Python机器学习库:scikit-learn
1、特性:
简单高效的数据挖掘和机器学习分析
对所有用户开放,根据不同需求可高度可重用性
基于Numpy,Scipy和matplotlib
开源,商用级别:获得BSD许可
2、覆盖问题领域:
分类(Classification),回归(Regression),聚类(Clustering),降维(dimensionality reduction)
模型选择(model selection),预处理(preprocessing)
3、使用scikit-learn
安装scikit-learn:pip,easy_install,Windows installer
安装必须package:numpy,Scipy和matplotlib,可使用Anaconda(包含numpy,scipy等科学计算常用package)
安装注意问题:python解释器版本(2.7 or 3.4?),32-bit or 64-bit系统
安装Graphviz:http://www.graphviz.org/ 配置环境变量 转化dot文件至pdf可视化决策树。
决策树(decision tree)应用:Datesets.csv数据集
from sklearn.feature_extraction import DictVectorizer #feature特征 extraction提取 dict字典 vectorizer向量化程序
import csv #csv程序
from sklearn import preprocessing #preprocessing预处理
from sklearn import tree #tree树
from sklearn.externals.six import StringIO #external外部的 string字符串
allElectronicsData = open(r'E:\\data\\DataSets.csv','rb') #electronics电子工业
reader = csv.reader(allElectronicsData)
headers = reader.next()
print(headers)
featureList = [] #特征示例
labelList = [] #标号表
for row in reader: #行
labelList.append(row[len(row) - 1])
rowDict = {}
for i in range(1, len(row) - 1):
rowDict[headers[i]] = row[i]
featureList.append(rowDict)
print(featureList)
vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()
print("dummyX:" + str(dummyX)) #dummy虚拟的
print(vec.get_feature_names())
print("labelList:" + str(labelList))
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
print("dummyY:" + str(dummyY))
clf = tree.DecisionTreeClassifier(criterion='entropy') #熵
clf = clf.fit(dummyX,dummyY)
print("clf:" + str(clf))
with open("allElectronicInformationGainOri.dot",'w') as f:
f = tree.export_graphviz(clf,feature_names=vec.get_feature_names(),out_file = f)
oneRowX = dummyX[0,:]
print("oneRowX:" + str(oneRowX))
newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0
print("newRowX:" + str(newRowX))
predictedY = clf.predict(newRowX)
print("predictedY:" + str(predictedY))