-
Notifications
You must be signed in to change notification settings - Fork 0
/
kneighbour.py
63 lines (51 loc) · 1.69 KB
/
kneighbour.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
from math import sqrt
import numpy as np
import warnings
import matplotlib.pyplot as plt
from matplotlib import style
from collections import Counter
import pandas as pd
import random
style.use('ggplot')
# dataset = {'k':[[1,2],[2,3],[3,1]], 'r':[[6,5],[7,7],[8,6]]}
# new_features = [5,7]
def k_nearest_neighbours(data, predict, k=3):
if len(data) >= k:
warnings.warn('K is less than total voting set')
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
# result = k_nearest_neighbours(dataset, new_features, k=3)
# print(result)
#
# [[plt.scatter(ii[0],ii[1],s=110,color=i) for ii in dataset[i]] for i in dataset]
# plt.scatter(new_features[0],new_features[1], color=result)
# plt.show()
df = pd.read_csv('breast-cancer-wisconsin.data')
df.replace('?', -99999, inplace=True)
df.drop(['id'],1,inplace=True)
full_data = df.astype(float).values.tolist()
random.shuffle(full_data)
test_size = 0.2
train_set = {2:[], 4:[]}
test_set = {2:[], 4:[]}
train_data = full_data[:-int(test_size*len(full_data))]
test_data = full_data[-int(test_size*len(full_data)):]
for i in train_data:
train_set[i[-1]].append(i[:-1])
for i in test_data:
test_set[i[-1]].append(i[:-1])
correct = 0
total = 0
for group in test_set:
for data in test_set[group]:
vote = k_nearest_neighbours(train_set, data, k=5)
if group == vote:
correct +=1
total +=1
print('Accuracy: ', correct/total)