Sklearn学习笔记2 分类问题

准备数据，这部分代码相同，后面只列出各个算法代码不同的部分。（朴素贝叶斯除外）

from sklearn.datasets import load_digits
digits= load_digits()
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(digits.data,digits.target,test_size=0.25,random_state=33)

from sklearn.preprocessing import StandardScaler

ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)

1 KNN算法

from sklearn.neighbors import KNeighborsClassifier
knc = KNeighborsClassifier()
knc.fit(X_train,y_train)
y_predict = knc.predict(X_test)

from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',knc.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

2 贝叶斯分类算法

2.1 sklearn.naive_bayes

2.2 GaussianNB

2.3 MultinomialNB

2.4 BernoulliNB

# 朴素贝叶斯实现对20类新闻的分类
from sklearn.datasets import fetch_20newsgroups
news = fetch_20newsgroups(subset='all')
print(len(news.data))
print(news.data[0])

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(news.data,news.target,test_size=0.25,random_state=33)
#文本特征向量转化模块
from sklearn.feature_extraction.text import CountVectorizer
vec = CountVectorizer()
X_train = vec.fit_transform(X_train)
X_test = vec.transform(X_test)

from sklearn.naive_bayes import MultinomialNB
mnb = MultinomialNB()
mnb.fit(X_train,y_train)
y_predict = mnb.predict(X_test)
from sklearn.metrics import classification_report
print('The accruacy of Naive Bayes is ',mnb.score(X_test,y_test))
print(classification_report(y_test,y_predict,target_names=news.target_names))

运行结果：

3 决策树算法

# 决策树求解手写数字分类问题
from sklearn.tree import DecisionTreeClassifier
dtc = DecisionTreeClassifier()
dtc.fit(X_train,y_train)
y_predict = dtc.predict(X_test)
from sklearn.metrics import classification_report
print (dtc.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

4 随机森林算法

# 随机森林求解手写数字分类问题
from sklearn.ensemble import RandomForestClassifier
rfc = RandomForestClassifier()
rfc.fit(X_train,y_train)
y_predict = rfc.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',rfc.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

5 SVM算法

# 支持向量机求解手写数字分类问题
from sklearn.svm import LinearSVC
lsvc = LinearSVC()
lsvc.fit(X_train,y_train)
y_predict = lsvc.predict(X_test)

运行结果：

6 GBDT

#  GBDT求解手写数字分类问题
from sklearn.ensemble import GradientBoostingClassifier
gbc = GradientBoostingClassifier()
gbc.fit(X_train,y_train)
y_predict = gbc.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',gbc.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

7 XGBoost

# XGBoost求解手写数字分类问题
from xgboost import XGBClassifier
xgbc = XGBClassifier()
xgbc.fit(X_train,y_train)
y_predict = xgbc.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',xgbc.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

8 逻辑回归

#  逻辑回归求解手写数字分类问题
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression()
lr.fit(X_train,y_train)
y_predict = lr.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',lr.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

9 线性判别分析LDA

#  线性判别分析LDA求解手写数字分类问题
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
LDA = LinearDiscriminantAnalysis()
LDA.fit(X_train,y_train)
y_predict = LDA.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',LDA.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

10 二次判别分析QDA

# 二次判别分析QDA求解手写数字分类问题
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
clf = QuadraticDiscriminantAnalysis()
clf.fit(X_train,y_train)
y_predict = clf.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',clf.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

11 Adaboost

# 基于决策树的Adaboost求解手写数字分类问题
from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
clf = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2, min_samples_split=20, min_samples_leaf=5),
                         algorithm="SAMME", n_estimators=200, learning_rate=0.8)
clf.fit(X_train,y_train)
y_predict = clf.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy  is',clf.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

12 多层感知机MLP

# 多层感知机MLP求解手写数字分类问题
from sklearn.neural_network import MLPClassifier
clf = MLPClassifier(hidden_layer_sizes=(100),
		        activation='relu',
		        solver='adam',
		        batch_size=128,
		        alpha=1e-4,
		        learning_rate_init=1e-3,
		        learning_rate='adaptive',
		        tol=1e-4,
		        max_iter=200)
clf.fit(X_train,y_train)
y_predict = clf.predict(X_test)
from sklearn.metrics import classification_report
print('The Accruacy of Linear SVC is',clf.score(X_test,y_test))
print (classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))

运行结果：

参考资料

https://www.cnblogs.com/lcmichelle/p/10743152.html

https://blog.csdn.net/fanyingkk/article/details/80240663?utm_medium=distribute.pc_aggpage_search_result.none-task-blog-2_allsobaiduend~default-1-80240663.nonecase&utm_term=sklearn%20%E5%A4%9A%E5%88%86%E7%B1%BB%E5%99%A8

https://blog.csdn.net/weixin_39504171/article/details/104673523?utm_medium=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param&depth_1-utm_source=distribute.pc_relevant_t0.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param