knn_self_real_data.py

import numpy as np
from math import sqrt
import warnings
from collections import Counter
import pandas as pd
import random

def k_nearest_neighbor(data, predict,k=3):
    if len(data)>=k:
        warnings.warn('chutiya hai kya?')
    distances = []
    for group in data:
        for feature in data[group]:
            euclidean_dist= np.linalg.norm(np.array(feature)-np.array(predict))
            distances.append([euclidean_dist,group])

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

df = pd.read_csv('breast_cancer.data.txt')
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 train_data:
    test_set[i[-1]].append(i[:-1])

correct = 0
total = 0

for group in test_set:
    for data in test_set[group]:
        vote,confidence = k_nearest_neighbor(train_set,data,k=5)
        if group == vote:
            correct += 1
        else:
            print(confidence)
        total+=1

print('accuracy is:', (correct/total)*100)