In [20]:

    

import random

from scipy.spatial import distance

from sklearn import datasets
#from sklearn import tree
from sklearn.cross_validation import train_test_split
from sklearn.metrics import accuracy_score
#from sklearn.neighbors import KNeighborsClassifier


    

In [35]:

    

def euc(a, b):
    # only measure distance to one neighbor
    return distance.euclidean(a, b)


    

In [36]:

    

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 = random.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(row, self.X_train[i])
            if dist < best_dist:
                best_dist = dist
                best_index = i
        return self.y_train[best_index]


    

In [37]:

    

iris = datasets.load_iris()

# by analogy of f(x) = y
X = iris.data  # array([[ 5.1,  3.5,  1.4,  0.2], [ 4.9,  3. ,  1.4,  0.2]])
y = iris.target  # array([0, 0])

# 0.5 means use half of data for testing
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)

# my_classifier = tree.DecisionTreeClassifier()
# my_classifier = KNeighborsClassifier()
my_classifier = ScrappyKNN()

my_classifier.fit(X_train, y_train)
predictions = my_classifier.predict(X_test)  # array([2, 0, 2])

accuracy_score(y_test, predictions)


    

    
Out[37]:





0.97333333333333338

In [ ]: