added some tests and improved description and vignette

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: mpathr
-Title: Handling Data From The M-Path Platform
+Title: Handling Data from the 'M-Path' Platform
 Version: 0.0.0.9000
 Authors@R: c(
     person("Merijn", "Mestdagh", email = "merijn.mestdagh@m-path.io", role = c("aut", "cre"),
@@ -9,7 +9,7 @@ Authors@R: c(
     person("Lara", "Navarrete", email = "larann901@gmail.com", role = c("aut"))
   )
 data: image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABIAAAASCAYAAABWzo5XAAAAWElEQVR42mNgGPTAxsZmJsVqQApgmGw1yApwKcQiT7phRBuCzzCSDSHGMKINIeDNmWQlA2IigKJwIssQkHdINgxfmBBtGDEBS3KCxBc7pMQgMYE5c/AXPwAwSX4lV3pTWwAAAABJRU5ErkJggg==
-Description: The goal of `mpathr` is to provide with a few utility functions to be able to read and perform some common operations in ESM data collected through the 'm-Path' platform (<https://m-path.io/landing/>).
+Description: The goal of `mpathr` is to provide with a few utility functions to be able to read and perform some common operations in ESM data collected through the 'm-Path' platform (<https://m-path.io/landing/>). The package provides functions to read data from 'm-Path', and to calculate response rate in data from Experience Sampling studies. 
 License: GPL (>= 3)
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)

R/read_mpath.R

@@ -180,7 +180,7 @@ read_mpath <- function(
 
     cli_warn(c(
       "There were problems when reading in the data:",
-      problems[1:100]
+      problems
     ))
   }
 

R/response_rate.R

@@ -5,9 +5,12 @@
 #' was answered or not
 #' @param participant_col name of the column that stores the participant id
 #' (or equivalent)
-#' @param time_col optional: name of the column that stores the time of the beep
-#' @param period_start optional: period start
-#' @param period_end optional: period end
+#' @param time_col optional: name of the column that stores the time of the
+#' beep, as a 'POSIXct' object.
+#' @param period_start string representing the starting date to
+#' calculate response rates (optional). Accepts dates in the following
+#' formats: \code{yyyy-mm-dd} or\code{yyyy/mm/dd}.
+#' @param period_end period end to calculate response rates (optional).
 #'
 #' @return a data frame with the response rate for each participant,
 #' and the number of beeps used to calculate the response rate

inst/WORDLIST

@@ -3,7 +3,9 @@ CMD
 ESM
 Github
 ORCID
+POSIXct
 SWLS
 ggplot
 preprocessed
 th
+yyyy

tests/testthat/test-read_mpath.R

@@ -126,14 +126,10 @@ test_that('List columns are being read as lists', {
 test_that('List columns are being read as the correct type', {
   for (col in meta_list_cols) {
     col_type <- meta[meta$columnName == col,]$typeAnswer
-    if (col_type == 'intList') {
+    if (col_type %in% c('intList', 'doubleList')) {
       expect_true(all(vapply(data[[col]],
-                             function(x) is.integer(x) || is.numeric(x),
+                             function(x) is.numeric(x),
                              FUN.VALUE = logical(1))))
-    } else if (col == 'doubleList') {
-      expect_true(all(vapply(data[[col]],
-                             is.numeric),
-                      FUN.VALUE = logical(1)))
     } else if (col == 'stringList') {
       expect_true(all(vapply(data[[col]],
                              is.character,
@@ -142,3 +138,58 @@ test_that('List columns are being read as the correct type', {
   }
 })
 
+# Test that problems are being printed when they occur:
+# Make small dataset that will result in parsing problems
+basic <- data.frame(connectionId = 228325.76, # this should be an int
+          code = '',
+          alias = '"example_alias"',
+          questionListName = '"example_questions"',
+          timeStampSent = 1722427206,
+          consent_yesno = 1,
+          slider_happy = 99)
+
+# Create metadata for the dataset above
+meta <- data.frame(columnName = c('"consent_yesno"', '"slider_happy"'),
+          fullQuestion = c('"Do you consent to participate in this study?"',
+                 '"How happy are you right now?"'),
+          typeQuestion = c('"yesno"', '"sliderNegPos"'),
+          typeAnswer = c('"int"', '"int"'),
+          fullQuestion_mixed = c(0,0),
+          typeQuestion_mixed =  c(0,0),
+          typeAnswer_mixed =  c(0,0))
+
+basic_file <- tempfile(fileext = ".csv")
+meta_file <- tempfile(fileext = ".csv")
+
+write.table(basic, basic_file, row.names = FALSE, sep = ";", quote = FALSE)
+write.table(meta, meta_file, row.names = FALSE, sep = ";", quote = FALSE)
+
+test_that("Problem with integer is printed", {
+
+  expect_warning(read_mpath(file = basic_file,
+                            meta_data = meta_file),
+                 "In row 2 column 1, expected an integer but got 228325.76.")
+
+})
+
+# Problems in meta_data
+meta <- data.frame(columnName = c('"consent_yesno"', '"slider_happy"'),
+                   fullQuestion =
+                     c('"Do you consent to participate in this study?"',
+                     '"How happy are you right now?"'),
+                   typeQuestion = c('"yesno"', '"sliderNegPos"'),
+                   typeAnswer = c('"int"', '"int"'),
+                   fullQuestion_mixed = c(0,0),
+                   typeQuestion_mixed =  c(10,0),
+                   typeAnswer_mixed =  c(0,0))
+
+meta_file <- tempfile(fileext = ".csv")
+write.table(meta, meta_file, row.names = FALSE, sep = ";", quote = FALSE)
+
+test_that("Problem with meta_data is printed", {
+
+  expect_warning(mpathr:::read_meta_data(meta_file),
+                 "In row 2 column 6, expected 1/0/T/F/TRUE/FALSE but got 10.")
+
+})
+

vignettes/mpathr.Rmd

@@ -18,8 +18,6 @@ knitr::opts_chunk$set(
 library(mpathr)
 ```
 
-# mpathr
-
 The main goal of `mpathr` is to provide functions to import data from the m-Path
 platform, as well as provide functions for common manipulations for
 ESM data.
@@ -58,7 +56,11 @@ participants' response rate. We provide a function `response_rate` that
 calculates the response_rate per participant for the entire duration of the 
 study, or for a specific time frame.\n
 
-For this, we can use the `example_data`. Which contains data from the same 
+This function takes as argument a `valid_col`, that takes a logical column that 
+stores whether the beep was answered by the participant, or not, as well as a 
+`participant_col`, that identifies each separate participant.
+
+We will show how to use this function with the `example_data`, that contains data from the same 
 study as the `example_basic.csv` file, but after some cleaning.\n
 
 ```{r}
@@ -85,8 +87,10 @@ response_rates[response_rates$response_rate < 0.5,]
 
 We could also be interested in seeing the participants' response rate during
 a specific period of time (for example, if we think a participant's compliance
-significantly dropped a certain date). In this case, we can specify the date 
-period that we are interested in:
+significantly dropped a certain date). In this case, we should supply the 
+function with the (otherwise optional) argument `time_col`, that should contain
+times stored as 'POSIXct' objects, and specify the date period that we are
+interested in (in the format 'yyyy-mm-dd' or 'yyyy/mm/dd'):
 
 ```{r}
 response_rates_after_15 <- response_rate(data = example_data,