fit the “model” to the training data using that method

1、fit the “model” to the training data using that method;

# a）Import the data into R
load("C:/Users/Administrator/Desktop/作业/作业/作业/20141202-01/trainVariables.rda")
# b)  Data exploration
# plot missing values patterns
library(dfexplore)

## Loading required package: ggplot2

dfplot(trainVariables)

# Now,l let’s count the number of missing values on hourSent
sum(is.na(trainVariables$hourSent))

## [1] 1649

# percent of cases with missing values on hourSent
sum(is.na(trainVariables))/nrow(trainVariables)

## [1] 0.4053

# Handle missing values
# Remove the hourSent
trainVariables1<-trainVariables[,-14]
# Remove observations containing missing values
trainVariables1<-trainVariables1[complete.cases(trainVariables1),]
# c)  use the function rpart() in the rpart package to build the model
library(rpart)
m<-rpart(isSpam~.,data=trainVariables1,method="class")
# draw Decision Tree chart
plot(m)
text(m,all=TRUE,digits=7,use.n=TRUE,cex=0.9,xpd=TRUE)

2、look at the confusion matrix and compute the Type I and II errors;

# a) Using the rpart model to predict the isSpam of trainVariables1
pre<-predict(m,trainVariables1[,-29],type="class")
#  b) Compute confusion matrix
table(trainVariables1[,29],pre)

##        pre
##         FALSE TRUE
##   FALSE  4325  213
##   TRUE    349 1200

# c) Compute accuracy
sum(pre==trainVariables1$isSpam)/length(pre)

## [1] 0.9077

# d) Compute the Type I
# The false positive rate (FP) is the proportion of negatives cases that were incorrectly classified as positive, as calculated # usingthe equation:
table(trainVariables1[,29],pre)[2]/nrow(trainVariables1[trainVariables1$isSpam=="FALSE",])

## [1] 0.07691

# e) Compute the Type II
# The false negative rate (FN) is the proportion of positives cases that were incorrectly classified as negative, as calculated # using the equation:
table(trainVariables1[,29],pre)[3]/nrow(trainVariables1[trainVariables1$isSpam=="TRUE",])

## [1] 0.1375

3. explore the misclassified observations and comment on any interesting characteristics.Perform these steps with a classification tree, and separately for k-nearest neighbors (kNN). Compare the results for the two methods on the training data. Do not use the test data to create the classifiers!

# a) Write knn algorithm
distance.matrix<-function(df){
  distance<-matrix(rep(NA,nrow(df)^2),nrow=nrow(df))
  for(i in 1:nrow(df))
    {
    for(j in 1:nrow(df))
      {
      distance[i,j]<-sqrt((df[i,'X']-df[j,'X'])^2+(df[i,'Y']-df[j,'Y'])^2)
      }
    }
  return(distance)
}
k.nearest.neighbors<-function(i,distance,k=5){
  return(order(distance[i,])[2:(k+1)])
}
myknn<-function(df,k=5){
  distance<-distance.matrix(df)
  predictions<-rep(NA,nrow(df))
  for(i in 1:nrow(df)){
    indices<-k.nearest.neighbors(i,distance,k=k)
    predictions[i]<-ifelse(mean(df[indices,'Lables'])>0.5,1,0)
  }
  return(predictions)
}