---
title: "Stat. 652 - NHANES kNN"
output: html_notebook
---

Here we try using Tidymodels and Recipe to fit a classifier, the kNN model.

Note the need to impute values because of the high percentage of missing values.

For the kNN we use only numeric features.

```{r}
library(pacman)

p_load(NHANES, tidyverse, tidymodels, naniar)
```

### Step 1: Access the data.

```{r}
data(NHANES)

NHANES
```

### Step 2: Clean the data.  Prepare the data and make a recipe for applying the steps needed to preprocess the data.

First drop all of the rows where the y-variable SleepTrouble is missing.

Second select all of the numeric variables because we are using kNN which computes distances and needs to have numeric variables.  We create a list of the numeric variables and then use the one_of() function to pick out the columns with these names.

```{r}
NHANES_SleepTrouble <- NHANES %>% select(-ID, -SleepHrsNight) %>%
  select( SleepTrouble, everything()) %>%
  drop_na(SleepTrouble)
NHANES_SleepTrouble

NHAMES_SleepTrouble_num <- dplyr::select_if(NHANES_SleepTrouble, is.numeric) %>% names()
NHAMES_SleepTrouble_num

NHANES_SleepTrouble <- NHANES_SleepTrouble %>% select(SleepTrouble, one_of(NHAMES_SleepTrouble_num) )
NHANES_SleepTrouble


```

Summarize the y-variable.

```{r}
NHANES_SleepTrouble %>% group_by(SleepTrouble) %>%
  summarize(n = n()) %>%
  mutate(freq = n / sum(n))
```

Make the first split with 80% of the data being in the trainning data set.

```{r}
NHANES_SleepTrouble_split <- initial_split(NHANES_SleepTrouble, prop = 0.8)
NHANES_SleepTrouble_split
```

Trainning data.

```{r}
NHANES_SleepTrouble_split %>%
  training() 
```

```{r}
NHANES_SleepTrouble_split %>%
  training() %>%
  vis_miss()
```

Create the recipe for applying the preprocessing.  Note the use of step_nzv(), which removes any columns that have very low variability, and the use of the step_medianimpute() function, which fills in the cells that are missing with the median of the column.

```{r}
NHANES_SleepTrouble_recipe <- training(NHANES_SleepTrouble_split) %>%
  recipe(SleepTrouble ~ .) %>%
  step_nzv(all_predictors()) %>%
  step_medianimpute(all_numeric()) %>%
  step_center(all_numeric(), -all_outcomes()) %>%
  step_scale(all_numeric(), -all_outcomes()) %>%
  prep()

summary(NHANES_SleepTrouble_recipe)

tidy(NHANES_SleepTrouble_recipe)

```


```{r}
NHANES_SleepTrouble_testing <- NHANES_SleepTrouble_recipe %>%
  bake(testing(NHANES_SleepTrouble_split)) 

NHANES_SleepTrouble_testing
```


```{r}
NHANES_SleepTrouble_training <- juice(NHANES_SleepTrouble_recipe)

NHANES_SleepTrouble_training
```

### Step 3: Training a model on the data

Setup the models.

```{r}
NHANES_SleepTrouble_kknn <- nearest_neighbor(neighbors = 21) %>%
  set_engine("kknn") %>%
  set_mode("classification") %>%
  fit(SleepTrouble ~ ., data = NHANES_SleepTrouble_training)

NHANES_SleepTrouble_ranger <- rand_forest(trees = 100) %>%
  set_engine("ranger") %>%
  set_mode("classification") %>%
  fit(SleepTrouble ~ ., data = NHANES_SleepTrouble_training)

NHANES_SleepTrouble_rf <- rand_forest(trees = 100) %>%
  set_engine("randomForest") %>%
  set_mode("classification") %>%
  fit(SleepTrouble ~ ., data = NHANES_SleepTrouble_training)
```


```{r}
predict(NHANES_SleepTrouble_kknn, NHANES_SleepTrouble_testing)

predict(NHANES_SleepTrouble_ranger, NHANES_SleepTrouble_testing)

predict(NHANES_SleepTrouble_rf, NHANES_SleepTrouble_testing)
```

```{r}
NHANES_SleepTrouble_kknn %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) 

NHANES_SleepTrouble_ranger %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) 

NHANES_SleepTrouble_rf %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) 
```


### Step 4: Evaluate the models.


```{r}
NHANES_SleepTrouble_kknn %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) %>%
  metrics(truth = SleepTrouble, estimate = .pred_class)

NHANES_SleepTrouble_ranger %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) %>%
  metrics(truth = SleepTrouble, estimate = .pred_class)

NHANES_SleepTrouble_rf %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) %>%
  metrics(truth = SleepTrouble, estimate = .pred_class)
```

```{r}
NHANES_SleepTrouble_kknn %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) %>%
  conf_mat(truth = SleepTrouble, estimate = .pred_class)

NHANES_SleepTrouble_ranger %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) %>%
  conf_mat(truth = SleepTrouble, estimate = .pred_class)

NHANES_SleepTrouble_rf %>%
  predict(NHANES_SleepTrouble_testing) %>%
  bind_cols(NHANES_SleepTrouble_testing) %>%
  conf_mat(truth = SleepTrouble, estimate = .pred_class)
```