【机器学习100天】Day11-K近邻法(K-NN)

代码

数据集(点击下载)

# 导入相关库
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# 导入数据集
dataset = pd.read_csv(r'D:\Python\100-Days-Of-ML-Code-master\datasets\Social_Network_Ads.csv')
X = dataset.iloc[:, [2, 3]].values
Y = dataset.iloc[:, 4].values

# 将数据划分成训练集和测试集
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=0)

# 特征缩放
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# 使用K-NN对训练集数据进行训练
from sklearn.neighbors import KNeighborsClassifier
classifier = KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2) # p=2：使用欧式距离； metric='minkowski'：用于树的距离度量。默认度量是 minkowski，并且 p=2 等效于标准欧几里得度量；
classifier.fit(X_train, Y_train)

# 对测试集进行预测
Y_pred = classifier.predict(X_test)

# 生成混淆矩阵
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)

# 可视化
from matplotlib.colors import ListedColormap
X_set, Y_set = X_train, Y_train
X1, X2 = np.meshgrid(np.arange(start=X_set[:, 0].min()-1, stop=X_set[:, 0].max()+1, step=0.01),
                     np.arange(start=X_set[:, 1].min()-1, stop=X_set[:, 1].max()+1, step=0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha=0.75, cmap=ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(Y_set)):
    plt.scatter(X_set[Y_set == j, 0], X_set[Y_set == j, 1],
                c=ListedColormap(('red', 'green'))(i), label=j)

plt.title(' K-NN(Training set)')
plt.xlabel(' Age')
plt.ylabel(' Estimated Salary')
plt.legend()
plt.show()

X_set, Y_set = X_test, Y_test
X1, X2 = np.meshgrid(np.arange(start=X_set[:, 0].min()-1, stop=X_set[:, 0].max()+1, step=0.01),
                     np.arange(start=X_set[:, 1].min()-1, stop=X_set[:, 1].max()+1, step=0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha=0.75, cmap=ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(Y_set)):
    plt.scatter(X_set[Y_set == j, 0], X_set[Y_set == j, 1],
                c=ListedColormap(('red', 'green'))(i), label=j)

plt.title(' K-NN(Test set)')
plt.xlabel(' Age')
plt.ylabel(' Estimated Salary')
plt.legend()
plt.show()

运行结果：

2.函数学习

sklearn.neighbors.KNeighborsClassifier







KNN算法是如何工作的？