# -*- coding: utf-8 -*- """ Created on Wed May 18 16:59:12 2022 @author: 1252319301 """ # In[1] # 导入依赖 import numpy as np import pandas as pd # In[2] # 直接引入sklearn中的数据集iris 鸢尾花 from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split # 切分数据集为训练集、测试集 from sklearn.metrics import accuracy_score # 用来计算分类预测的准确率 # In[3] # 导入数据 iris = load_iris() # print(type(iris)) #class 'sklearn.utils.Bunch' # print(iris.keys()) #dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename']) df = pd.DataFrame(data=iris.data, columns=iris.feature_names) #df['species_num'] = iris.target df['species'] = iris.target_names[iris.target] #print(df) #print(df.describe()) # 处理数据 x = iris.data y = iris.target.reshape(-1,1) # 将一维 转 二维 # In[4] # ============================================================================= # 划分数据集 # ============================================================================= x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.3,random_state=35,stratify=y) #stratify 按照层级等比例分类 #print(x_test.shape,y_test.shape) #(45, 4) (45, 1) #print(x_train.shape,y_train.shape) #(105, 4) (105, 1) #print(type(x_test)) ##print(np.abs(x_train-x_test[0])) #(4,) #print(x_test[0]) #[5.8 2.7 5.1 1.9] #print(x_test[0].reshape(1,-1)) #[[5.8 2.7 5.1 1.9]] #print(x_test[0].reshape(1,-1).shape) #(1, 4) # In[5] # 距离函数定义 a,b 向量(x_test - x_train) x_test 是 # x_test （在np处理时） 必须是一维向量, x_train 可以是矩阵 # 曼哈顿距离 def l1_distance(a,b): return np.sum(np.abs(a-b),axis=1) # 结果保存一列,不加axis会累计为一个值，不是一列 # 欧式距离 def l2_distance(a,b): return np.sqrt( np.sum( (a-b)**2, axis=1 ) ) # In[6] # ============================================================================= # 核心算法 # ============================================================================= # 分类器 ,继承object类 class kNN(object): # 定义构造器(k，近邻 和 距离函数) def __init__(self, n_neighbors = 1, dist_func = l1_distance): self.n_neighbors = n_neighbors self.dist_func = dist_func # 训练模型方法 (knn，训练的过程:无，只传入训练集，然后根据训练集计算距离即可) def fit(self, x, y): self.x_train = x self.y_train = y # 模型预测方法 def predict(self, x): # 初始化预测分类数组 0数组 ,形状和 类型 y_pred = np.zeros((x.shape[0], 1), dtype=self.y_train.dtype) # 遍历输入的x for i,x_test in enumerate(x): # 计算 测试数据与 所有训练数据 距离 distances = self.dist_func(self.x_train, x_test) # 给距离排序, 取出 索引值 argsort()排序完序的原来的下标值 ''' dist = np.array([3,2,1]) print(np.argsort(dist)) [2,1,0] ''' nn_index = np.argsort(distances) # 选择最近的k个点，保存分类类别 ravel 二维转一维 nn_y = self.y_train[nn_index[:self.n_neighbors]].ravel() # 统计类别出现频率最高的，赋给y_pred[i] bincount() 统计每个值出现的次数 ''' dist = np.arrar([2,1,0,1,1,2]) print(np.bincount(dist)) # [1,3,2] ,1个0，3个1， 2个2 print(np.argmax(np.bincount(dist))) # 1 ,值最大的下标 ''' y_pred[i] = np.argmax(np.bincount(nn_y)) return y_pred # In[7] # 测试 # 实例knn knn = kNN(n_neighbors= 3) # 训练 knn.fit(x_train, y_train) # 预测 y_pred = knn.predict(x_test) # 评估(预测准确率) accuracy = accuracy_score(y_test,y_pred) print("预测准确率：",accuracy) ''' k = 3,l1, 预测准确率： 0.9333333333333333 ''' # In[8] # 自动化测试 # 实例knn knn = kNN(n_neighbors= 3) result_list = [] # 训练 knn.fit(x_train, y_train) # 距离函数 for p in [1,2]: knn.dist_func = l1_distance if p==1 else l2_distance # k 奇数选取 for k in range(1, 10, 2): knn.n_neighbors = k # 预测 y_pred = knn.predict(x_test) accuracy = accuracy_score(y_test,y_pred) result_list.append([k,'l1_distance' if p==1 else 'l2_distance',accuracy]) df = pd.DataFrame(result_list,columns=['k','距离函数','预测准确率']) print(df) ''' k 距离函数 预测准确率 0 1 l1_distance 0.933333 1 3 l1_distance 0.933333 2 5 l1_distance 0.977778 3 7 l1_distance 0.955556 4 9 l1_distance 0.955556 5 1 l2_distance 0.933333 6 3 l2_distance 0.933333 7 5 l2_distance 0.977778 8 7 l2_distance 0.977778 9 9 l2_distance 0.977778 '''
