad 0.636364 11 7\n",
4809 "86 Gambia 0.511111 45 23\n",
4810 "42 Benin 0.500000 26 13\n",
4811 "14 Liberia 0.500000 40 20\n",
4812 "63 Mozambique 0.500000 34 17\n",
4813 "78 El Salvador 0.424242 33 14\n",
4814 "62 Senegal 0.416667 36 15\n",
4815 "20 Pakistan 0.415730 89 37\n",
4816 "106 Nepal 0.402174 92 37\n",
4817 "least outliers \n",
4818 " Country Outliers N_Country N_Outliers\n",
4819 "1 Lithuania 0.000000 47 0\n",
4820 "119 Denmark 0.000000 16 0\n",
4821 "113 Iceland 0.000000 14 0\n",
4822 "27 South Korea 0.000000 11 0\n",
4823 "15 Netherlands 0.015152 66 1\n",
4824 "120 Kazakhstan 0.034884 86 3\n",
4825 "30 Afghanistan 0.041667 24 1\n",
4826 "102 Nicaragua 0.050000 20 1\n",
4827 "112 Israel 0.050000 100 5\n",
4828 "28 Tajikistan 0.052632 19 1\n",
4829 "writing file\n",
4830 "iteration 8\n",
4831 "classifying...\n",
4832 "/import/c4dm-04/mariap/train_data_melodia_8_8.pickle\n",
4833 "0.165005035342\n",
4834 "detecting outliers...\n",
4835 "most outliers \n",
4836 " Country Outliers N_Country N_Outliers\n",
4837 "95 Chad 0.636364 11 7\n",
4838 "43 Benin 0.576923 26 15\n",
4839 "136 Botswana 0.571429 77 44\n",
4840 "14 Liberia 0.525000 40 21\n",
4841 "86 Gambia 0.488889 45 22\n",
4842 "78 El Salvador 0.484848 33 16\n",
4843 "64 Mozambique 0.470588 34 16\n",
4844 "62 Fiji 0.466667 15 7\n",
4845 "20 Pakistan 0.436782 87 38\n",
4846 "63 Senegal 0.416667 36 15\n",
4847 "least outliers \n",
4848 " Country Outliers N_Country N_Outliers\n",
4849 "1 Lithuania 0.000000 47 0\n",
4850 "119 Denmark 0.000000 16 0\n",
4851 "113 Iceland 0.000000 14 0\n",
4852 "27 South Korea 0.000000 11 0\n",
4853 "102 Nicaragua 0.000000 20 0\n",
4854 "28 Tajikistan 0.000000 19 0\n",
4855 "15 Netherlands 0.015152 66 1\n",
4856 "89 Croatia 0.032258 31 1\n",
4857 "120 Kazakhstan 0.034884 86 3\n",
4858 "30 Afghanistan 0.041667 24 1\n",
4859 "writing file\n",
4860 "iteration 9\n",
4861 "classifying...\n",
4862 "/import/c4dm-04/mariap/train_data_melodia_8_9.pickle\n",
4863 "0.168630986212\n",
4864 "detecting outliers...\n",
4865 "most outliers \n",
4866 " Country Outliers N_Country N_Outliers\n",
4867 "43 Benin 0.576923 26 15\n",
4868 "136 Botswana 0.567901 81 46\n",
4869 "60 Chad 0.545455 11 6\n",
4870 "86 Gambia 0.533333 45 24\n",
4871 "14 Liberia 0.525000 40 21\n",
4872 "65 Uganda 0.482759 87 42\n",
4873 "64 Mozambique 0.470588 34 16\n",
4874 "20 Pakistan 0.465909 88 41\n",
4875 "135 French Guiana 0.464286 28 13\n",
4876 "67 Brazil 0.460000 100 46\n",
4877 "least outliers \n",
4878 " Country Outliers N_Country N_Outliers\n",
4879 "1 Lithuania 0.000000 47 0\n",
4880 "90 French Polynesia 0.000000 15 0\n",
4881 "102 Nicaragua 0.000000 20 0\n",
4882 "113 Iceland 0.000000 14 0\n",
4883 "119 Denmark 0.000000 16 0\n",
4884 "15 Netherlands 0.015152 66 1\n",
4885 "18 New Zealand 0.029412 34 1\n",
4886 "120 Kazakhstan 0.034884 86 3\n",
4887 "31 Czech Republic 0.048780 41 2\n",
4888 "28 Tajikistan 0.052632 19 1\n",
4791 "writing file\n" 4889 "writing file\n"
4792 ] 4890 ]
4793 } 4891 }
4794 ], 4892 ],
4795 "source": [ 4893 "source": [
4796 "n_iters = 7\n", 4894 "n_iters = 10\n",
4797 "OUTPUT_FILES = load_dataset.OUTPUT_FILES\n", 4895 "OUTPUT_FILES = load_dataset.OUTPUT_FILES\n",
4798 "MAPPER_OUTPUT_FILES = mapper.OUTPUT_FILES\n", 4896 "MAPPER_OUTPUT_FILES = mapper.OUTPUT_FILES\n",
4799 "for n in range(n_iters):\n", 4897 "for n in range(n_iters):\n",
4800 " print \"iteration %d\" % n\n", 4898 " print \"iteration %d\" % n\n",
4801 " CLASS_INPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for \n", 4899 " CLASS_INPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for \n",
4838 "<br> Sort by outlier percentage in descending order." 4936 "<br> Sort by outlier percentage in descending order."
