{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%run ../../../common_functions/import_all.py\n",
"\n",
"from common_functions.setup_notebook import set_css_style, setup_matplotlib, config_ipython\n",
"\n",
"from sklearn.cluster import KMeans\n",
"from sklearn.preprocessing import scale\n",
"\n",
"from common_functions.kmeans_helpers import (retrieve_cluster_points, \n",
" compute_wcss, \n",
" compute_gap_statistic, \n",
" evaluate_gap_statistic_best_k)\n",
"\n",
"dataset = '../../datasets/oldfaithful.txt'\n",
"\n",
"config_ipython()\n",
"setup_matplotlib()\n",
"set_css_style()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# k-means: trying it!"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Let's use the \"old faithful\" dataset\n",
"\n",
"We will use the Old Faithful classic dataset, a copy of which is available in this repo under folder `datasets/` for convenience. "
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" eruptions | \n",
" waiting | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 3.600 | \n",
" 79 | \n",
"
\n",
" \n",
" | 1 | \n",
" 1.800 | \n",
" 54 | \n",
"
\n",
" \n",
" | 2 | \n",
" 3.333 | \n",
" 74 | \n",
"
\n",
" \n",
" | 3 | \n",
" 2.283 | \n",
" 62 | \n",
"
\n",
" \n",
" | 4 | \n",
" 4.533 | \n",
" 85 | \n",
"
\n",
" \n",
"
\n",
"