Downloads: 1
Diff of
/notebooks/stats.ipynb
[000000]
..
[23d48c]
Switch to unified view
| a | b/notebooks/stats.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 27, |
||
| 6 | "metadata": { |
||
| 7 | "scrolled": false |
||
| 8 | }, |
||
| 9 | "outputs": [ |
||
| 10 | { |
||
| 11 | "data": { |
||
| 12 | "text/plain": [ |
||
| 13 | " dataset cutoff algorithm rank_auc \n", |
||
| 14 | " geis_250.00 :30 1 visit :210 LR :210 Min. : 1.0 \n", |
||
| 15 | " geis_250.00_cutoff182:30 1 year :210 RF :210 1st Qu.: 8.0 \n", |
||
| 16 | " geis_250.00_cutoff365:30 6 months:210 XGB:210 Median :15.5 \n", |
||
| 17 | " geis_250.40 :30 Mean :15.5 \n", |
||
| 18 | " geis_250.40_cutoff182:30 3rd Qu.:23.0 \n", |
||
| 19 | " geis_250.40_cutoff365:30 Max. :30.0 \n", |
||
| 20 | " geis_327.23 :30 \n", |
||
| 21 | " geis_327.23_cutoff182:30 \n", |
||
| 22 | " geis_327.23_cutoff365:30 \n", |
||
| 23 | " geis_331.0 :30 \n", |
||
| 24 | " geis_331.0_cutoff182 :30 \n", |
||
| 25 | " geis_331.0_cutoff365 :30 \n", |
||
| 26 | " geis_530.81 :30 \n", |
||
| 27 | " geis_530.81_cutoff182:30 \n", |
||
| 28 | " geis_530.81_cutoff365:30 \n", |
||
| 29 | " geis_571.8 :30 \n", |
||
| 30 | " geis_571.8_cutoff182 :30 \n", |
||
| 31 | " geis_571.8_cutoff365 :30 \n", |
||
| 32 | " geis_585.9 :30 \n", |
||
| 33 | " geis_585.9_cutoff182 :30 \n", |
||
| 34 | " geis_585.9_cutoff365 :30 " |
||
| 35 | ] |
||
| 36 | }, |
||
| 37 | "metadata": {}, |
||
| 38 | "output_type": "display_data" |
||
| 39 | } |
||
| 40 | ], |
||
| 41 | "source": [ |
||
| 42 | "setwd('/media/bill/Drive/projects/geis-ehr/analysis')\n", |
||
| 43 | "\n", |
||
| 44 | "df <- read.csv(\"auc_rankings.csv\",header=TRUE,sep=',')\n", |
||
| 45 | "# df <- subset(df,!is.na(rank))\n", |
||
| 46 | "# df <- subset(df,dataset!='505_tecator')\n", |
||
| 47 | "# df <- subset(df,algorithm != 'LR')\n", |
||
| 48 | "summary(df,maxsum=21)\n" |
||
| 49 | ] |
||
| 50 | }, |
||
| 51 | { |
||
| 52 | "cell_type": "code", |
||
| 53 | "execution_count": 29, |
||
| 54 | "metadata": {}, |
||
| 55 | "outputs": [ |
||
| 56 | { |
||
| 57 | "data": { |
||
| 58 | "text/plain": [ |
||
| 59 | "\n", |
||
| 60 | "\tPairwise comparisons using Wilcoxon signed rank test \n", |
||
| 61 | "\n", |
||
| 62 | "data: dfs$rank_auc and dfs$algorithm \n", |
||
| 63 | "\n", |
||
| 64 | " LR RF \n", |
||
| 65 | "RF 1.0e-12 - \n", |
||
| 66 | "XGB 1.1e-12 7.8e-12\n", |
||
| 67 | "\n", |
||
| 68 | "P value adjustment method: bonferroni " |
||
| 69 | ] |
||
| 70 | }, |
||
| 71 | "metadata": {}, |
||
| 72 | "output_type": "display_data" |
||
| 73 | } |
||
| 74 | ], |
||
