---
title: "hcruR"
output: rmarkdown::html_document
vignette: >
  %\VignetteIndexEntry{hcruR}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

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

### Load library and the data
```{r setup}
# Load library
library(hcruR)

# Load sample data
data(hcru_sample_data)
data <- hcru_sample_data
head(hcru_sample_data)
```

### Generate HCRU summary using dplyr (this can be used for create HCRU plots)

```{r}
# Step 1: Estimate HCRU
hcru_summary <- estimate_hcru(data,
  cohort_col = "cohort",
  patient_id_col = "patient_id",
  admit_col = "admission_date",
  discharge_col = "discharge_date",
  index_col = "index_date",
  visit_col = "visit_date",
  encounter_id_col = "encounter_id",
  setting_col = "care_setting",
  cost_col = "cost_usd",
  readmission_col = "readmission",
  time_window_col = "period",
  los_col = "length_of_stay",
  custom_var_list = NULL,
  pre_days = 180,
  post_days = 365,
  readmission_days_rule = 30,
  group_var_main = "cohort",
  group_var_by = "care_setting",
  test = NULL,
  timeline = "Pre",
  gt_output = FALSE
)

hcru_summary
```

### Generate HCRU summary using gtsummary (a publication ready output) 

```{r,  results = 'asis'}
# Step 1: Estimate HCRU
hcru_summary_gt <- estimate_hcru(data,
  cohort_col = "cohort",
  patient_id_col = "patient_id",
  admit_col = "admission_date",
  discharge_col = "discharge_date",
  index_col = "index_date",
  visit_col = "visit_date",
  encounter_id_col = "encounter_id",
  setting_col = "care_setting",
  cost_col = "cost_usd",
  readmission_col = "readmission",
  time_window_col = "period",
  los_col = "length_of_stay",
  custom_var_list = NULL,
  pre_days = 180,
  post_days = 365,
  readmission_days_rule = 30,
  group_var_main = "cohort",
  group_var_by = "care_setting",
  test = NULL,
  timeline = "Pre",
  gt_output = TRUE
)

hcru_summary_gt$`Summary by settings using gtsummary`
```


### Generate the HCRU plot: average visits by cohort and time-line

```{r}
# Calculate the average visits
sum_df1 <- hcru_summary$`Summary by settings using dplyr` |>
  dplyr::group_by(
    .data[["time_window"]],
    .data[["cohort"]],
    .data[["care_setting"]]
  ) |>
  dplyr::summarise(
    AVG_VISIT = mean(.data[["Visits"]], na.rm = TRUE), .groups = "drop"
  )

# Load the plot_hcru function
p1 <- plot_hcru(
  summary_df = sum_df1,
  x_var = "time_window",
  y_var = "AVG_VISIT",
  cohort_col = "cohort",
  facet_var = "care_setting",
  facet_var_n = 3,
  title = "Average visits by domain and cohort",
  x_label = "Healthcare Setting (Domain)",
  y_label = "Average visit",
  fill_label = "Cohort"
)

p1
```

### Generate HCRU plot for average cost by cohort and timeline

```{r}
# Calculate the total cost
df2 <- hcru_summary$`Summary by settings using dplyr` |>
  dplyr::group_by(
    .data[["time_window"]],
    .data[["cohort"]],
    .data[["care_setting"]]
  ) |>
  dplyr::summarise(
    AVG_COST = sum(.data[["Cost"]], na.rm = TRUE), .groups = "drop"
  )

p2 <- plot_hcru(
  summary_df = df2,
  x_var = "time_window",
  y_var = "AVG_COST",
  cohort_col = "cohort",
  facet_var = "care_setting",
  facet_var_n = 3,
  title = "Average cost by domain and cohort",
  x_label = "Healthcare Setting (Domain)",
  y_label = "Average cost",
  fill_label = "Cohort"
)

p2
```