From af794a5805aee4a6403a04b6bd7fe1001b9bd511 Mon Sep 17 00:00:00 2001
From: Isa Stallworthy <31548151+istallworthy@users.noreply.github.com>
Date: Fri, 15 Sep 2023 16:57:56 -0400
Subject: [PATCH] data type checking

---
 R/inspectData.R            | 14 +++++++++++---
 examplePipelineRevised.Rmd |  2 +-
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/R/inspectData.R b/R/inspectData.R
index 64e2f74d..3f5055c7 100644
--- a/R/inspectData.R
+++ b/R/inspectData.R
@@ -137,7 +137,7 @@ inspectData <- function(data, home_dir, exposure, exposure_time_pts, outcome, tv
   }
 
 
-  if(!inherits(data, data.frame)){
+  if(!inherits(data, "data.frame")){
     warning(paste0("Your data is a ", class(data), ". Convert to data frame before running devMSMs."),
             call. = FALSE)
   }
@@ -147,8 +147,16 @@ inspectData <- function(data, home_dir, exposure, exposure_time_pts, outcome, tv
                                    "numeric"), "continuous", "binary")
 
   # Data type
-  cat("Please inspect the following table of data types to ensure they are correct for each variable:")
-  print(str(data))
+  cat("The following variables are designated as numeric:", "\n")
+  print(paste(colnames(data)[sapply(data, class) == "numeric"], sep = ",", collapse = ", "))
+
+  cat("The following variables are designated as factors:", "\n")
+  print(paste(colnames(data)[sapply(data, class) == "factor"], sep = ",", collapse = ", "))
+
+  oth <- data.frame(variable = names(sapply(data, class)) [!sapply(data, class) %in% c("numeric", "factor")],
+                    type = sapply(data, class) [!sapply(data, class) %in% c("numeric", "factor")])
+  cat(knitr::kable(oth, caption = "Other variable types",
+                   format = 'pipe'), sep = "\n")
 
 
   # Exposure summary
diff --git a/examplePipelineRevised.Rmd b/examplePipelineRevised.Rmd
index ce40978b..a441f01d 100644
--- a/examplePipelineRevised.Rmd
+++ b/examplePipelineRevised.Rmd
@@ -88,7 +88,7 @@ data <- read.csv("/Users/isabella/Library/CloudStorage/Box-Box/BSL General/MSMs/
 data <- as.data.frame(data)
 
 library(dplyr)
-data_df <- data_mids[[1]]
+data_df <- complete(data_mids, 1)
 data_df <- data_df %>% dplyr::select(-c(contains(c(":", "Childhood", "Infancy", "Toddlerhood", "pcx"))))
 
 data <- data_df #single df