import os
import hnswlib
import numpy as np


"""
Example of index building, search and serialization/deserialization
"""

dim = 16
num_elements = 10000

# Generating sample data
data = np.float32(np.random.random((num_elements, dim)))

# We split the data in two batches:
data1 = data[:num_elements // 2]
data2 = data[num_elements // 2:]

# Declaring index
p = hnswlib.Index(space='l2', dim=dim)  # possible options are l2, cosine or ip

# Initing index
# max_elements - the maximum number of elements (capacity). Will throw an exception if exceeded
# during insertion of an element.
# The capacity can be increased by saving/loading the index, see below.
#
# ef_construction - controls index search speed/build speed tradeoff
#
# M - is tightly connected with internal dimensionality of the data. Strongly affects the memory consumption (~M)
# Higher M leads to higher accuracy/run_time at fixed ef/efConstruction

p.init_index(max_elements=num_elements//2, ef_construction=100, M=16)

# Controlling the recall by setting ef:
# higher ef leads to better accuracy, but slower search
p.set_ef(10)

# Set number of threads used during batch search/construction
# By default using all available cores
p.set_num_threads(4)

print("Adding first batch of %d elements" % (len(data1)))
p.add_items(data1)

# Query the elements for themselves and measure recall:
labels, distances = p.knn_query(data1, k=1)
print("Recall for the first batch:", np.mean(labels.reshape(-1) == np.arange(len(data1))), "\n")

# Serializing and deleting the index:
index_path='first_half.bin'
print("Saving index to '%s'" % index_path)
p.save_index(index_path)
del p

# Reiniting, loading the index
p = hnswlib.Index(space='l2', dim=dim)  # the space can be changed - keeps the data, alters the distance function.

print("\nLoading index from 'first_half.bin'\n")

# Increase the total capacity (max_elements), so that it will handle the new data
p.load_index("first_half.bin", max_elements = num_elements)

print("Adding the second batch of %d elements" % (len(data2)))
p.add_items(data2)

# Query the elements for themselves and measure recall:
labels, distances = p.knn_query(data, k=1)
print("Recall for two batches:", np.mean(labels.reshape(-1) == np.arange(len(data))), "\n")

os.remove("first_half.bin")