手寫knn

算法：

1. 算距離：給定未知對象，計算它與訓練集中的每個對象的距離； 
2. 找近鄰：圈定距離最近的k個訓練對象，作爲未知對象的近鄰； 
3. 做分類：在這k個近鄰中出線次數最多的類別就是測試對象的預測類別。

代碼：

from scipy.io import arff
import numpy as np
import pandas as pd

radius = 4  # search radius


def distance(point1, point2):
    return np.sqrt(np.sum([(point1[i] - point2[i]) ** 2 for i in range(4)]))


iris = arff.loadarff('iris.arff')
df = pd.DataFrame(iris[0])
length = df.shape[0]
classes = list(set(df['class']))
classes_length = len(classes)
classes_dict = dict()
for i in range(classes_length):
    classes_dict[classes[i]] = i
for i in range(length):
    df.iloc[i, 4] = classes_dict[df.iloc[i, 4]]
df = df.sample(frac=1)  # shuffle data randomly
train_data = df.iloc[0:100]
test_data = df.iloc[100:]
train_length = train_data.shape[0]
test_length = test_data.shape[0]
accuracy = 0
for i in range(test_length):
    classes_count = np.zeros([classes_length])
    for j in range(train_length):
        if distance(test_data.iloc[i], train_data.iloc[j]) < radius:
            classes_count[int(train_data.iloc[j, 4])] += 1
    predict_class = np.argmax(classes_count)
    if predict_class == int(test_data.iloc[i, 4]):
        accuracy += 1
print('accuracy rate', accuracy / test_length)