Regularized Regression in R
Uploaded by
Yanbo PANRegularized Regression in R
Uploaded by
Yanbo PANR for Data Science Lecture 5
Chang Liu
R for Data Science Lecture 5
Contents
Regularized Regression 3
Ridge penalty . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Lasso penalty . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
Elastic Net Regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
K-nearest Neighbors Algorithm 46
Decision Tree 49
Bagging (extension: Random forest) 53
Unique Value 56
Length 57
Gsub 59
sampling 61
Stratified Sampling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61
Cluster Sampling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63
Systematic Sampling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64
Chang Liu 2
R for Data Science Lecture 5
Regularized Regression
Linear models (LMs) provide a simple, yet effective, approach to predictive modeling. Moreover,
when certain assumptions required by LMs are met (e.g., constant variance), the estimated
coefficients are unbiased and, of all linear unbiased estimates, have the lowest variance. However,
in today’s world, data sets being analyzed typically contain a large number of features. As the
number of features grow, certain assumptions typically break down and these models tend to
overfit the training data, causing our out of sample error to increase. Regularization methods
provide a means to constrain or regularize the estimated coefficients, which can reduce the
variance and decrease out of sample error.
Ridge penalty
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
Chang Liu 3
R for Data Science Lecture 5
## v ggplot2 3.3.6 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.1.1 v forcats 0.5.1
## Warning: package 'dplyr' was built under R version 4.0.5
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
#define response variable
y <- mtcars$hp
#define matrix of predictor variables
x <- [Link](mtcars[, c('mpg', 'wt', 'drat', 'qsec')])
Next, we’ll use the glmnet() function to fit the ridge regression model and specify alpha=0.
Note that setting alpha equal to 1 is equivalent to using Lasso Regression and setting alpha to
some value between 0 and 1 is equivalent to using an elastic net.
library(glmnet)
## Loading required package: Matrix
##
## Attaching package: 'Matrix'
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
## Loaded glmnet 4.0-2
#fit ridge regression model
model <- glmnet(x, y, alpha = 0)
#view summary of model
summary(model)
Chang Liu 4
R for Data Science Lecture 5
## Length Class Mode
## a0 100 -none- numeric
## beta 400 dgCMatrix S4
## df 100 -none- numeric
## dim 2 -none- numeric
## lambda 100 -none- numeric
## [Link] 100 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## call 4 -none- call
## nobs 1 -none- numeric
Next, we’ll identify the lambda value that produces the lowest test mean squared error (MSE)
by using k-fold cross-validation.
Fortunately, glmnet has the function [Link]() that automatically performs k-fold cross vali-
dation using k = 10 folds.
#perform k-fold cross-validation to find optimal lambda value
cv_model <- [Link](x, y, alpha = 0)
#find optimal lambda value that minimizes test MSE
best_lambda <- cv_model$[Link]
best_lambda
## [1] 13.27979
#produce plot of test MSE by lambda value
plot(cv_model)
Chang Liu 5
R for Data Science Lecture 5
5000 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4
Mean−Squared Error
3000
1000
2 4 6 8 10
Log(λ)
best_model <- glmnet(x, y, alpha = 0, lambda = best_lambda)
coef(best_model)
## 5 x 1 sparse Matrix of class "dgCMatrix"
## s0
## (Intercept) 470.705022
## mpg -3.280904
## wt 18.505501
## drat -2.468512
## qsec -17.298734
Chang Liu 6
R for Data Science Lecture 5
Lasso penalty
#define response variable
y <- mtcars$hp
#define matrix of predictor variables
x <- [Link](mtcars[, c('mpg', 'wt', 'drat', 'qsec')])
Next, we will use the glmnet() function to fit the lasso regression model and specify alpha=1.
Note that setting alpha equal to 0 is equivalent to using ridge regression and setting alpha to
some value between 0 and 1 is equivalent to using an elastic net.
To determine what value to use for lambda, we’ll perform k-fold cross-validation and identify
the lambda value that produces the lowest test mean squared error (MSE).
Note that the function [Link]() automatically performs k-fold cross validation using k = 10
folds.
Chang Liu 7
R for Data Science Lecture 5
library(glmnet)
#perform k-fold cross-validation to find optimal lambda value
cv_model <- [Link](x, y, alpha = 1)
#find optimal lambda value that minimizes test MSE
best_lambda <- cv_model$[Link]
best_lambda
## [1] 2.928367
#produce plot of test MSE by lambda value
plot(cv_model)
4 4 4 4 4 4 3 3 3 3 3 3 3 3 3 3 3 3 2 2 2 0
5000
Mean−Squared Error
3000
1000
−2 −1 0 1 2 3 4
Log(λ)
We can also use the final lasso regression model to make predictions on new observations.
#find coefficients of best model
best_model <- glmnet(x, y, alpha = 1, lambda = best_lambda)
coef(best_model)
## 5 x 1 sparse Matrix of class "dgCMatrix"
Chang Liu 8
R for Data Science Lecture 5
## s0
## (Intercept) 483.169999
## mpg -2.981768
## wt 21.029736
## drat .
## qsec -19.286215
#define new observation
new = matrix(c(24, 2.5, 3.5, 18.5), nrow=1, ncol=4)
#use lasso regression model to predict response value
predict(best_model, s = best_lambda, newx = new)
## 1
## [1,] 107.3869
Chang Liu 9
R for Data Science Lecture 5
Elastic Net Regression
#[Link]("dplyr")
#[Link]("glmnet")
#[Link]("ggplot2")
#[Link]("caret")
library(glmnet)
library(caret)
## Warning: package 'caret' was built under R version 4.0.5
## Loading required package: lattice
##
## Attaching package: 'caret'
Chang Liu 10
R for Data Science Lecture 5
## The following object is masked from 'package:purrr':
##
## lift
# X and Y datasets
Y <- mtcars %>%
select(disp) %>%
scale(center = TRUE, scale = FALSE) %>%
[Link]()
X<- mtcars %>%
select(-disp) %>%
[Link]()
# Model Building : Elastic Net Regression
control <- trainControl(method = "repeatedcv",
number = 5,
repeats = 5,
search = "random",
verboseIter = TRUE)
# Training ELastic Net Regression model
elastic_model <- train(disp ~ .,
data = cbind(Y, X),
method = "glmnet",
preProcess = c("center", "scale"),
tuneLength = 25,
trControl = control)
## + Fold1.Rep1: alpha=0.63950, lambda=0.004507
## - Fold1.Rep1: alpha=0.63950, lambda=0.004507
## + Fold1.Rep1: alpha=0.04530, lambda=0.016509
## - Fold1.Rep1: alpha=0.04530, lambda=0.016509
## + Fold1.Rep1: alpha=0.97420, lambda=0.004648
## - Fold1.Rep1: alpha=0.97420, lambda=0.004648
## + Fold1.Rep1: alpha=0.34773, lambda=0.060861
## - Fold1.Rep1: alpha=0.34773, lambda=0.060861
## + Fold1.Rep1: alpha=0.51433, lambda=0.001761
## - Fold1.Rep1: alpha=0.51433, lambda=0.001761
## + Fold1.Rep1: alpha=0.31833, lambda=0.479416
## - Fold1.Rep1: alpha=0.31833, lambda=0.479416
Chang Liu 11
R for Data Science Lecture 5
## + Fold1.Rep1: alpha=0.74806, lambda=0.327981
## - Fold1.Rep1: alpha=0.74806, lambda=0.327981
## + Fold1.Rep1: alpha=0.14914, lambda=0.028964
## - Fold1.Rep1: alpha=0.14914, lambda=0.028964
## + Fold1.Rep1: alpha=0.84515, lambda=0.897325
## - Fold1.Rep1: alpha=0.84515, lambda=0.897325
## + Fold1.Rep1: alpha=0.93503, lambda=0.082985
## - Fold1.Rep1: alpha=0.93503, lambda=0.082985
## + Fold1.Rep1: alpha=0.38077, lambda=1.148290
## - Fold1.Rep1: alpha=0.38077, lambda=1.148290
## + Fold1.Rep1: alpha=0.84280, lambda=0.045415
## - Fold1.Rep1: alpha=0.84280, lambda=0.045415
## + Fold1.Rep1: alpha=0.98348, lambda=0.006142
## - Fold1.Rep1: alpha=0.98348, lambda=0.006142
## + Fold1.Rep1: alpha=0.78895, lambda=0.042054
## - Fold1.Rep1: alpha=0.78895, lambda=0.042054
## + Fold1.Rep1: alpha=0.52859, lambda=0.428235
## - Fold1.Rep1: alpha=0.52859, lambda=0.428235
## + Fold1.Rep1: alpha=0.73053, lambda=0.015889
## - Fold1.Rep1: alpha=0.73053, lambda=0.015889
## + Fold1.Rep1: alpha=0.90284, lambda=0.445782
## - Fold1.Rep1: alpha=0.90284, lambda=0.445782
## + Fold1.Rep1: alpha=0.32570, lambda=0.081177
## - Fold1.Rep1: alpha=0.32570, lambda=0.081177
## + Fold1.Rep1: alpha=0.75140, lambda=0.561138
## - Fold1.Rep1: alpha=0.75140, lambda=0.561138
## + Fold1.Rep1: alpha=0.03599, lambda=0.001115
## - Fold1.Rep1: alpha=0.03599, lambda=0.001115
## + Fold1.Rep1: alpha=0.25504, lambda=2.954617
## - Fold1.Rep1: alpha=0.25504, lambda=2.954617
## + Fold1.Rep1: alpha=0.86475, lambda=0.043683
## - Fold1.Rep1: alpha=0.86475, lambda=0.043683
## + Fold1.Rep1: alpha=0.10863, lambda=0.154091
## - Fold1.Rep1: alpha=0.10863, lambda=0.154091
## + Fold1.Rep1: alpha=0.98116, lambda=7.405037
## - Fold1.Rep1: alpha=0.98116, lambda=7.405037
## + Fold1.Rep1: alpha=0.94388, lambda=0.002046
## - Fold1.Rep1: alpha=0.94388, lambda=0.002046
Chang Liu 12
R for Data Science Lecture 5
## + Fold2.Rep1: alpha=0.63950, lambda=0.004507
## - Fold2.Rep1: alpha=0.63950, lambda=0.004507
## + Fold2.Rep1: alpha=0.04530, lambda=0.016509
## - Fold2.Rep1: alpha=0.04530, lambda=0.016509
## + Fold2.Rep1: alpha=0.97420, lambda=0.004648
## - Fold2.Rep1: alpha=0.97420, lambda=0.004648
## + Fold2.Rep1: alpha=0.34773, lambda=0.060861
## - Fold2.Rep1: alpha=0.34773, lambda=0.060861
## + Fold2.Rep1: alpha=0.51433, lambda=0.001761
## - Fold2.Rep1: alpha=0.51433, lambda=0.001761
## + Fold2.Rep1: alpha=0.31833, lambda=0.479416
## - Fold2.Rep1: alpha=0.31833, lambda=0.479416
## + Fold2.Rep1: alpha=0.74806, lambda=0.327981
## - Fold2.Rep1: alpha=0.74806, lambda=0.327981
## + Fold2.Rep1: alpha=0.14914, lambda=0.028964
## - Fold2.Rep1: alpha=0.14914, lambda=0.028964
## + Fold2.Rep1: alpha=0.84515, lambda=0.897325
## - Fold2.Rep1: alpha=0.84515, lambda=0.897325
## + Fold2.Rep1: alpha=0.93503, lambda=0.082985
## - Fold2.Rep1: alpha=0.93503, lambda=0.082985
## + Fold2.Rep1: alpha=0.38077, lambda=1.148290
## - Fold2.Rep1: alpha=0.38077, lambda=1.148290
## + Fold2.Rep1: alpha=0.84280, lambda=0.045415
## - Fold2.Rep1: alpha=0.84280, lambda=0.045415
## + Fold2.Rep1: alpha=0.98348, lambda=0.006142
## - Fold2.Rep1: alpha=0.98348, lambda=0.006142
## + Fold2.Rep1: alpha=0.78895, lambda=0.042054
## - Fold2.Rep1: alpha=0.78895, lambda=0.042054
## + Fold2.Rep1: alpha=0.52859, lambda=0.428235
## - Fold2.Rep1: alpha=0.52859, lambda=0.428235
## + Fold2.Rep1: alpha=0.73053, lambda=0.015889
## - Fold2.Rep1: alpha=0.73053, lambda=0.015889
## + Fold2.Rep1: alpha=0.90284, lambda=0.445782
## - Fold2.Rep1: alpha=0.90284, lambda=0.445782
## + Fold2.Rep1: alpha=0.32570, lambda=0.081177
## - Fold2.Rep1: alpha=0.32570, lambda=0.081177
## + Fold2.Rep1: alpha=0.75140, lambda=0.561138
## - Fold2.Rep1: alpha=0.75140, lambda=0.561138
Chang Liu 13
R for Data Science Lecture 5
## + Fold2.Rep1: alpha=0.03599, lambda=0.001115
## - Fold2.Rep1: alpha=0.03599, lambda=0.001115
## + Fold2.Rep1: alpha=0.25504, lambda=2.954617
## - Fold2.Rep1: alpha=0.25504, lambda=2.954617
## + Fold2.Rep1: alpha=0.86475, lambda=0.043683
## - Fold2.Rep1: alpha=0.86475, lambda=0.043683
## + Fold2.Rep1: alpha=0.10863, lambda=0.154091
## - Fold2.Rep1: alpha=0.10863, lambda=0.154091
## + Fold2.Rep1: alpha=0.98116, lambda=7.405037
## - Fold2.Rep1: alpha=0.98116, lambda=7.405037
## + Fold2.Rep1: alpha=0.94388, lambda=0.002046
## - Fold2.Rep1: alpha=0.94388, lambda=0.002046
## + Fold3.Rep1: alpha=0.63950, lambda=0.004507
## - Fold3.Rep1: alpha=0.63950, lambda=0.004507
## + Fold3.Rep1: alpha=0.04530, lambda=0.016509
## - Fold3.Rep1: alpha=0.04530, lambda=0.016509
## + Fold3.Rep1: alpha=0.97420, lambda=0.004648
## - Fold3.Rep1: alpha=0.97420, lambda=0.004648
## + Fold3.Rep1: alpha=0.34773, lambda=0.060861
## - Fold3.Rep1: alpha=0.34773, lambda=0.060861
## + Fold3.Rep1: alpha=0.51433, lambda=0.001761
## - Fold3.Rep1: alpha=0.51433, lambda=0.001761
## + Fold3.Rep1: alpha=0.31833, lambda=0.479416
## - Fold3.Rep1: alpha=0.31833, lambda=0.479416
## + Fold3.Rep1: alpha=0.74806, lambda=0.327981
## - Fold3.Rep1: alpha=0.74806, lambda=0.327981
## + Fold3.Rep1: alpha=0.14914, lambda=0.028964
## - Fold3.Rep1: alpha=0.14914, lambda=0.028964
## + Fold3.Rep1: alpha=0.84515, lambda=0.897325
## - Fold3.Rep1: alpha=0.84515, lambda=0.897325
## + Fold3.Rep1: alpha=0.93503, lambda=0.082985
## - Fold3.Rep1: alpha=0.93503, lambda=0.082985
## + Fold3.Rep1: alpha=0.38077, lambda=1.148290
## - Fold3.Rep1: alpha=0.38077, lambda=1.148290
## + Fold3.Rep1: alpha=0.84280, lambda=0.045415
## - Fold3.Rep1: alpha=0.84280, lambda=0.045415
## + Fold3.Rep1: alpha=0.98348, lambda=0.006142
## - Fold3.Rep1: alpha=0.98348, lambda=0.006142
Chang Liu 14
R for Data Science Lecture 5
## + Fold3.Rep1: alpha=0.78895, lambda=0.042054
## - Fold3.Rep1: alpha=0.78895, lambda=0.042054
## + Fold3.Rep1: alpha=0.52859, lambda=0.428235
## - Fold3.Rep1: alpha=0.52859, lambda=0.428235
## + Fold3.Rep1: alpha=0.73053, lambda=0.015889
## - Fold3.Rep1: alpha=0.73053, lambda=0.015889
## + Fold3.Rep1: alpha=0.90284, lambda=0.445782
## - Fold3.Rep1: alpha=0.90284, lambda=0.445782
## + Fold3.Rep1: alpha=0.32570, lambda=0.081177
## - Fold3.Rep1: alpha=0.32570, lambda=0.081177
## + Fold3.Rep1: alpha=0.75140, lambda=0.561138
## - Fold3.Rep1: alpha=0.75140, lambda=0.561138
## + Fold3.Rep1: alpha=0.03599, lambda=0.001115
## - Fold3.Rep1: alpha=0.03599, lambda=0.001115
## + Fold3.Rep1: alpha=0.25504, lambda=2.954617
## - Fold3.Rep1: alpha=0.25504, lambda=2.954617
## + Fold3.Rep1: alpha=0.86475, lambda=0.043683
## - Fold3.Rep1: alpha=0.86475, lambda=0.043683
## + Fold3.Rep1: alpha=0.10863, lambda=0.154091
## - Fold3.Rep1: alpha=0.10863, lambda=0.154091
## + Fold3.Rep1: alpha=0.98116, lambda=7.405037
## - Fold3.Rep1: alpha=0.98116, lambda=7.405037
## + Fold3.Rep1: alpha=0.94388, lambda=0.002046
## - Fold3.Rep1: alpha=0.94388, lambda=0.002046
## + Fold4.Rep1: alpha=0.63950, lambda=0.004507
## - Fold4.Rep1: alpha=0.63950, lambda=0.004507
## + Fold4.Rep1: alpha=0.04530, lambda=0.016509
## - Fold4.Rep1: alpha=0.04530, lambda=0.016509
## + Fold4.Rep1: alpha=0.97420, lambda=0.004648
## - Fold4.Rep1: alpha=0.97420, lambda=0.004648
## + Fold4.Rep1: alpha=0.34773, lambda=0.060861
## - Fold4.Rep1: alpha=0.34773, lambda=0.060861
## + Fold4.Rep1: alpha=0.51433, lambda=0.001761
## - Fold4.Rep1: alpha=0.51433, lambda=0.001761
## + Fold4.Rep1: alpha=0.31833, lambda=0.479416
## - Fold4.Rep1: alpha=0.31833, lambda=0.479416
## + Fold4.Rep1: alpha=0.74806, lambda=0.327981
## - Fold4.Rep1: alpha=0.74806, lambda=0.327981
Chang Liu 15
R for Data Science Lecture 5
## + Fold4.Rep1: alpha=0.14914, lambda=0.028964
## - Fold4.Rep1: alpha=0.14914, lambda=0.028964
## + Fold4.Rep1: alpha=0.84515, lambda=0.897325
## - Fold4.Rep1: alpha=0.84515, lambda=0.897325
## + Fold4.Rep1: alpha=0.93503, lambda=0.082985
## - Fold4.Rep1: alpha=0.93503, lambda=0.082985
## + Fold4.Rep1: alpha=0.38077, lambda=1.148290
## - Fold4.Rep1: alpha=0.38077, lambda=1.148290
## + Fold4.Rep1: alpha=0.84280, lambda=0.045415
## - Fold4.Rep1: alpha=0.84280, lambda=0.045415
## + Fold4.Rep1: alpha=0.98348, lambda=0.006142
## - Fold4.Rep1: alpha=0.98348, lambda=0.006142
## + Fold4.Rep1: alpha=0.78895, lambda=0.042054
## - Fold4.Rep1: alpha=0.78895, lambda=0.042054
## + Fold4.Rep1: alpha=0.52859, lambda=0.428235
## - Fold4.Rep1: alpha=0.52859, lambda=0.428235
## + Fold4.Rep1: alpha=0.73053, lambda=0.015889
## - Fold4.Rep1: alpha=0.73053, lambda=0.015889
## + Fold4.Rep1: alpha=0.90284, lambda=0.445782
## - Fold4.Rep1: alpha=0.90284, lambda=0.445782
## + Fold4.Rep1: alpha=0.32570, lambda=0.081177
## - Fold4.Rep1: alpha=0.32570, lambda=0.081177
## + Fold4.Rep1: alpha=0.75140, lambda=0.561138
## - Fold4.Rep1: alpha=0.75140, lambda=0.561138
## + Fold4.Rep1: alpha=0.03599, lambda=0.001115
## - Fold4.Rep1: alpha=0.03599, lambda=0.001115
## + Fold4.Rep1: alpha=0.25504, lambda=2.954617
## - Fold4.Rep1: alpha=0.25504, lambda=2.954617
## + Fold4.Rep1: alpha=0.86475, lambda=0.043683
## - Fold4.Rep1: alpha=0.86475, lambda=0.043683
## + Fold4.Rep1: alpha=0.10863, lambda=0.154091
## - Fold4.Rep1: alpha=0.10863, lambda=0.154091
## + Fold4.Rep1: alpha=0.98116, lambda=7.405037
## - Fold4.Rep1: alpha=0.98116, lambda=7.405037
## + Fold4.Rep1: alpha=0.94388, lambda=0.002046
## - Fold4.Rep1: alpha=0.94388, lambda=0.002046
## + Fold5.Rep1: alpha=0.63950, lambda=0.004507
## - Fold5.Rep1: alpha=0.63950, lambda=0.004507
Chang Liu 16
R for Data Science Lecture 5
## + Fold5.Rep1: alpha=0.04530, lambda=0.016509
## - Fold5.Rep1: alpha=0.04530, lambda=0.016509
## + Fold5.Rep1: alpha=0.97420, lambda=0.004648
## - Fold5.Rep1: alpha=0.97420, lambda=0.004648
## + Fold5.Rep1: alpha=0.34773, lambda=0.060861
## - Fold5.Rep1: alpha=0.34773, lambda=0.060861
## + Fold5.Rep1: alpha=0.51433, lambda=0.001761
## - Fold5.Rep1: alpha=0.51433, lambda=0.001761
## + Fold5.Rep1: alpha=0.31833, lambda=0.479416
## - Fold5.Rep1: alpha=0.31833, lambda=0.479416
## + Fold5.Rep1: alpha=0.74806, lambda=0.327981
## - Fold5.Rep1: alpha=0.74806, lambda=0.327981
## + Fold5.Rep1: alpha=0.14914, lambda=0.028964
## - Fold5.Rep1: alpha=0.14914, lambda=0.028964
## + Fold5.Rep1: alpha=0.84515, lambda=0.897325
## - Fold5.Rep1: alpha=0.84515, lambda=0.897325
## + Fold5.Rep1: alpha=0.93503, lambda=0.082985
## - Fold5.Rep1: alpha=0.93503, lambda=0.082985
## + Fold5.Rep1: alpha=0.38077, lambda=1.148290
## - Fold5.Rep1: alpha=0.38077, lambda=1.148290
## + Fold5.Rep1: alpha=0.84280, lambda=0.045415
## - Fold5.Rep1: alpha=0.84280, lambda=0.045415
## + Fold5.Rep1: alpha=0.98348, lambda=0.006142
## - Fold5.Rep1: alpha=0.98348, lambda=0.006142
## + Fold5.Rep1: alpha=0.78895, lambda=0.042054
## - Fold5.Rep1: alpha=0.78895, lambda=0.042054
## + Fold5.Rep1: alpha=0.52859, lambda=0.428235
## - Fold5.Rep1: alpha=0.52859, lambda=0.428235
## + Fold5.Rep1: alpha=0.73053, lambda=0.015889
## - Fold5.Rep1: alpha=0.73053, lambda=0.015889
## + Fold5.Rep1: alpha=0.90284, lambda=0.445782
## - Fold5.Rep1: alpha=0.90284, lambda=0.445782
## + Fold5.Rep1: alpha=0.32570, lambda=0.081177
## - Fold5.Rep1: alpha=0.32570, lambda=0.081177
## + Fold5.Rep1: alpha=0.75140, lambda=0.561138
## - Fold5.Rep1: alpha=0.75140, lambda=0.561138
## + Fold5.Rep1: alpha=0.03599, lambda=0.001115
## - Fold5.Rep1: alpha=0.03599, lambda=0.001115
Chang Liu 17
R for Data Science Lecture 5
## + Fold5.Rep1: alpha=0.25504, lambda=2.954617
## - Fold5.Rep1: alpha=0.25504, lambda=2.954617
## + Fold5.Rep1: alpha=0.86475, lambda=0.043683
## - Fold5.Rep1: alpha=0.86475, lambda=0.043683
## + Fold5.Rep1: alpha=0.10863, lambda=0.154091
## - Fold5.Rep1: alpha=0.10863, lambda=0.154091
## + Fold5.Rep1: alpha=0.98116, lambda=7.405037
## - Fold5.Rep1: alpha=0.98116, lambda=7.405037
## + Fold5.Rep1: alpha=0.94388, lambda=0.002046
## - Fold5.Rep1: alpha=0.94388, lambda=0.002046
## + Fold1.Rep2: alpha=0.63950, lambda=0.004507
## - Fold1.Rep2: alpha=0.63950, lambda=0.004507
## + Fold1.Rep2: alpha=0.04530, lambda=0.016509
## - Fold1.Rep2: alpha=0.04530, lambda=0.016509
## + Fold1.Rep2: alpha=0.97420, lambda=0.004648
## - Fold1.Rep2: alpha=0.97420, lambda=0.004648
## + Fold1.Rep2: alpha=0.34773, lambda=0.060861
## - Fold1.Rep2: alpha=0.34773, lambda=0.060861
## + Fold1.Rep2: alpha=0.51433, lambda=0.001761
## - Fold1.Rep2: alpha=0.51433, lambda=0.001761
## + Fold1.Rep2: alpha=0.31833, lambda=0.479416
## - Fold1.Rep2: alpha=0.31833, lambda=0.479416
## + Fold1.Rep2: alpha=0.74806, lambda=0.327981
## - Fold1.Rep2: alpha=0.74806, lambda=0.327981
## + Fold1.Rep2: alpha=0.14914, lambda=0.028964
## - Fold1.Rep2: alpha=0.14914, lambda=0.028964
## + Fold1.Rep2: alpha=0.84515, lambda=0.897325
## - Fold1.Rep2: alpha=0.84515, lambda=0.897325
## + Fold1.Rep2: alpha=0.93503, lambda=0.082985
## - Fold1.Rep2: alpha=0.93503, lambda=0.082985
## + Fold1.Rep2: alpha=0.38077, lambda=1.148290
## - Fold1.Rep2: alpha=0.38077, lambda=1.148290
## + Fold1.Rep2: alpha=0.84280, lambda=0.045415
## - Fold1.Rep2: alpha=0.84280, lambda=0.045415
## + Fold1.Rep2: alpha=0.98348, lambda=0.006142
## - Fold1.Rep2: alpha=0.98348, lambda=0.006142
## + Fold1.Rep2: alpha=0.78895, lambda=0.042054
## - Fold1.Rep2: alpha=0.78895, lambda=0.042054
Chang Liu 18
R for Data Science Lecture 5
## + Fold1.Rep2: alpha=0.52859, lambda=0.428235
## - Fold1.Rep2: alpha=0.52859, lambda=0.428235
## + Fold1.Rep2: alpha=0.73053, lambda=0.015889
## - Fold1.Rep2: alpha=0.73053, lambda=0.015889
## + Fold1.Rep2: alpha=0.90284, lambda=0.445782
## - Fold1.Rep2: alpha=0.90284, lambda=0.445782
## + Fold1.Rep2: alpha=0.32570, lambda=0.081177
## - Fold1.Rep2: alpha=0.32570, lambda=0.081177
## + Fold1.Rep2: alpha=0.75140, lambda=0.561138
## - Fold1.Rep2: alpha=0.75140, lambda=0.561138
## + Fold1.Rep2: alpha=0.03599, lambda=0.001115
## - Fold1.Rep2: alpha=0.03599, lambda=0.001115
## + Fold1.Rep2: alpha=0.25504, lambda=2.954617
## - Fold1.Rep2: alpha=0.25504, lambda=2.954617
## + Fold1.Rep2: alpha=0.86475, lambda=0.043683
## - Fold1.Rep2: alpha=0.86475, lambda=0.043683
## + Fold1.Rep2: alpha=0.10863, lambda=0.154091
## - Fold1.Rep2: alpha=0.10863, lambda=0.154091
## + Fold1.Rep2: alpha=0.98116, lambda=7.405037
## - Fold1.Rep2: alpha=0.98116, lambda=7.405037
## + Fold1.Rep2: alpha=0.94388, lambda=0.002046
## - Fold1.Rep2: alpha=0.94388, lambda=0.002046
## + Fold2.Rep2: alpha=0.63950, lambda=0.004507
## - Fold2.Rep2: alpha=0.63950, lambda=0.004507
## + Fold2.Rep2: alpha=0.04530, lambda=0.016509
## - Fold2.Rep2: alpha=0.04530, lambda=0.016509
## + Fold2.Rep2: alpha=0.97420, lambda=0.004648
## - Fold2.Rep2: alpha=0.97420, lambda=0.004648
## + Fold2.Rep2: alpha=0.34773, lambda=0.060861
## - Fold2.Rep2: alpha=0.34773, lambda=0.060861
## + Fold2.Rep2: alpha=0.51433, lambda=0.001761
## - Fold2.Rep2: alpha=0.51433, lambda=0.001761
## + Fold2.Rep2: alpha=0.31833, lambda=0.479416
## - Fold2.Rep2: alpha=0.31833, lambda=0.479416
## + Fold2.Rep2: alpha=0.74806, lambda=0.327981
## - Fold2.Rep2: alpha=0.74806, lambda=0.327981
## + Fold2.Rep2: alpha=0.14914, lambda=0.028964
## - Fold2.Rep2: alpha=0.14914, lambda=0.028964
Chang Liu 19
R for Data Science Lecture 5