4839 ] 4937 ]
4840 }, 4938 },
4841 { 4939 {
4842 "cell_type": "code", 4940 "cell_type": "code",
4843 "execution_count": null, 4941 "execution_count": 45,
4844 "metadata": { 4942 "metadata": {},
4845 "collapsed": true
4846 },
4847 "outputs": [], 4943 "outputs": [],
4848 "source": [ 4944 "source": [
4849 "ranked_countries = pd.DataFrame()\n", 4945 "ranked_countries = pd.DataFrame()\n",
4850 "ranked_outliers = pd.DataFrame()\n", 4946 "ranked_outliers = pd.DataFrame()\n",
4851 "for n in range(n_iters):\n", 4947 "for n in range(n_iters):\n",
4852 " df_global = pd.read_csv('../data/outliers_'+str(n)+'.csv')\n", 4948 " df_global = pd.read_csv('../data/outliers_'+str(n)+'.csv')\n",
4853 " df_global = df_global.sort_values('Outliers', axis=0, ascending=False, inplace=True)\n", 4949 " df_global = df_global.sort_values('Outliers', axis=0, ascending=False).reset_index()\n",
4854 " ranked_countries = pd.concat([ranked_countries, df_global['Country']], axis=1)\n", 4950 " ranked_countries = pd.concat([ranked_countries, df_global['Country']], axis=1)\n",
4855 " ranked_outliers = pd.concat([ranked_outliers, df_global['Outliers']], axis=1)" 4951 " ranked_outliers = pd.concat([ranked_outliers, df_global['Outliers']], axis=1)"
4952 ]
4953 },
4954 {
4955 "cell_type": "code",
4956 "execution_count": 49,
4957 "metadata": {},
4958 "outputs": [
4959 {
4960 "data": {
4961 "text/plain": [
4962 "(133, 10)"
4963 ]
4964 },
4965 "execution_count": 49,
4966 "metadata": {},
4967 "output_type": "execute_result"
4968 }
4969 ],
4970 "source": [
4971 "ranked_outliers.shape"
4856 ] 4972 ]
4857 }, 4973 },
4858 { 4974 {
4859 "cell_type": "markdown", 4975 "cell_type": "markdown",
4860 "metadata": {}, 4976 "metadata": {},
4862 "Remove countries with 0% outliers as these are in random (probably alphabetical) order." 4978 "Remove countries with 0% outliers as these are in random (probably alphabetical) order."
