R Language Machine Learning package

From:http://www.zhizhihu.com/html/y2009/410.html

Machine learning is an interdisciplinary area of computer science and statistics, and R on machine learning consists of the following aspects:
1) Neural Network (neural Networks):
The Nnet packet performs a single hidden layer feedforward neural network, and Nnet is part of the VR package (http://cran.r-project.org/web/packages/VR/index.html).
2) Recursive splitting (Recursive partitioning):
Recursive splitting uses the tree structure model to do regression, classification and survival analysis, mainly in Rpart packet (http://cran.r-project.org/web/packages/rpart/index.html) and Tree packet (HTTP/ cran.r-project.org/web/packages/tree/index.html), especially recommended Rpart packages. Weka also has this recursive splitting method, such as: J4.8, C4.5, M5, packet Rweka provides an interface for functions of R and Weka (http://cran.r-project.org/web/packages/RWeka/index.html).
The party package provides a two-class recursive split algorithm that can be used for unbiased variable selection and stop criteria: the function ctree () detects the relationship between the independent variable and the dependent variable by the non-parametric conditional inference method, and the function mob () is able to establish a parametric model (http://cran.r-project.org/web /packages/party/index.html). In addition, the party package also provides a visual display of two branch tree and node distribution.
The Mvpart package is a Rpart improvement package that handles the problem of multivariate dependent variables (http://cran.r-project.org/web/packages/mvpart/index.html). Rpart.permutation Packet Replacement Method (permutation) evaluation Tree Effectiveness (http://cran.r-project.org/web/packages/rpart.permutation/ index.html). Knntree package establishes a classification tree, each leaf node is a KNN classifier (http://cran.r-project.org/web/packages/knnTree/index.html). The Logicreg package does logistic regression analysis for most of the arguments are two variables (http://cran.r-project.org/web/packages/LogicReg/index.html). Maptree Pack (http://cran.r-project.org/web/packages/maptree/index.html) and Pinktoe pack (http://cran.r-project.org/web/ packages/pinktoe/index.html) provides a visual function of the tree structure.
3) Stochastic forest (random forests):
The Randomforest package provides functions for regression and classification using random forests (http://cran.r-project.org/web/packages/randomForest/index.html). Ipred pack bagging thought to do regression, classification and survival analysis, combining multiple models (http://cran.r-project.org/web/packages/ipred/index.html). The party package also provides a random forest law (http://cran.r-project.org/web/packages/party/index.html) based on the conditional inference tree. VARSELRF Pack Random forest Law to do variable selection (http://cran.r-project.org/web/packages/varSelRF/index.html).
4) regularized and Shrinkage Methods:
LASSO2 Pack (http://cran.r-project.org/web/packages/lasso2/index.html) and Lars Pack (http://cran.r-project.org/web/packages /lars/index.html) can execute a regression model in which the parameters are subject to certain limitations. The Elasticnet package calculates all shrinkage parameters (http://cran.r-project.org/web/packages/elasticnet/index.html). Glmpath package can get generalized linear model and Cox model of L1 regularization path (http://cran.r-project.org/web/packages/glmpath/index.html). Penalized package Execution Lasso (L1) and Ridge (L2) penalty regression model (penalized regression models) (http://cran.r-project.org/web/packages/ penalized/index.html). The PAMR package performs a reduced centroid taxonomy (shrunken centroids classifier) (http://cran.r-project.org/web/packages/pamr/index.html). The earth package can do multiple adaptive spline regression (multivariate adaptive regression splines) (http://cran.r-project.org/web/packages/earth/ index.html).
5) Boosting:
GBM Pack (http://cran.r-project.org/web/packages/gbm/index.html) and boost pack (http://cran.r-project.org/web/packages/ boost/index.html) performs a variety of gradient boosting algorithms, GBM packages do tree-based gradient descent boosting,boost packets including Logitboost and L2boost. The Gammoost package provides programs based on the boosting generalized additive model (generalized additive models) (http://cran.r-project.org/web/packages/GAMMoost/ index.html). The Mboost package makes model-based boosting (http://cran.r-project.org/web/packages/mboost/index.html).
6) Support vector machines (supported vectors machines):
The SVM () function of the e1071 package provides an interface for R and LIBSVM (http://cran.r-project.org/web/packages/e1071/index.html). The Kernlab package provides a flexible framework for learning methods based on kernel functions, including SVM, RVM ... (http://cran.r-project.org/web/packages/kernlab/index.html). The Klar package provides an interface for R and Svmlight (http://cran.r-project.org/web/packages/klaR/index.html).
7) Bayesian method (Bayesian Methods):
Bayestree package execution Bayesian Additive Regression Trees (BART) algorithm (http://cran.r-project.org/web/packages/BayesTree/ Index.html,http://www-stat.wharton.upenn.edu/~edgeorge/research_papers/bart%206--06.pdf). TGP Bayesian Semi-parametric nonlinear regression (Bayesian nonstationary, semiparametric nonlinear regression) (http://cran.r-project.org/web/ packages/tgp/index.html).
8) Optimization based on genetic algorithm (optimization using genetic algorithms):
Gafit Pack (http://cran.r-project.org/web/packages/gafit/index.html) and Rgenoud pack (http://cran.r-project.org/web/ packages/rgenoud/index.html) provides optimization programs based on genetic algorithms.
9) Association Rule (Association Rules):
The Arules package provides a data structure that effectively handles sparse two metadata, and provides function Apriori and Eclat algorithms for mining frequent itemsets, maximum frequent itemsets, closed frequent itemsets, and association rules (http://cran.r-project.org/web/ packages/arules/index.html).
10) Model selection and validation (models selection and validation):
The tune () function of the e1071 package selects the appropriate parameter (http://cran.r-project.org/web/packages/e1071/index.html) within the specified range. The Errorest () function of the ipred package uses a resampling method (cross-validation, bootstrap) to estimate the classification error rate (http://cran.r-project.org/web/packages/ipred/index.html). The function in the Svmpath package can be used to select the cost parameter C (http://cran.r-project.org/web/packages/svmpath/index.html) of the support vector machine. The ROCR package provides functions for visualizing the performance of the classifier, such as the ROC Curve (http://cran.r-project.org/web/packages/ROCR/index.html). The caret package provides a variety of functions for establishing predictive models, including parameter selection and importance measurement (http://cran.r-project.org/web/packages/caret/index.html). CARETLSF Pack (http://cran.r-project.org/web/packages/caretLSF/index.html) and CARETNWS (http://cran.r-project.org/web/ packages/caretnws/index.html) package provides functionality similar to the caret package.
11) Basis of statistical learning (Elements of statistical learning):
Book "The Elements of statistical learning:data Mining, inference, and prediction" (http://www-stat.stanford.edu/~tibs/ elemstatlearn/) data sets, functions, and examples are packaged in the Elemstatlearn package (http://cran.r-project.org/web/packages/ElemStatLearn/ index.html).

Website: http://cran.r-project.org/web/views/MachineLearning.html Maintenance staff: Torsten Hothorn

R Language Machine Learning package