Comparison to regular sparse group LASSO

Compare directly to SGL.ipynb

Compare to sglasso.ipynb

Comparison to regular sparse group LASSO.ipynb

Cox stacked block - Ruilin penalty.ipynb

Cox stacked block.ipynb

Cox stacked.ipynb

Generating an instance.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Loading required package: rms\n",
      "Loading required package: Hmisc\n",
      "Loading required package: lattice\n",
      "Loading required package: survival\n",
      "Loading required package: Formula\n",
      "Loading required package: ggplot2\n",
      "\n",
      "Attaching package: ‘Hmisc’\n",
      "\n",
      "The following objects are masked from ‘package:base’:\n",
      "\n",
      "    format.pval, units\n",
      "\n",
      "Loading required package: SparseM\n",
      "\n",
      "Attaching package: ‘SparseM’\n",
      "\n",
      "The following object is masked from ‘package:base’:\n",
      "\n",
      "    backsolve\n",
      "\n",
      "Loading required package: mgcv\n",
      "Loading required package: nlme\n",
      "This is mgcv 1.8-28. For overview type 'help(\"mgcv-package\")'.\n",
      "Warning message in FUN(X[[i]], ...):\n",
      "“946 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“992 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“989 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1001 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1039 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“987 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1053 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1050 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“905 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“989 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1023 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1064 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1123 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1072 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1046 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1152 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1092 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1083 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1006 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”Warning message in FUN(X[[i]], ...):\n",
      "“1149 observations have drawn durations\n",
      "                                    at the minimum or maximum possible value. Generating coefficients\n",
      "                                    and other quantities of interest are unlikely to be returned\n",
      "                                    by models due to truncation. Consider making user-supplied coefficients\n",
      "                                    smaller, making T bigger, or decreasing the variance of the X variables.”"
     ]
    }
   ],
   "source": [
    "#install.packages('coxed', repos='http://cloud.r-project.org')\n",
    "library(coxed)\n",
    "set.seed(0)\n",
    "K = 20\n",
    "p = 5000\n",
    "X_list = list()\n",
    "censor_list = list()\n",
    "y_list = list()\n",
    "true_beta = matrix(rnorm(K*p),K,p)\n",
    "\n",
    "for (i in 1:K){\n",
    "  N = (1000+10*i)\n",
    "  X = matrix(as.numeric(rbinom(N*p, 1, 0.5)), N, p)\n",
    "  simdata = sim.survdata(T=120, num.data.frames=1, X = X, beta=true_beta[i,])\n",
    "  df = simdata$data\n",
    "  y =  df$y\n",
    "  censor_list[[i]] = as.numeric(df$failed)\n",
    "  X_list[[i]] = X\n",
    "  y_list[[i]] = df$y\n",
    "}\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "save(X_list, y_list, censor_list, file='instance.RData')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loss\n",
    "\n",
    "So, our loss is \n",
    "$$\n",
    "\\sum_{k=1}^K \\frac{1}{{\\tt nrow}(X_k)} \\text{CoxLoss}(X_k\\beta[,k], Y_k ,\\delta_k)\n",
    "$$\n",
    "with penalty\n",
    "$$\n",
    "\\lambda (\\alpha  \\|\\beta\\|_1 + (1 - \\alpha) \\sum_{j=1}^p  \\sqrt{k} \\|\\beta[j,]\\|_2 \n",
    "$$\n",
    "?\n",
    "\n",
    "And your code is doing  10 equally spaced on logscale from 1 to 0.1?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "jupytext": {
   "cell_metadata_filter": "all,-slideshow"
  },
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}