Python和R代码机器学习算法速查对比表

大数据文摘

发布于 2018-05-22 17:51:59

6410

发布于 2018-05-22 17:51:59

文章被收录于专栏：大数据文摘

翻译：丁雪校对：王方思

在拿破仑·希尔（Napolean Hill）所著的《思考致富》（Think and Grow Rich）一书中，他为我们引述了Darby苦挖金矿多年后，就在离矿脉一步之遥的时候与宝藏失之交臂的故事。

思考致富中文版的豆瓣阅读链接：

http://read.douban.com/reader/ebook/10954762/

根据该书内容进行的修改

如今，我虽然不知道这故事是真是假，但是我明确知道在我身边有不少这样的“数据Darby”。这些人了解机器学习的目的和执行，对待任何研究问题只使用2-3种算法。他们不用更好的算法和技术来更新自身，只因为他们太顽固，或者他们只是在耗费时间而不求进步。

像Darby这一类人，他们总是在接近终点的时候而错失良机。最终，他们以计算量大、难度大或是无法设定合适的阈值来优化模型等借口，放弃了机器学习。这有什么意义？你听说过这些人吗？

今天给出的速查表旨在改变这群“数据Darby”对机器学习的态度，使他们成为身体力行的倡导者。这里收集了10个最为常用的机器学习算法，附上了Python和R代码。

考虑到机器学习方法在建模中得到了更多的运用，以下速查表可以作为代码指南来帮助你掌握机器学习算法运用。祝你好运！

对于那些超级懒惰的数据Darbies，我们将让你的生活过得更轻松。你可以在此下载PDF版的速查表，便可直接复制粘贴代码。

机器学习算法
类型
监督学习	非监督学习	增强学习
决策树K-近邻算法随机决策森林Logistics回归分析	Apriori算法K-均值算法系统聚类	马尔科夫决策过程增强学习算法（Q-学习）

线性回归	#Import Library#Import other necessary libraries like pandas,#numpy...from sklearn import linear_model#Load Train and Test datasets#Identify feature and response variable(s) and#values must be numeric and numpy arraysx_train=input_variables_values_training_datasets y_train=target_variables_values_training_datasets x_test=input_variables_values_test_datasets#Create linear regression objectlinear = linear_model.LinearRegression()#Train the model using the training sets and #check scorelinear.fit(x_train, y_train) linear.score(x_train, y_train)#Equation coefficient and Intercept print('Coefficient: \n', linear.coef_) print('Intercept: \n', linear.intercept_) #Predict Outputpredicted= linear.predict(x_test)	#Load Train and Test datasets#Identify feature and response variable(s) and#values must be numeric and numpy arraysx_train <- input_variables_values_training_datasetsy_train <- target_variables_values_training_datasetsx_test <- input_variables_values_test_datasetsx <- cbind(x_train,y_train)#Train the model using the training sets and#check scorelinear <- lm(y_train ~ ., data = x)summary(linear)#Predict Outputpredicted= predict(linear,x_test)
逻辑回归	#Import Libraryfrom sklearn.linear_model import LogisticRegression#Assumed you have, X (predictor) and Y (target)#for training data set and x_test(predictor)#of test_dataset#Create logistic regression objectmodel = LogisticRegression()#Train the model using the training sets#and check scoremodel.fit(X, y)model.score(X, y)#Equation coefficient and Interceptprint('Coefficient: \n', model.coef_)print('Intercept: \n', model.intercept_)#Predict Outputpredicted= model.predict(x_test)	x <- cbind(x_train,y_train)#Train the model using the training sets and check #scorelogistic <- glm(y_train ~ ., data = x,family='binomial') summary(logistic)#Predict Outputpredicted= predict(logistic,x_test)
决策树	#Import Library#Import other necessary libraries like pandas, numpy... from sklearn import tree#Assumed you have, X (predictor) and Y (target) for#training data set and x_test(predictor) of #test_dataset#Create tree objectmodel = tree.DecisionTreeClassifier(criterion='gini') #for classification, here you can change the #algorithm as gini or entropy (information gain) by#default it is gin#model = tree.DecisionTreeRegressor() for#regression#Train the model using the training sets and check #scoremodel.fit(X, y)model.score(X, y)#Predict Outputpredicted= model.predict(x_test)	#Import Librarylibrary(rpart)x <-cbind(x_train,y_train)#grow treefit <- rpart(y_train ~ ., data = x,method="class") summary(fit)#Predict Outputpredicted= predict(fit,x_test)
支持向量机	#Import Libraryfrom sklearn import svm#Assumed you have, X (predictor) and Y (target) for #training data set and x_test(predictor) of test_dataset#Create SVM classification objectmodel = svm.svc()#there are various options associatedwith it, this is simple for classification.#Train the model using the training sets and check #scoremodel.fit(X, y)model.score(X, y)#Predict Outputpredicted= model.predict(x_test)	#Import Librarylibrary(e1071)x <- cbind(x_train,y_train) #Fitting modelfit <-svm(y_train ~ ., data = x) summary(fit)#Predict Outputpredicted= predict(fit,x_test)
贝叶斯算法	#Import Libraryfrom sklearn.naive_bayes import GaussianNB#Assumed you have, X (predictor) and Y (target) for#training data set and x_test(predictor) of test_dataset#Create SVM classification object model = GaussianNB()#there is other distribution for multinomial classes like Bernoulli Naive Bayes#Train the model using the training sets and check#scoremodel.fit(X, y)#Predict Outputpredicted= model.predict(x_test)	#Import Librarylibrary(e1071)x <- cbind(x_train,y_train)#Fitting modelfit <-naiveBayes(y_train ~ ., data = x) summary(fit)#Predict Outputpredicted= predict(fit,x_test)
k-近邻算法析	#Import Libraryfrom sklearn.neighbors import KNeighborsClassifier#Assumed you have, X (predictor) and Y (target) for#training data set and x_test(predictor) of test_dataset#Create KNeighbors classifier object model KNeighborsClassifier(n_neighbors=6)#default value for n_neighbors is 5#Train the model using the training sets and check score model.fit(X, y)#Predict Outputpredicted= model.predict(x_test)	#Import Librarylibrary(knn)x <- cbind(x_train,y_train)#Fitting modelfit <-knn(y_train ~ ., data = x,k=5) summary(fit)#Predict Outputpredicted= predict(fit,x_test)

