This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# 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) | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#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)) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# 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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# 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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
install.packages("relaimpo") | |
library(relaimpo) | |
#fit linear model: | |
Ozone_model <- lm(ozone_reading ~ . , data = Ozone) | |
#Get relative importance: | |
Relative_importance <- calc.relimp(lmMod, type = "lmg", rela = TRUE) | |
# Relative importance scaled to 100 and plot: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
install.packages('PerformanceAnalytics') | |
library(PerformanceAnalytics) | |
chart.Correlation(Ozone, histogram=TRUE, pch=19) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#read in data | |
Ozone <- read.csv("https://raw.githubusercontent.com/selva86/datasets/master/ozone.csv", stringsAsFactors=F) |
NewerOlder