Machine learning for hackers reading notes (vi) regularization: text regression

data<-' f:\\learning\\ml_for_hackers\\ml_for_hackers-master\\06-regularization\\data\\ '

Ranks <-read.csv (file.path (data, ' oreilly.csv '), stringsasfactors = FALSE)

Library (' TM ')

Documents <-data.frame (Text = Ranks$long.desc.)
Row.names (documents) <-1:nrow (documents)

#获得语料库

Corpus <-Corpus (Dataframesource (documents))

#R2版本用corpus <-Tm_map (Corpus, ToLower)

Corpus <-Tm_map (Corpus, Content_transformer (ToLower))

#R2版本用corpus <-Tm_map (Corpus, Stripwhitespace)

Corpus <-Tm_map (Corpus, Content_transformer (Stripwhitespace))

#去除英文停用词
Corpus <-Tm_map (Corpus, Removewords, Stopwords (' 中文版 '))

#得到词项文档矩阵

DTM <-Documenttermmatrix (Corpus)

X <-As.matrix (DTM)
Y <-Rev (1:100) #反转1: 100, the result is 100. 1

Set.seed (1)

Library (' Glmnet ')

Performance <-Data.frame ()

For (Lambda in C (0.1, 0.25, 0.5, 1, 2, 5))
{
For (i-1:50)
{
Indices <-sample (1:100, 80)

Training.x <-X[indices,]
Training.y <-Y[indices]

Test.x <-X[-indices,]
Test.y <-Y[-indices]

Glm.fit <-glmnet (training.x, TRAINING.Y)

Predicted.y <-Predict (Glm.fit, test.x, s = lambda)

Rmse <-sqrt (Mean ((PREDICTED.Y-TEST.Y) ^ 2))

Performance <-Rbind (performance,data.frame (Lambda = lambda,iteration = I,rmse = RMSE))
}
}

Ggplot (Performance, AES (x = Lambda, y = RMSE)) +stat_summary (fun.data = ' Mean_cl_boot ', Geom = ' errorbar ') +

Stat_summary (fun.data = ' Mean_cl_boot ', Geom = ' point ')

#从图上看, failure

#失败了作分类, Judge if a book could be in the top 50.

Y <-Rep (c (1, 0), each = 50)

#作逻辑回归

Regularized.fit <-glmnet (x, y, family = ' binomial ')

#预测一下

Predict (regularized.fit, newx = x, s = 0.001)

#出来的结果并不是分类, but a bunch of numbers, so change

IfElse (Predict (regularized.fit, newx = x, s = 0.001) > 0, 1, 0)

#第二种方法, turn the predicted result into a probability value

Library (' Boot ')

Inv.logit (Predict (regularized.fit, newx = x, s = 0.001))

#看效果

Set.seed (1)

Performance <-Data.frame ()

For (i in 1:250)
{
Indices <-sample (1:100, 80)

Training.x <-X[indices,]
Training.y <-Y[indices]

Test.x <-X[-indices,]
Test.y <-Y[-indices]

For (Lambda in C (0.0001, 0.001, 0.0025, 0.005, 0.01, 0.025, 0.5, 0.1))
{
Glm.fit <-glmnet (training.x, training.y, family = ' binomial ')
Predicted.y <-IfElse (Predict (Glm.fit, test.x, s = lambda) > 0, 1, 0)
Error.rate <-mean (predicted.y! = test.y)

Performance <-Rbind (performance,data.frame (Lambda = lambda,iteration = I,errorrate = error.rate))

}
}

#画个图
Ggplot (Performance, AES (x = Lambda, y = errorrate)) +
Stat_summary (fun.data = ' Mean_cl_boot ', Geom = ' errorbar ') +
Stat_summary (fun.data = ' Mean_cl_boot ', Geom = ' point ') +scale_x_log10 ()

Machine learning for hackers reading notes (vi) regularization: text regression