yaqilu_assign7

.gitignore

@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata

Assignment7.Rmd

@@ -11,27 +11,43 @@ 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", head = TRUE)
 ```
 
 #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)
+D2 <- select(D1, 1:7)
+D2$level.up <- ifelse(D2$level.up == "yes", 1,0)
+D3 <- gather(D2, "measure", "score", 2:7)
 
-#Then visualize the relationships between variables
+p1 <- ggplot(D3, aes(score)) + facet_wrap(~measure, scales = "free")
+p1 + geom_histogram(stat = "count")
 
+#Then visualize the relationships between variables
+pairs(D2)
 #Try to capture an intution about the data and the relationships
 
 ```
 #Classification tree
 ```{r}
 #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)
 
+library(rpart)
+c.tree1 <- rpart(level.up ~ forum.posts + pre.test.score, method = "class", data = D1, control=rpart.control(minsplit=1, minbucket=1, cp=0.001))
+
 #Plot and generate a CP table for your tree 
 
+printcp(c.tree1)
+plot(c.tree1)
+text(c.tree1)
+
 #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.
@@ -44,7 +60,7 @@ plot(performance(pred.detail, "tpr", "fpr"))
 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
 
 #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?
 ```
@@ -53,15 +69,15 @@ unlist(slot(performance(Pred2,"auc"), "y.values"))#Unlist liberates the AUC valu
 ```{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 <- 
+threshold.pred1 <- ifelse(D1$pred >= 0.8, "yes", "no")
 
 #Now generate three diagnostics:
 
-D1$accuracy.model1 <-
+D1$accuracy.model1 <-mean(ifelse(D1$level.up == D1$threshold.pred1, 1, 0))
 
-D1$precision.model1 <- 
+D1$precision.model1 <- sum(D1$truepos.model1)/(sum(D1$truepos.model1) + sum(D1$falsepos.model1))
 
-D1$recall.model1 <- 
+D1$recall.model1 <- sum(D1$truepos.model1)/(sum(D1$truepos.model1) + sum(D1$falseneg.model1))
 
 #Finally, calculate Kappa for your model according to:
 

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