自己实现简单分类器

# coding: utf-8

from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.metrics import accuracy_score
import numpy as np


from scipy.spatial import distance


def euc(a, b):
    return distance.euclidean(a,b)

class ScrappyKNN():
    def fit(self, X_train, y_train):
        self.X_train = X_train
        self.y_train = y_train
        
    def predict(self, X_test):
        predictions = []
        for row in X_test:
            #label = np.random.randint(2)
            #label = radom.choice(self.y_train)
            label = self.closest(row)
            predictions.append(label)
        return predictions

    def closest(self, row):
        best_dist = euc(row, self.X_train[0])
        best_index = 0
        for i in range(1, len(self.X_train)):
            dist = euc(X_train[i], row)
            if dist   < best_dist:
                best_dist = dist
                best_index = i
        return self.y_train[best_index]

iris = datasets.load_iris()

X = iris.data
y = iris.target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size =.5)

#my_classifier = KNeighboursClassifier()
my_classifier = ScrappyKNN()
my_classifier.fit(X_train, y_train)
predictions = my_classifier.predict(X_test)

accuracy_score(y_test, predictions)