Skip to content

Instantly share code, notes, and snippets.

@kmike

kmike/sklearn-text-example-2.ipynb

Last active May 23, 2017 22:34
Show Gist options
  • Save kmike/1ca97deb392bc26e62e89f4ac5dd97f3 to your computer and use it in GitHub Desktop.
Save kmike/1ca97deb392bc26e62e89f4ac5dd97f3 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
sklearn-text-example-2.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
" <style>\n",
" table.eli5-weights tr:hover {\n",
" filter: brightness(85%);\n",
" }\n",
"</style>\n",
"\n",
"\n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
" \n",
"\n",
" \n",
" <table class=\"eli5-weights-wrapper\" style=\"border-collapse: collapse; border: none; margin-bottom: 1.5em;\">\n",
" <tr>\n",
" \n",
" <td style=\"padding: 0.5em; border: 1px solid black; text-align: center;\">\n",
" <b>\n",
" \n",
" y=alt.atheism\n",
" \n",
"</b>\n",
"\n",
"top features\n",
" </td>\n",
" \n",
" <td style=\"padding: 0.5em; border: 1px solid black; text-align: center;\">\n",
" <b>\n",
" \n",
" y=comp.graphics\n",
" \n",
"</b>\n",
"\n",
"top features\n",
" </td>\n",
" \n",
" <td style=\"padding: 0.5em; border: 1px solid black; text-align: center;\">\n",
" <b>\n",
" \n",
" y=sci.med\n",
" \n",
"</b>\n",
"\n",
"top features\n",
" </td>\n",
" \n",
" <td style=\"padding: 0.5em; border: 1px solid black; text-align: center;\">\n",
" <b>\n",
" \n",
" y=soc.religion.christian\n",
" \n",
"</b>\n",
"\n",
"top features\n",
" </td>\n",
" \n",
" </tr>\n",
" <tr>\n",
" \n",
" \n",
" <td style=\"padding: 0px; border: 1px solid black; vertical-align: top;\">\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" <table class=\"eli5-weights\"\n",
" style=\"border-collapse: collapse; border: none; margin-top: 0em; table-layout: auto; width: 100%;\">\n",
" <thead>\n",
" <tr style=\"border: none;\">\n",
" \n",
" <th style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\" title=\"Feature weights. Note that weights do not account for feature value scales, so if feature values have different scales, features with highest weights might not be the most important.\">\n",
" Weight<sup>?</sup>\n",
" </th>\n",
" \n",
" <th style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">Feature</th>\n",
" \n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 85.36%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +2.020\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" atheism\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 85.90%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.914\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" keith\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 88.64%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.407\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" mathew\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 88.67%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.400\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" okcforum\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.26%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.297\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" islamic\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.53%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.252\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" atheists\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.68%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.226\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" umd\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.80%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.205\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" islam\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.87%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.194\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" mangoe\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.08%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.159\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" morality\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.15%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.147\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" sandvik\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.19%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.140\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" writes\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.29%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.123\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" caltech\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.34%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.115\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" benedikt\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.58%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.076\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" osrhe\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.58%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 8182 more positive &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 80.00%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 15831 more negative &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
" \n",
"\n",
" </tbody>\n",
" </table>\n",
"\n",
" \n",
" \n",
" </td>\n",
" \n",
" <td style=\"padding: 0px; border: 1px solid black; vertical-align: top;\">\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" <table class=\"eli5-weights\"\n",
" style=\"border-collapse: collapse; border: none; margin-top: 0em; table-layout: auto; width: 100%;\">\n",
" <thead>\n",
" <tr style=\"border: none;\">\n",
" \n",
" <th style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\" title=\"Feature weights. Note that weights do not account for feature value scales, so if feature values have different scales, features with highest weights might not be the most important.\">\n",
" Weight<sup>?</sup>\n",
" </th>\n",
" \n",
" <th style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">Feature</th>\n",
" \n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 80.00%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +3.155\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" graphics\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.53%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.607\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" image\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.87%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.544\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" 3d\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.95%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.530\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" software\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 88.56%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.420\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" file\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 88.72%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.392\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" images\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 88.84%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.370\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" files\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.14%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.319\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" windows\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.27%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.297\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" card\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.36%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.281\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" points\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.42%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.270\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" video\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.50%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.257\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" tiff\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.80%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.206\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" code\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.82%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.203\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" looking\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.84%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.198\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" 42\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.84%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 7481 more positive &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 80.00%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 14901 more negative &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