4863 ] 4979 ]
4864 }, 4980 },
4865 { 4981 {
4866 "cell_type": "code", 4982 "cell_type": "code",
4867 "execution_count": null, 4983 "execution_count": 48,
4868 "metadata": { 4984 "metadata": {},
4869 "collapsed": true 4985 "outputs": [
4870 }, 4986 {
4871 "outputs": [], 4987 "name": "stdout",
4988 "output_type": "stream",
4989 "text": [
4990 " Country Country Country Country Country Country \\\n",
4991 "0 Botswana Chad Botswana Botswana Chad Botswana \n",
4992 "1 Ivory Coast Fiji Gambia Ivory Coast Botswana Ivory Coast \n",
4993 "2 Gambia Gambia Ivory Coast Gambia Ivory Coast Pakistan \n",
4994 "3 Benin Benin Fiji Benin Fiji Chad \n",
4995 "4 Fiji Pakistan Benin Fiji Gambia Fiji \n",
4996 "\n",
4997 " Country Country Country Country \n",
4998 "0 Botswana Botswana Chad Benin \n",
4999 "1 Ivory Coast Chad Benin Botswana \n",
5000 "2 Gambia Gambia Botswana Chad \n",
5001 "3 Pakistan Mozambique Liberia Gambia \n",
5002 "4 Fiji Benin Gambia Liberia \n",
5003 " Outliers Outliers Outliers Outliers Outliers Outliers Outliers \\\n",
5004 "0 0.590909 0.545455 0.615385 0.617284 0.727273 0.607143 0.574468 \n",
5005 "1 0.571429 0.533333 0.520833 0.571429 0.630952 0.571429 0.571429 \n",
5006 "2 0.541667 0.520833 0.500000 0.541667 0.571429 0.553191 0.520833 \n",
5007 "3 0.538462 0.500000 0.466667 0.538462 0.533333 0.545455 0.516854 \n",
5008 "4 0.466667 0.500000 0.461538 0.533333 0.520833 0.533333 0.466667 \n",
5009 "\n",
5010 " Outliers Outliers Outliers \n",
5011 "0 0.636364 0.636364 0.576923 \n",
5012 "1 0.636364 0.576923 0.567901 \n",
5013 "2 0.511111 0.571429 0.545455 \n",
5014 "3 0.500000 0.525000 0.533333 \n",
5015 "4 0.500000 0.488889 0.525000 \n"
5016 ]
5017 }
5018 ],
4872 "source": [ 5019 "source": [
4873 "zero_idx = np.where(np.sum(ranked_outliers, axis=1)==0)[0]\n", 5020 "zero_idx = np.where(np.sum(ranked_outliers, axis=1)==0)[0]\n",
4874 "first_zero_idx = np.min(zero_idx)\n", 5021 "first_zero_idx = np.min(zero_idx)\n",
4875 "ranked_countries = ranked_countries.iloc[:first_zero_idx, :]\n", 5022 "ranked_countries = ranked_countries.iloc[:first_zero_idx, :]\n",
4876 "ranked_outliers = ranked_outliers.iloc[:first_zero_idx, :]\n", 5023 "ranked_outliers = ranked_outliers.iloc[:first_zero_idx, :]\n",
4886 "And now kendalltau correlation" 5033 "And now kendalltau correlation"
4887 ] 5034 ]
4888 }, 5035 },
4889 { 5036 {
4890 "cell_type": "code", 5037 "cell_type": "code",
4891 "execution_count": 33, 5038 "execution_count": 54,
4892 "metadata": {}, 5039 "metadata": {},
4893 "outputs": [ 5040 "outputs": [
4894 { 5041 {
4895 "name": "stdout", 5042 "name": "stdout",
4896 "output_type": "stream", 5043 "output_type": "stream",
4897 "text": [ 5044 "text": [
4898 "KendalltauResult(correlation=0.99999999999999989, pvalue=2.5428927239036995e-67)\n" 5045 "KendalltauResult(correlation=0.11870585554796083, pvalue=0.042684955693776824)\n",
5046 "KendalltauResult(correlation=0.061289587605377081, pvalue=0.29535042403787393)\n",
5047 "KendalltauResult(correlation=0.14057871952608797, pvalue=0.016384498702657929)\n",
5048 "KendalltauResult(correlation=0.043062200956937809, pvalue=0.46219181347134564)\n",
5049 "KendalltauResult(correlation=0.038049669628617007, pvalue=0.51591269004232343)\n",
5050 "KendalltauResult(correlation=0.15516062884483939, pvalue=0.0080680863973824919)\n",
5051 "KendalltauResult(correlation=0.097972203235361141, pvalue=0.094371801845320874)\n",
5052 "KendalltauResult(correlation=0.070403280929596718, pvalue=0.22933906132681292)\n",
5053 "KendalltauResult(correlation=0.087263613579403057, pvalue=0.13624109595088119)\n",
