#!/usr/bin/env python

import numpy as np

from sklearn.metrics.pairwise import cosine_similarity
from sklearn.cluster import DBSCAN

total_samples = 1000
dimensionality = 3
points = np.random.rand(total_samples, dimensionality)

cosine_distance = cosine_similarity(points)

# option 1) vectors are close to each other if they are parallel
bespoke_distance = np.abs(np.abs(cosine_distance) -1)

# option 2) vectors are close to each other if they point in the same direction
bespoke_distance = np.abs(cosine_distance - 1)

results = DBSCAN(metric='precomputed', eps=0.25).fit(bespoke_distance)