Random Forest

TImporting Libray

library(randomForest)

## randomForest 4.6-14

## Type rfNews() to see new features/changes/bug fixes.

Loading Data into the dataframe from CSV

dataframe <- read.csv("~/AI/DataSet/DecisionTreeDataSet.csv",header=T, na.strings=c("","NA"))
names(dataframe)

## [1] "Temperature" "Outlook"     "Humidity"    "Windy"       "Golf"

Seperating Test and Train Data

train <- na.omit(dataframe)
test <- dataframe[is.na(dataframe$Golf),]

Visualizing train data

train

Visualizing test data where golf is to be predicted by decision tree later

test

rf <- randomForest(
  as.factor(Golf) ~ .,
  data=train,
  importance = TRUE
)

summary(rf)

##                 Length Class  Mode     
## call               4   -none- call     
## type               1   -none- character
## predicted         14   factor numeric  
## err.rate        1500   -none- numeric  
## confusion          6   -none- numeric  
## votes             28   matrix numeric  
## oob.times         14   -none- numeric  
## classes            2   -none- character
## importance        16   -none- numeric  
## importanceSD      12   -none- numeric  
## localImportance    0   -none- NULL     
## proximity          0   -none- NULL     
## ntree              1   -none- numeric  
## mtry               1   -none- numeric  
## forest            14   -none- list     
## y                 14   factor numeric  
## test               0   -none- NULL     
## inbag              0   -none- NULL     
## terms              3   terms  call

getTree(rf, 1, labelVar=TRUE)

importance(rf) 

##                    No         Yes MeanDecreaseAccuracy MeanDecreaseGini
## Temperature -5.011112 -5.03988484            -7.360167        0.6459323
## Outlook      6.660717  2.96561307             6.415526        2.2072407
## Humidity     4.622113 -0.51422958             2.596054        1.3663751
## Windy       -2.561929  0.09603357            -1.122286        1.0114805

predTrain <- predict(rf, test, type = "class")
test$Golf = predTrain
test