5054 "KendalltauResult(correlation=0.026657552973342449, pvalue=0.64900123852931668)\n",
5055 "KendalltauResult(correlation=0.012531328320802006, pvalue=0.83057867073317604)\n",
5056 "KendalltauResult(correlation=0.15698336750968331, pvalue=0.0073549938316186895)\n",
5057 "KendalltauResult(correlation=0.072226019594440652, pvalue=0.21750692637496993)\n",
5058 "KendalltauResult(correlation=0.064479380268853956, pvalue=0.27093205134080134)\n",
5059 "KendalltauResult(correlation=0.07518796992481204, pvalue=0.19922707586147026)\n",
5060 "KendalltauResult(correlation=0.017088174982911826, pvalue=0.77046791234681555)\n",
5061 "KendalltauResult(correlation=0.098200045568466648, pvalue=0.093608177106345392)\n",
5062 "KendalltauResult(correlation=0.11004784688995217, pvalue=0.060250899787989511)\n",
5063 "KendalltauResult(correlation=0.051720209614946465, pvalue=0.37719896672100306)\n",
5064 "KendalltauResult(correlation=0.099567099567099596, pvalue=0.089129953079656793)\n",
5065 "KendalltauResult(correlation=-0.081795397584871282, pvalue=0.16254238954046385)\n",
5066 "KendalltauResult(correlation=0.089769879243563472, pvalue=0.12534294310051713)\n",
5067 "KendalltauResult(correlation=0.10047846889952156, pvalue=0.086241531926005505)\n",
5068 "KendalltauResult(correlation=0.014809751651856917, pvalue=0.80037548797424396)\n",
5069 "KendalltauResult(correlation=0.021189336978810668, pvalue=0.71751195692767422)\n",
5070 "KendalltauResult(correlation=0.020733652312599684, pvalue=0.7233346465763022)\n",
5071 "KendalltauResult(correlation=-0.057644110275689227, pvalue=0.32501053989276085)\n",
5072 "KendalltauResult(correlation=0.04647983595352017, pvalue=0.42743119135699703)\n",
5073 "KendalltauResult(correlation=-0.02939166097060834, pvalue=0.6157855679677966)\n",
5074 "KendalltauResult(correlation=-0.01754385964912281, pvalue=0.76452558103925983)\n",
5075 "KendalltauResult(correlation=-0.00022784233310549102, pvalue=0.99689609964041026)\n",
5076 "KendalltauResult(correlation=0.053087263613579412, pvalue=0.36471883993264553)\n",
5077 "KendalltauResult(correlation=0.11027568922305765, pvalue=0.059721613251292195)\n",
5078 "KendalltauResult(correlation=0.1319207108680793, pvalue=0.024296399889465414)\n",
5079 "KendalltauResult(correlation=0.11050353155616316, pvalue=0.059196189350124301)\n",
5080 "KendalltauResult(correlation=0.081339712918660295, pvalue=0.16489618845189757)\n",
5081 "KendalltauResult(correlation=0.091136933242196419, pvalue=0.11969173188443738)\n",
5082 "KendalltauResult(correlation=0.010252904989747097, pvalue=0.86103426355600943)\n",
5083 "KendalltauResult(correlation=0.026201868307131469, pvalue=0.6546080905364744)\n",
5084 "KendalltauResult(correlation=0.056049213943950793, pvalue=0.33857618122131272)\n",
5085 "KendalltauResult(correlation=0.075415812257917533, pvalue=0.19786889281527764)\n",
5086 "KendalltauResult(correlation=0.026657552973342449, pvalue=0.64900123852931668)\n",
5087 "KendalltauResult(correlation=0.091136933242196419, pvalue=0.11969173188443738)\n",
5088 "KendalltauResult(correlation=0.1964000911369333, pvalue=0.00079845943724486494)\n",
5089 "KendalltauResult(correlation=0.049441786283891551, pvalue=0.39857590952666144)\n"
4899 ] 5090 ]
4900 } 5091 }
4901 ], 5092 ],
4902 "source": [ 5093 "source": [
4903 "from scipy.stats import kendalltau\n", 5094 "from scipy.stats import kendalltau\n",
4904 "for i in range(len(ranked_countries)-1):\n", 5095 "for i in range(n_iters-1):\n",
4905 " for j in range(i+1, len(ranked_countries)):\n", 5096 " for j in range(i+1, n_iters):\n",
