StatsLearning Lect10 R trees B 111213

preview_player
Показать описание

  1. Data Science Analytics
Рекомендации по теме
StatsLearning Lect10 R 0:15:36

StatsLearning Lect10 R trees B 111213

StatsLearning Lect10 R 0:10:14

StatsLearning Lect10 R trees A 111213

StatsLearning Lect10 R 0:10:33

StatsLearning Lect10 R modelselection B 111213

StatsLearning Lect10 R 0:08:23

StatsLearning Lect10 R A LDA 111213

StatsLearning Lect10 R 0:05:02

StatsLearning Lect10 R B Knearest 111213

StatsLearning Lect10 R 0:11:22

StatsLearning Lect10 R C validation 111213

StatsLearning Lect10 R 0:10:15

StatsLearning Lect10 R classification1 111213

StatsLearning Lect10 R 0:05:33

StatsLearning Lect10 R modelselection C 111213

SMuRT - Store 0:04:07

SMuRT - Store Multi-dimensional Spacial data using R-Tree

StatsLearning Lect10 R 0:07:41

StatsLearning Lect10 R D bootstrap 111213

StatsLearning Chapter 10 0:12:37

StatsLearning Chapter 10 - part 1

StatsLearning Chapter 8 0:12:03

StatsLearning Chapter 8 - part 5

StatsLearning Lect12 R 0:10:14

StatsLearning Lect12 R SVM A 111213

StatsLearning R Unsupervised 0:06:34

StatsLearning R Unsupervised C 112713

Computer Science: R-tree 0:01:55

Computer Science: R-tree insertion procedure when leaf is full

The History and 0:59:02

The History and Use of R

StatsLearning Chapter 3 0:15:38

StatsLearning Chapter 3 - part 3

StatsLearning Chapter 5 0:10:08

StatsLearning Chapter 5 - part 3

25 Model selection 0:26:54

25 Model selection 3

Ridge regression vs. 0:05:18

Ridge regression vs. linear regression

#82: Scikit-learn 79:Supervised 0:48:40

#82: Scikit-learn 79:Supervised Learning 57: Intuition for Decision Trees

[12-min poster] BART: 0:14:37

[12-min poster] BART: Bayesian Additive Regression Trees - A Methodology Study

SQB7019 Week 9 2:06:52

SQB7019 Week 9 (SVM decision boundaries, validating classifier performance, cross validation)

Data Mining with 0:50:09

Data Mining with R - Lecture 9 (Cross Validation)

Комментарии
Автор

When I tried to run this code Today I have some difference, I guess it is because the updates in the packages, But one thing i couldn't solve was the line 107
"predmat <- predict(boost.Boston, newdata = Boston[-train], n.trees=n.trees)"

Throws me an error:
"Error in eval(predvars, data, env) : object 'zn' not found"

Haav
Автор

I think the obb and test curves appear switched.
Because in matplot you put (test.err, oob .err) but in legend you put ('OOB', 'Test'). Am I right?
This explains why the result was at first theoretically surprising.

leonardojose