Created
September 18, 2016 12:43
-
-
Save yabyzq/f40f9f22fd3d78e2b86d9ffe516cde27 to your computer and use it in GitHub Desktop.
simple R algorithms
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#Prepare training and test data | |
test_index <- which (1:length(iris[,1])%% 5 == 0) | |
iris_train <- iris[-test_index, ] | |
iris_test <- iris[test_index, ] | |
library(car) | |
test_index <- which (1:nrow(Prestige)%% 4 == 0) | |
prestige_train <- Prestige[-test_index, ] | |
prestige_test <- Prestige[test_index, ] | |
#Linear Regression --log(income) + education | |
model.lm <- lm(prestige~., data = prestige_train) | |
predict.lm <- predict(model.lm , newdata = prestige_test) | |
summary(model.lm) | |
cor(predict.lm, prestige_test$prestige) | |
#Logistic Regression | |
newcol = data.frame(isSetosa=(iris_train$Species == 'setosa')) | |
traindata <- cbind(iris_train, newcol) | |
traindata[c(1,50,100),] | |
logisticModel <- glm(isSetosa ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width , data=traindata, family="binomial") | |
prob <- predict(logisticModel, newdata=iris_test, type='response') | |
table(prob>=0.5, iris_test$Species == 'setosa') | |
#Use regularisation | |
library(glmnet) | |
cv.fit <- cv.glmnet(as.matrix(prestige_train[,c(-4, -6)]), as.vector(prestige_train[,4]), | |
nlambda=100, alpha=0.7, family="gaussian") | |
plot(cv.fit) | |
coef(cv.fit) | |
prediction <- predict(cv.fit, newx=as.matrix(prestige_test[,c(-4, -6)])) | |
cor(prediction, as.vector(prestige_test[,4])) | |
#Neutral network | |
library(neuralnet) | |
nnet_iristrain <- cbind(iris_train, iris_train$Species == 'setosa') | |
nnet_iristrain <- cbind(nnet_iristrain, iris_train$Species == 'versicolor') | |
nnet_iristrain <- cbind(nnet_iristrain, iris_train$Species == 'virginica') | |
names(nnet_iristrain)[6:8] <- c('setosa', 'versicolor', 'virginica') | |
nn <- neuralnet(setosa+versicolor+virginica ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width, | |
data=nnet_iristrain, hidden=c(3)) | |
plot(nn) | |
mypredict <- compute(nn, iris_test[-5])$net.result | |
maxidx <- function(arr) { | |
return(which(arr == max(arr))) | |
} | |
idx <- apply(mypredict, c(1), maxidx) | |
prediction <- c('setosa', 'versicolor', 'virginica')[idx] | |
table(prediction, iris_test$Species) | |
#SVM | |
library(e1071) | |
tune <- tune.svm(Species~., data=iris_train, gamma=10^(-6:-1), cost=10^(1:4)) | |
summary(tune) | |
model <- svm(Species~., data=iris_train, method="C-classification", kernel="radial", probability=T, gamma=0.001, cost=10000) | |
prediction <- predict(model, iris_test, probability=T) | |
table(prediction, iris_test$Species) | |
#Bayesian | |
library(e1071) | |
model <- naiveBayes(Species~., data=iris_train) | |
prediction <- predict(model, iris_test[,-5]) | |
table(prediction, iris_test[,5]) | |
#KNN k | |
library(class) | |
train_input <- as.matrix(iris_train[,-5]) | |
train_output <- as.vector(iris_train[,5]) | |
test_input <- as.matrix(iris_test[,-5]) | |
prediction <- knn(train_input, test_input, train_output, k=3) | |
table(prediction, iris_test$Species) | |
#Decision Tree | |
library(rpart) | |
treemodel <- rpart(Species~., data=iris_train) | |
plot(treemodel) | |
text(treemodel, use.n=T) | |
prediction <- predict(treemodel, newdata=iris_test, type='class') | |
table(prediction, iris_test$Species) | |
#RF | |
library(randomForest) | |
model <- randomForest(Species~., data=iris_train, nTree=500) | |
prediction <- predict(model, newdata=iris_test, type='class') | |
table(prediction, iris_test$Species) | |
importance(model) | |
qplot(Petal.Length, Petal.Width, color=Species, data=iris_train) | |
qplot(Sepal.Length, Sepal.Wdith, color=Species, data=iris_train) | |
#Boosting | |
library(gbm) | |
newcol = data.frame(isVersicolor=(iris_train$Species=='versicolor')) | |
iris_train <- cbind(iris_train, newcol) | |
model <- gbm(isVersicolor ~ Sepal.Length + Sepal.Width + Petal.Length + Petal.Width, data=iris_train, | |
n.trees=1000, interaction.depth=2, distribution="bernoulli") | |
prediction <- predict.gbm(model, iris_test, type="response", n.trees=1000) | |
table(prediction>=0.5, iris_test$Species == 'versicolor') | |
summary(model) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment