KNN cosine 余弦相似度计算

# coding: utf-8
import collections
import numpy as np
import os
from sklearn.neighbors import NearestNeighbors


def cos(vector1,vector2):
    dot_product = 0.0;
    normA = 0.0;
    normB = 0.0;
    for a,b in zip(vector1,vector2):
        dot_product += a*b
        normA += a**2
        normB += b**2
    if normA == 0.0 or normB==0.0:
        return None
    else:
        return dot_product / ((normA*normB)**0.5)


def iterbrowse(path):
    for home, dirs, files in os.walk(path):
        for filename in files:
            yield os.path.join(home, filename)


def get_data(filename):
    white_verify = []
    with open(filename) as f:
        lines = f.readlines()
        for line in lines:
            a = line.split("\t")
            if len(a) != 78:
                print(line)