KNN分类sklearn的make_moons数据集

本文介绍了如何运用Python的sklearn库中的KNN(K近邻)分类器对make_moons数据集进行建模和预测。通过实例代码展示了数据预处理、模型训练和评估的全过程。

直接上代码

from sklearn.datasets import make_moons
from numpy import *
import numpy as np
import operator
from os import listdir
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
#创建数据集
x, y = make_moons(n_samples=200, noise=0.15, random_state=0)
# Max-Min标准化
# 建立MinMaxScaler对象
minmax = preprocessing.MinMaxScaler()
# 标准化处理
data_minmax = minmax.fit_transform(x)

#
import numpy as np import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap from sklearn.preprocessing import StandardScaler from sklearn.model_selection import train_test_split from sklearn.datasets import make_moons, make_circles, make_classification from sklearn.tree import DecisionTreeClassifier from sklearn.ensemble import RandomForestClassifier from sklearn.svm import SVC from sklearn.neighbors import KNeighborsClassifier from sklearn.naive_bayes import GaussianNB # 设置分类决策边界精细程度 h = 0.02 # 设置随机种子 rng = np.random.RandomState(2) # 设置分类模型 names = ["决策树", "随机森林", "线性支持向量机", "高斯核支持向量机", "K近邻算法", "朴素贝叶斯算法", ] classifiers = [DecisionTreeClassifier(max_depth=5), RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1), SVC(kernel="linear", C=0.025), SVC(gamma=2, C=1), KNeighborsClassifier(3), GaussianNB(),] # 设置数据集合 X, y = make_classification(n_features=2, n_redundant=0, n_informative=2, random_state=1, n_clusters_per_class=1) X += 2*rng.uniform(size=X.shape) linearly_separable = (X, y) datasets = [make_moons(noise=0.3, random_state=0), make_circles(noise=0.2, factor=0.5, random_state=1), linearly_separable] # 绘制图像 figure = plt.figure(figsize=(25, 9)); i = 1 for ds in datasets: X, y = ds X = StandardScaler().fit_transform(X) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4) x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5 y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5 xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h)) cm = plt.cm.RdBu cm_bright = ListedColormap(['#FF0000', '#0000FF']) ax = plt.subplot(len(datasets), len(classifiers) + 1, i) ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright) ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6) ax.set_xlim(xx.min(), xx.max()) ax.set_ylim(yy.min(), yy.max()) ax.set_xticks(()) ax.set_yticks(()) i += 1 for name, clf in zip(names, classifiers): ax = plt.subplot(len(datasets), len(classifiers) + 1, i) clf.fit(X_train, y_train) score = clf.score(X_test, y_test) if hasattr(clf, "decision_function"): Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()]) else: Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1] Z = Z.reshape(xx.shape) ax.contourf(xx, yy, Z, cmap=cm, alpha=.8) ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright) ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6) ax.set_xlim(xx.min(), xx.max()) ax.set_ylim(yy.min(), yy.max()) ax.set_xticks(()) ax.set_yticks(()) ax.set_title(name) ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'), size=15, horizontalalignment='right') i += 1 figure.subplots_adjust(left=.02, right=.98) plt.show()
最新发布
06-20
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值