Understanding and Applying XGBoost Classification Trees in R

preview_player
Показать описание
===== Likes: 78 👍: Dislikes: 1 👎: 98.734% : Updated on 01-21-2023 11:57:17 EST =====
Ever wonder if you can score in the top leaderboards of any kaggle competition? Look on further! Check out the XGBoost Model, an ensemble boosting method, known for its powerful robustness. This is an industry grade model that is heavily applied in many industries. Knowing this algorithm can get your foot in the door in many industries containing Data Science!!!

Github link:

Data Set Link:

--------------------------------------------------
Additional Material to check out !

Ensemble Method Boosting:

Ensemble Method Stacking:

Ensemble Method Bagging:

Methods of Sampling:
--------------------------------------------------

0:00 - In-depth explanation of XGBoost
5:00 - Summary of XGBoost Algorithm
6:03 - Understanding Data & Applying XGBoost
11:20 - Explaining XGBoost Gridsearch Parameters
14:25 - TrainControl & Final model & Evaluation
Рекомендации по теме
Комментарии
Автор

Thank you for this video! Can you also show how to get variable importance?

annsu
Автор

Please help me, when I running the code I get an error message like this: .xgb.Dmatrix(x, 0, , drop=FALSE):unsused argument (drop=FALSE)

philippekamdem
Автор

Great video! Do you know how to get prediction or confidence interval for xgboost?

deannanuboshi
Автор

When I run my data into my predict, I can a value between 0 and 1. I assume this is a probability value. How do you decide which probability output is equal to "<50K" versus ">50K".

wereskiryan
Автор

What needs to be matrix type? Both train_x and train_y or train_y? I passed train_x as dataframe and train_y as vector (because it has only one column). Model runs just fine (i ran the model just like you did). However model at my end returned following variables. There is no Accuracy, Kappa. Any pointers? . My model code is below (it is same as in the video)
max_depth nrounds RMSE Rsquared MAE



grid_tune <- expand.grid(
nrounds=c(500, 100, 1500),
max_depth=c(2, 4, 6),
eta=0.3,
gamma=0,
colsample_bytree=1,
min_child_weight=1,
subsample=1)

train_control <- trainControl(method="cv",
number=3,
verboseIter=TRUE,
allowParallel=TRUE)

xgb_tune<-train(x=train_x,
y=as.numeric(train_y),
trControl=train_control,
tuneGrid=grid_tune,
method="xgbTree",
verbose=TRUE
)

xgb_tune

trishiasingla
Автор

How many model should be there in XGBoost ?

Stoic_might
Автор

so confusing, where is dtrain, dtest using xgb.DMatrix

adrianlandwonski