{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"___\n",
"\n",
"
\n",
"___\n",
"Copyright by Pierian Data Inc.\n",
"For more information, visit us at www.pieriandata.com"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Introduction to DBSCAN\n",
"\n",
"\n",
"Let's briefly explore visually the differences between DBSCAN and other clustering techniques, such as K-Means Clustering."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## DBSCAN and Clustering Examples"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"blobs = pd.read_csv('../DATA/cluster_blobs.csv')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" X1 | \n",
" X2 | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 4.645333 | \n",
" 6.822294 | \n",
"
\n",
" \n",
" | 1 | \n",
" 4.784032 | \n",
" 6.422883 | \n",
"
\n",
" \n",
" | 2 | \n",
" -5.851786 | \n",
" 5.774331 | \n",
"
\n",
" \n",
" | 3 | \n",
" -7.459592 | \n",
" 6.456415 | \n",
"
\n",
" \n",
" | 4 | \n",
" 4.918911 | \n",
" 6.961479 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"sns.scatterplot(data=blobs,x='X1',y='X2')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"moons = pd.read_csv('../DATA/cluster_moons.csv')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" X1 | \n",
" X2 | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 0.674362 | \n",
" -0.444625 | \n",
"
\n",
" \n",
" | 1 | \n",
" 1.547129 | \n",
" -0.239796 | \n",
"
\n",
" \n",
" | 2 | \n",
" 1.601930 | \n",
" -0.230792 | \n",
"
\n",
" \n",
" | 3 | \n",
" 0.014563 | \n",
" 0.449752 | \n",
"
\n",
" \n",
" | 4 | \n",
" 1.503476 | \n",
" -0.389164 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"sns.scatterplot(data=moons,x='X1',y='X2')"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"circles = pd.read_csv('../DATA/cluster_circles.csv')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" X1 | \n",
" X2 | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" -0.348677 | \n",
" 0.010157 | \n",
"
\n",
" \n",
" | 1 | \n",
" -0.176587 | \n",
" -0.954283 | \n",
"
\n",
" \n",
" | 2 | \n",
" 0.301703 | \n",
" -0.113045 | \n",
"
\n",
" \n",
" | 3 | \n",
" -0.782889 | \n",
" -0.719468 | \n",
"
\n",
" \n",
" | 4 | \n",
" -0.733280 | \n",
" -0.757354 | \n",
"
\n",
" \n",
"
\n",
"