| 75 | "source": [ |
||
| 76 | "dfs <- subset(df,cutoff=='1 visit')\n", |
||
| 77 | "pairwise.wilcox.test(dfs$rank_auc, dfs$algorithm, p.adjust.method = 'bonferroni',\n", |
||
| 78 | " paired = T)" |
||
| 79 | ] |
||
| 80 | }, |
||
| 81 | { |
||
| 82 | "cell_type": "code", |
||
| 83 | "execution_count": 31, |
||
| 84 | "metadata": {}, |
||
| 85 | "outputs": [ |
||
| 86 | { |
||
| 87 | "data": { |
||
| 88 | "text/plain": [ |
||
| 89 | "\n", |
||
| 90 | "\tPairwise comparisons using Wilcoxon signed rank test \n", |
||
| 91 | "\n", |
||
| 92 | "data: dfs$rank_auc and dfs$algorithm \n", |
||
| 93 | "\n", |
||
| 94 | " LR RF \n", |
||
| 95 | "RF 1.0e-12 - \n", |
||
| 96 | "XGB 1.0e-12 2.3e-12\n", |
||
| 97 | "\n", |
||
| 98 | "P value adjustment method: bonferroni " |
||
| 99 | ] |
||
| 100 | }, |
||
| 101 | "metadata": {}, |
||
| 102 | "output_type": "display_data" |
||
| 103 | } |
||
| 104 | ], |
||
| 105 | "source": [ |
||
| 106 | "dfs <- subset(df,cutoff=='6 months')\n", |
||
| 107 | "pairwise.wilcox.test(dfs$rank_auc, dfs$algorithm, p.adjust.method = 'bonferroni',\n", |
||
| 108 | " paired = T)" |
||
| 109 | ] |
||
| 110 | }, |
||
| 111 | { |
||
| 112 | "cell_type": "code", |
||
| 113 | "execution_count": 28, |
||
| 114 | "metadata": {}, |
||
| 115 | "outputs": [ |
||
| 116 | { |
||
| 117 | "data": { |
||
| 118 | "text/plain": [ |
||
| 119 | "\n", |
||
| 120 | "\tPairwise comparisons using Wilcoxon signed rank test \n", |
||
| 121 | "\n", |
||
| 122 | "data: dfs$rank_auc and dfs$algorithm \n", |
||
| 123 | "\n", |
||
| 124 | " LR RF \n", |
||
| 125 | "RF 1.0e-12 - \n", |
||
| 126 | "XGB 1.0e-12 9.5e-12\n", |
||
| 127 | "\n", |
||
| 128 | "P value adjustment method: bonferroni " |
||
| 129 | ] |
||
| 130 | }, |
||
| 131 | "metadata": {}, |
||
| 132 | "output_type": "display_data" |
||
| 133 | } |
||
| 134 | ], |
||
| 135 | "source": [ |
||
| 136 | "dfs <- subset(df,cutoff=='1 year')\n", |
||
| 137 | "pairwise.wilcox.test(dfs$rank_auc, dfs$algorithm, p.adjust.method = 'bonferroni',\n", |
||
| 138 | " paired = T)" |
||
| 139 | ] |
||
| 140 | } |
||
| 141 | ], |
||
| 142 | "metadata": { |
||
| 143 | "kernelspec": { |
||
| 144 | "display_name": "R", |
||
| 145 | "language": "R", |
||
| 146 | "name": "ir" |
||
| 147 | }, |
||
| 148 | "language_info": { |
||
| 149 | "codemirror_mode": "r", |
||
| 150 | "file_extension": ".r", |
||
| 151 | "mimetype": "text/x-r-source", |
||
| 152 | "name": "R", |
||
| 153 | "pygments_lexer": "r", |
||
| 154 | "version": "3.5.1" |
||
| 155 | } |
||
| 156 | }, |
||
| 157 | "nbformat": 4, |
||
| 158 | "nbformat_minor": 2 |
||
| 159 | } |