Random Forest

Dropout RF.R

@@ -0,0 +1,128 @@
+library(tidyverse)
+library(caret)
+library(randomForest)
+
+dropout_clean <- read.csv("C:/Users/Mark/Desktop/Grad School/PDAT630/dropout_clean.csv")
+factor_cols=c("Marital.status","Scholarship.holder","Tuition.fees.up.to.date","Gender","Displaced","Daytime.evening.attendance","Course","Previous.qualification","Mother.s.qualification","Father.s.qualification","Mother.s.occupation","Father.s.occupation","International","Target")
+dropout_clean[factor_cols] <- lapply(dropout_clean[factor_cols], factor)
+str(dropout_clean)
+
+## Random Forest 1
+dropout_clean_rf1=dropout_clean
+str(dropout_clean_rf1)
+
+df.train1 <- sample_frac(dropout_clean_rf1, size = .85)
+df.test1 <- setdiff(dropout_clean_rf1, df.train1)
+
+dropout.rf1 <- randomForest(Target ~ ., 
+                           importance = TRUE,
+                           #proximity = TRUE,
+                           data = df.train1)
+print(dropout.rf1)
+pred1=predict(dropout.rf1, df.test1, type="response")
+print(confusionMatrix(as.factor(df.test1$Target), pred1)$overall[1])
+
+oob.error.data <- data.frame(
+  Trees=rep(1:nrow(dropout.rf1$err.rate), times=4),
+  Type=rep(c("OOB", "Dropout", "Enrolled",
+             "Graduate"), each=nrow(dropout.rf1$err.rate)),
+  Error=c(dropout.rf1$err.rate[,"OOB"], 
+          dropout.rf1$err.rate[,"Dropout"], 
+          dropout.rf1$err.rate[,"Enrolled"],
+          dropout.rf1$err.rate[,"Graduate"]))
+
+ggplot(data=oob.error.data, aes(x=Trees, y=Error)) +
+  geom_line(aes(color=Type))+
+  ggtitle("Random Forest #1 Error vs Number Of Trees")
+
+
+## Random Forest 2
+dropout_clean_rf2=dropout_clean
+str(dropout_clean_rf2)
+
+df.train2 <- sample_frac(dropout_clean_rf2, size = .85)
+df.test2 <- setdiff(dropout_clean_rf2, df.train2)
+
+dropout.rf2 <- randomForest(Target ~ ., 
+                            importance = TRUE,
+                            #proximity = TRUE,
+                            data = df.train2,
+                            mtry=2)
+print(dropout.rf2)
+pred2=predict(dropout.rf2, df.test2, type="response")
+print(confusionMatrix(as.factor(df.test2$Target), pred2)$overall[2])
+
+oob.error.data <- data.frame(
+  Trees=rep(1:nrow(dropout.rf2$err.rate), times=4),
+  Type=rep(c("OOB", "Dropout", "Enrolled",
+             "Graduate"), each=nrow(dropout.rf2$err.rate)),
+  Error=c(dropout.rf2$err.rate[,"OOB"], 
+          dropout.rf2$err.rate[,"Dropout"], 
+          dropout.rf2$err.rate[,"Enrolled"],
+          dropout.rf2$err.rate[,"Graduate"]))
+
+ggplot(data=oob.error.data, aes(x=Trees, y=Error)) +
+  geom_line(aes(color=Type))+
+  ggtitle("Random Forest #2 Error vs Number Of Trees")
+
+
+
+## Random Forest 3
+dropout_clean_rf3=mutate(dropout_clean, Target = factor(ifelse(Target == "Dropout", "Dropout", "Did Not Dropout")))
+str(dropout_clean_rf3)
+
+table(dropout_clean$Target)
+table(dropout_clean_rf3$Target)
+
+df.train3 <- sample_frac(dropout_clean_rf3, size = .85)
+df.test3 <- setdiff(dropout_clean_rf3, df.train3)
+
+dropout.rf3 <- randomForest(Target ~ ., 
+                           importance = TRUE,
+                           #proximity = TRUE,
+                           data = df.train3
+                           #keep.forest=TRUE,
+                           ,mtry=2
+                           )
+print(dropout.rf3)
+pred3=predict(dropout.rf3, df.test3, type="response")
+print(confusionMatrix(as.factor(df.test3$Target), pred3)$overall[1])
+
+oob.error.data <- data.frame(
+  Trees=rep(1:nrow(dropout.rf3$err.rate), times=3),
+  Type=rep(c("OOB", "Dropout", #"Enrolled",
+             "Did Not Dropout"), each=nrow(dropout.rf3$err.rate)),
+  Error=c(dropout.rf3$err.rate[,"OOB"], 
+          dropout.rf3$err.rate[,"Dropout"], 
+          #dropout.rf3$err.rate[,"Enrolled"],
+          dropout.rf3$err.rate[,"Did Not Dropout"]))
+
+ggplot(data=oob.error.data, aes(x=Trees, y=Error)) +
+  geom_line(aes(color=Type))+
+  ggtitle("Random Forest #3 Error vs Number Of Trees")
+
+
+varImpPlot(dropout.rf3,
+           main="Variable Importance Plot"
+           )
+
+
+oob.values <- vector(length=10)
+for(i in 1:10) {
+  temp.model <- randomForest(Target ~ ., data=df.train1,importance = TRUE, mtry=i)
+  oob.values[i] <- temp.model$err.rate[nrow(temp.model$err.rate),1]
+}
+oob.values
+## find the minimum error
+min(oob.values)
+## 2
+
+oob.values <- vector(length=10)
+for(i in 1:10) {
+  temp.model <- randomForest(Target ~ ., data=df.train3, mtry=i)
+  oob.values[i] <- temp.model$err.rate[nrow(temp.model$err.rate),1]
+}
+oob.values
+## find the minimum error
+min(oob.values)
+## 2