硬聚类算法	#Import Libraryfrom sklearn.cluster import KMeans#Assumed you have, X (attributes) for training data set#and x_test(attributes) of test_dataset#Create KNeighbors classifier object modelk_means = KMeans(n_clusters=3, random_state=0)#Train the model using the training sets and check score model.fit(X)#Predict Outputpredicted= model.predict(x_test)	#Import Librarylibrary(cluster)fit <- kmeans(X, 3)#5 cluster solution
随机森林算法	#Import Libraryfrom sklearn.ensemble import RandomForestClassifier#Assumed you have, X (predictor) and Y (target) for#training data set and x_test(predictor) of test_dataset#Create Random Forest objectmodel= RandomForestClassifier()#Train the model using the training sets and check score model.fit(X, y)#Predict Outputpredicted= model.predict(x_test)	#Import Librarylibrary(randomForest)x <- cbind(x_train,y_train)#Fitting modelfit <- randomForest(Species ~ ., x,ntree=500) summary(fit)#Predict Outputpredicted= predict(fit,x_test)
降维算法	#Import Libraryfrom sklearn import decomposition#Assumed you have training and test data set as train and#test#Create PCA object pca= decomposition.PCA(n_components=k) #default value of k =min(n_sample, n_features)#For Factor analysis#fa= decomposition.FactorAnalysis()#Reduced the dimension of training dataset using PCA train_reduced = pca.fit_transform(train)#Reduced the dimension of test datasettest_reduced = pca.transform(test)	#Import Librarylibrary(stats)pca <- princomp(train, cor = TRUE)train_reduced <- predict(pca,train)test_reduced <- predict(pca,test)
GBDT	#Import Libraryfrom sklearn.ensemble import GradientBoostingClassifier#Assumed you have, X (predictor) and Y (target) for#training data set and x_test(predictor) of test_dataset#Create Gradient Boosting Classifier objectmodel= GradientBoostingClassifier(n_estimators=100, \ learning_rate=1.0, max_depth=1, random_state=0)#Train the model using the training sets and check score model.fit(X, y)#Predict Outputpredicted= model.predict(x_test)	#Import Librarylibrary(caret)x <- cbind(x_train,y_train)#Fitting modelfitControl <- trainControl( method = "repeatedcv", + number = 4, repeats = 4)fit <- train(y ~ ., data = x, method = "gbm",+ trControl = fitControl,verbose = FALSE)predicted= predict(fit,x_test,type= "prob")[,2]