BenHeubl

Keys,DeviceName,Uniqueness,Benefits,Website Link,DeviceDescription
246,3L Labs Footlogger,9,28,http://vandrico.com/node/246,"The 3L Labs Footlogger is a wearable fitness tracking device that aims at spotting health problems early, as well as logging daily activity. Placed in the user's shoe, 8 sensors coupled to 1 accelerometer help identify and record exercise habits. The data is then disclosed to the user via text or smartphone app. This computing device's technology can be used for athletes training, regular everyday workouts and rehabilitation."
387,4D Force,5,13,http://vandrico.com/node/387,"The 4D Force is a wearable technology that detects brain waves and converts them into electric signals. 4D Force developed a platform that can capture and compute high quality EEG/ EOG/EMG signals. With the device, users can control games by using the power of their thoughts. 4D Force can also be used for medical purposes as it has the ability to interpret electrical signals generated by the body, and create recommen

BenHeubl

boruta_signif <-names(boruta_output_Boruta$finalDecision[boruta_output_Boruta$finalDecision %in% c("Confirmed", "Tentative")])
print(boruta_signif)

#Plot:
plot(boruta_output_Boruta, cex.axis=.7, las=2, xlab="", main="Variable Importance")

BenHeubl

Brexit_test$pred <- predict(Brexit_model_final, Brexit_test, type = "class")
base_accuracy <- mean(Brexit_test$pred == Brexit_test$Percent.Leave)

base_accuracy

BenHeubl

model_random_forrest_optimal <- randomForest(INCOME ~ ., 
data = TrainSet,
ntree = 500, mtry = 3, 
importance = TRUE)

model_decision_RF = predict(model_random_forrest_optimal, data = TrainSet)
table(model_decision_RF, TrainSet$INCOME)
mean(model_decision_RF == TrainSet$INCOME)

#[1] 0.7757143

BenHeubl

install.packages("rpart")
install.packages("caret")
install.packages("e1071")
library(rpart)
library(caret)
library(e1071)

model_decision_tree = train(INCOME ~ ., data = TrainSet, method = "rpart")

model_decision_tree_prediction = predict(model_decision_tree, data = TrainSet)

BenHeubl

# Using For loop to identify the right mtry for model (this took around 4 minutes for me. Get yourself a drink :-)

accuracy_list =c()
for (i in 3:8) {
print(i)
model_optimal <- randomForest(INCOME ~ ., data = TrainSet, ntree = 500, mtry = i, importance = TRUE)
predValid <- predict(model_optimal, ValidSet, type = "class")
accuracy_list[i-2] = mean(predValid == ValidSet$INCOME)
}

BenHeubl

income <- read.csv("https://raw.githubusercontent.com/selva86/datasets/master/income.csv")

incomeR <- income %>%
mutate(INCOME = if_else(INCOME == "-10.000)", "Under 30k",
if_else(INCOME == "[10.000–15.000)", "Under 30k",
if_else(INCOME == "[15.000–20.000)", "Under 30k",
if_else(INCOME == "[20.000–25.000)", "Under 30k",
if_else(INCOME == "[25.000–30.000)", "Under 30k", 'Over 30k')))))) %>% mutate_if(is.factor, fct_explicit_na, na_level = 'Unknown') %>%
mutate(INCOME = as.factor(INCOME))

BenHeubl

#mode function
getmode <- function(v) {
 uniqv <- unique(v)
 uniqv[which.max(tabulate(match(v, uniqv)))]
}

incomeR_mode_income <- incomeR %>% 
 group_by(INCOME) %>%
 summarise(mode = getmode(OCCUPATION))
 

BenHeubl

# ggplotting our featuer importance:
Feature_importance <- importance(model_base)
var_Importance <- data.frame(Variables = row.names(Feature_importance), 
Importance = round(importance[ ,'MeanDecreaseGini'],2))

#Create ranks for variable based on importance
Rank_Importance <- var_Importance %>%
mutate(Rank = paste0('#',dense_rank(desc(Importance))))

#Relative importance of our varaibles

BenHeubl

# read in the data from github repo:
income <- read.csv("https://raw.githubusercontent.com/selva86/datasets/master/income.csv")

set.seed(100)

# We shuffle row-wise:
incomeR <- income[sample(nrow(income)),]

#check rownames (see above screenshot)
colnames(incomeR)