Neil Neil - 4 months ago 39
Python Question

DBSCAN for clustering of geographic location data

I have a dataframe with latitude and longitude pairs.

Here is my dataframe look like.

order_lat order_long
0 19.111841 72.910729
1 19.111342 72.908387
2 19.111342 72.908387
3 19.137815 72.914085
4 19.119677 72.905081
5 19.119677 72.905081
6 19.119677 72.905081
7 19.120217 72.907121
8 19.120217 72.907121
9 19.119677 72.905081
10 19.119677 72.905081
11 19.119677 72.905081
12 19.111860 72.911346
13 19.111860 72.911346
14 19.119677 72.905081
15 19.119677 72.905081
16 19.119677 72.905081
17 19.137815 72.914085
18 19.115380 72.909144
19 19.115380 72.909144
20 19.116168 72.909573
21 19.119677 72.905081
22 19.137815 72.914085
23 19.137815 72.914085
24 19.112955 72.910102
25 19.112955 72.910102
26 19.112955 72.910102
27 19.119677 72.905081
28 19.119677 72.905081
29 19.115380 72.909144
30 19.119677 72.905081
31 19.119677 72.905081
32 19.119677 72.905081
33 19.119677 72.905081
34 19.119677 72.905081
35 19.111860 72.911346
36 19.111841 72.910729
37 19.131674 72.918510
38 19.119677 72.905081
39 19.111860 72.911346
40 19.111860 72.911346
41 19.111841 72.910729
42 19.111841 72.910729
43 19.111841 72.910729
44 19.115380 72.909144
45 19.116625 72.909185
46 19.115671 72.908985
47 19.119677 72.905081
48 19.119677 72.905081
49 19.119677 72.905081
50 19.116183 72.909646
51 19.113827 72.893833
52 19.119677 72.905081
53 19.114100 72.894985
54 19.107491 72.901760
55 19.119677 72.905081


I want to cluster this points which are nearest to each other(200 meters distance) following is my distance matrix.

from scipy.spatial.distance import pdist, squareform
distance_matrix = squareform(pdist(X, (lambda u,v: haversine(u,v))))

array([[ 0. , 0.2522482 , 0.2522482 , ..., 1.67313071,
1.05925366, 1.05420922],
[ 0.2522482 , 0. , 0. , ..., 1.44111548,
0.81742536, 0.98978355],
[ 0.2522482 , 0. , 0. , ..., 1.44111548,
0.81742536, 0.98978355],
...,
[ 1.67313071, 1.44111548, 1.44111548, ..., 0. ,
1.02310118, 1.22871515],
[ 1.05925366, 0.81742536, 0.81742536, ..., 1.02310118,
0. , 1.39923529],
[ 1.05420922, 0.98978355, 0.98978355, ..., 1.22871515,
1.39923529, 0. ]])


Then I am applying DBSCAN clustering algorithm on distance matrix.

from sklearn.cluster import DBSCAN

db = DBSCAN(eps=2,min_samples=5)
y_db = db.fit_predict(distance_matrix)


I don't know how to choose eps & min_samples value. It clusters the points which are way too far, in one cluster.(approx 2 km in distance) Is it because it calculates euclidean distance while clustering? please help.

Answer

DBSCAN is meant to be used on the raw data, with a spatial index for acceleration. The only tool I know with acceleration for geo distances is ELKI (Java) - scikit-learn unfortunately only supports this for a few distances like Euclidean distance (see sklearn.neighbors.NearestNeighbors). But apparently, you can affort to precompute pairwise distances, so this is not (yet) an issue.

However, you did not read the documentation carefully enough, and your assumption that DBSCAN uses a distance matrix is wrong:

from sklearn.cluster import DBSCAN
db = DBSCAN(eps=2,min_samples=5)
db.fit_predict(distance_matrix)

uses Euclidean distance on the distance matrix rows, which obviously does not make any sense.

See the documentation of DBSCAN (emphasis added):

class sklearn.cluster.DBSCAN(eps=0.5, min_samples=5, metric='euclidean', algorithm='auto', leaf_size=30, p=None, random_state=None)

metric : string, or callable

The metric to use when calculating distance between instances in a feature array. If metric is a string or callable, it must be one of the options allowed by metrics.pairwise.calculate_distance for its metric parameter. If metric is “precomputed”, X is assumed to be a distance matrix and must be square. X may be a sparse matrix, in which case only “nonzero” elements may be considered neighbors for DBSCAN.

similar for fit_predict:

X : array or sparse (CSR) matrix of shape (n_samples, n_features), or array of shape (n_samples, n_samples)

A feature array, or array of distances between samples if metric='precomputed'.

In other words, you need to do

db = DBSCAN(eps=2, min_samples=5, metric="precomputed")