C4.5,CART,randomforest的实践

#################################Weka-J48(C4.5)#################################

##############################R语言：C4.5######################################

###############################C5.0#############################

data(churn)

treeModel <- C5.0(x = churnTrain[, -20], y = churnTrain$churn)

treeModel

summary(treeModel)

ruleModel <- C5.0(churn ~ ., data = churnTrain, rules = TRUE)

ruleModel

summary(ruleModel)

##################J48#######################

data(iris)

View(iris)

str(iris)

dim(iris)

summary(iris)

#第二步：加载RWeka包

library(RWeka)

#第三步：使用C4.5决策树算法对iris数据集做分类

iris_j48 <- J48(Species ~ ., data = iris)

iris_j48

#第四步：决策树模型摘要分析

summary(iris_j48)

#第五步：模型的可视化

plot(iris_j48)

#第六步：irsi全部数据训练决策树模型的交叉验证

eval_j48 <- evaluate_Weka_classifier(iris_j48, numFolds = 10, complexity = FALSE, seed = 1, class = TRUE)

eval_j48

#第七步：Weka-control的了解

WOW("J48")

#第八步：建立成本敏感决策树分类模型

csc <- CostSensitiveClassifier(Species ~ ., data = iris, control = Weka_control(`cost-matrix` = matrix(c(0, 10, 0, 0, 0, 0, 0, 10, 0), ncol = 3), W = "weka.classifiers.trees.J48", M = TRUE))

eval_csc <- evaluate_Weka_classifier(csc, numFolds = 10, complexity = FALSE, seed = 1, class = TRUE)

eval_csc

##########################R语言：CART##########################################

library(rpart)

sol.rpart<-rpart(Sepal.Length~Sepal.Width+Petal.Length+Petal.Width,data=iris)

plot(sol.rpart,uniform=TRUE,compress=TRUE,lty=3,branch=0.7)

text(sol.rpart,all=TRUE,digits=7,use.n=TRUE,cex=0.9,xpd=TRUE)

####################R语言：RandomForest#################################

library(randomForest)

## Classification:

##data(iris)

set.seed(71)

iris.rf <- randomForest(Species ~ ., data=iris, importance=TRUE,

proximity=TRUE)

print(iris.rf)

## Look at variable importance:

round(importance(iris.rf), 2)

## Do MDS on 1 - proximity:

iris.mds <- cmdscale(1 - iris.rf$proximity, eig=TRUE)

op <- par(pty="s")

pairs(cbind(iris[,1:4], iris.mds$points), cex=0.6, gap=0,

col=c("red", "green", "blue")[as.numeric(iris$Species)],

main="Iris Data: Predictors and MDS of Proximity Based on RandomForest")

par(op)

print(iris.mds$GOF)

## The `unsupervised' case:

set.seed(17)

iris.urf <- randomForest(iris[, -5])

MDSplot(iris.urf, iris$Species)

## stratified sampling: draw 20, 30, and 20 of the species to grow each tree.

(iris.rf2 <- randomForest(iris[1:4], iris$Species,

sampsize=c(20, 30, 20)))

## Regression:

## data(airquality)

set.seed(131)

ozone.rf <- randomForest(Ozone ~ ., data=airquality, mtry=3,

importance=TRUE, na.action=na.omit)

print(ozone.rf)

## Show "importance" of variables: higher value mean more important:

round(importance(ozone.rf), 2)

## "x" can be a matrix instead of a data frame:

set.seed(17)

x <- matrix(runif(5e2), 100)

y <- gl(2, 50)

(myrf <- randomForest(x, y))

(predict(myrf, x))

## "complicated" formula:

(swiss.rf <- randomForest(sqrt(Fertility) ~ . - Catholic + I(Catholic < 50),

data=swiss))

(predict(swiss.rf, swiss))

## Test use of 32-level factor as a predictor:

set.seed(1)

x <- data.frame(x1=gl(53, 10), x2=runif(530), y=rnorm(530))

(rf1 <- randomForest(x[-3], x[[3]], ntree=10))

## Grow no more than 4 nodes per tree:

(treesize(randomForest(Species ~ ., data=iris, maxnodes=4, ntree=30)))

## test proximity in regression

iris.rrf <- randomForest(iris[-1], iris[[1]], ntree=101, proximity=TRUE, oob.prox=FALSE)

str(iris.rrf$proximity)

########################Weka:RandomForest######################################

#######################Matlab:RandomForest ###################################

%%%随机森林分类器(Random Forest)

Factor = TreeBagger(nTree, train_data, train_label);

[Predict_label,Scores] = predict(Factor, test_data);

%%%scores是语义向量(概率输出)

############################Python:RandomForest ################################

利用Python的两个模块，分别为pandas和scikit-learn来实现随机森林.

from sklearn.datasets import load_iris

from sklearn.ensemble import RandomForestClassifier

import pandas as pd

import numpy as np

iris = load_iris()

df = pd.DataFrame(iris.data, columns=iris.feature_names)

df['is_train'] = np.random.uniform(0, 1, len(df)) <= .75

df['species'] = pd.Factor(iris.target, iris.target_names)

df.head()

train, test = df[df['is_train']==True], df[df['is_train']==False]

features = df.columns[:4]

clf = RandomForestClassifier(n_jobs=2)

y, _ = pd.factorize(train['species'])

clf.fit(train[features], y)

preds = iris.target_names[clf.predict(test[features])]

pd.crosstab(test['species'], preds, rownames=['actual'], colnames=['preds'])