---
title: "Filter Cohorts"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{a07_filter_cohorts}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

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

```{r setup}
library(CohortConstructor)
library(CohortCharacteristics)
library(ggplot2)
```

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

library(CDMConnector)
library(dplyr, warn.conflicts = FALSE)

if (Sys.getenv("EUNOMIA_DATA_FOLDER") == ""){
  Sys.setenv("EUNOMIA_DATA_FOLDER" = file.path(tempdir(), "eunomia"))}
if (!dir.exists(Sys.getenv("EUNOMIA_DATA_FOLDER"))){ dir.create(Sys.getenv("EUNOMIA_DATA_FOLDER"))
  downloadEunomiaData()  
}
```

For this example we'll use the Eunomia synthetic data from the CDMConnector package.

```{r}
con <- DBI::dbConnect(duckdb::duckdb(), dbdir = eunomia_dir())
cdm <- cdm_from_con(con, cdm_schema = "main", 
                    write_schema = c(prefix = "my_study_", schema = "main"))
```

Let's start by creating two drug cohorts, one for users of diclofenac and another for users of acetaminophen.

```{r}
cdm$medications <- conceptCohort(cdm = cdm, 
                                 conceptSet = list("diclofenac" = 1124300,
                                                   "acetaminophen" = 1127433), 
                                 name = "medications")
cohortCount(cdm$medications)
```

```{r}
cdm$medications_sample <- sampleCohorts(cdm$medications,cohortId = 1, n = 100, name = "medications_sample")

cohortCount(cdm$medications_sample)
```