## + Fold2.Rep2: alpha=0.84515, lambda=0.897325
## - Fold2.Rep2: alpha=0.84515, lambda=0.897325
## + Fold2.Rep2: alpha=0.93503, lambda=0.082985
## - Fold2.Rep2: alpha=0.93503, lambda=0.082985
## + Fold2.Rep2: alpha=0.38077, lambda=1.148290
## - Fold2.Rep2: alpha=0.38077, lambda=1.148290
## + Fold2.Rep2: alpha=0.84280, lambda=0.045415
## - Fold2.Rep2: alpha=0.84280, lambda=0.045415
## + Fold2.Rep2: alpha=0.98348, lambda=0.006142
## - Fold2.Rep2: alpha=0.98348, lambda=0.006142
## + Fold2.Rep2: alpha=0.78895, lambda=0.042054
## - Fold2.Rep2: alpha=0.78895, lambda=0.042054
## + Fold2.Rep2: alpha=0.52859, lambda=0.428235
## - Fold2.Rep2: alpha=0.52859, lambda=0.428235
## + Fold2.Rep2: alpha=0.73053, lambda=0.015889
## - Fold2.Rep2: alpha=0.73053, lambda=0.015889
## + Fold2.Rep2: alpha=0.90284, lambda=0.445782
## - Fold2.Rep2: alpha=0.90284, lambda=0.445782
## + Fold2.Rep2: alpha=0.32570, lambda=0.081177
## - Fold2.Rep2: alpha=0.32570, lambda=0.081177
## + Fold2.Rep2: alpha=0.75140, lambda=0.561138
## - Fold2.Rep2: alpha=0.75140, lambda=0.561138
## + Fold2.Rep2: alpha=0.03599, lambda=0.001115
## - Fold2.Rep2: alpha=0.03599, lambda=0.001115
## + Fold2.Rep2: alpha=0.25504, lambda=2.954617
## - Fold2.Rep2: alpha=0.25504, lambda=2.954617
## + Fold2.Rep2: alpha=0.86475, lambda=0.043683
## - Fold2.Rep2: alpha=0.86475, lambda=0.043683
## + Fold2.Rep2: alpha=0.10863, lambda=0.154091
## - Fold2.Rep2: alpha=0.10863, lambda=0.154091
## + Fold2.Rep2: alpha=0.98116, lambda=7.405037
## - Fold2.Rep2: alpha=0.98116, lambda=7.405037
## + Fold2.Rep2: alpha=0.94388, lambda=0.002046
## - Fold2.Rep2: alpha=0.94388, lambda=0.002046
## + Fold3.Rep2: alpha=0.63950, lambda=0.004507
## - Fold3.Rep2: alpha=0.63950, lambda=0.004507
## + Fold3.Rep2: alpha=0.04530, lambda=0.016509
## - Fold3.Rep2: alpha=0.04530, lambda=0.016509
Chang Liu 20
R for Data Science Lecture 5
## + Fold3.Rep2: alpha=0.97420, lambda=0.004648
## - Fold3.Rep2: alpha=0.97420, lambda=0.004648
## + Fold3.Rep2: alpha=0.34773, lambda=0.060861
## - Fold3.Rep2: alpha=0.34773, lambda=0.060861
## + Fold3.Rep2: alpha=0.51433, lambda=0.001761
## - Fold3.Rep2: alpha=0.51433, lambda=0.001761
## + Fold3.Rep2: alpha=0.31833, lambda=0.479416
## - Fold3.Rep2: alpha=0.31833, lambda=0.479416
## + Fold3.Rep2: alpha=0.74806, lambda=0.327981
## - Fold3.Rep2: alpha=0.74806, lambda=0.327981
## + Fold3.Rep2: alpha=0.14914, lambda=0.028964
## - Fold3.Rep2: alpha=0.14914, lambda=0.028964
## + Fold3.Rep2: alpha=0.84515, lambda=0.897325
## - Fold3.Rep2: alpha=0.84515, lambda=0.897325
## + Fold3.Rep2: alpha=0.93503, lambda=0.082985
## - Fold3.Rep2: alpha=0.93503, lambda=0.082985
## + Fold3.Rep2: alpha=0.38077, lambda=1.148290
## - Fold3.Rep2: alpha=0.38077, lambda=1.148290
## + Fold3.Rep2: alpha=0.84280, lambda=0.045415
## - Fold3.Rep2: alpha=0.84280, lambda=0.045415
## + Fold3.Rep2: alpha=0.98348, lambda=0.006142
## - Fold3.Rep2: alpha=0.98348, lambda=0.006142
## + Fold3.Rep2: alpha=0.78895, lambda=0.042054
## - Fold3.Rep2: alpha=0.78895, lambda=0.042054
## + Fold3.Rep2: alpha=0.52859, lambda=0.428235
## - Fold3.Rep2: alpha=0.52859, lambda=0.428235
## + Fold3.Rep2: alpha=0.73053, lambda=0.015889
## - Fold3.Rep2: alpha=0.73053, lambda=0.015889
## + Fold3.Rep2: alpha=0.90284, lambda=0.445782
## - Fold3.Rep2: alpha=0.90284, lambda=0.445782
## + Fold3.Rep2: alpha=0.32570, lambda=0.081177
## - Fold3.Rep2: alpha=0.32570, lambda=0.081177
## + Fold3.Rep2: alpha=0.75140, lambda=0.561138
## - Fold3.Rep2: alpha=0.75140, lambda=0.561138
## + Fold3.Rep2: alpha=0.03599, lambda=0.001115
## - Fold3.Rep2: alpha=0.03599, lambda=0.001115
## + Fold3.Rep2: alpha=0.25504, lambda=2.954617
## - Fold3.Rep2: alpha=0.25504, lambda=2.954617
Chang Liu 21
R for Data Science Lecture 5
## + Fold3.Rep2: alpha=0.86475, lambda=0.043683
## - Fold3.Rep2: alpha=0.86475, lambda=0.043683
## + Fold3.Rep2: alpha=0.10863, lambda=0.154091
## - Fold3.Rep2: alpha=0.10863, lambda=0.154091
## + Fold3.Rep2: alpha=0.98116, lambda=7.405037
## - Fold3.Rep2: alpha=0.98116, lambda=7.405037
## + Fold3.Rep2: alpha=0.94388, lambda=0.002046
## - Fold3.Rep2: alpha=0.94388, lambda=0.002046
## + Fold4.Rep2: alpha=0.63950, lambda=0.004507
## - Fold4.Rep2: alpha=0.63950, lambda=0.004507
## + Fold4.Rep2: alpha=0.04530, lambda=0.016509
## - Fold4.Rep2: alpha=0.04530, lambda=0.016509
## + Fold4.Rep2: alpha=0.97420, lambda=0.004648
## - Fold4.Rep2: alpha=0.97420, lambda=0.004648
## + Fold4.Rep2: alpha=0.34773, lambda=0.060861
## - Fold4.Rep2: alpha=0.34773, lambda=0.060861
## + Fold4.Rep2: alpha=0.51433, lambda=0.001761
## - Fold4.Rep2: alpha=0.51433, lambda=0.001761
## + Fold4.Rep2: alpha=0.31833, lambda=0.479416
## - Fold4.Rep2: alpha=0.31833, lambda=0.479416
## + Fold4.Rep2: alpha=0.74806, lambda=0.327981
## - Fold4.Rep2: alpha=0.74806, lambda=0.327981
## + Fold4.Rep2: alpha=0.14914, lambda=0.028964
## - Fold4.Rep2: alpha=0.14914, lambda=0.028964
## + Fold4.Rep2: alpha=0.84515, lambda=0.897325
## - Fold4.Rep2: alpha=0.84515, lambda=0.897325
## + Fold4.Rep2: alpha=0.93503, lambda=0.082985
## - Fold4.Rep2: alpha=0.93503, lambda=0.082985
## + Fold4.Rep2: alpha=0.38077, lambda=1.148290
## - Fold4.Rep2: alpha=0.38077, lambda=1.148290
## + Fold4.Rep2: alpha=0.84280, lambda=0.045415
## - Fold4.Rep2: alpha=0.84280, lambda=0.045415
## + Fold4.Rep2: alpha=0.98348, lambda=0.006142
## - Fold4.Rep2: alpha=0.98348, lambda=0.006142
## + Fold4.Rep2: alpha=0.78895, lambda=0.042054
## - Fold4.Rep2: alpha=0.78895, lambda=0.042054
## + Fold4.Rep2: alpha=0.52859, lambda=0.428235
## - Fold4.Rep2: alpha=0.52859, lambda=0.428235
Chang Liu 22
R for Data Science Lecture 5
## + Fold4.Rep2: alpha=0.73053, lambda=0.015889
## - Fold4.Rep2: alpha=0.73053, lambda=0.015889
## + Fold4.Rep2: alpha=0.90284, lambda=0.445782
## - Fold4.Rep2: alpha=0.90284, lambda=0.445782
## + Fold4.Rep2: alpha=0.32570, lambda=0.081177
## - Fold4.Rep2: alpha=0.32570, lambda=0.081177
## + Fold4.Rep2: alpha=0.75140, lambda=0.561138
## - Fold4.Rep2: alpha=0.75140, lambda=0.561138
## + Fold4.Rep2: alpha=0.03599, lambda=0.001115
## - Fold4.Rep2: alpha=0.03599, lambda=0.001115
## + Fold4.Rep2: alpha=0.25504, lambda=2.954617
## - Fold4.Rep2: alpha=0.25504, lambda=2.954617
## + Fold4.Rep2: alpha=0.86475, lambda=0.043683
## - Fold4.Rep2: alpha=0.86475, lambda=0.043683
## + Fold4.Rep2: alpha=0.10863, lambda=0.154091
## - Fold4.Rep2: alpha=0.10863, lambda=0.154091
## + Fold4.Rep2: alpha=0.98116, lambda=7.405037
## - Fold4.Rep2: alpha=0.98116, lambda=7.405037
## + Fold4.Rep2: alpha=0.94388, lambda=0.002046
## - Fold4.Rep2: alpha=0.94388, lambda=0.002046
## + Fold5.Rep2: alpha=0.63950, lambda=0.004507
## - Fold5.Rep2: alpha=0.63950, lambda=0.004507
## + Fold5.Rep2: alpha=0.04530, lambda=0.016509
## - Fold5.Rep2: alpha=0.04530, lambda=0.016509
## + Fold5.Rep2: alpha=0.97420, lambda=0.004648
## - Fold5.Rep2: alpha=0.97420, lambda=0.004648
## + Fold5.Rep2: alpha=0.34773, lambda=0.060861
## - Fold5.Rep2: alpha=0.34773, lambda=0.060861
## + Fold5.Rep2: alpha=0.51433, lambda=0.001761
## - Fold5.Rep2: alpha=0.51433, lambda=0.001761
## + Fold5.Rep2: alpha=0.31833, lambda=0.479416
## - Fold5.Rep2: alpha=0.31833, lambda=0.479416
## + Fold5.Rep2: alpha=0.74806, lambda=0.327981
## - Fold5.Rep2: alpha=0.74806, lambda=0.327981
## + Fold5.Rep2: alpha=0.14914, lambda=0.028964
## - Fold5.Rep2: alpha=0.14914, lambda=0.028964
## + Fold5.Rep2: alpha=0.84515, lambda=0.897325
## - Fold5.Rep2: alpha=0.84515, lambda=0.897325
Chang Liu 23
R for Data Science Lecture 5
## + Fold5.Rep2: alpha=0.93503, lambda=0.082985
## - Fold5.Rep2: alpha=0.93503, lambda=0.082985
## + Fold5.Rep2: alpha=0.38077, lambda=1.148290
## - Fold5.Rep2: alpha=0.38077, lambda=1.148290
## + Fold5.Rep2: alpha=0.84280, lambda=0.045415
## - Fold5.Rep2: alpha=0.84280, lambda=0.045415
## + Fold5.Rep2: alpha=0.98348, lambda=0.006142
## - Fold5.Rep2: alpha=0.98348, lambda=0.006142
## + Fold5.Rep2: alpha=0.78895, lambda=0.042054
## - Fold5.Rep2: alpha=0.78895, lambda=0.042054
## + Fold5.Rep2: alpha=0.52859, lambda=0.428235
## - Fold5.Rep2: alpha=0.52859, lambda=0.428235
## + Fold5.Rep2: alpha=0.73053, lambda=0.015889
## - Fold5.Rep2: alpha=0.73053, lambda=0.015889
## + Fold5.Rep2: alpha=0.90284, lambda=0.445782
## - Fold5.Rep2: alpha=0.90284, lambda=0.445782
## + Fold5.Rep2: alpha=0.32570, lambda=0.081177
## - Fold5.Rep2: alpha=0.32570, lambda=0.081177
## + Fold5.Rep2: alpha=0.75140, lambda=0.561138
## - Fold5.Rep2: alpha=0.75140, lambda=0.561138
## + Fold5.Rep2: alpha=0.03599, lambda=0.001115
## - Fold5.Rep2: alpha=0.03599, lambda=0.001115
## + Fold5.Rep2: alpha=0.25504, lambda=2.954617
## - Fold5.Rep2: alpha=0.25504, lambda=2.954617
## + Fold5.Rep2: alpha=0.86475, lambda=0.043683
## - Fold5.Rep2: alpha=0.86475, lambda=0.043683
## + Fold5.Rep2: alpha=0.10863, lambda=0.154091
## - Fold5.Rep2: alpha=0.10863, lambda=0.154091
## + Fold5.Rep2: alpha=0.98116, lambda=7.405037
## - Fold5.Rep2: alpha=0.98116, lambda=7.405037
## + Fold5.Rep2: alpha=0.94388, lambda=0.002046
## - Fold5.Rep2: alpha=0.94388, lambda=0.002046
## + Fold1.Rep3: alpha=0.63950, lambda=0.004507
## - Fold1.Rep3: alpha=0.63950, lambda=0.004507
## + Fold1.Rep3: alpha=0.04530, lambda=0.016509
## - Fold1.Rep3: alpha=0.04530, lambda=0.016509
## + Fold1.Rep3: alpha=0.97420, lambda=0.004648
## - Fold1.Rep3: alpha=0.97420, lambda=0.004648
Chang Liu 24
R for Data Science Lecture 5
## + Fold1.Rep3: alpha=0.34773, lambda=0.060861
## - Fold1.Rep3: alpha=0.34773, lambda=0.060861
## + Fold1.Rep3: alpha=0.51433, lambda=0.001761
## - Fold1.Rep3: alpha=0.51433, lambda=0.001761
## + Fold1.Rep3: alpha=0.31833, lambda=0.479416
## - Fold1.Rep3: alpha=0.31833, lambda=0.479416
## + Fold1.Rep3: alpha=0.74806, lambda=0.327981
## - Fold1.Rep3: alpha=0.74806, lambda=0.327981
## + Fold1.Rep3: alpha=0.14914, lambda=0.028964
## - Fold1.Rep3: alpha=0.14914, lambda=0.028964
## + Fold1.Rep3: alpha=0.84515, lambda=0.897325
## - Fold1.Rep3: alpha=0.84515, lambda=0.897325
## + Fold1.Rep3: alpha=0.93503, lambda=0.082985
## - Fold1.Rep3: alpha=0.93503, lambda=0.082985
## + Fold1.Rep3: alpha=0.38077, lambda=1.148290
## - Fold1.Rep3: alpha=0.38077, lambda=1.148290
## + Fold1.Rep3: alpha=0.84280, lambda=0.045415
## - Fold1.Rep3: alpha=0.84280, lambda=0.045415
## + Fold1.Rep3: alpha=0.98348, lambda=0.006142
## - Fold1.Rep3: alpha=0.98348, lambda=0.006142
## + Fold1.Rep3: alpha=0.78895, lambda=0.042054
## - Fold1.Rep3: alpha=0.78895, lambda=0.042054
## + Fold1.Rep3: alpha=0.52859, lambda=0.428235
## - Fold1.Rep3: alpha=0.52859, lambda=0.428235
## + Fold1.Rep3: alpha=0.73053, lambda=0.015889
## - Fold1.Rep3: alpha=0.73053, lambda=0.015889
## + Fold1.Rep3: alpha=0.90284, lambda=0.445782
## - Fold1.Rep3: alpha=0.90284, lambda=0.445782
## + Fold1.Rep3: alpha=0.32570, lambda=0.081177
## - Fold1.Rep3: alpha=0.32570, lambda=0.081177
## + Fold1.Rep3: alpha=0.75140, lambda=0.561138
## - Fold1.Rep3: alpha=0.75140, lambda=0.561138
## + Fold1.Rep3: alpha=0.03599, lambda=0.001115
## - Fold1.Rep3: alpha=0.03599, lambda=0.001115
## + Fold1.Rep3: alpha=0.25504, lambda=2.954617
## - Fold1.Rep3: alpha=0.25504, lambda=2.954617
## + Fold1.Rep3: alpha=0.86475, lambda=0.043683
## - Fold1.Rep3: alpha=0.86475, lambda=0.043683
Chang Liu 25
R for Data Science Lecture 5
