233 lines (232 with data), 23.3 kB
{
"cells": [
{
"cell_type": "markdown",
"id": "74403734-e2d4-4df2-9c02-3f601563726d",
"metadata": {},
"source": [
"## shap kernel-explainer: backgroud samples:10\n",
"\n",
"#### O(m*l*(2n+2048)), where l is the number of background samples, n is number of features and m is number of samples"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "50b75b53-4ae4-441e-a602-cef152571243",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import seaborn as sns\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b3464074-e898-4606-ba9c-7d85461008a9",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 36,
"id": "0c009855-ec86-4cd1-a6f6-e4037d2a0635",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('time.csv')"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "ab2a6b41-0d41-4733-a797-d70d75a82c26",
"metadata": {},
"outputs": [],
"source": [
"df = df.unstack().reset_index()\n",
"\n",
"df.columns = ['explainer', 'repeats', 'time(s)']"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "70b73338-3122-49aa-9827-b2604680e08d",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>explainer</th>\n",
" <th>repeats</th>\n",
" <th>time(s)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Shap-explainer</td>\n",
" <td>0</td>\n",
" <td>3812.300000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Shap-explainer</td>\n",
" <td>1</td>\n",
" <td>3829.370000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Shap-explainer</td>\n",
" <td>2</td>\n",
" <td>3835.060000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Simp-explainer</td>\n",
" <td>0</td>\n",
" <td>2.501675</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Simp-explainer</td>\n",
" <td>1</td>\n",
" <td>2.388111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Simp-explainer</td>\n",
" <td>2</td>\n",
" <td>2.249441</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" explainer repeats time(s)\n",
"0 Shap-explainer 0 3812.300000\n",
"1 Shap-explainer 1 3829.370000\n",
"2 Shap-explainer 2 3835.060000\n",
"3 Simp-explainer 0 2.501675\n",
"4 Simp-explainer 1 2.388111\n",
"5 Simp-explainer 2 2.249441"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 69,
"id": "92abe92f-3f42-412a-9def-c027429eab35",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x576 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import seaborn as sns\n",
"sns.set(font_scale=1.4, style='white')\n",
"\n",
"fig, ax = plt.subplots(figsize=(6,8))\n",
"\n",
"g = sns.barplot(x = 'explainer', y = 'time(s)', data = df, ax=ax)\n",
"\n",
"g.set_yscale(\"log\")\n",
"_ = g.set(xlabel=\" \", ylabel=\"time(s)\")\n",
"\n",
"ax.tick_params(axis='x', rotation=0, labelsize=20)\n",
"ax.tick_params(axis='y', rotation=0, labelsize=20)\n",
"ax.set_ylabel(\"Time(s)\", fontsize=22)\n",
"sns.despine(ax = ax, top=True, right=True, left=False, bottom=False)\n",
"\n",
"ax.text(-0.2, 4200, '~1 hr', fontsize=22)\n",
"ax.text(0.65, 4, '~2.3 sec', fontsize=22)\n",
"\n",
"fig.savefig('./time.pdf', bbox_inches='tight', dpi=400) "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2f0540f8-7bd2-484a-b6ea-960331ae848e",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "63eb182b-40b1-4581-a80e-320a81ba1985",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "6db1d809-f08e-4e40-877c-c271fd38a72d",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.6.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}