___

Copyright by Pierian Data Inc. For more information, visit us at www.pieriandata.com

Introduction to DBSCAN¶

Let's briefly explore visually the differences between DBSCAN and other clustering techniques, such as K-Means Clustering.

DBSCAN and Clustering Examples¶

In [1]:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

In [2]:

blobs = pd.read_csv('../DATA/cluster_blobs.csv')

In [3]:

blobs.head()

Out[3]:

In [4]:

sns.scatterplot(data=blobs,x='X1',y='X2')

Out[4]:

<AxesSubplot:xlabel='X1', ylabel='X2'>

In [5]:

moons = pd.read_csv('../DATA/cluster_moons.csv')

In [6]:

moons.head()

Out[6]:

In [23]:

sns.scatterplot(data=moons,x='X1',y='X2')

Out[23]:

<AxesSubplot:xlabel='X1', ylabel='X2'>

In [8]:

circles = pd.read_csv('../DATA/cluster_circles.csv')

In [9]:

circles.head()

Out[9]:

In [10]:

sns.scatterplot(data=circles,x='X1',y='X2')

Out[10]:

<AxesSubplot:xlabel='X1', ylabel='X2'>

In [11]:

def display_categories(model,data):
    labels = model.fit_predict(data)
    sns.scatterplot(data=data,x='X1',y='X2',hue=labels,palette='Set1')

In [12]:

from sklearn.cluster import KMeans
model = KMeans(n_clusters = 2)

In [27]:

display_categories(model,moons)

In [14]:

model = KMeans(n_clusters = 3)
display_categories(model,blobs)

In [25]:

model = KMeans(n_clusters = 2)
display_categories(model,circles)

In [16]:

from sklearn.cluster import DBSCAN

In [17]:

model = DBSCAN(eps=0.6)

In [18]:

display_categories(model,blobs)

In [28]:

model = DBSCAN(eps=0.15)
plt.figure(figsize=(10,6),dpi=150)
display_categories(model,moons)

In [20]:

display_categories(model,circles)

Let's further explore DBSCAN Hyperparameters!