diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..5b6a065 --- /dev/null +++ b/.gitignore @@ -0,0 +1,4 @@ +.Rproj.user +.Rhistory +.RData +.Ruserdata diff --git a/Assignment7.Rmd b/Assignment7.Rmd index 105cbdf..3c68a55 100644 --- a/Assignment7.Rmd +++ b/Assignment7.Rmd @@ -1,7 +1,7 @@ --- title: "Assignment 7 - Answers" -author: "Charles Lang" -date: "11/30/2016" +author: "Ling Ai" +date: "12/2/2019" output: html_document --- @@ -11,60 +11,85 @@ In the following assignment you will be looking at data from an one level of an #Upload data ```{r} - +D1 <-read.csv("online.data.csv") ``` #Visualization ```{r} +library(ggplot2) +library(dplyr) +library(tidyr) #Start by creating histograms of the distributions for all variables (#HINT: look up "facet" in the ggplot documentation) +D1$level.up <- ifelse(D1$level.up == "yes",1,0) +D2 <- gather(D1, "variable", "score", 2:7) + +ggplot(D2, aes(score)) + facet_wrap(~variable, scales = "free") + geom_histogram() #Then visualize the relationships between variables +pairs(D1) #Try to capture an intution about the data and the relationships ``` #Classification tree ```{r} +library(rpart) #Create a classification tree that predicts whether a student "levels up" in the online course using three variables of your choice (As we did last time, set all controls to their minimums) +c.tree1 <- rpart(level.up ~ post.test.score + post.test.score + messages + forum.posts + av.assignment.score, method="class", data= D1) #Plot and generate a CP table for your tree +printcp(c.tree1) +post(c.tree1, file = "tree1.ps", title = "level up") #Generate a probability value that represents the probability that a student levels up based your classification tree -D1$pred <- predict(rp, type = "prob")[,2]#Last class we used type = "class" which predicted the classification for us, this time we are using type = "prob" to see the probability that our classififcation is based on. +D1$pred <- predict(c.tree1, type = "prob")[,2]#Last class we used type = "class" which predicted the classification for us, this time we are using type = "prob" to see the probability that our classififcation is based on. ``` ## Part II #Now you can generate the ROC curve for your model. You will need to install the package ROCR to do this. ```{r} +#install.packages("ROCR") library(ROCR) #Plot the curve pred.detail <- prediction(D1$pred, D1$level.up) -plot(performance(pred.detail, "tpr", "fpr")) +plot(performance(pred.detail, "tpr", "fpr")) #"tpr" true positive rate, "fpr" false positive rate abline(0, 1, lty = 2) #Calculate the Area Under the Curve -unlist(slot(performance(Pred2,"auc"), "y.values"))#Unlist liberates the AUC value from the "performance" object created by ROCR +unlist(slot(performance(pred.detail,"auc"), "y.values")) + +#Unlist liberates the AUC value from the "performance" object created by ROCR +#the area under the curve is 1 #Now repeat this process, but using the variables you did not use for the previous model and compare the plots & results of your two models. Which one do you think was the better model? Why? + +pred.detail1 <- prediction(D1$post.test.score, D1$level.up) +plot(performance(pred.detail1, "tpr", "fpr")) +abline(0, 1, lty = 2) +unlist(slot(performance(pred.detail1,"auc"), "y.values")) + +# The first model is better because it's AUC value is 1 and the second model has 0.919925. ``` ## Part III #Thresholds ```{r} #Look at the ROC plot for your first model. Based on this plot choose a probability threshold that balances capturing the most correct predictions against false positives. Then generate a new variable in your data set that classifies each student according to your chosen threshold. -threshold.pred1 <- +D1$threshold.pred1 <- ifelse(D1$pred >= 0.5, 1, 0) #Now generate three diagnostics: -D1$accuracy.model1 <- +D1$accuracy.model1 <- mean(ifelse(D1$level.up == D1$threshold.pred1, 1, 0)) +D1$accuracy.model1 <- as.integer(D1$accuracy.model1) +accuracy1 <- sum(D1$accuracy.model1) / length(D1$accuracy.model1) -D1$precision.model1 <- - -D1$recall.model1 <- +D1$precision.model1 <- ifelse(D1$level.up == 1 & D1$threshold.pred1 == 1, 1, 0) +precision1 <- sum(D1$precision.model1) / sum (D1$threshold.pred1) +D1$recall.model1 <- ifelse(D1$level.up == 1 & D1$threshold.pred1 == 1, 1, 0) +recall1 <- sum(D1$precision.model1) / sum(D1$level.up) #Finally, calculate Kappa for your model according to: - #First generate the table of comparisons table1 <- table(D1$level.up, D1$threshold.pred1) @@ -75,7 +100,23 @@ matrix1 <- as.matrix(table1) kappa(matrix1, exact = TRUE)/kappa(matrix1) #Now choose a different threshold value and repeat these diagnostics. What conclusions can you draw about your two thresholds? +D1$threshold.pred2 <- ifelse(D1$pred >= 0.9, 1, 0) + +D1$accuracy.model2 <- mean(ifelse(D1$level.up == D1$threshold.pred2, 1, 0)) +D1$accuracy.model2 <- as.integer(D1$accuracy.model2) +accuracy2 <- sum(D1$accuracy.model2) / length(D1$accuracy.model2) + +D1$precision.model2 <- ifelse(D1$level.up == 1 & D1$threshold.pred2 == 1, 1, 0) +precision2 <- sum(D1$precision.model2) / sum (D1$threshold.pred2) +D1$recall.model2 <- ifelse(D1$level.up == 1 & D1$threshold.pred2 == 1, 1, 0) +recall2 <- sum(D1$precision.model2) / sum(D1$level.up) + + +table2 <- table(D1$level.up, D1$threshold.pred2) +matrix2 <- as.matrix(table2) +kappa(matrix2, exact = TRUE)/kappa(matrix2) +#For two models the value of kappa are the same. ``` ### To Submit Your Assignment diff --git a/assignment7.Rproj b/assignment7.Rproj new file mode 100644 index 0000000..8e3c2eb --- /dev/null +++ b/assignment7.Rproj @@ -0,0 +1,13 @@ +Version: 1.0 + +RestoreWorkspace: Default +SaveWorkspace: Default +AlwaysSaveHistory: Default + +EnableCodeIndexing: Yes +UseSpacesForTab: Yes +NumSpacesForTab: 2 +Encoding: UTF-8 + +RnwWeave: Sweave +LaTeX: pdfLaTeX diff --git a/tree1.ps b/tree1.ps new file mode 100644 index 0000000..54ad3cf Binary files /dev/null and b/tree1.ps differ