機(jī)器學(xué)習(xí)實(shí)戰(zhàn)-KNN算法-鳶尾花分類(lèi)

# 導(dǎo)入算法包以及數(shù)據(jù)集 from sklearn import neighbors from sklearn import datasets from sklearn.model_selection import train_test_split from sklearn.metrics import classification_report import random # 載入數(shù)據(jù) iris = datasets.load_iris() print(iris)

# 打亂數(shù)據(jù)切分?jǐn)?shù)據(jù)集 # x_train,x_test,y_train,y_test = train_test_split(iris.data, iris.target, test_size=0.2) #分割數(shù)據(jù)0.2為測(cè)試數(shù)據(jù)，0.8為訓(xùn)練數(shù)據(jù)#打亂數(shù)據(jù) data_size = iris.data.shape[0] index = [i for i in range(data_size)] random.shuffle(index) iris.data = iris.data[index] iris.target = iris.target[index]#切分?jǐn)?shù)據(jù)集 test_size = 40 x_train = iris.data[test_size:] x_test = iris.data[:test_size] y_train = iris.target[test_size:] y_test = iris.target[:test_size]# 構(gòu)建模型 model = neighbors.KNeighborsClassifier(n_neighbors=3) model.fit(x_train, y_train) prediction = model.predict(x_test)print(classification_report(y_test, prediction))

機(jī)器學(xué)習(xí)實(shí)戰(zhàn)-KNN算法-水果分類(lèi)

from sklearn.neighbors import KNeighborsClassifier import numpy as np import pandas as pd from sklearn.preprocessing import LabelEncoder import matplotlib.pyplot as plt

data = pd.read_csv('fruit_data.csv') data

labelencoder = LabelEncoder() data.iloc[:,0] = labelencoder.fit_transform(data.iloc[:,0]) data

labelencoder.classes_

from sklearn.model_selection import train_test_split # 切分?jǐn)?shù)據(jù)集，stratify=y表示切分后訓(xùn)練集和測(cè)試集中的數(shù)據(jù)類(lèi)型的比例跟切分前y中的比例一致 # 比如切分前y中0和1的比例為1:2，切分后y_train和y_test中0和1的比例也都是1:2 # 設(shè)置random_state，使用同樣的隨機(jī)方式來(lái)切分?jǐn)?shù)據(jù) x_train,x_test,y_train,y_test = train_test_split(data.iloc[:,1:], data.iloc[:,0], test_size=0.3, stratify=data.iloc[:,0], random_state=20) # 保存不同k值測(cè)試集準(zhǔn)確率 test_scores = [] # 保存不同k值訓(xùn)練集準(zhǔn)確率 train_scores = []# 設(shè)置30個(gè)k值 k = 30 for i in range(1,k):knn = KNeighborsClassifier(i)knn.fit(x_train,y_train)# 保存測(cè)試集準(zhǔn)確率test_scores.append(knn.score(x_test,y_test))# 保存訓(xùn)練集準(zhǔn)確率train_scores.append(knn.score(x_train,y_train)) plt.title('k-NN Varying number of neighbors') plt.plot(range(1,k),test_scores,label="Test") plt.plot(range(1,k),train_scores,label="Train") plt.legend() plt.xticks(range(1,k)) plt.xlabel('k') plt.ylabel('accuracy') plt.show()

# 選擇一個(gè)最好的k值作為模型參數(shù) k = np.argmax(test_scores)+1 knn = KNeighborsClassifier(k) knn.fit(x_train,y_train) print(k) print(knn.score(x_test,y_test))

總結(jié)

以上是生活随笔為你收集整理的机器学习实战-KNN算法-20的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。