4906 " print kendalltau(ranked_countries.iloc[:, i], ranked_countries.iloc[:, j])" 5097 " print kendalltau(ranked_countries.iloc[:, i], ranked_countries.iloc[:, j])"
4907 ] 5098 ]
4908 }, 5099 },
4909 { 5100 {
4910 "cell_type": "code", 5101 "cell_type": "code",
4911 "execution_count": 34, 5102 "execution_count": 53,
4912 "metadata": {}, 5103 "metadata": {},
4913 "outputs": [ 5104 "outputs": [
4914 { 5105 {
4915 "data": { 5106 "data": {
4916 "text/plain": [ 5107 "text/plain": [
4917 "SpearmanrResult(correlation=1.0, pvalue=0.0)" 5108 "133"
4918 ] 5109 ]
4919 }, 5110 },
4920 "execution_count": 34, 5111 "execution_count": 53,
4921 "metadata": {}, 5112 "metadata": {},
4922 "output_type": "execute_result" 5113 "output_type": "execute_result"
4923 } 5114 }
4924 ], 5115 ],
4925 "source": [ 5116 "source": [
5117 "len(ranked_countries)"
5118 ]
5119 },
5120 {
5121 "cell_type": "code",
5122 "execution_count": 56,
5123 "metadata": {},
5124 "outputs": [],
5125 "source": [
4926 "from scipy.stats import spearmanr\n", 5126 "from scipy.stats import spearmanr\n",
4927 "spearmanr(ranked_countries)" 5127 "r, p = spearmanr(ranked_countries)"
5128 ]
5129 },
5130 {
5131 "cell_type": "code",
5132 "execution_count": 58,
5133 "metadata": {},
5134 "outputs": [
5135 {
5136 "data": {
5137 "text/plain": [
5138 "array([[ 1.00000000e+00, 1.74432009e-01, 8.97001663e-02,\n",
5139 " 1.99727609e-01, 6.82200753e-02, 5.39272197e-02,\n",
5140 " 2.21325022e-01, 1.33629528e-01, 1.08109487e-01,\n",
5141 " 1.31114761e-01],\n",
5142 " [ 1.74432009e-01, 1.00000000e+00, 4.20573142e-02,\n",
5143 " 2.07251507e-02, 2.28481652e-01, 1.01916936e-01,\n",
5144 " 1.01442548e-01, 1.12532008e-01, 1.89806266e-02,\n",
5145 " 1.48213138e-01],\n",
5146 " [ 8.97001663e-02, 4.20573142e-02, 1.00000000e+00,\n",
5147 " 1.53308985e-01, 7.91412044e-02, 1.41734934e-01,\n",
5148 " -1.14419359e-01, 1.23519450e-01, 1.50641189e-01,\n",
5149 " 3.17074913e-02],\n",
5150 " [ 1.99727609e-01, 2.07251507e-02, 1.53308985e-01,\n",
5151 " 1.00000000e+00, 3.04934657e-02, 3.27786903e-02,\n",
5152 " -7.58255884e-02, 6.98727824e-02, -4.16900460e-02,\n",
5153 " -2.15208986e-02],\n",
5154 " [ 6.82200753e-02, 2.28481652e-01, 7.91412044e-02,\n",
5155 " 3.04934657e-02, 1.00000000e+00, -8.00848798e-04,\n",
5156 " 8.02532110e-02, 1.65796105e-01, 1.91678314e-01,\n",
5157 " 1.62863060e-01],\n",
5158 " [ 5.39272197e-02, 1.01916936e-01, 1.41734934e-01,\n",
5159 " 3.27786903e-02, -8.00848798e-04, 1.00000000e+00,\n",
5160 " 1.17969619e-01, 1.31221881e-01, 2.06996460e-02,\n",
5161 " 3.92160863e-02],\n",
5162 " [ 2.21325022e-01, 1.01442548e-01, -1.14419359e-01,\n",
5163 " -7.58255884e-02, 8.02532110e-02, 1.17969619e-01,\n",
5164 " 1.00000000e+00, 8.75832730e-02, 1.10578345e-01,\n",
5165 " 4.28326583e-02],\n",
5166 " [ 1.33629528e-01, 1.12532008e-01, 1.23519450e-01,\n",
5167 " 6.98727824e-02, 1.65796105e-01, 1.31221881e-01,\n",
5168 " 8.75832730e-02, 1.00000000e+00, 1.31374909e-01,\n",
5169 " 2.78868814e-01],\n",
5170 " [ 1.08109487e-01, 1.89806266e-02, 1.50641189e-01,\n",
5171 " -4.16900460e-02, 1.91678314e-01, 2.06996460e-02,\n",
5172 " 1.10578345e-01, 1.31374909e-01, 1.00000000e+00,\n",
5173 " 7.53103927e-02],\n",
5174 " [ 1.31114761e-01, 1.48213138e-01, 3.17074913e-02,\n",
5175 " -2.15208986e-02, 1.62863060e-01, 3.92160863e-02,\n",
5176 " 4.28326583e-02, 2.78868814e-01, 7.53103927e-02,\n",
5177 " 1.00000000e+00]])"
5178 ]
5179 },
5180 "execution_count": 58,
5181 "metadata": {},
5182 "output_type": "execute_result"
5183 }
5184 ],
5185 "source": [
5186 "r"
4928 ] 5187 ]
4929 }, 5188 },
4930 { 5189 {
4931 "cell_type": "code", 5190 "cell_type": "code",
4932 "execution_count": null, 5191 "execution_count": null,