---
title: "tidy xgboost"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{tidy xgboost}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

options(rlang_trace_top_env = rlang::current_env())
```

```{r setup, message=FALSE, warning=FALSE, results='hide'}
library(autostats)
library(workflows)
library(dplyr)
library(tune)
library(rsample)
library(hardhat)
library(broom.mixed)
library(Ckmeans.1d.dp)
library(igraph)
```

`autostats` provides convenient wrappers for modeling, visualizing, and predicting using a tidy workflow. The emphasis is on rapid iteration and quick results using an intuitive interface based off the `tibble` and `tidy_formula`. 

# Prepare data 

Set up the iris data set for modeling. Create dummies and any new columns before making the formula. This way the same formula can be use throughout the modeling and prediction process. 


```{r}
set.seed(34)

 iris %>%
  dplyr::as_tibble() %>% 
  framecleaner::create_dummies(remove_first_dummy  = TRUE) -> iris1

 iris1 %>%
 tidy_formula(target = Petal.Length) -> petal_form
 
 petal_form

```
Use the rsample package to split into train and validation sets.

```{r}
iris1 %>%
  rsample::initial_split() -> iris_split

iris_split %>%
  rsample::analysis() -> iris_train

iris_split %>%
  rsample::assessment() -> iris_val

iris_split
```


# Fit boosting models and visualize

Fit models to the training set using the formula to predict `Petal.Length`. Variable importance using gain for each `xgboost` model can be visualized.


## xgboost with grid search hyperparameter optimization

`auto_tune_xgboost` returns a workflow object with tuned parameters and requires some postprocessing to get a trained `xgb.Booster` object like `tidy_xgboost`.

`xgboost` also can be tuned using a grid that is created internally using `dials::grid_max_entropy`. The `n_iter` parameter is passed to `grid_size`. Parallelization is highly effective in this method, so the default argument `parallel = TRUE` is recommended. 

```{r eval=T}
iris_train %>%
  auto_tune_xgboost(formula = petal_form, n_iter = 5L,trees = 20L, loss_reduction = 2, mtry = 3, tune_method = "grid", parallel = FALSE, counts = TRUE) -> xgb_tuned_grid

xgb_tuned_grid %>%
  parsnip::fit(iris_train) %>% 
  parsnip::extract_fit_engine() -> xgb_tuned_fit_grid


xgb_tuned_fit_grid %>% 
  visualize_model()
```


## xgboost with default parameters

```{r}
iris_train %>%
  tidy_xgboost(formula = petal_form) -> xgb_base

```


## xgboost with hand-picked parameters

```{r}
iris_train %>% 
  tidy_xgboost(petal_form, 
               trees = 250L, 
               tree_depth = 3L, 
               sample_size = .5,
               mtry = .5,
               min_n = 2) -> xgb_opt


```


# predict on validation set

## make predictions 

Predictions are iteratively added to the validation data frame. The name of the column is
automatically created using the models name and the prediction target. 


```{r}

xgb_base %>%
  tidy_predict(newdata = iris_val, form = petal_form) -> iris_val2

xgb_opt %>% 
  tidy_predict(newdata = iris_val2, petal_form) -> iris_val3


iris_val3 %>% 
  names()
```

## predictions with eval_preds

Instead of evaluationg these prediction 1 by 1, This step is automated with `eval_preds`. This function is specifically designed to evaluate predicted columns with names given from `tidy_predict`.

```{r}
iris_val3 %>% 
  eval_preds() 
```

# get shapley values

`tidy_shap` has similar syntax to `tidy_predict` and can be used to get shapley values from `xgboost` models on a validation set. 


```{r}
xgb_base %>% 
  tidy_shap(newdata = iris_val, form = petal_form) -> shap_list

```

```{r}
shap_list$shap_tbl
```

```{r}
shap_list$shap_summary
```

```{r}
shap_list$swarmplot
```

```{r eval=FALSE, message=FALSE, warning=FALSE}
shap_list$scatterplots
```

## understand xgboost with other functions from the original package

Overfittingin the base config may be related to growing deep trees. 

```{r}
 xgb_base %>% 
  xgboost::xgb.plot.deepness()
```


```{r}
 xgb_base %>% 
  xgboost::xgb.plot.deepness()
```
Plot the first tree in the model. The small \emph{cover} in terminal leaves suggests overfitting in the base model. 
```{r eval=FALSE, message=FALSE, warning=FALSE}
xgb_base %>% 
  xgboost::xgb.plot.tree(model = ., trees = 1)
```