## + Fold1.Rep3: alpha=0.10863, lambda=0.154091
## - Fold1.Rep3: alpha=0.10863, lambda=0.154091
## + Fold1.Rep3: alpha=0.98116, lambda=7.405037
## - Fold1.Rep3: alpha=0.98116, lambda=7.405037
## + Fold1.Rep3: alpha=0.94388, lambda=0.002046
## - Fold1.Rep3: alpha=0.94388, lambda=0.002046
## + Fold2.Rep3: alpha=0.63950, lambda=0.004507
## - Fold2.Rep3: alpha=0.63950, lambda=0.004507
## + Fold2.Rep3: alpha=0.04530, lambda=0.016509
## - Fold2.Rep3: alpha=0.04530, lambda=0.016509
## + Fold2.Rep3: alpha=0.97420, lambda=0.004648
## - Fold2.Rep3: alpha=0.97420, lambda=0.004648
## + Fold2.Rep3: alpha=0.34773, lambda=0.060861
## - Fold2.Rep3: alpha=0.34773, lambda=0.060861
## + Fold2.Rep3: alpha=0.51433, lambda=0.001761
## - Fold2.Rep3: alpha=0.51433, lambda=0.001761
## + Fold2.Rep3: alpha=0.31833, lambda=0.479416
## - Fold2.Rep3: alpha=0.31833, lambda=0.479416
## + Fold2.Rep3: alpha=0.74806, lambda=0.327981
## - Fold2.Rep3: alpha=0.74806, lambda=0.327981
## + Fold2.Rep3: alpha=0.14914, lambda=0.028964
## - Fold2.Rep3: alpha=0.14914, lambda=0.028964
## + Fold2.Rep3: alpha=0.84515, lambda=0.897325
## - Fold2.Rep3: alpha=0.84515, lambda=0.897325
## + Fold2.Rep3: alpha=0.93503, lambda=0.082985
## - Fold2.Rep3: alpha=0.93503, lambda=0.082985
## + Fold2.Rep3: alpha=0.38077, lambda=1.148290
## - Fold2.Rep3: alpha=0.38077, lambda=1.148290
## + Fold2.Rep3: alpha=0.84280, lambda=0.045415
## - Fold2.Rep3: alpha=0.84280, lambda=0.045415
## + Fold2.Rep3: alpha=0.98348, lambda=0.006142
## - Fold2.Rep3: alpha=0.98348, lambda=0.006142
## + Fold2.Rep3: alpha=0.78895, lambda=0.042054
## - Fold2.Rep3: alpha=0.78895, lambda=0.042054
## + Fold2.Rep3: alpha=0.52859, lambda=0.428235
## - Fold2.Rep3: alpha=0.52859, lambda=0.428235
## + Fold2.Rep3: alpha=0.73053, lambda=0.015889
## - Fold2.Rep3: alpha=0.73053, lambda=0.015889
Chang Liu 26
R for Data Science Lecture 5
## + Fold2.Rep3: alpha=0.90284, lambda=0.445782
## - Fold2.Rep3: alpha=0.90284, lambda=0.445782
## + Fold2.Rep3: alpha=0.32570, lambda=0.081177
## - Fold2.Rep3: alpha=0.32570, lambda=0.081177
## + Fold2.Rep3: alpha=0.75140, lambda=0.561138
## - Fold2.Rep3: alpha=0.75140, lambda=0.561138
## + Fold2.Rep3: alpha=0.03599, lambda=0.001115
## - Fold2.Rep3: alpha=0.03599, lambda=0.001115
## + Fold2.Rep3: alpha=0.25504, lambda=2.954617
## - Fold2.Rep3: alpha=0.25504, lambda=2.954617
## + Fold2.Rep3: alpha=0.86475, lambda=0.043683
## - Fold2.Rep3: alpha=0.86475, lambda=0.043683
## + Fold2.Rep3: alpha=0.10863, lambda=0.154091
## - Fold2.Rep3: alpha=0.10863, lambda=0.154091
## + Fold2.Rep3: alpha=0.98116, lambda=7.405037
## - Fold2.Rep3: alpha=0.98116, lambda=7.405037
## + Fold2.Rep3: alpha=0.94388, lambda=0.002046
## - Fold2.Rep3: alpha=0.94388, lambda=0.002046
## + Fold3.Rep3: alpha=0.63950, lambda=0.004507
## - Fold3.Rep3: alpha=0.63950, lambda=0.004507
## + Fold3.Rep3: alpha=0.04530, lambda=0.016509
## - Fold3.Rep3: alpha=0.04530, lambda=0.016509
## + Fold3.Rep3: alpha=0.97420, lambda=0.004648
## - Fold3.Rep3: alpha=0.97420, lambda=0.004648
## + Fold3.Rep3: alpha=0.34773, lambda=0.060861
## - Fold3.Rep3: alpha=0.34773, lambda=0.060861
## + Fold3.Rep3: alpha=0.51433, lambda=0.001761
## - Fold3.Rep3: alpha=0.51433, lambda=0.001761
## + Fold3.Rep3: alpha=0.31833, lambda=0.479416
## - Fold3.Rep3: alpha=0.31833, lambda=0.479416
## + Fold3.Rep3: alpha=0.74806, lambda=0.327981
## - Fold3.Rep3: alpha=0.74806, lambda=0.327981
## + Fold3.Rep3: alpha=0.14914, lambda=0.028964
## - Fold3.Rep3: alpha=0.14914, lambda=0.028964
## + Fold3.Rep3: alpha=0.84515, lambda=0.897325
## - Fold3.Rep3: alpha=0.84515, lambda=0.897325
## + Fold3.Rep3: alpha=0.93503, lambda=0.082985
## - Fold3.Rep3: alpha=0.93503, lambda=0.082985
Chang Liu 27
R for Data Science Lecture 5
## + Fold3.Rep3: alpha=0.38077, lambda=1.148290
## - Fold3.Rep3: alpha=0.38077, lambda=1.148290
## + Fold3.Rep3: alpha=0.84280, lambda=0.045415
## - Fold3.Rep3: alpha=0.84280, lambda=0.045415
## + Fold3.Rep3: alpha=0.98348, lambda=0.006142
## - Fold3.Rep3: alpha=0.98348, lambda=0.006142
## + Fold3.Rep3: alpha=0.78895, lambda=0.042054
## - Fold3.Rep3: alpha=0.78895, lambda=0.042054
## + Fold3.Rep3: alpha=0.52859, lambda=0.428235
## - Fold3.Rep3: alpha=0.52859, lambda=0.428235
## + Fold3.Rep3: alpha=0.73053, lambda=0.015889
## - Fold3.Rep3: alpha=0.73053, lambda=0.015889
## + Fold3.Rep3: alpha=0.90284, lambda=0.445782
## - Fold3.Rep3: alpha=0.90284, lambda=0.445782
## + Fold3.Rep3: alpha=0.32570, lambda=0.081177
## - Fold3.Rep3: alpha=0.32570, lambda=0.081177
## + Fold3.Rep3: alpha=0.75140, lambda=0.561138
## - Fold3.Rep3: alpha=0.75140, lambda=0.561138
## + Fold3.Rep3: alpha=0.03599, lambda=0.001115
## - Fold3.Rep3: alpha=0.03599, lambda=0.001115
## + Fold3.Rep3: alpha=0.25504, lambda=2.954617
## - Fold3.Rep3: alpha=0.25504, lambda=2.954617
## + Fold3.Rep3: alpha=0.86475, lambda=0.043683
## - Fold3.Rep3: alpha=0.86475, lambda=0.043683
## + Fold3.Rep3: alpha=0.10863, lambda=0.154091
## - Fold3.Rep3: alpha=0.10863, lambda=0.154091
## + Fold3.Rep3: alpha=0.98116, lambda=7.405037
## - Fold3.Rep3: alpha=0.98116, lambda=7.405037
## + Fold3.Rep3: alpha=0.94388, lambda=0.002046
## - Fold3.Rep3: alpha=0.94388, lambda=0.002046
## + Fold4.Rep3: alpha=0.63950, lambda=0.004507
## - Fold4.Rep3: alpha=0.63950, lambda=0.004507
## + Fold4.Rep3: alpha=0.04530, lambda=0.016509
## - Fold4.Rep3: alpha=0.04530, lambda=0.016509
## + Fold4.Rep3: alpha=0.97420, lambda=0.004648
## - Fold4.Rep3: alpha=0.97420, lambda=0.004648
## + Fold4.Rep3: alpha=0.34773, lambda=0.060861
## - Fold4.Rep3: alpha=0.34773, lambda=0.060861
Chang Liu 28
R for Data Science Lecture 5
## + Fold4.Rep3: alpha=0.51433, lambda=0.001761
## - Fold4.Rep3: alpha=0.51433, lambda=0.001761
## + Fold4.Rep3: alpha=0.31833, lambda=0.479416
## - Fold4.Rep3: alpha=0.31833, lambda=0.479416
## + Fold4.Rep3: alpha=0.74806, lambda=0.327981
## - Fold4.Rep3: alpha=0.74806, lambda=0.327981
## + Fold4.Rep3: alpha=0.14914, lambda=0.028964
## - Fold4.Rep3: alpha=0.14914, lambda=0.028964
## + Fold4.Rep3: alpha=0.84515, lambda=0.897325
## - Fold4.Rep3: alpha=0.84515, lambda=0.897325
## + Fold4.Rep3: alpha=0.93503, lambda=0.082985
## - Fold4.Rep3: alpha=0.93503, lambda=0.082985
## + Fold4.Rep3: alpha=0.38077, lambda=1.148290
## - Fold4.Rep3: alpha=0.38077, lambda=1.148290
## + Fold4.Rep3: alpha=0.84280, lambda=0.045415
## - Fold4.Rep3: alpha=0.84280, lambda=0.045415
## + Fold4.Rep3: alpha=0.98348, lambda=0.006142
## - Fold4.Rep3: alpha=0.98348, lambda=0.006142
## + Fold4.Rep3: alpha=0.78895, lambda=0.042054
## - Fold4.Rep3: alpha=0.78895, lambda=0.042054
## + Fold4.Rep3: alpha=0.52859, lambda=0.428235
## - Fold4.Rep3: alpha=0.52859, lambda=0.428235
## + Fold4.Rep3: alpha=0.73053, lambda=0.015889
## - Fold4.Rep3: alpha=0.73053, lambda=0.015889
## + Fold4.Rep3: alpha=0.90284, lambda=0.445782
## - Fold4.Rep3: alpha=0.90284, lambda=0.445782
## + Fold4.Rep3: alpha=0.32570, lambda=0.081177
## - Fold4.Rep3: alpha=0.32570, lambda=0.081177
## + Fold4.Rep3: alpha=0.75140, lambda=0.561138
## - Fold4.Rep3: alpha=0.75140, lambda=0.561138
## + Fold4.Rep3: alpha=0.03599, lambda=0.001115
## - Fold4.Rep3: alpha=0.03599, lambda=0.001115
## + Fold4.Rep3: alpha=0.25504, lambda=2.954617
## - Fold4.Rep3: alpha=0.25504, lambda=2.954617
## + Fold4.Rep3: alpha=0.86475, lambda=0.043683
## - Fold4.Rep3: alpha=0.86475, lambda=0.043683
## + Fold4.Rep3: alpha=0.10863, lambda=0.154091
## - Fold4.Rep3: alpha=0.10863, lambda=0.154091
Chang Liu 29
R for Data Science Lecture 5
## + Fold4.Rep3: alpha=0.98116, lambda=7.405037
## - Fold4.Rep3: alpha=0.98116, lambda=7.405037
## + Fold4.Rep3: alpha=0.94388, lambda=0.002046
## - Fold4.Rep3: alpha=0.94388, lambda=0.002046
## + Fold5.Rep3: alpha=0.63950, lambda=0.004507
## - Fold5.Rep3: alpha=0.63950, lambda=0.004507
## + Fold5.Rep3: alpha=0.04530, lambda=0.016509
## - Fold5.Rep3: alpha=0.04530, lambda=0.016509
## + Fold5.Rep3: alpha=0.97420, lambda=0.004648
## - Fold5.Rep3: alpha=0.97420, lambda=0.004648
## + Fold5.Rep3: alpha=0.34773, lambda=0.060861
## - Fold5.Rep3: alpha=0.34773, lambda=0.060861
## + Fold5.Rep3: alpha=0.51433, lambda=0.001761
## - Fold5.Rep3: alpha=0.51433, lambda=0.001761
## + Fold5.Rep3: alpha=0.31833, lambda=0.479416
## - Fold5.Rep3: alpha=0.31833, lambda=0.479416
## + Fold5.Rep3: alpha=0.74806, lambda=0.327981
## - Fold5.Rep3: alpha=0.74806, lambda=0.327981
## + Fold5.Rep3: alpha=0.14914, lambda=0.028964
## - Fold5.Rep3: alpha=0.14914, lambda=0.028964
## + Fold5.Rep3: alpha=0.84515, lambda=0.897325
## - Fold5.Rep3: alpha=0.84515, lambda=0.897325
## + Fold5.Rep3: alpha=0.93503, lambda=0.082985
## - Fold5.Rep3: alpha=0.93503, lambda=0.082985
## + Fold5.Rep3: alpha=0.38077, lambda=1.148290
## - Fold5.Rep3: alpha=0.38077, lambda=1.148290
## + Fold5.Rep3: alpha=0.84280, lambda=0.045415
## - Fold5.Rep3: alpha=0.84280, lambda=0.045415
## + Fold5.Rep3: alpha=0.98348, lambda=0.006142
## - Fold5.Rep3: alpha=0.98348, lambda=0.006142
## + Fold5.Rep3: alpha=0.78895, lambda=0.042054
## - Fold5.Rep3: alpha=0.78895, lambda=0.042054
## + Fold5.Rep3: alpha=0.52859, lambda=0.428235
## - Fold5.Rep3: alpha=0.52859, lambda=0.428235
## + Fold5.Rep3: alpha=0.73053, lambda=0.015889
## - Fold5.Rep3: alpha=0.73053, lambda=0.015889
## + Fold5.Rep3: alpha=0.90284, lambda=0.445782
## - Fold5.Rep3: alpha=0.90284, lambda=0.445782
Chang Liu 30
R for Data Science Lecture 5
## + Fold5.Rep3: alpha=0.32570, lambda=0.081177
## - Fold5.Rep3: alpha=0.32570, lambda=0.081177
## + Fold5.Rep3: alpha=0.75140, lambda=0.561138
## - Fold5.Rep3: alpha=0.75140, lambda=0.561138
## + Fold5.Rep3: alpha=0.03599, lambda=0.001115
## - Fold5.Rep3: alpha=0.03599, lambda=0.001115
## + Fold5.Rep3: alpha=0.25504, lambda=2.954617
## - Fold5.Rep3: alpha=0.25504, lambda=2.954617
## + Fold5.Rep3: alpha=0.86475, lambda=0.043683
## - Fold5.Rep3: alpha=0.86475, lambda=0.043683
## + Fold5.Rep3: alpha=0.10863, lambda=0.154091
## - Fold5.Rep3: alpha=0.10863, lambda=0.154091
## + Fold5.Rep3: alpha=0.98116, lambda=7.405037
## - Fold5.Rep3: alpha=0.98116, lambda=7.405037
## + Fold5.Rep3: alpha=0.94388, lambda=0.002046
## - Fold5.Rep3: alpha=0.94388, lambda=0.002046
## + Fold1.Rep4: alpha=0.63950, lambda=0.004507
## - Fold1.Rep4: alpha=0.63950, lambda=0.004507
## + Fold1.Rep4: alpha=0.04530, lambda=0.016509
## - Fold1.Rep4: alpha=0.04530, lambda=0.016509
## + Fold1.Rep4: alpha=0.97420, lambda=0.004648
## - Fold1.Rep4: alpha=0.97420, lambda=0.004648
## + Fold1.Rep4: alpha=0.34773, lambda=0.060861
## - Fold1.Rep4: alpha=0.34773, lambda=0.060861
## + Fold1.Rep4: alpha=0.51433, lambda=0.001761
## - Fold1.Rep4: alpha=0.51433, lambda=0.001761
## + Fold1.Rep4: alpha=0.31833, lambda=0.479416
## - Fold1.Rep4: alpha=0.31833, lambda=0.479416
## + Fold1.Rep4: alpha=0.74806, lambda=0.327981
## - Fold1.Rep4: alpha=0.74806, lambda=0.327981
## + Fold1.Rep4: alpha=0.14914, lambda=0.028964
## - Fold1.Rep4: alpha=0.14914, lambda=0.028964
## + Fold1.Rep4: alpha=0.84515, lambda=0.897325
## - Fold1.Rep4: alpha=0.84515, lambda=0.897325
## + Fold1.Rep4: alpha=0.93503, lambda=0.082985
## - Fold1.Rep4: alpha=0.93503, lambda=0.082985
## + Fold1.Rep4: alpha=0.38077, lambda=1.148290
## - Fold1.Rep4: alpha=0.38077, lambda=1.148290
Chang Liu 31
