逻辑回归分类

import numpy as np
from sklearn import linear_model

X = np.array([[4, 7], [3.5, 8], [3.1, 6.2], [0.5, 1], [1, 2], [1.2, 1.9], [6, 2], [5.7, 1.5], [5.4, 2.2]])
y = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2])

# 逻辑回归分类器
# solver：求解器，有‘newton-cg’、‘lbfgs’、‘liblinear’、‘sag’、‘saga’五种选择，默认是‘liblinear’
# C：正则化系数，越小正则化强度越高，越大越不容易过拟合，默认是1.0
classifier = linear_model.LogisticRegression(solver='liblinear', C=100)

classifier.fit(X, y)

朴素贝叶斯分类

• 朴素贝叶斯分类器是用贝叶斯定理进行建模的监督学习分类器
• 贝叶斯定理: P(A∩B) = P(A)*P(B|A)=P(B)*P(A|B)。如上公式也可变形为：P(A|B)=P(B|A)*P(A)/P(B)
• P(类别|特征)=P(特征|类别)*P(类别)/P(特征)

import numpy as np
from sklearn.naive_bayes import GaussianNB

X = np.array([[4, 7], [3.5, 8], [3.1, 6.2], [0.5, 1], [1, 2], [1.2, 1.9], [6, 2], [5.7, 1.5], [5.4, 2.2]])
y = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2])

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=5)

# 训练分类器
classifier_gaussiannb = GaussianNB()
classifier_gaussiannb.fit(X_train, y_train)
y_test_pred = classifier_gaussiannb.predict(X_test)

pdf在线免费转word文档 https://orcc.online/pdf

支持向量机 SVM (可分类、可回归)

• 核函数与 SVM http://www.eric-kim.net/eric-kim-net/posts/1/kernel_trick.html
• SVM 使用核函数, 把 N 维空间映射到 M 维空间(M>N), 在更高的纬度上可能可以线性可分,再映射回原来的空间维度
• 核函数的作用是将低维空间的点映射到高维空间, 然后在高维空间上进行分类
• 核函数不需要计算所有高维空间的点，使计算成为可能

from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=5)

# kernel：linear:线性核函数; rbf:径向基函数 高斯核函数; poly:多项式核函数; sigmoid: sigmoid核函数; 默认是线性核函数
params = {'kernel': 'linear','class_weight': 'balanced'}

classifier = SVC(**params)
classifier.fit(X_train, y_train)

target_names = ['Class-' + str(int(i)) for i in set(y)]
print("#"*30)
print("Classifier performance on training dataset")
print(classification_report(y_train, classifier.predict(X_train),target_names=target_names))
print("#"*30)

IT免费在线工具网 https://orcc.online