Upload New File

c97d2992 · Sanghoon · ff61d903 · c97d2992
Commit c97d2992 authored May 04, 2022 by Sanghoon
Hide whitespace changes
Inline Side-by-side

Showing with 108 additions and 0 deletions

VotingModel_code.R ...ve Bayes Classification/Voting Example/VotingModel_code.R +108 -0

No files found.
--- a/Crash Course on Naive Bayes Classification/Voting Example/VotingModel_code.R
+++ b/Crash Course on Naive Bayes Classification/Voting Example/VotingModel_code.R
+# Problem : Can these models be used to predict how lawmakers may vote?
+#Prepare a clean R environment in work space.
+rm(list=ls())
+#Use setwd() to navigate the data directory and specify desired folder. Here we are using Rstudio Editor directory.
+setwd(dirname(rstudioapi::getSourceEditorContext()$path))
+#Import our csv file data
+data=read.csv("VotingData.csv",header=TRUE) #Load data
+TrainingPct=0.6 #Percent of data to train model on
+TrainingSample=floor(TrainingPct*dim(data)[1])  #Number of observations to train the model on
+TestSample=dim(data)[1]-TrainingSample #Number of observations to test the model on
+TrainingData=data[1:TrainingSample,]  #Get the training data
+#Find probabilities associtaed with democrat voting
+DemData=subset(TrainingData,TrainingData$Party=="democrat")
+#Store All Probabilities in a Matrix (2 rows, across all votes)
+ProbMat=matrix(0,2,(dim(DemData)[2]-3+1+1))
+m=2 #Equivalent sample size for Laplacian correction
+p=1/2  #Prior probability for Laplacian correction
+for (j in 3:dim(DemData)[2])
+{
+  ProbMat[1,j-2]=(sum(DemData[,j]=="y")+m*p)/(dim(DemData)[1]+m)
+}
+#Find Probabilities Associated with Republican Voting
+GOPData=subset(TrainingData,TrainingData$Party=="republican")
+for (j in 3:dim(GOPData)[2])
+{
+  ProbMat[2,j-2]=(sum(GOPData[,j]=="y")+m*p)/(dim(GOPData)[1]+m)
+}
+#Tag on marignal probabilities
+FinalInd=dim(ProbMat)[2]
+ProbMat[1:2,FinalInd]=c(sum(TrainingData$Party=="democrat")/dim(TrainingData)[1],sum(TrainingData$Party=="republican")/dim(TrainingData)[1])
+colnames(ProbMat)=c(names(data)[3:dim(data)[2]],"MargProb")
+rownames(ProbMat)=unique(TrainingData$Party)
+TestData=data[(TrainingSample+1):dim(data)[1],]
+AssignedMat=matrix(0,dim(TestData)[1],3)
+#Use the NB classifier on test Data
+VotingModel_fn<-function(TestVec,ProbMat){
+  ProbTestMat=matrix(0,2,dim(ProbMat)[2])
+  #TestVec is the member of interests' vote record
+  for (j in 1:length(TestVec)){
+    for (k in 1:2){
+      #Compute probabilities if vote yes or no via if loop
+      if (TestVec[j]=="y"){
+        ProbTestMat[k,j]=ProbMat[k,j]
+      }  else  {
+        ProbTestMat[k,j]=1-ProbMat[k,j]
+      }
+    }
+  }
+  ProbTestMat[1:2,(length(TestVec)+1)]=ProbMat[1:2,(length(TestVec)+1)]
+  Probs=apply(ProbTestMat,1,prod)  #Compute product of probabilities for the candidate being of either party
+  ind=which.max(Probs)  #Find which probability is higher
+  AssignedVec=c(Probs,unique(TrainingData$Party)[ind])  #Probability of being a democrat, being a republican, and which one is assigned
+  return(list(AssignedVec=as.numeric(AssignedVec[1:2]),AssignedParty=AssignedVec[3]))  #Elements returned as a list.
+}
+for (i in 1:dim(TestData)[1]){
+  for (j in 3:dim(TestData)[2]){
+  TestVec=TestData[i,3:dim(TestData)[2]]
+  result<-VotingModel_fn(TestVec,ProbMat)
+  AssignedMat[i,]=c(as.numeric(result$AssignedVec),result$AssignedParty)
+  }
+}
+CheckMat=data.frame(cbind(TestData$Party,AssignedMat[,3]))
+colnames(CheckMat)=c("Actual","Assigned")
+Pct_Accuracy=sum(CheckMat$Actual==CheckMat$Assigned)/dim(TestData)[1]  #computes the percent accuracy
+print("Classifier Percent Accuracy") #Print our accuracy as percent value.
+print(Pct_Accuracy)
+Example=read.csv("ArbitraryMember.csv")
+result<-VotingModel_fn(Example,ProbMat)
+print(result)
+#Executing function in a sample data set to predict likelihood of voting
+Example=read.csv("ArbitraryMember.csv")  #load data
+result<-VotingModel_fn(Example,ProbMat)
+print(result)