R for Data Science Lecture 5
## + Fold1.Rep4: alpha=0.84280, lambda=0.045415
## - Fold1.Rep4: alpha=0.84280, lambda=0.045415
## + Fold1.Rep4: alpha=0.98348, lambda=0.006142
## - Fold1.Rep4: alpha=0.98348, lambda=0.006142
## + Fold1.Rep4: alpha=0.78895, lambda=0.042054
## - Fold1.Rep4: alpha=0.78895, lambda=0.042054
## + Fold1.Rep4: alpha=0.52859, lambda=0.428235
## - Fold1.Rep4: alpha=0.52859, lambda=0.428235
## + Fold1.Rep4: alpha=0.73053, lambda=0.015889
## - Fold1.Rep4: alpha=0.73053, lambda=0.015889
## + Fold1.Rep4: alpha=0.90284, lambda=0.445782
## - Fold1.Rep4: alpha=0.90284, lambda=0.445782
## + Fold1.Rep4: alpha=0.32570, lambda=0.081177
## - Fold1.Rep4: alpha=0.32570, lambda=0.081177
## + Fold1.Rep4: alpha=0.75140, lambda=0.561138
## - Fold1.Rep4: alpha=0.75140, lambda=0.561138
## + Fold1.Rep4: alpha=0.03599, lambda=0.001115
## - Fold1.Rep4: alpha=0.03599, lambda=0.001115
## + Fold1.Rep4: alpha=0.25504, lambda=2.954617
## - Fold1.Rep4: alpha=0.25504, lambda=2.954617
## + Fold1.Rep4: alpha=0.86475, lambda=0.043683
## - Fold1.Rep4: alpha=0.86475, lambda=0.043683
## + Fold1.Rep4: alpha=0.10863, lambda=0.154091
## - Fold1.Rep4: alpha=0.10863, lambda=0.154091
## + Fold1.Rep4: alpha=0.98116, lambda=7.405037
## - Fold1.Rep4: alpha=0.98116, lambda=7.405037
## + Fold1.Rep4: alpha=0.94388, lambda=0.002046
## - Fold1.Rep4: alpha=0.94388, lambda=0.002046
## + Fold2.Rep4: alpha=0.63950, lambda=0.004507
## - Fold2.Rep4: alpha=0.63950, lambda=0.004507
## + Fold2.Rep4: alpha=0.04530, lambda=0.016509
## - Fold2.Rep4: alpha=0.04530, lambda=0.016509
## + Fold2.Rep4: alpha=0.97420, lambda=0.004648
## - Fold2.Rep4: alpha=0.97420, lambda=0.004648
## + Fold2.Rep4: alpha=0.34773, lambda=0.060861
## - Fold2.Rep4: alpha=0.34773, lambda=0.060861
## + Fold2.Rep4: alpha=0.51433, lambda=0.001761
## - Fold2.Rep4: alpha=0.51433, lambda=0.001761
Chang Liu 32
R for Data Science Lecture 5
## + Fold2.Rep4: alpha=0.31833, lambda=0.479416
## - Fold2.Rep4: alpha=0.31833, lambda=0.479416
## + Fold2.Rep4: alpha=0.74806, lambda=0.327981
## - Fold2.Rep4: alpha=0.74806, lambda=0.327981
## + Fold2.Rep4: alpha=0.14914, lambda=0.028964
## - Fold2.Rep4: alpha=0.14914, lambda=0.028964
## + Fold2.Rep4: alpha=0.84515, lambda=0.897325
## - Fold2.Rep4: alpha=0.84515, lambda=0.897325
## + Fold2.Rep4: alpha=0.93503, lambda=0.082985
## - Fold2.Rep4: alpha=0.93503, lambda=0.082985
## + Fold2.Rep4: alpha=0.38077, lambda=1.148290
## - Fold2.Rep4: alpha=0.38077, lambda=1.148290
## + Fold2.Rep4: alpha=0.84280, lambda=0.045415
## - Fold2.Rep4: alpha=0.84280, lambda=0.045415
## + Fold2.Rep4: alpha=0.98348, lambda=0.006142
## - Fold2.Rep4: alpha=0.98348, lambda=0.006142
## + Fold2.Rep4: alpha=0.78895, lambda=0.042054
## - Fold2.Rep4: alpha=0.78895, lambda=0.042054
## + Fold2.Rep4: alpha=0.52859, lambda=0.428235
## - Fold2.Rep4: alpha=0.52859, lambda=0.428235
## + Fold2.Rep4: alpha=0.73053, lambda=0.015889
## - Fold2.Rep4: alpha=0.73053, lambda=0.015889
## + Fold2.Rep4: alpha=0.90284, lambda=0.445782
## - Fold2.Rep4: alpha=0.90284, lambda=0.445782
## + Fold2.Rep4: alpha=0.32570, lambda=0.081177
## - Fold2.Rep4: alpha=0.32570, lambda=0.081177
## + Fold2.Rep4: alpha=0.75140, lambda=0.561138
## - Fold2.Rep4: alpha=0.75140, lambda=0.561138
## + Fold2.Rep4: alpha=0.03599, lambda=0.001115
## - Fold2.Rep4: alpha=0.03599, lambda=0.001115
## + Fold2.Rep4: alpha=0.25504, lambda=2.954617
## - Fold2.Rep4: alpha=0.25504, lambda=2.954617
## + Fold2.Rep4: alpha=0.86475, lambda=0.043683
## - Fold2.Rep4: alpha=0.86475, lambda=0.043683
## + Fold2.Rep4: alpha=0.10863, lambda=0.154091
## - Fold2.Rep4: alpha=0.10863, lambda=0.154091
## + Fold2.Rep4: alpha=0.98116, lambda=7.405037
## - Fold2.Rep4: alpha=0.98116, lambda=7.405037
Chang Liu 33
R for Data Science Lecture 5
## + Fold2.Rep4: alpha=0.94388, lambda=0.002046
## - Fold2.Rep4: alpha=0.94388, lambda=0.002046
## + Fold3.Rep4: alpha=0.63950, lambda=0.004507
## - Fold3.Rep4: alpha=0.63950, lambda=0.004507
## + Fold3.Rep4: alpha=0.04530, lambda=0.016509
## - Fold3.Rep4: alpha=0.04530, lambda=0.016509
## + Fold3.Rep4: alpha=0.97420, lambda=0.004648
## - Fold3.Rep4: alpha=0.97420, lambda=0.004648
## + Fold3.Rep4: alpha=0.34773, lambda=0.060861
## - Fold3.Rep4: alpha=0.34773, lambda=0.060861
## + Fold3.Rep4: alpha=0.51433, lambda=0.001761
## - Fold3.Rep4: alpha=0.51433, lambda=0.001761
## + Fold3.Rep4: alpha=0.31833, lambda=0.479416
## - Fold3.Rep4: alpha=0.31833, lambda=0.479416
## + Fold3.Rep4: alpha=0.74806, lambda=0.327981
## - Fold3.Rep4: alpha=0.74806, lambda=0.327981
## + Fold3.Rep4: alpha=0.14914, lambda=0.028964
## - Fold3.Rep4: alpha=0.14914, lambda=0.028964
## + Fold3.Rep4: alpha=0.84515, lambda=0.897325
## - Fold3.Rep4: alpha=0.84515, lambda=0.897325
## + Fold3.Rep4: alpha=0.93503, lambda=0.082985
## - Fold3.Rep4: alpha=0.93503, lambda=0.082985
## + Fold3.Rep4: alpha=0.38077, lambda=1.148290
## - Fold3.Rep4: alpha=0.38077, lambda=1.148290
## + Fold3.Rep4: alpha=0.84280, lambda=0.045415
## - Fold3.Rep4: alpha=0.84280, lambda=0.045415
## + Fold3.Rep4: alpha=0.98348, lambda=0.006142
## - Fold3.Rep4: alpha=0.98348, lambda=0.006142
## + Fold3.Rep4: alpha=0.78895, lambda=0.042054
## - Fold3.Rep4: alpha=0.78895, lambda=0.042054
## + Fold3.Rep4: alpha=0.52859, lambda=0.428235
## - Fold3.Rep4: alpha=0.52859, lambda=0.428235
## + Fold3.Rep4: alpha=0.73053, lambda=0.015889
## - Fold3.Rep4: alpha=0.73053, lambda=0.015889
## + Fold3.Rep4: alpha=0.90284, lambda=0.445782
## - Fold3.Rep4: alpha=0.90284, lambda=0.445782
## + Fold3.Rep4: alpha=0.32570, lambda=0.081177
## - Fold3.Rep4: alpha=0.32570, lambda=0.081177
Chang Liu 34
R for Data Science Lecture 5
## + Fold3.Rep4: alpha=0.75140, lambda=0.561138
## - Fold3.Rep4: alpha=0.75140, lambda=0.561138
## + Fold3.Rep4: alpha=0.03599, lambda=0.001115
## - Fold3.Rep4: alpha=0.03599, lambda=0.001115
## + Fold3.Rep4: alpha=0.25504, lambda=2.954617
## - Fold3.Rep4: alpha=0.25504, lambda=2.954617
## + Fold3.Rep4: alpha=0.86475, lambda=0.043683
## - Fold3.Rep4: alpha=0.86475, lambda=0.043683
## + Fold3.Rep4: alpha=0.10863, lambda=0.154091
## - Fold3.Rep4: alpha=0.10863, lambda=0.154091
## + Fold3.Rep4: alpha=0.98116, lambda=7.405037
## - Fold3.Rep4: alpha=0.98116, lambda=7.405037
## + Fold3.Rep4: alpha=0.94388, lambda=0.002046
## - Fold3.Rep4: alpha=0.94388, lambda=0.002046
## + Fold4.Rep4: alpha=0.63950, lambda=0.004507
## - Fold4.Rep4: alpha=0.63950, lambda=0.004507
## + Fold4.Rep4: alpha=0.04530, lambda=0.016509
## - Fold4.Rep4: alpha=0.04530, lambda=0.016509
## + Fold4.Rep4: alpha=0.97420, lambda=0.004648
## - Fold4.Rep4: alpha=0.97420, lambda=0.004648
## + Fold4.Rep4: alpha=0.34773, lambda=0.060861
## - Fold4.Rep4: alpha=0.34773, lambda=0.060861
## + Fold4.Rep4: alpha=0.51433, lambda=0.001761
## - Fold4.Rep4: alpha=0.51433, lambda=0.001761
## + Fold4.Rep4: alpha=0.31833, lambda=0.479416
## - Fold4.Rep4: alpha=0.31833, lambda=0.479416
## + Fold4.Rep4: alpha=0.74806, lambda=0.327981
## - Fold4.Rep4: alpha=0.74806, lambda=0.327981
## + Fold4.Rep4: alpha=0.14914, lambda=0.028964
## - Fold4.Rep4: alpha=0.14914, lambda=0.028964
## + Fold4.Rep4: alpha=0.84515, lambda=0.897325
## - Fold4.Rep4: alpha=0.84515, lambda=0.897325
## + Fold4.Rep4: alpha=0.93503, lambda=0.082985
## - Fold4.Rep4: alpha=0.93503, lambda=0.082985
## + Fold4.Rep4: alpha=0.38077, lambda=1.148290
## - Fold4.Rep4: alpha=0.38077, lambda=1.148290
## + Fold4.Rep4: alpha=0.84280, lambda=0.045415
## - Fold4.Rep4: alpha=0.84280, lambda=0.045415
Chang Liu 35
R for Data Science Lecture 5
## + Fold4.Rep4: alpha=0.98348, lambda=0.006142
## - Fold4.Rep4: alpha=0.98348, lambda=0.006142
## + Fold4.Rep4: alpha=0.78895, lambda=0.042054
## - Fold4.Rep4: alpha=0.78895, lambda=0.042054
## + Fold4.Rep4: alpha=0.52859, lambda=0.428235
## - Fold4.Rep4: alpha=0.52859, lambda=0.428235
## + Fold4.Rep4: alpha=0.73053, lambda=0.015889
## - Fold4.Rep4: alpha=0.73053, lambda=0.015889
## + Fold4.Rep4: alpha=0.90284, lambda=0.445782
## - Fold4.Rep4: alpha=0.90284, lambda=0.445782
## + Fold4.Rep4: alpha=0.32570, lambda=0.081177
## - Fold4.Rep4: alpha=0.32570, lambda=0.081177
## + Fold4.Rep4: alpha=0.75140, lambda=0.561138
## - Fold4.Rep4: alpha=0.75140, lambda=0.561138
## + Fold4.Rep4: alpha=0.03599, lambda=0.001115
## - Fold4.Rep4: alpha=0.03599, lambda=0.001115
## + Fold4.Rep4: alpha=0.25504, lambda=2.954617
## - Fold4.Rep4: alpha=0.25504, lambda=2.954617
## + Fold4.Rep4: alpha=0.86475, lambda=0.043683
## - Fold4.Rep4: alpha=0.86475, lambda=0.043683
## + Fold4.Rep4: alpha=0.10863, lambda=0.154091
## - Fold4.Rep4: alpha=0.10863, lambda=0.154091
## + Fold4.Rep4: alpha=0.98116, lambda=7.405037
## - Fold4.Rep4: alpha=0.98116, lambda=7.405037
## + Fold4.Rep4: alpha=0.94388, lambda=0.002046
## - Fold4.Rep4: alpha=0.94388, lambda=0.002046
## + Fold5.Rep4: alpha=0.63950, lambda=0.004507
## - Fold5.Rep4: alpha=0.63950, lambda=0.004507
## + Fold5.Rep4: alpha=0.04530, lambda=0.016509
## - Fold5.Rep4: alpha=0.04530, lambda=0.016509
## + Fold5.Rep4: alpha=0.97420, lambda=0.004648
## - Fold5.Rep4: alpha=0.97420, lambda=0.004648
## + Fold5.Rep4: alpha=0.34773, lambda=0.060861
## - Fold5.Rep4: alpha=0.34773, lambda=0.060861
## + Fold5.Rep4: alpha=0.51433, lambda=0.001761
## - Fold5.Rep4: alpha=0.51433, lambda=0.001761
## + Fold5.Rep4: alpha=0.31833, lambda=0.479416
## - Fold5.Rep4: alpha=0.31833, lambda=0.479416
Chang Liu 36
R for Data Science Lecture 5
## + Fold5.Rep4: alpha=0.74806, lambda=0.327981
## - Fold5.Rep4: alpha=0.74806, lambda=0.327981
## + Fold5.Rep4: alpha=0.14914, lambda=0.028964
## - Fold5.Rep4: alpha=0.14914, lambda=0.028964
## + Fold5.Rep4: alpha=0.84515, lambda=0.897325
## - Fold5.Rep4: alpha=0.84515, lambda=0.897325
## + Fold5.Rep4: alpha=0.93503, lambda=0.082985
## - Fold5.Rep4: alpha=0.93503, lambda=0.082985
## + Fold5.Rep4: alpha=0.38077, lambda=1.148290
## - Fold5.Rep4: alpha=0.38077, lambda=1.148290
## + Fold5.Rep4: alpha=0.84280, lambda=0.045415
## - Fold5.Rep4: alpha=0.84280, lambda=0.045415
## + Fold5.Rep4: alpha=0.98348, lambda=0.006142
## - Fold5.Rep4: alpha=0.98348, lambda=0.006142
## + Fold5.Rep4: alpha=0.78895, lambda=0.042054
## - Fold5.Rep4: alpha=0.78895, lambda=0.042054
## + Fold5.Rep4: alpha=0.52859, lambda=0.428235
## - Fold5.Rep4: alpha=0.52859, lambda=0.428235
## + Fold5.Rep4: alpha=0.73053, lambda=0.015889
## - Fold5.Rep4: alpha=0.73053, lambda=0.015889
## + Fold5.Rep4: alpha=0.90284, lambda=0.445782
## - Fold5.Rep4: alpha=0.90284, lambda=0.445782
## + Fold5.Rep4: alpha=0.32570, lambda=0.081177
## - Fold5.Rep4: alpha=0.32570, lambda=0.081177
## + Fold5.Rep4: alpha=0.75140, lambda=0.561138
## - Fold5.Rep4: alpha=0.75140, lambda=0.561138
## + Fold5.Rep4: alpha=0.03599, lambda=0.001115
## - Fold5.Rep4: alpha=0.03599, lambda=0.001115
## + Fold5.Rep4: alpha=0.25504, lambda=2.954617
## - Fold5.Rep4: alpha=0.25504, lambda=2.954617
## + Fold5.Rep4: alpha=0.86475, lambda=0.043683
## - Fold5.Rep4: alpha=0.86475, lambda=0.043683
## + Fold5.Rep4: alpha=0.10863, lambda=0.154091
## - Fold5.Rep4: alpha=0.10863, lambda=0.154091
## + Fold5.Rep4: alpha=0.98116, lambda=7.405037
## - Fold5.Rep4: alpha=0.98116, lambda=7.405037
## + Fold5.Rep4: alpha=0.94388, lambda=0.002046
## - Fold5.Rep4: alpha=0.94388, lambda=0.002046
Chang Liu 37
R for Data Science Lecture 5
## + Fold1.Rep5: alpha=0.63950, lambda=0.004507
## - Fold1.Rep5: alpha=0.63950, lambda=0.004507
## + Fold1.Rep5: alpha=0.04530, lambda=0.016509
## - Fold1.Rep5: alpha=0.04530, lambda=0.016509
## + Fold1.Rep5: alpha=0.97420, lambda=0.004648
## - Fold1.Rep5: alpha=0.97420, lambda=0.004648
## + Fold1.Rep5: alpha=0.34773, lambda=0.060861
## - Fold1.Rep5: alpha=0.34773, lambda=0.060861
## + Fold1.Rep5: alpha=0.51433, lambda=0.001761
## - Fold1.Rep5: alpha=0.51433, lambda=0.001761
## + Fold1.Rep5: alpha=0.31833, lambda=0.479416
## - Fold1.Rep5: alpha=0.31833, lambda=0.479416
## + Fold1.Rep5: alpha=0.74806, lambda=0.327981
## - Fold1.Rep5: alpha=0.74806, lambda=0.327981
## + Fold1.Rep5: alpha=0.14914, lambda=0.028964
## - Fold1.Rep5: alpha=0.14914, lambda=0.028964
## + Fold1.Rep5: alpha=0.84515, lambda=0.897325
## - Fold1.Rep5: alpha=0.84515, lambda=0.897325
## + Fold1.Rep5: alpha=0.93503, lambda=0.082985
## - Fold1.Rep5: alpha=0.93503, lambda=0.082985
## + Fold1.Rep5: alpha=0.38077, lambda=1.148290
## - Fold1.Rep5: alpha=0.38077, lambda=1.148290
## + Fold1.Rep5: alpha=0.84280, lambda=0.045415
## - Fold1.Rep5: alpha=0.84280, lambda=0.045415
## + Fold1.Rep5: alpha=0.98348, lambda=0.006142
## - Fold1.Rep5: alpha=0.98348, lambda=0.006142
## + Fold1.Rep5: alpha=0.78895, lambda=0.042054
## - Fold1.Rep5: alpha=0.78895, lambda=0.042054
## + Fold1.Rep5: alpha=0.52859, lambda=0.428235
## - Fold1.Rep5: alpha=0.52859, lambda=0.428235
## + Fold1.Rep5: alpha=0.73053, lambda=0.015889
## - Fold1.Rep5: alpha=0.73053, lambda=0.015889
## + Fold1.Rep5: alpha=0.90284, lambda=0.445782
## - Fold1.Rep5: alpha=0.90284, lambda=0.445782
## + Fold1.Rep5: alpha=0.32570, lambda=0.081177
## - Fold1.Rep5: alpha=0.32570, lambda=0.081177
## + Fold1.Rep5: alpha=0.75140, lambda=0.561138
## - Fold1.Rep5: alpha=0.75140, lambda=0.561138
Chang Liu 38
R for Data Science Lecture 5
## + Fold1.Rep5: alpha=0.03599, lambda=0.001115
## - Fold1.Rep5: alpha=0.03599, lambda=0.001115
## + Fold1.Rep5: alpha=0.25504, lambda=2.954617
## - Fold1.Rep5: alpha=0.25504, lambda=2.954617
## + Fold1.Rep5: alpha=0.86475, lambda=0.043683
## - Fold1.Rep5: alpha=0.86475, lambda=0.043683
## + Fold1.Rep5: alpha=0.10863, lambda=0.154091
## - Fold1.Rep5: alpha=0.10863, lambda=0.154091
## + Fold1.Rep5: alpha=0.98116, lambda=7.405037
## - Fold1.Rep5: alpha=0.98116, lambda=7.405037
## + Fold1.Rep5: alpha=0.94388, lambda=0.002046
## - Fold1.Rep5: alpha=0.94388, lambda=0.002046
## + Fold2.Rep5: alpha=0.63950, lambda=0.004507
## - Fold2.Rep5: alpha=0.63950, lambda=0.004507
## + Fold2.Rep5: alpha=0.04530, lambda=0.016509
## - Fold2.Rep5: alpha=0.04530, lambda=0.016509
## + Fold2.Rep5: alpha=0.97420, lambda=0.004648
## - Fold2.Rep5: alpha=0.97420, lambda=0.004648
## + Fold2.Rep5: alpha=0.34773, lambda=0.060861
## - Fold2.Rep5: alpha=0.34773, lambda=0.060861
## + Fold2.Rep5: alpha=0.51433, lambda=0.001761
## - Fold2.Rep5: alpha=0.51433, lambda=0.001761
## + Fold2.Rep5: alpha=0.31833, lambda=0.479416
## - Fold2.Rep5: alpha=0.31833, lambda=0.479416
## + Fold2.Rep5: alpha=0.74806, lambda=0.327981
## - Fold2.Rep5: alpha=0.74806, lambda=0.327981
## + Fold2.Rep5: alpha=0.14914, lambda=0.028964
## - Fold2.Rep5: alpha=0.14914, lambda=0.028964
## + Fold2.Rep5: alpha=0.84515, lambda=0.897325
## - Fold2.Rep5: alpha=0.84515, lambda=0.897325
## + Fold2.Rep5: alpha=0.93503, lambda=0.082985
## - Fold2.Rep5: alpha=0.93503, lambda=0.082985
## + Fold2.Rep5: alpha=0.38077, lambda=1.148290
## - Fold2.Rep5: alpha=0.38077, lambda=1.148290
## + Fold2.Rep5: alpha=0.84280, lambda=0.045415
## - Fold2.Rep5: alpha=0.84280, lambda=0.045415
## + Fold2.Rep5: alpha=0.98348, lambda=0.006142
## - Fold2.Rep5: alpha=0.98348, lambda=0.006142
Chang Liu 39
R for Data Science Lecture 5
## + Fold2.Rep5: alpha=0.78895, lambda=0.042054
## - Fold2.Rep5: alpha=0.78895, lambda=0.042054
## + Fold2.Rep5: alpha=0.52859, lambda=0.428235
## - Fold2.Rep5: alpha=0.52859, lambda=0.428235
## + Fold2.Rep5: alpha=0.73053, lambda=0.015889
## - Fold2.Rep5: alpha=0.73053, lambda=0.015889
## + Fold2.Rep5: alpha=0.90284, lambda=0.445782
## - Fold2.Rep5: alpha=0.90284, lambda=0.445782
## + Fold2.Rep5: alpha=0.32570, lambda=0.081177
## - Fold2.Rep5: alpha=0.32570, lambda=0.081177
## + Fold2.Rep5: alpha=0.75140, lambda=0.561138
## - Fold2.Rep5: alpha=0.75140, lambda=0.561138
## + Fold2.Rep5: alpha=0.03599, lambda=0.001115
## - Fold2.Rep5: alpha=0.03599, lambda=0.001115
## + Fold2.Rep5: alpha=0.25504, lambda=2.954617
## - Fold2.Rep5: alpha=0.25504, lambda=2.954617
## + Fold2.Rep5: alpha=0.86475, lambda=0.043683
## - Fold2.Rep5: alpha=0.86475, lambda=0.043683
## + Fold2.Rep5: alpha=0.10863, lambda=0.154091
## - Fold2.Rep5: alpha=0.10863, lambda=0.154091
## + Fold2.Rep5: alpha=0.98116, lambda=7.405037
## - Fold2.Rep5: alpha=0.98116, lambda=7.405037
## + Fold2.Rep5: alpha=0.94388, lambda=0.002046
## - Fold2.Rep5: alpha=0.94388, lambda=0.002046
## + Fold3.Rep5: alpha=0.63950, lambda=0.004507
## - Fold3.Rep5: alpha=0.63950, lambda=0.004507
## + Fold3.Rep5: alpha=0.04530, lambda=0.016509
## - Fold3.Rep5: alpha=0.04530, lambda=0.016509
## + Fold3.Rep5: alpha=0.97420, lambda=0.004648
## - Fold3.Rep5: alpha=0.97420, lambda=0.004648
## + Fold3.Rep5: alpha=0.34773, lambda=0.060861
## - Fold3.Rep5: alpha=0.34773, lambda=0.060861
## + Fold3.Rep5: alpha=0.51433, lambda=0.001761
## - Fold3.Rep5: alpha=0.51433, lambda=0.001761
## + Fold3.Rep5: alpha=0.31833, lambda=0.479416
## - Fold3.Rep5: alpha=0.31833, lambda=0.479416
## + Fold3.Rep5: alpha=0.74806, lambda=0.327981
## - Fold3.Rep5: alpha=0.74806, lambda=0.327981
Chang Liu 40
R for Data Science Lecture 5
## + Fold3.Rep5: alpha=0.14914, lambda=0.028964
## - Fold3.Rep5: alpha=0.14914, lambda=0.028964
## + Fold3.Rep5: alpha=0.84515, lambda=0.897325
## - Fold3.Rep5: alpha=0.84515, lambda=0.897325
## + Fold3.Rep5: alpha=0.93503, lambda=0.082985
## - Fold3.Rep5: alpha=0.93503, lambda=0.082985
## + Fold3.Rep5: alpha=0.38077, lambda=1.148290
## - Fold3.Rep5: alpha=0.38077, lambda=1.148290
## + Fold3.Rep5: alpha=0.84280, lambda=0.045415
## - Fold3.Rep5: alpha=0.84280, lambda=0.045415
## + Fold3.Rep5: alpha=0.98348, lambda=0.006142
## - Fold3.Rep5: alpha=0.98348, lambda=0.006142
## + Fold3.Rep5: alpha=0.78895, lambda=0.042054
## - Fold3.Rep5: alpha=0.78895, lambda=0.042054
## + Fold3.Rep5: alpha=0.52859, lambda=0.428235
## - Fold3.Rep5: alpha=0.52859, lambda=0.428235
## + Fold3.Rep5: alpha=0.73053, lambda=0.015889
## - Fold3.Rep5: alpha=0.73053, lambda=0.015889
## + Fold3.Rep5: alpha=0.90284, lambda=0.445782
## - Fold3.Rep5: alpha=0.90284, lambda=0.445782
## + Fold3.Rep5: alpha=0.32570, lambda=0.081177
## - Fold3.Rep5: alpha=0.32570, lambda=0.081177
## + Fold3.Rep5: alpha=0.75140, lambda=0.561138
## - Fold3.Rep5: alpha=0.75140, lambda=0.561138
## + Fold3.Rep5: alpha=0.03599, lambda=0.001115
## - Fold3.Rep5: alpha=0.03599, lambda=0.001115
## + Fold3.Rep5: alpha=0.25504, lambda=2.954617
## - Fold3.Rep5: alpha=0.25504, lambda=2.954617
## + Fold3.Rep5: alpha=0.86475, lambda=0.043683
## - Fold3.Rep5: alpha=0.86475, lambda=0.043683
## + Fold3.Rep5: alpha=0.10863, lambda=0.154091
## - Fold3.Rep5: alpha=0.10863, lambda=0.154091
## + Fold3.Rep5: alpha=0.98116, lambda=7.405037
## - Fold3.Rep5: alpha=0.98116, lambda=7.405037
## + Fold3.Rep5: alpha=0.94388, lambda=0.002046
## - Fold3.Rep5: alpha=0.94388, lambda=0.002046
## + Fold4.Rep5: alpha=0.63950, lambda=0.004507
## - Fold4.Rep5: alpha=0.63950, lambda=0.004507
Chang Liu 41
R for Data Science Lecture 5
## + Fold4.Rep5: alpha=0.04530, lambda=0.016509
## - Fold4.Rep5: alpha=0.04530, lambda=0.016509
## + Fold4.Rep5: alpha=0.97420, lambda=0.004648
## - Fold4.Rep5: alpha=0.97420, lambda=0.004648
## + Fold4.Rep5: alpha=0.34773, lambda=0.060861
## - Fold4.Rep5: alpha=0.34773, lambda=0.060861
## + Fold4.Rep5: alpha=0.51433, lambda=0.001761
## - Fold4.Rep5: alpha=0.51433, lambda=0.001761
## + Fold4.Rep5: alpha=0.31833, lambda=0.479416
## - Fold4.Rep5: alpha=0.31833, lambda=0.479416
## + Fold4.Rep5: alpha=0.74806, lambda=0.327981
## - Fold4.Rep5: alpha=0.74806, lambda=0.327981
## + Fold4.Rep5: alpha=0.14914, lambda=0.028964
## - Fold4.Rep5: alpha=0.14914, lambda=0.028964
## + Fold4.Rep5: alpha=0.84515, lambda=0.897325
## - Fold4.Rep5: alpha=0.84515, lambda=0.897325
## + Fold4.Rep5: alpha=0.93503, lambda=0.082985
## - Fold4.Rep5: alpha=0.93503, lambda=0.082985
## + Fold4.Rep5: alpha=0.38077, lambda=1.148290
## - Fold4.Rep5: alpha=0.38077, lambda=1.148290
## + Fold4.Rep5: alpha=0.84280, lambda=0.045415
## - Fold4.Rep5: alpha=0.84280, lambda=0.045415
## + Fold4.Rep5: alpha=0.98348, lambda=0.006142
## - Fold4.Rep5: alpha=0.98348, lambda=0.006142
## + Fold4.Rep5: alpha=0.78895, lambda=0.042054
## - Fold4.Rep5: alpha=0.78895, lambda=0.042054
## + Fold4.Rep5: alpha=0.52859, lambda=0.428235
## - Fold4.Rep5: alpha=0.52859, lambda=0.428235
## + Fold4.Rep5: alpha=0.73053, lambda=0.015889
## - Fold4.Rep5: alpha=0.73053, lambda=0.015889
## + Fold4.Rep5: alpha=0.90284, lambda=0.445782
## - Fold4.Rep5: alpha=0.90284, lambda=0.445782
## + Fold4.Rep5: alpha=0.32570, lambda=0.081177
## - Fold4.Rep5: alpha=0.32570, lambda=0.081177
## + Fold4.Rep5: alpha=0.75140, lambda=0.561138
## - Fold4.Rep5: alpha=0.75140, lambda=0.561138
## + Fold4.Rep5: alpha=0.03599, lambda=0.001115
## - Fold4.Rep5: alpha=0.03599, lambda=0.001115
Chang Liu 42
R for Data Science Lecture 5
## + Fold4.Rep5: alpha=0.25504, lambda=2.954617
## - Fold4.Rep5: alpha=0.25504, lambda=2.954617
## + Fold4.Rep5: alpha=0.86475, lambda=0.043683
## - Fold4.Rep5: alpha=0.86475, lambda=0.043683
## + Fold4.Rep5: alpha=0.10863, lambda=0.154091
## - Fold4.Rep5: alpha=0.10863, lambda=0.154091
## + Fold4.Rep5: alpha=0.98116, lambda=7.405037
## - Fold4.Rep5: alpha=0.98116, lambda=7.405037
## + Fold4.Rep5: alpha=0.94388, lambda=0.002046
## - Fold4.Rep5: alpha=0.94388, lambda=0.002046
## + Fold5.Rep5: alpha=0.63950, lambda=0.004507
## - Fold5.Rep5: alpha=0.63950, lambda=0.004507
## + Fold5.Rep5: alpha=0.04530, lambda=0.016509
## - Fold5.Rep5: alpha=0.04530, lambda=0.016509
## + Fold5.Rep5: alpha=0.97420, lambda=0.004648
## - Fold5.Rep5: alpha=0.97420, lambda=0.004648
## + Fold5.Rep5: alpha=0.34773, lambda=0.060861
## - Fold5.Rep5: alpha=0.34773, lambda=0.060861
## + Fold5.Rep5: alpha=0.51433, lambda=0.001761
## - Fold5.Rep5: alpha=0.51433, lambda=0.001761
## + Fold5.Rep5: alpha=0.31833, lambda=0.479416
## - Fold5.Rep5: alpha=0.31833, lambda=0.479416
## + Fold5.Rep5: alpha=0.74806, lambda=0.327981
## - Fold5.Rep5: alpha=0.74806, lambda=0.327981
## + Fold5.Rep5: alpha=0.14914, lambda=0.028964
## - Fold5.Rep5: alpha=0.14914, lambda=0.028964
## + Fold5.Rep5: alpha=0.84515, lambda=0.897325
## - Fold5.Rep5: alpha=0.84515, lambda=0.897325
## + Fold5.Rep5: alpha=0.93503, lambda=0.082985
## - Fold5.Rep5: alpha=0.93503, lambda=0.082985
## + Fold5.Rep5: alpha=0.38077, lambda=1.148290
## - Fold5.Rep5: alpha=0.38077, lambda=1.148290
## + Fold5.Rep5: alpha=0.84280, lambda=0.045415
## - Fold5.Rep5: alpha=0.84280, lambda=0.045415
## + Fold5.Rep5: alpha=0.98348, lambda=0.006142
## - Fold5.Rep5: alpha=0.98348, lambda=0.006142
## + Fold5.Rep5: alpha=0.78895, lambda=0.042054
## - Fold5.Rep5: alpha=0.78895, lambda=0.042054
Chang Liu 43
R for Data Science Lecture 5
## + Fold5.Rep5: alpha=0.52859, lambda=0.428235
## - Fold5.Rep5: alpha=0.52859, lambda=0.428235
## + Fold5.Rep5: alpha=0.73053, lambda=0.015889
## - Fold5.Rep5: alpha=0.73053, lambda=0.015889
## + Fold5.Rep5: alpha=0.90284, lambda=0.445782
## - Fold5.Rep5: alpha=0.90284, lambda=0.445782
## + Fold5.Rep5: alpha=0.32570, lambda=0.081177
## - Fold5.Rep5: alpha=0.32570, lambda=0.081177
## + Fold5.Rep5: alpha=0.75140, lambda=0.561138
## - Fold5.Rep5: alpha=0.75140, lambda=0.561138
## + Fold5.Rep5: alpha=0.03599, lambda=0.001115
## - Fold5.Rep5: alpha=0.03599, lambda=0.001115
## + Fold5.Rep5: alpha=0.25504, lambda=2.954617
## - Fold5.Rep5: alpha=0.25504, lambda=2.954617
## + Fold5.Rep5: alpha=0.86475, lambda=0.043683
## - Fold5.Rep5: alpha=0.86475, lambda=0.043683
## + Fold5.Rep5: alpha=0.10863, lambda=0.154091
## - Fold5.Rep5: alpha=0.10863, lambda=0.154091
## + Fold5.Rep5: alpha=0.98116, lambda=7.405037
## - Fold5.Rep5: alpha=0.98116, lambda=7.405037
## + Fold5.Rep5: alpha=0.94388, lambda=0.002046
## - Fold5.Rep5: alpha=0.94388, lambda=0.002046
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 0.255, lambda = 2.95 on full training set
# Model Prediction
y_hat_pre <- predict(elastic_model, X)
y_hat_pre
## Mazda RX4 Mazda RX4 Wag Datsun 710 Hornet 4 Drive
## -76.689730 -63.507267 -101.480805 -3.325839
## Hornet Sportabout Valiant Duster 360 Merc 240D
## 93.829305 4.352543 106.753683 -93.017947
## Merc 230 Merc 280 Merc 280C Merc 450SE
## -101.213698 -41.043819 -46.153274 114.245778
## Merc 450SL Merc 450SLC Cadillac Fleetwood Lincoln Continental
## 88.607576 88.721132 183.384131 202.849050
Chang Liu 44
R for Data Science Lecture 5
## Chrysler Imperial Fiat 128 Honda Civic Toyota Corolla
## 209.473900 -133.055889 -197.967302 -162.997974
## Toyota Corona Dodge Challenger AMC Javelin Camaro Z28
## -100.028842 86.105235 76.459696 129.422705
## Pontiac Firebird Fiat X1-9 Porsche 914-2 Lotus Europa
## 122.084701 -146.857166 -107.839739 -155.648579
## Ford Pantera L Ferrari Dino Maserati Bora Volvo 142E
## 100.300718 -67.158840 74.668657 -83.272098
# Plot
plot(elastic_model, main = "Elastic Net Regression")
Elastic Net Regression
Regularization Parameter
0.0165093099991542 0.0829852579927621
0.0289642507893573 0.154090592241317
0.0420535300675737 0.327981224069327
0.0436832243254204 0.428235457044259
0.0454153120956423 0.445781722010769
0.0608610736326484 0.47941572765797
0.0811774345923398 0.561137521217022
RMSE (Repeated Cross−Validation)
42
40
38
36
0.0 0.2 0.4 0.6 0.8 1.0
Mixing Percentage
Chang Liu 45
R for Data Science Lecture 5
K-nearest Neighbors Algorithm
K-Nearest Neighbor or K-NN is a Supervised Non-linear classification algorithm. K-NN is a
Non-parametric algorithm i.e it doesn’t make any assumption about underlying data or its
distribution. It is one of the simplest and widely used algorithm which depends on it’s k
value(Neighbors) and finds it’s applications in many industries like finance industry, healthcare
industry etc.
In the KNN algorithm, K specifies the number of neighbors and its algorithm is as follows:
• Choose the number K of neighbor.
• Take the K Nearest Neighbor of unknown data point according to distance.
• Among the K-neighbors, Count the number of data points in each category.
• Assign the new data point to a category, where you counted the most neighbors.
For the Nearest Neighbor classifier, the distance between two points is expressed in the form of
Euclidean Distance.
df <- data(iris) ##load data
head(iris) ## see the studcture
Chang Liu 46
R for Data Science Lecture 5
## [Link] [Link] [Link] [Link] Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
##Generate a random number that is 90% of the total number of rows in dataset.
ran <- sample(1:nrow(iris), 0.9 * nrow(iris))
##the normalization function is created
nor <-function(x) { (x -min(x))/(max(x)-min(x)) }
##Run nomalization on first 4 coulumns of dataset because they are the predictors
iris_norm <- [Link](lapply(iris[,c(1,2,3,4)], nor))
summary(iris_norm)
## [Link] [Link] [Link] [Link]
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.00000
## 1st Qu.:0.2222 1st Qu.:0.3333 1st Qu.:0.1017 1st Qu.:0.08333
## Median :0.4167 Median :0.4167 Median :0.5678 Median :0.50000
## Mean :0.4287 Mean :0.4406 Mean :0.4675 Mean :0.45806
## 3rd Qu.:0.5833 3rd Qu.:0.5417 3rd Qu.:0.6949 3rd Qu.:0.70833
## Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.00000
##extract training set
iris_train <- iris_norm[ran,]
##extract testing set
iris_test <- iris_norm[-ran,]
##extract 5th column of train dataset because it will be used as 'cl' argument in knn
,→ function.
iris_target_category <- iris[ran,5]
##extract 5th column if test dataset to measure the accuracy
iris_test_category <- iris[-ran,5]
##load the package class
library(class)
##run knn function
pr <- knn(iris_train,iris_test,cl=iris_target_category,k=13)
Chang Liu 47
R for Data Science Lecture 5
##create confusion matrix
tab <- table(pr,iris_test_category)
##this function divides the correct predictions by total number of predictions that
,→ tell us how accurate teh model is.
accuracy <- function(x){sum(diag(x)/(sum(rowSums(x)))) * 100}
accuracy (tab)
## [1] 100
In the iris dataset that is already available in R, I have run the k-nearest neighbor algorithm
that gave me 80% accurate result. First, I normalized the data to convert [Link],
[Link], [Link] and [Link] into a standardized 0-to-1 form so that we can fit
them into one box (one graph) and also because our main objective is to predict whether a
flower is virginica, Versicolor, or setosa and that is why I excluded the column 5 and stored
it into another variable called iris_target_category. Then, I separated the normalized values
into training and testing dataset. Imagine it this way, that the values from training dataset
are firstly drawn on a graph and after we run knn function with all the necessary arguments,
we introduce testing dataset’s values into the graph and calculate Euclidean distance with
each and every already stored point in graph. Now, although we know which flower it is in
testing dataset, we still predict the values and store them in variable called “pr” so that we can
compare predicted values with original testing dataset’s values. This way we understand the
accuracy of our model and if we are to get new 50 values in future and we are asked to predict
the category of those 50 values, we can do that with this model.
Chang Liu 48
R for Data Science Lecture 5
Decision Tree
Decision Trees are versatile Machine Learning algorithm that can perform both classification
and regression tasks. They are very powerful algorithms, capable of fitting complex datasets.
Besides, decision trees are fundamental components of random forests, which are among the
most potent Machine Learning algorithms available today.
library(tidyverse)
library(rpart)
library(partykit)
## Loading required package: grid
## Loading required package: libcoin
## Loading required package: mvtnorm
happiness2017 <- read_csv("data/happinessdata_2017.csv")
## Rows: 1420 Columns: 10
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (2): country, continent
## dbl (8): year, life_ladder, logGDP, social_support, life_exp, freedom, gener...
##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
happiness2017 <- happiness2017 %>%
mutate(life_exp_category = case_when(life_exp > 60 ~ "Good",
life_exp <= 60 ~ "Poor"))
[Link](834)
n <- nrow(happiness2017); # number of obs in the full dataset n
# Add row IDs to happiness data
happiness2017 <- happiness2017 %>% rowid_to_column() # Random sample of 80% of row
,→ indices
Chang Liu 49
R for Data Science Lecture 5
training_indices <- sample(1:n, size=round(0.8*n))
train <- happiness2017 %>% filter(rowid %in% training_indices)
test <- happiness2017 %>% filter(!(rowid %in% training_indices))
# Fit the tree based on training data
tree1 <- rpart(life_exp_category ~ social_support, data=train)
plot([Link](tree1), type="simple")
1
social_support
≥ 0.83 < 0.83
2 3
Good
social_support
(n = 576, err = 10.6%)
≥ 0.725 < 0.725
4 5
Good Poor
(n = 315, err = 42.2%) (n = 230, err = 29.6%)
# Fit the tree based on training data
tree2 <- rpart(life_exp_category ~ logGDP + social_support + freedom + generosity,
,→ data=train)
plot([Link](tree2), type="simple")
Chang Liu 50
R for Data Science Lecture 5
1
logGDP
2≥ 8.723 < 8.723 3
Good
logGDP
(n = 750, err = 8.1%)
4 ≥ 8.265 < 8.265
11
Poor
social_support
(n = 279, err = 11.5%)
5 ≥ 0.737 < 0.737
10
Poor
logGDP
(n = 34, err = 17.6%)
6< 8.504 ≥ 8.504 7
Good
social_support
(n = 44, err = 9.1%)
8≥ 0.833< 0.8339
Good Poor
(n = 7, err = 0.0%)
(n = 17, err = 0.0%)
### Tree from (b)
predicted_tree1 <- predict(tree1, newdata = test, type="class")
table(predicted_tree1, test$life_exp_category)
##
## predicted_tree1 Good Poor
## Good 183 47
## Poor 11 39
m <- table(predicted_tree1, test$life_exp_category)
tp <- m[1,1] / sum(m[,1])
tn <- m[2,2] / sum(m[,2])
accuracy <- sum(diag(m))/sum(m)
c(tp, tn, accuracy)
## [1] 0.9432990 0.4534884 0.7928571
Chang Liu 51
R for Data Science Lecture 5
predicted_tree2 <- predict(tree2, newdata = test, type="class")
table(predicted_tree2, test$life_exp_category)
##
## predicted_tree2 Good Poor
## Good 188 18
## Poor 6 68
m <- table(predicted_tree2, test$life_exp_category)
tp <- m[1,1] / sum(m[,1])
tn <- m[2,2] / sum(m[,2])
accuracy <- sum(diag(m))/sum(m)
c(tp, tn, accuracy)
## [1] 0.9690722 0.7906977 0.9142857
Chang Liu 52
R for Data Science Lecture 5
Bagging (extension: Random forest)
Bagging is a powerful method to improve the performance of simple models and reduce overfitting
of more complex models. The principle is very easy to understand, instead of fitting the model on
one sample of the population, several models are fitted on different samples (with replacement)
of the population. Then, these models are aggregated by using their average, weighted average
or a voting system (mainly for classification).
Though bagging reduces the explanatory ability of your model, it makes it much more robust
and able to get the “big picture” from your data.
To build a bagged trees, the process is easy. Let’s say you want 100 models that you will average,
for each of the hundred iterations you will:
• Take a sample with replacement of your original dataset
• Train a regression tree on this sample (you can learn more on classification trees there,
regression trees are similar)
• Save the model with your other models
Once you trained all your models, to get a prediction from your bagged model on new data, you
will need to:
• Get the estimate from each of the individual trees you saved.
• Average the estimates.
library(rpart)
require(ggplot2)
library([Link])
##
## Attaching package: '[Link]'
## The following objects are masked from 'package:dplyr':
##
## between, first, last
## The following object is masked from 'package:purrr':
##
## transpose
Chang Liu 53
R for Data Science Lecture 5
[Link](456)
##Reading data
bagging_data=[Link](airquality)
ggplot(bagging_data,aes(Wind,Ozone))+geom_point()+ggtitle("Ozone vs wind speed")
## Warning: Removed 37 rows containing missing values (geom_point).
Ozone vs wind speed
150
100
Ozone
50
5 10 15 20
Wind
data_test=[Link](bagging_data[,.(Ozone,Wind)])
##Training data
train_index=[Link](nrow(data_test),size=round(nrow(data_test)*0.8),replace = F)
data_test[train_index,train:=TRUE][-train_index,train:=FALSE]
data_test
## Ozone Wind train
## 1: 41 7.4 TRUE
## 2: 36 8.0 FALSE
Chang Liu 54
R for Data Science Lecture 5
## 3: 12 12.6 TRUE
## 4: 18 11.5 TRUE
## 5: 28 14.9 TRUE
## ---
## 112: 14 16.6 TRUE
## 113: 30 6.9 TRUE
## 114: 14 14.3 TRUE
## 115: 18 8.0 TRUE
## 116: 20 11.5 TRUE
##Model without bagging
no_bag_model=rpart(Ozone~Wind,data_test[train_index],control=[Link](minsplit=6))
result_no_bag=predict(no_bag_model,bagging_data)
##Training of the bagged model
n_model=100
bagged_models=list()
for (i in 1:n_model)
{
new_sample=sample(train_index,size=length(train_index),replace=T)
,→ bagged_models=c(bagged_models,list(rpart(Ozone~Wind,data_test[new_sample],control=[Link](m
}
##Getting estimate from the bagged model
bagged_result=NULL
i=0
for (from_bag_model in bagged_models)
{
if ([Link](bagged_result))
bagged_result=predict(from_bag_model,bagging_data)
else
bagged_result=(i*bagged_result+predict(from_bag_model,bagging_data))/(i+1)
i=i+1
}
Chang Liu 55
R for Data Science Lecture 5
Unique Value
df <- [Link](team=c('A', 'A', 'B', 'B', 'C', 'C'),
points=c(90, 99, 90, 85, 90, 85),
assists=c(33, 33, 31, 39, 34, 34),
rebounds=c(30, 28, 24, 24, 28, 28))
unique(df$team)
## [1] "A" "B" "C"
unique(df$points)
## [1] 90 99 85
#find and sort unique values in 'points' column
sort(unique(df$points))
## [1] 85 90 99
#find and sort unique values in 'points' column
sort(unique(df$points), decreasing=TRUE)
## [1] 99 90 85
#find and count unique values in 'points' column
table(df$points)
##
## 85 90 99
## 2 3 1
Chang Liu 56
R for Data Science Lecture 5
Length
#create vector
my_vector <- c(2, 7, 6, 6, 9, 10, 14, 13, 4, 20, NA)
#calculate length of vector
length(my_vector)
## [1] 11
my_vector <- c(2, 7, 6, 6, 9, 10, 14, 13, 4, 20, NA)
#calculate length of vector, excluding NA values
sum()
## [1] 10
#create list
my_list <- list(A=1:5, B=c('hey', 'hi'), C=c(3, 5, 7))
#calculate length of entire list
length(my_list)
## [1] 3
#calculate length of first element in list
length(my_list[[1]])
## [1] 5
#create data frame
df <- [Link](team=c('A', 'B', 'B', 'B', 'C', 'D'),
points=c(10, 15, 29, 24, 30, 31))
nrow(df)
## [1] 6
Chang Liu 57
R for Data Science Lecture 5
#define string
my_string <- "hey there"
#calculate length of string
length(my_string)
## [1] 1
#define string
my_string <- "hey there"
#calculate total characters in string
nchar(my_string)
## [1] 9
Chang Liu 58
R for Data Science Lecture 5
Gsub
The gsub() function in R can be used to replace all occurrences of certain text within a string
in R.
gsub(pattern, replacement, x)
• pattern: The pattern to look for
• replacement: The replacement for the pattern
• x: The string to search
x <- "This is a fun sentence"
#replace 'fun' with 'great'
x <- gsub('fun', 'great', x)
#view updated string
x
## [1] "This is a great sentence"
#define vector
x <- c('Mavs', 'Mavs', 'Spurs', 'Nets', 'Spurs', 'Mavs')
#replace 'Mavs' with 'M'
x <- gsub('Mavs', 'M', x)
#view updated vector
x
## [1] "M" "M" "Spurs" "Nets" "Spurs" "M"
#define vector
x <- c('A', 'A', 'B', 'C', 'D', 'D')
#replace 'A' or 'B' or 'C' with 'X'
Chang Liu 59
R for Data Science Lecture 5
x <- gsub('A|B|C', 'X', x)
#view updated string
x
## [1] "X" "X" "X" "X" "D" "D"
#define data frame
df <- [Link](team=c('A', 'B', 'C', 'D'),
conf=c('West', 'West', 'East', 'East'),
points=c(99, 98, 92, 87),
rebounds=c(18, 22, 26, 19))
#replace 'West' and 'East' with 'W' and 'E'
df$conf <- gsub('West', 'W', df$conf)
df$conf <- gsub('East', 'E', df$conf)
#view updated data frame
df
## team conf points rebounds
## 1 A W 99 18
## 2 B W 98 22
## 3 C E 92 26
## 4 D E 87 19
Chang Liu 60
R for Data Science Lecture 5
sampling
Stratified Sampling
Researchers often take samples from a population and use the data from the sample to draw
conclusions about the population as a whole.
One commonly used sampling method is stratified random sampling, in which a population is
split into groups and a certain number of members from each group are randomly selected to
be included in the sample.
#make this example reproducible
[Link](1)
#create data frame
df <- [Link](grade = rep(c('Freshman', 'Sophomore', 'Junior', 'Senior'),
,→ each=100),
gpa = rnorm(400, mean=85, sd=3))
#view first six rows of data frame
head(df)
## grade gpa
## 1 Freshman 83.12064
## 2 Freshman 85.55093
## 3 Freshman 82.49311
## 4 Freshman 89.78584
## 5 Freshman 85.98852
## 6 Freshman 82.53859
library(dplyr)
#obtain stratified sample
strat_sample <- df %>%
group_by(grade) %>%
sample_n(size=10)
#find frequency of students from each grade
table(strat_sample$grade)
Chang Liu 61
R for Data Science Lecture 5
##
## Freshman Junior Senior Sophomore
## 10 10 10 10
library(dplyr)
#obtain stratified sample
strat_sample <- df %>%
group_by(grade) %>%
sample_frac(size=.15)
#find frequency of students from each grade
table(strat_sample$grade)
##
## Freshman Junior Senior Sophomore
## 15 15 15 15
Chang Liu 62
R for Data Science Lecture 5
Cluster Sampling
One commonly used sampling method is cluster sampling, in which a population is split into
clusters and all members of some clusters are chosen to be included in the sample.
[Link](1)
#create data frame
df <- [Link](tour = rep(1:10, each=20),
experience = rnorm(200, mean=7, sd=1))
#view first six rows of data frame
head(df)
## tour experience
## 1 1 6.373546
## 2 1 7.183643
## 3 1 6.164371
## 4 1 8.595281
## 5 1 7.329508
## 6 1 6.179532
#randomly choose 4 tour groups out of the 10
clusters <- sample(unique(df$tour), size=4, replace=F)
#define sample as all members who belong to one of the 4 tour groups
cluster_sample <- df[df$tour %in% clusters, ]
#view how many customers came from each tour
table(cluster_sample$tour)
##
## 1 2 3 7
## 20 20 20 20
Chang Liu 63
R for Data Science Lecture 5
Systematic Sampling
One commonly used sampling method is systematic sampling, which is implemented with a
simple two step process:
1. Place each member of a population in some order.
2. Choose a random starting point and select every nth member to be in the sample.
#make this example reproducible
[Link](1)
#create simple function to generate random last names
randomNames <- function(n = 5000) {
[Link](paste0, replicate(5, sample(LETTERS, n, TRUE), FALSE))
}
#create data frame
df <- [Link](last_name = randomNames(500),
gpa = rnorm(500, mean=82, sd=3))
#view first six rows of data frame
head(df)
## last_name gpa
## 1 YLGRG 74.66755
## 2 DCVUK 80.74210
## 3 GZXSE 80.89685
## 4 ARZOG 80.31026
## 5 BNVRR 77.83073
## 6 WMWJM 80.10269
#define function to obtain systematic sample
obtain_sys = function(N,n){
k = ceiling(N/n)
r = sample(1:k, 1)
seq(r, r + k*(n-1), k)
}
#obtain systematic sample
sys_sample_df = df[obtain_sys(nrow(df), 100), ]
Chang Liu 64
R for Data Science Lecture 5
#view first six rows of data frame
head(sys_sample_df)
## last_name gpa
## 5 BNVRR 77.83073
## 10 SBTFE 81.51290
## 15 VPJTO 80.63059
## 20 OVQCE 83.80557
## 25 NLJRM 83.35642
## 30 YMCZO 82.31994
Chang Liu 65
Common questions
Powered by AIAltering alpha from 0.84280 to 0.10863 between folds significantly affects the learning rate of the model. An alpha of 0.84280 implies a higher learning rate, allowing the model to make larger updates in the optimization process, potentially speeding up convergence but increasing the risk of overshooting optimal values. Conversely, an alpha of 0.10863 suggests a slower learning rate which could enhance stability and precision in the optimization process but might require more iterations for convergence, potentially leading to underfitting if not adjusted correctly .
Repeated updates of parameters such as alpha=0.34570 and lambda=0.081177 across different folds assist in ensuring consistent model convergence. These repeated settings can create a stable learning environment across varying data splits, promoting iterative learning that reliably approaches the optimal solution. The specific combination reflects a harmony between learning speed (alpha) and model complexity (lambda), which contributes to smoothly achieving convergence without large parameter swings .
The lambda parameter in Fold1.Rep1 and Fold1.Rep2 ranges from 0.001115 to 7.405037. In data modeling, specifically in techniques like regularization, lambda (often the regularization parameter) controls the trade-off between fitting the training data well and keeping the model parameters small to avoid overfitting. A smaller lambda value will prioritize fitting the training data well, possibly at the cost of overfitting, while a larger lambda value will prioritize smaller coefficients to increase model generalization .
Optimal selection of parameter sets such as alpha=0.98348 and lambda=0.006142 helps in fine-tuning the balance between model flexibility and simplicity. A high alpha aids in faster convergence while a low lambda suggests minor regularization, preventing extreme parameter values and reducing model complexity. This careful balancing can minimize overfitting by ensuring the model captures essential data patterns but remains generalized enough for unseen data, thereby enhancing predictive reliability .
The diverse ranges of alpha values across data folds underscore the need for flexibility in model training and evaluation by demonstrating the varying rate of adaptation required for different data complexities. Such variability forces models to be adaptable and responsive to different data subtleties, ensuring comprehensive learning while managing convergence stability. Variability in alpha mirrors different learning constraints that could be caused by data noise, encouraging nuanced hyperparameter tuning to improve overall model resiliency in capturing critical trends or patterns .
A lambda range from 0.001115 to 0.897325 indicates variability in the degree of regularization applied across folds. This affects model performance by modulating the trade-off between bias and variance, with lower values leading to potentially higher variance and more complex models, while higher values produce more bias with simpler models. Such range impacts computational cost by varying the required convergence iteration counts, where too low lambda values can increase iterations due to more detailed pattern fitting computations and higher values can lead to faster convergence but with potentially less accurate models. This sensitivity necessitates careful balance between computational resources and model accuracy .
The consistent appearance of certain alpha values suggests that these values may contribute to model stability across different folds and repetitions. This consistency could indicate that certain alpha settings offer a balanced convergence speed and model adaptability across diverse datasets, enhancing overall model robustness. It shows that these values likely provide a reliable baseline performance, reducing the variability in model predictions across the validation process .
The combination of irregular alpha and lambda values like alpha=0.25504 and lambda=2.954617 can substantially affect predictive accuracy. A relatively low alpha suggests a slower learning rate, potentially requiring more iterations but offering stability, while a high lambda value implies strong regularization, potentially leading to oversimplified model outputs. This skew towards underfitting because of excessive shrinkage and slow parameter adaption can result in poor capture of significant data patterns, thereby reducing predictive accuracy and model reliability .
Variations in alpha and lambda across different folds influence model validation by providing insights into the stability and robustness of model performance across different data subsets. Alpha, often related to learning rate or scaling factor in algorithms, affects convergence speed and direction, while lambda adjusts the penalty for model complexity. Different combinations can lead to variations in performance metrics across folds, indicating whether a model is overfitted or capable of generalizing well. Validating through cross-validation helps in identifying the most consistent parameter settings that generalize effectively .
A lambda value as large as 7.405037 introduces a significant penalty for model complexity, which in optimization techniques within R for data science would likely lead to simpler models by constraining the adjustable parameter space with higher regularization forces. This might result in models that underfit the training data due to excessive shrinkage of parameter values, potentially improving generalization but at the risk of losing important data patterns .
You might also like
- Linear Regression and Regularization TechniquesNo ratings yetLinear Regression and Regularization Techniques27 pages
- Supervised Learning & Regularization in PythonNo ratings yetSupervised Learning & Regularization in Python29 pages
- Regularization Techniques in Machine LearningNo ratings yetRegularization Techniques in Machine Learning36 pages
- Model Evaluation Metrics in Machine LearningNo ratings yetModel Evaluation Metrics in Machine Learning13 pages
- MConverter - Eu No2 Linear Regression Lab-W26No ratings yetMConverter - Eu No2 Linear Regression Lab-W267 pages
- Causal Lasso and Model Selection TechniquesNo ratings yetCausal Lasso and Model Selection Techniques38 pages
- High-Dimensional Linear Regression TechniquesNo ratings yetHigh-Dimensional Linear Regression Techniques6 pages
- Supervised Machine Learning: Regression InsightsNo ratings yetSupervised Machine Learning: Regression Insights11 pages
- Regression Techniques in Machine LearningNo ratings yetRegression Techniques in Machine Learning56 pages
- Machine Learning: Overfitting & RegressionNo ratings yetMachine Learning: Overfitting & Regression16 pages
- Ridge Regression Explained: Key ConceptsNo ratings yetRidge Regression Explained: Key Concepts73 pages
- Understanding Logistic and Ridge RegressionNo ratings yetUnderstanding Logistic and Ridge Regression8 pages
- Linear Regression Fundamentals ExplainedNo ratings yetLinear Regression Fundamentals Explained6 pages
- Polynomial and Regularized Regression TechniquesNo ratings yetPolynomial and Regularized Regression Techniques9 pages
- Comprehensive Guide to Regression ModelsNo ratings yetComprehensive Guide to Regression Models10 pages
- Polynomial Regression and Overfitting AnalysisNo ratings yetPolynomial Regression and Overfitting Analysis71 pages
- Day 4 Supervised Learning and Linear RegressionNo ratings yetDay 4 Supervised Learning and Linear Regression9 pages
- Cross-Validation and Regularization TechniquesNo ratings yetCross-Validation and Regularization Techniques7 pages
- Regularization Techniques: Ridge & LassoNo ratings yetRegularization Techniques: Ridge & Lasso7 pages
- Supervised Learning and Predictive ModelingNo ratings yetSupervised Learning and Predictive Modeling6 pages
- Machine Learning Overview by dcamenischNo ratings yetMachine Learning Overview by dcamenisch12 pages
- Supervised Machine Learning: Regression InsightsNo ratings yetSupervised Machine Learning: Regression Insights22 pages
- Understanding Linear and Polynomial RegressionNo ratings yetUnderstanding Linear and Polynomial Regression24 pages
- Overfitting and Cross-Validation ExplainedNo ratings yetOverfitting and Cross-Validation Explained32 pages
- Data Structures & Algorithms Course OverviewNo ratings yetData Structures & Algorithms Course Overview101 pages
- Modular Bi-Propellant Rocket Engine DevelopmentNo ratings yetModular Bi-Propellant Rocket Engine Development15 pages
- WinPE Startup Script for Boot Mode DetectionNo ratings yetWinPE Startup Script for Boot Mode Detection3 pages
- ACS Edu Mobile Legends Tournament RulesNo ratings yetACS Edu Mobile Legends Tournament Rules14 pages
- MS Word Project: Business Document GuideNo ratings yetMS Word Project: Business Document Guide3 pages
- GlobalSign Client Certificates API GuideNo ratings yetGlobalSign Client Certificates API Guide48 pages
- Coaxial Cable Dielectric Testing StandardNo ratings yetCoaxial Cable Dielectric Testing Standard5 pages
- PS2 Laser Potentiometer Adjustment GuideNo ratings yetPS2 Laser Potentiometer Adjustment Guide10 pages