knearest.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

# Copyright (C) 2018  David Arroyo Menéndez

# Author: David Arroyo Menéndez <davidam@gnu.org>
# Maintainer: David Arroyo Menéndez <davidam@gnu.org>

# This file is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3, or (at your option)
# any later version.

# This file is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with GNU Emacs; see the file COPYING.  If not, write to
# the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
# Boston, MA 02110-1301 USA,
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
import warnings
from math import sqrt
from collections import Counter
style.use('fivethirtyeight')

def k_nearest_neighbors(data, predict, k=3):
    if len(data) >= k:
        warnings.warn('K is set to a value less than total voting groups!')
    distances = []
    for group in data:
        for features in data[group]:
            euclidean_distance = np.linalg.norm(np.array(features)-np.array(predict))
            distances.append([euclidean_distance,group])

    votes = [i[1] for i in sorted(distances)[:k]]
    vote_result = Counter(votes).most_common(1)[0][0]
    return vote_result

dataset = {'k':[[1,2],[2,3],[3,1]], 'r':[[6,5],[7,7],[8,6]]}
new_features = [5,7]
[[plt.scatter(ii[0],ii[1],s=100,color=i) for ii in dataset[i]] for i in dataset]
# same as:
##for i in dataset:
##    for ii in dataset[i]:
##        plt.scatter(ii[0],ii[1],s=100,color=i)

plt.scatter(new_features[0], new_features[1], s=100)

result = k_nearest_neighbors(dataset, new_features)
plt.scatter(new_features[0], new_features[1], s=100, color = result)
plt.show()