" \n",
"\n",
" </tbody>\n",
" </table>\n",
"\n",
" \n",
" \n",
" </td>\n",
" \n",
" <td style=\"padding: 0px; border: 1px solid black; vertical-align: top;\">\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" <table class=\"eli5-weights\"\n",
" style=\"border-collapse: collapse; border: none; margin-top: 0em; table-layout: auto; width: 100%;\">\n",
" <thead>\n",
" <tr style=\"border: none;\">\n",
" \n",
" <th style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\" title=\"Feature weights. Note that weights do not account for feature value scales, so if feature values have different scales, features with highest weights might not be the most important.\">\n",
" Weight<sup>?</sup>\n",
" </th>\n",
" \n",
" <th style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">Feature</th>\n",
" \n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 85.32%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +2.028\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" doctor\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 86.47%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.806\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" msg\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 86.52%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.795\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" pitt\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.69%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.577\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" disease\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 88.09%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.504\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" health\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 88.99%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.345\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" cancer\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.04%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.335\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" treatment\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.79%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.207\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" medical\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.86%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.196\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" pain\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.15%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.148\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" photography\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.17%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.143\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" food\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.28%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.125\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" medicine\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.37%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.111\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" com\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 90.37%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 11462 more positive &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 89.89%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 13796 more negative &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 89.89%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" -1.191\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" graphics\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 88.58%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" -1.417\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" god\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
"\n",
" </tbody>\n",
" </table>\n",
"\n",
" \n",
" \n",
" </td>\n",
" \n",
" <td style=\"padding: 0px; border: 1px solid black; vertical-align: top;\">\n",
" \n",
" \n",
" \n",
" \n",
" \n",
" <table class=\"eli5-weights\"\n",
" style=\"border-collapse: collapse; border: none; margin-top: 0em; table-layout: auto; width: 100%;\">\n",
" <thead>\n",
" <tr style=\"border: none;\">\n",
" \n",
" <th style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\" title=\"Feature weights. Note that weights do not account for feature value scales, so if feature values have different scales, features with highest weights might not be the most important.\">\n",
" Weight<sup>?</sup>\n",
" </th>\n",
" \n",
" <th style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">Feature</th>\n",
" \n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 83.84%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +2.327\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" church\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 84.25%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +2.244\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" christians\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 85.29%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +2.034\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" rutgers\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 85.30%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +2.032\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" christ\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.02%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.702\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" christian\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.17%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.674\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" jesus\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.54%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.605\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" god\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 87.72%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.571\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" athos\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.02%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.340\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" christianity\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.10%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.326\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" clh\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.61%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.238\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" 1993\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.71%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.221\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" hell\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.85%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" +1.197\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" sin\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" \n",
" <tr style=\"background-color: hsl(120, 100.00%, 89.85%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 8631 more positive &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 89.23%); border: none;\">\n",
" <td colspan=\"2\" style=\"padding: 0 0.5em 0 0.5em; text-align: center; border: none; white-space: nowrap;\">\n",
" <i>&hellip; 17663 more negative &hellip;</i>\n",
" </td>\n",
" </tr>\n",
" \n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 89.23%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" -1.304\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" nntp\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
" <tr style=\"background-color: hsl(0, 100.00%, 89.19%); border: none;\">\n",
" <td style=\"padding: 0 1em 0 0.5em; text-align: right; border: none;\">\n",
" -1.309\n",
" </td>\n",
" <td style=\"padding: 0 0.5em 0 0.5em; text-align: left; border: none;\">\n",
" host\n",
" </td>\n",
" \n",
"</tr>\n",
" \n",
"\n",
" </tbody>\n",
" </table>\n",
"\n",
" \n",
" \n",
" </td>\n",
" \n",
" \n",
" </tr>\n",
" </table>\n",
" \n",
"\n",
" \n",
" \n",
"\n",
"\n",
" \n",
" \n",
"\n",
"\n",
" \n",
" \n",
"\n",
"\n",
" \n",
" \n",
"\n",
"\n",
" \n",
"\n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
" \n",
"\n",
"\n",
"\n"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import eli5\n",
"eli5.show_weights(text_clf, top=15, \n",
" target_names=twenty_train.target_names)"
]
}
],
"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": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment