Advanced Analytics
Welcome
I BUILD A MODEL
1
Introduction
2
Data understanding
2.1
Imort Data
2.2
Data overview
2.3
Data splitting
2.4
Data exploration
3
Model building
3.1
Model specification
3.2
Model training
3.3
Model predictions
3.4
Model evaluation
II RESAMPLING
4
Validation set
5
Data understanding
5.1
Import data
5.2
Data splitting
5.3
Validation set
6
Model building
6.1
Model specification
6.2
Evaluate models
6.3
Fit model 1
6.4
Fit model 2
6.5
Performance metrics
7
Train best model
8
Evaluate final model
III RECIPES
9
Data preprocessing
10
Data understanding
10.1
Import data
10.2
Data splitting
10.3
Validation set
11
Data preparation
11.1
recipe()
11.2
Helper functions
11.3
step_novel()
11.4
step_dummy()
11.5
step_zv()
11.6
step_normalize()
12
Model building
12.1
Specify model
12.2
Create workflow
12.3
Evaluate model
13
Last fit and evaluation
IV WORKFLOWS & MODELS
14
Workflows
15
Data preparation
15.1
Data overview
16
Data splitting
17
Create recipe and roles
17.1
Create features
17.1.1
Date
17.1.2
Dummy variables
17.1.3
Zero variance
17.1.4
Correlations
18
Model building
18.1
Logistic regression
18.2
Decision tree
18.3
Random forest
18.4
Boosted tree (XGBoost)
19
Recipe and Models
19.1
Fit models with workflows
19.1.1
Logistic regression
19.1.2
Decision tree
19.1.3
Random forest
19.1.4
XGBoost
19.2
Train models
19.2.1
Logistic regression
19.2.2
Decision tree
19.2.3
Random forest
19.2.4
XG Boost
19.3
Model recipe objects
19.3.1
Logistic regression
19.3.2
Decision tree
19.3.3
Random forest
19.3.4
XG Boost
19.4
Summary
20
Prediction
20.1
Logistic regression
20.1.1
ROC curve
20.1.2
AUC
20.1.3
Accuracy
20.1.4
Recall
20.1.5
Precision
References
Published with bookdown
Advanced Analytics with Tidymodels in R
References
Géron, Aurélien. 2019.
Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems
. O’Reilly Media.