DBSCAN¶

DBSCAN is a popular algorithm for finding clusters of spatial data. It identifies core points that have enough (defined by the user) neighbors within some distance (also user defined). Points that are not core points but are within the distance of a core point are considered border points of the cluster. Points that are not core points and are not within the distance of a core point are considered outliers and not part of any cluster.

The algorithm requires two parameters:

• epsilon - The farthest apart two points can be while still being considered connected or related. epsilon must be a positive double float.
• minPoints - The minimum number of neighbor points (as determined by epsilon). A point needs minPoints neighbors to be considered a core point. minPoints must be a positive integer.

Example overview¶

In this example, we will generate some random data and use DBSCAN to cluster that data. Then, we'll visualize the clusters using a scatter plot.

This demo is derived from the scikit-learn DBSCAN demo.

In [ ]:

%pip install scikit-learn

%pip install scikit-learn

Define Sedona Context¶

In [ ]:

from sedona.spark import SedonaContext

config = SedonaContext.builder().getOrCreate()
sedona = SedonaContext.create(config)

from sedona.spark import SedonaContext config = SedonaContext.builder().getOrCreate() sedona = SedonaContext.create(config)

Data Generation¶

In the following code section, we'll generate some data using sklearn's make_blobs function. We've set the data to consist of 750 points with 3 clusters. After clustering the data, we'll visualize it in pyplot.

In [ ]:

from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt

center_clusters = [[1, 1], [-1, -1], [1, -1]]
feature_matrix, labels_true = make_blobs(
   n_samples=750, centers=center_clusters, cluster_std=0.4, random_state=0
)

feature_matrix = StandardScaler().fit_transform(feature_matrix)

plt.scatter(feature_matrix[:, 0], feature_matrix[:, 1])
plt.show()

from sklearn.datasets import make_blobs from sklearn.preprocessing import StandardScaler import matplotlib.pyplot as plt center_clusters = [[1, 1], [-1, -1], [1, -1]] feature_matrix, labels_true = make_blobs( n_samples=750, centers=center_clusters, cluster_std=0.4, random_state=0 ) feature_matrix = StandardScaler().fit_transform(feature_matrix) plt.scatter(feature_matrix[:, 0], feature_matrix[:, 1]) plt.show()

Clustering¶

In the following section, we'll use the DBSCAN implementation in Wherobots to cluster the data in a dataframe, setting epsilon to 0.3 and minPoints to 10.

Wherobots' DBSCAN returns outliers by default.

In [ ]:

import pyspark.sql.functions as f
from sedona.sql.st_constructors import ST_MakePoint
from sedona.stats.clustering.dbscan import dbscan

df = sedona.createDataFrame(feature_matrix).select(ST_MakePoint("_1", "_2").alias("geometry"))
clusters_df = dbscan(df, 0.3, 10, include_outliers=True)

import pyspark.sql.functions as f from sedona.sql.st_constructors import ST_MakePoint from sedona.stats.clustering.dbscan import dbscan df = sedona.createDataFrame(feature_matrix).select(ST_MakePoint("_1", "_2").alias("geometry")) clusters_df = dbscan(df, 0.3, 10, include_outliers=True)

In [ ]:

clusters_df.show()

clusters_df.show()

Visualization¶

Finally, we'll visualize the clusters using geopandas. Some manipulations are made to the data to improve the clarity of the visualization.

In [ ]:

import geopandas as gpd
import pyspark.sql.types as t

pdf = (clusters_df
       .withColumn("isCore", (f.col("isCore").cast(t.IntegerType()) + 1) * 40)
       .withColumn("cluster", f.hash("cluster").cast(t.StringType()))
       .toPandas()
      )
gdf = gpd.GeoDataFrame(pdf, geometry="geometry")

gdf.plot(
    figsize=(10, 8),
    column="cluster",
    markersize=gdf['isCore'],
    edgecolor='lightgray',
)

import geopandas as gpd import pyspark.sql.types as t pdf = (clusters_df .withColumn("isCore", (f.col("isCore").cast(t.IntegerType()) + 1) * 40) .withColumn("cluster", f.hash("cluster").cast(t.StringType())) .toPandas() ) gdf = gpd.GeoDataFrame(pdf, geometry="geometry") gdf.plot( figsize=(10, 8), column="cluster", markersize=gdf['isCore'], edgecolor='lightgray', )