sklearn各分类模型的比较

2020-3-7补充

import numpy as np, matplotlib.pyplot as mp
from sklearn.model_selection import train_test_split  # 数据切分
from sklearn.preprocessing import StandardScaler  # 数据标准化
from sklearn.datasets import make_moons, make_circles, make_classification  # 数据集
from sklearn.linear_model import LogisticRegression  # 逻辑回归
from sklearn.neural_network import MLPClassifier  # 多层感知机
from sklearn.neighbors import KNeighborsClassifier  # K最近邻
from sklearn.svm import SVC  # 支持向量机
from sklearn.gaussian_process import GaussianProcessClassifier  # 高斯过程
from sklearn.gaussian_process.kernels import RBF  # 高斯核函数
from sklearn.tree import DecisionTreeClassifier  # 决策树
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier,\
    ExtraTreesClassifier, BaggingClassifier  # 集成方法
from sklearn.naive_bayes import GaussianNB  # 高斯朴素贝叶斯
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis, LinearDiscriminantAnalysis  # 判别分析
from xgboost import XGBClassifier  # 极端梯度提升（eXtreme Gradient Boosting）
from warnings import filterwarnings
filterwarnings('ignore')  # 忽略警告

# 建模、设定参数
classifiers = [
    ('Logistic Regression', LogisticRegression()),  # 逻辑回归
    ('Nearest Neighbors', KNeighborsClassifier(3)),  # K最近邻
    ('Linear SVM', SVC(kernel='linear', C=0.025)),  # 线性的支持向量机
    ('RBF SVM', SVC(gamma=2, C=1)),  # 径向基函数的支持向量机
    ('Gaussian Process', GaussianProcessClassifier(1.0 * RBF(1.0))),  # 基于拉普拉斯近似的高斯过程
    ('Decision Tree', DecisionTreeClassifier(max_depth=5)),  # 决策树
    ('Random Forest', RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1)),  # 随机森林
    ('AdaBoost', AdaBoostClassifier()),  # 通过迭代弱分类器而产生最终的强分类器的算法
    ('Extra Trees', ExtraTreesClassifier()),
    ('GradientBoosting', GradientBoostingClassifier()),  # 梯度提升树
    ('Bagging', BaggingClassifier()),
    ('Naive Bayes', GaussianNB()),  # 朴素贝叶斯
    ('QDA', QuadraticDiscriminantAnalysis()),  # 二次判别分析
    ('LDA', LinearDiscriminantAnalysis()),  # 线性判别分析
    ('MLP', MLPClassifier(alpha=1)),  # 多层感知机
    ('XGB', XGBClassifier()),  # 极端梯度提升
]

# 创建随机样本集
X, y = make_classification(n_features=2, n_redundant=0, n_informative=2, random_state=1, n_clusters_per_class=1)
rng = np.random.RandomState(2)
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]

# 遍历样本集
figure = mp.figure(figsize=(20, 4))
i = 1  # 子图参数
h = .02  # 网眼步长（绘制等高线图的参数）
for ds_cnt, ds in enumerate(datasets):
    # 数据预处理，切分训练集和测试集
    X, y = ds
    X = StandardScaler().fit_transform(X)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4, random_state=42)

    # 用于绘制等高线图
    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))

    # 绘制原始样本集
    ax = mp.subplot(len(datasets), len(classifiers) + 1, i)
    if ds_cnt == 0:
        ax.set_title('Input data', size=9)
    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, edgecolors='k')  # 绘制训练集散点图
    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, alpha=0.5, edgecolors='k')  # 绘制测试集散点图
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())
    i += 1

    # 遍历分类器
    for name, clf in classifiers:
        ax = mp.subplot(len(datasets), len(classifiers) + 1, i)
        clf.fit(X_train, y_train)  # 训练
        score = clf.score(X_test, y_test)  # 模型评分

        # 绘制决策边界
        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, 2, alpha=.8)  # 等高线图
        # 散点图
        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, edgecolors='k')  # 训练集
        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, edgecolors='k', alpha=0.6)  # 测试集
        # 刻度、标签、标题等
        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())
        ax.set_yticks(())
        if ds_cnt == 0:
            ax.set_title(name, size=10)
        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'), size=9, horizontalalignment='right')
        i += 1
mp.tight_layout()
mp.show()

En	Cn
boost	n. 推动；vt. 促进
preprocess	vt. 预处理
gamma	希腊语的第三个字母：$\gamma$
quadratic	二次方程式；二次的
discriminant	判别式
percept	n. 认知
radial	n. 射线，光线；adj. 半径的；放射状的
MLP	Multi Layered Perceptron
RBF	Radial Basis Function
linearly separable	线性可分
tick	n. 滴答声；记号；