---
title: "R Notebook"
output: html_notebook
---



```{r}
library(pacman)

p_load(NHANES, tidyverse, tidymodels)
```

### 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.

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

```

Summarize the y-variable.

```{r}
NHANES_SleepHrsNight %>% group_by(SleepHrsNight) %>%
  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_SleepHrsNight_split <- initial_split(NHANES_SleepHrsNight, prop = 0.8)
NHANES_SleepHrsNight_split
```

Trainning data.

```{r}
NHANES_SleepHrsNight_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, the use of the step_knnimpute() function, which fills in the cells that are missing with the median of the column, and tghe use of the step_corr() function, which removes highly correlated input features.

```{r}
NHANES_SleepHrsNight_recipe <- training(NHANES_SleepHrsNight_split) %>%
  recipe(SleepHrsNight ~ .) %>%
  step_nzv(all_predictors()) %>%
  step_knnimpute(all_predictors()) %>%
  step_corr(all_numeric()) %>%
  prep()

summary(NHANES_SleepTrouble_recipe)

tidy(NHANES_SleepTrouble_recipe)
```


```{r}
NHANES_SleepHrsNight_testing <- NHANES_SleepHrsNight_recipe %>%
  bake(testing(NHANES_SleepHrsNight_split)) 

NHANES_SleepHrsNight_testing
```


```{r}
NHANES_SleepHrsNight_training <- juice(NHANES_SleepHrsNight_recipe)

NHANES_SleepHrsNight_training
```

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

Setup the models.

```{r}

NHANES_SleepHrsNight_lm <- linear_reg() %>% 
  set_engine("lm") %>%
  set_mode("regression") %>%
  fit(SleepHrsNight ~ ., data = NHANES_SleepHrsNight_training)

```


```{r}
predict(NHANES_SleepHrsNight_lm, NHANES_SleepHrsNight_testing)
```

```{r}
NHANES_SleepHrsNight_lm %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) 
```

### Step 4: Evaluate the models.

```{r}
NHANES_SleepHrsNight_lm %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) %>%
  metrics(truth = SleepHrsNight, estimate = .pred)
```


```{r}
NHANES_SleepHrsNight_lm %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) %>%
  rmse(truth = SleepHrsNight, estimate = .pred)

```


### Step 5: Improve the model.

GLM model using regularization.

Setup the models.

```{r}

NHANES_SleepHrsNight_glm <- linear_reg(penalty = 0.001, mixture = 0.5) %>% 
  set_engine("glmnet") %>%
  set_mode("regression") %>%
  fit(SleepHrsNight ~ ., data = NHANES_SleepHrsNight_training)

```


```{r}
predict(NHANES_SleepHrsNight_glm, NHANES_SleepHrsNight_testing)
```

```{r}
NHANES_SleepHrsNight_glm %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) 
```


```{r}
NHANES_SleepHrsNight_glm %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) %>%
  metrics(truth = SleepHrsNight, estimate = .pred)
```


```{r}
NHANES_SleepHrsNight_glm %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) %>%
  rmse(truth = SleepHrsNight, estimate = .pred)

```

Setup the models.

```{r}

NHANES_SleepHrsNight_ranger <- rand_forest(trees = 1000) %>% 
  set_engine("ranger") %>%
  set_mode("regression") %>%
  fit(SleepHrsNight ~ ., data = NHANES_SleepHrsNight_training)

```


```{r}
predict(NHANES_SleepHrsNight_ranger, NHANES_SleepHrsNight_testing)
```

```{r}
NHANES_SleepHrsNight_ranger %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) 
```


```{r}
NHANES_SleepHrsNight_ranger %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) %>%
  metrics(truth = SleepHrsNight, estimate = .pred)
```


```{r}
NHANES_SleepHrsNight_ranger %>%
  predict(NHANES_SleepHrsNight_testing) %>%
  bind_cols(NHANES_SleepHrsNight_testing) %>%
  rmse(truth = SleepHrsNight, estimate = .pred)

```