python机器学习及实践-第二章

1.监督学习代码

import pandas as pd
import numpy as np
column_names=['Sample code number','Clump Thickness','Uniformity of Cell Size','Uniformity of Cell Shape','Marginal Adhesion','Single Epithelial Cell Size','Bare Nuclei','Bland Chromatin','Normal Nucleoli','Mitoses','Class']
#read_csv还可以在线读取数据
data=pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data',names=column_names)
#nan用来标识未标记的数据 和None类似 但又有一些区别
data=data.replace(to_replace='?',value=np.nan)
#DataFrame.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)
#axis:
#axis=0: 删除包含缺失值的行
#axis=1: 删除包含缺失值的列
#how: 与axis配合使用
#how=‘any’ :只要有缺失值出现，就删除该行货列
#how=‘all’: 所有的值都缺失，才删除行或列
#thresh： axis中至少有thresh个非缺失值，否则删除
#比如 axis=0，thresh=10：标识如果该行中非缺失值的数量小于10，将删除改行
#subset: list
#在哪些列中查看是否有缺失值
#inplace: 是否在原数据上操作。如果为真，返回None否则返回新的copy，去掉了缺失值
data=data.dropna(how='any')
data.shape
#逻辑回归 梯度下降分类
#train_test_split用于分割数据
from sklearn.cross_validation import train_test_split 
#X_train,X_test, y_train, y_test = cross_validation.train_test_split(train_data,train_target,test_size=0.4, random_state=0)
X_train,X_test, y_train, y_test = train_test_split(data[column_names[1:10]],data[column_names[10]],test_size=0.25, random_state=33)
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import SGDClassifier
#标准化数据 类似即归一化
ss=StandardScaler()
X_train=ss.fit_transform(X_train)
X_test=ss.fit_transform(X_test)
lr=LogisticRegression()
sgdc=SGDClassifier()
lr.fit(X_train,y_train)
lr_y_predict=lr.predict(X_test)
sgdc.fit(X_train,y_train)
sgdc_y_predict=sgdc.predict(X_test)
from sklearn.metrics import classification_report
print('Accuracy of LR Classifier:',lr.score(X_test,y_test))
#classification_report 输出准确率 F1值等模板
print(classification_report(y_test,lr_y_predict,target_names=['Benign','Malignant']))
print('Accuracy of SGD Classifier:',sgdc.score(X_test,y_test))
#classification_report 输出准确率 F1值等模板
print(classification_report(y_test,sgdc_y_predict,target_names=['Benign','Malignant']))
#支持向量机
#导入手写数字识别数据
#type 获取数据类型 dtype获取数组数据类型  astype()修改数据类型
from sklearn.datasets import load_digits
digits=load_digits()
digits.data.shape
from sklearn.cross_validation 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
from sklearn.svm import LinearSVC
from sklearn.metrics import classification_report
ss=StandardScaler()
X_train=ss.fit_transform(X_train)
X_test=ss.fit_transform(X_test)
lsvc=LinearSVC()
lsvc.fit(X_train,y_train)
y_predict=lsvc.predict(X_test)
print('Accuracy of LinearSVC :',lsvc.score(X_test,y_test))
print(classification_report(y_test,y_predict,target_names=digits.target_names.astype(str)))
#朴素贝叶斯分类
from sklearn.datasets import fetch_20newsgroups
news=fetch_20newsgroups( )
from sklearn.cross_validation 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)
#将文本转化成特征向量
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('Accuracy of Mulitinomial:',mnb.score(X_test,y_test))
print(classification_report(y_test,y_predict,target_names=news.target_names))
#k-近邻
from sklearn.datasets import load_iris
iris=load_iris( )
from sklearn.cross_validation import train_test_split
X_train,X_test,y_train,y_test=train_test_split(iris.data,iris.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)
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('Accuracy of Mulitinomial:',knc.score(X_tes