Machine Learning – Tutorial 17

Writing our own K Nearest Neighbours in Code

https://pythonprogramming.net/coding-k-nearest-neighbors-machine-learning-tutorial/

# imports
import numpy as np
from math import sqrt
import matplotlib.pyplot as plt
import warnings
from collections import Counter

# To set charts to save as images we need to change the default behaviour
from matplotlib import style # inport style to change default behaviour of plot
style.use('ggplot') # use ggplot

dataset = {'k':[[1,2],[2,3],[3,1]], 'r':[[6,5],[7,7],[8,6]]} # defines as a dictionary 2 classes (k&r) with 3 features (lists of lists)
new_features = [5,7]

## Expanded one line for loop
#for i in dataset:
#    for ii in dataset[i]:
#        plt.scatter(ii[0],ii[1],s=100, color=i)


# define function
def K_nearest_neighbours(data, predict, k=3):
    if len(data) >= k:
        warnings.warn('K is set to 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]]
    print(Counter(votes).most_common(1))
    vote_result = Counter(votes).most_common(1)[0][0]

    return vote_result

# generate results
results = K_nearest_neighbours(dataset, new_features, k=3)
print(results)
[[plt.scatter(ii[0],ii[1],s=100,color=i) for ii in dataset[i]] for i in dataset] # one line for loop
plt.scatter(new_features[0], new_features[1], color=results,s=100)
plt.show()

Leave a Reply