import numpy as np

from pyclam.datasets import bullseye
from pyclam.manifold import Manifold
from pyclam import criterion

# Get the data.
data, _ = bullseye()
# data is a numpy.ndarray in this case but it could just as easily be a numpy.memmap if your data cannot fit in RAM.
# We used memmaps for the research, though it does impose file-io costs.

manifold = Manifold(data=data, metric='euclidean')
# Any metric allowed by scipy's cdist function is allowed in Manifold.
# You can also define your own distance function. It will work so long as scipy allows it.

manifold.build(criterion.MaxDepth(20), criterion.MinRadius(0.25))
# Manifold.build can optionally take any number of early stopping criteria.
# pyclam.criterion defines some criteria that we have used in research.
# You are free to define your own.
# Take a look at pyclam/criterion.py for hints of how to define custom criteria.

# A sample rho-nearest neighbors search query
query, radius = data[0], 0.05
results = manifold.find_points(point=query, radius=radius)
# results is a dictionary of indexes of hits in data and the distance to those hits.

# A sample k-nearest neighbors search query
results = manifold.find_knn(point=query, k=25)