[分类算法]常用功能实现

前言：分类是机器学习中的重要的一种功能，在机器学习的研究历史中，诞生了大量的分类算法，而每种算法都有其优势和不足。

本文汇总了常用的分类算法及其实现方式，方便快速查询使用。（本文使用鸢尾花数据集，是三类别分类）

以下9种分类算法，使用相同的数据进行训练和测试，在测试集上的准确率(accuracy)分别为：

1.随机森林：100%

2.决策树：100%

3.K近邻：100%

4.支持向量机：100%

5.逻辑回归：96.67%

6.线性支持向量机：100%

7.随机梯度下降：96.67%

8.感知机：100%

9.朴素贝叶斯：96.67%

import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import sklearn
from sklearn import datasets
from sklearn.metrics import accuracy_score

from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier

from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC, LinearSVC
from sklearn.linear_model import LogisticRegression

from sklearn.linear_model import SGDClassifier
from sklearn.linear_model import Perceptron
from sklearn.naive_bayes import GaussianNB

from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score

from sklearn.model_selection import GridSearchCV

iris = datasets.load_iris()
x,y = iris.data,iris.target

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=0)

res = []

#1. 随机森林分类
print('随机森林分类')
clf = RandomForestClassifier(n_estimators=100)
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#2. 决策树分类
print('决策树分类')
clf = DecisionTreeClassifier()
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#3. KNN
print('KNN')
clf = KNeighborsClassifier(n_neighbors = 13)
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#4. SVM分类
print('SVM')
clf = SVC(gamma='scale')
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#5. 逻辑回归分类
print('LogisticRegression')
clf = LogisticRegression(solver='lbfgs',multi_class='ovr')
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#6. linear svm分类
print('linear SVM')
clf = LinearSVC(max_iter=10000)
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#7. 随机梯度下降分类
print('SGD')
clf = SGDClassifier(max_iter=1000,tol=1e-3)
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#8. 感知机分类
print('Perceptron')
clf = Perceptron(max_iter=1000,tol=1e-3)
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#9. 朴素贝叶斯分类
print('Naive Bayes')
clf = GaussianNB()
clf.fit(x_train, y_train)
cross_score = cross_val_score(clf, x_train, y_train, cv=3, scoring="accuracy")
print(cross_score)
y_predict = clf.predict(x_test)
score = accuracy_score(y_test,y_predict)
res.append(score)
print()

#10. 得分比较
print(res)