v3.0.0 infrastructure with CCHS master file harmonization

.Rbuildignore

@@ -10,3 +10,4 @@
 ^CRAN-RELEASE$
 ^CODE_OF_CONDUCT.md
 ^.github
+^\.github$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

.github/workflows/R-CMD-check.yaml

@@ -0,0 +1,33 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+
+name: R-CMD-check.yaml
+
+permissions: read-all
+
+jobs:
+  R-CMD-check:
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck
+          needs: check
+
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true
+          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'

.gitignore

@@ -4,3 +4,4 @@
 .Ruserdata
 *.DS_Store
 docs/
+..Rcheck/

DESCRIPTION

@@ -1,8 +1,10 @@
 Package: cchsflow
 Type: Package
 Title: Transforming and Harmonizing CCHS Variables
-Version: 2.1.0
-Date: 2022-05-05
+Version: 2.2.0
+Date: 2025-06-29
+Author: See Authors@R
+Maintainer: Kitty Chen <[email protected]>
 Authors@R: c(
     person(given = "Doug",
            family = "Manuel",
@@ -38,7 +40,9 @@ Depends:
   dplyr (>= 0.8.2),
   sjlabelled (>= 1.0.17),
   stringr (>= 1.2.0),
-  magrittr
+  magrittr,
+  yaml,
+  readr
 Description: Supporting the use of the Canadian Community Health Survey 
              (CCHS) by transforming variables from each cycle into harmonized, 
              consistent versions that span survey cycles (currently, 2001 to 
@@ -53,7 +57,12 @@ Encoding: UTF-8
 LazyData: true
 URL: https://big-life-lab.github.io/cchsflow/, https://github.com/Big-Life-Lab/cchsflow
 BugReports: https://github.com/Big-Life-Lab/cchsflow/issues
-RoxygenNote: 7.1.2
+RoxygenNote: 7.3.2
 Suggests: 
-    testthat (>= 3.0.0)
+    testthat (>= 3.0.0),
+    kableExtra,
+    DT,
+    rmarkdown,
+    knitr,
+    pkgdown
 Config/testthat/edition: 3

NAMESPACE

@@ -1,17 +1,6 @@
 # Generated by roxygen2: do not edit by hand
 
-export(ALCDTTM)
-export(ALCDTYP)
-export(ALWDDLY)
-export(ALWDWKY)
-export(ALW_1)
-export(ALW_2A1)
-export(ALW_2A2)
-export(ALW_2A3)
-export(ALW_2A4)
-export(ALW_2A5)
-export(ALW_2A6)
-export(ALW_2A7)
+# Note: Deprecated alcohol functions removed in v3.0.0 modernization
 export(COPD_Emph_der_fun1)
 export(COPD_Emph_der_fun2)
 export(DPSDPP)
@@ -21,46 +10,57 @@ export(LBFA_31A)
 export(LBFA_31A_a)
 export(LBFA_31A_b)
 export(RACDPAL_fun)
-export(SMKDSTY_fun)
-export(SMKG040_fun)
-export(SMKG203_fun)
-export(SMKG207_fun)
+# Note: Deprecated smoking functions removed in v3.0.0 modernization
 export(SPS_5_fun)
+# Note: SPU25_fun deprecated and removed
 export(active_transport1_fun)
 export(active_transport2_fun)
 export(active_transport3_fun)
-export(adjusted_bmi_fun)
-export(adl_fun)
+export(adjust_bmi)
 export(adl_score_5_fun)
+export(adl_score_6_fun)
 export(age_cat_fun)
-export(binge_drinker_fun)
-export(bmi_fun)
-export(bmi_fun_cat)
+export(assess_adl)
+export(assess_binge_drinking)
+export(assess_drinking_risk_long)
+export(assess_drinking_risk_short)
+export(calculate_bmi)
+export(calculate_energy_expenditure)
+export(categorize_bmi)
 export(diet_score_fun)
 export(diet_score_fun_cat)
 export(energy_exp_fun)
 export(food_insecurity_der)
+export(has_cchs_missing_codes)
 export(if_else2)
 export(immigration_fun)
 export(is_equal)
-export(low_drink_long_fun)
-export(low_drink_score_fun)
-export(low_drink_score_fun1)
-export(low_drink_short_fun)
 export(merge_rec_data)
 export(multiple_conditions_fun1)
 export(multiple_conditions_fun2)
-export(pack_years_fun)
-export(pack_years_fun_cat)
+# Note: Deprecated pack years functions removed in v3.0.0 modernization
 export(pct_time_fun)
 export(pct_time_fun_cat)
+# Note: All preprocess functions removed from exports in v3.0.0
+# These are now internal functions used within derived variable functions
+# - preprocess_cchs_missing_codes() -> internal use only
+# - preprocess_smoking_variable() -> internal use only
+# - Deprecated pattern functions removed completely
 export(rec_with_table)
 export(resp_condition_fun1)
 export(resp_condition_fun2)
 export(resp_condition_fun3)
+export(score_adl)
+export(score_adl_6)
 export(set_data_labels)
-export(smoke_simple_fun)
-export(time_quit_smoking_fun)
+# Modernized v3.0.0 smoking functions
+export(calculate_smoking_status)
+export(calculate_time_quit_smoking)
+export(calculate_pack_years)
+export(calculate_smoke_simple)
+export(standardise_csv)
+# Note: Deprecated time_quit_smoking functions removed in v3.0.0 modernization
+export(validate_missing_code_preprocessing)
 importFrom(dplyr,do)
 importFrom(dplyr,rowwise)
 importFrom(dplyr,select)
@@ -70,3 +70,4 @@ importFrom(sjlabelled,"set_label<-")
 importFrom(sjlabelled,set_label)
 importFrom(sjlabelled,set_labels)
 importFrom(stringr,str_match)
+# Note: Legacy functions (adl_fun, bmi_fun, binge_drinker_fun, etc.) moved to R/legacy/ - no longer exported

NEWS.md

@@ -1,3 +1,26 @@
+# cchsflow 3.0.0
+2025-06-28
+
+## Major infrastructure enhancement
+This release represents a **major infrastructure enhancement** adding support for `_i` cycle databases (master/shared continuous data) across the cchsflow ecosystem.
+
+### Key metrics
+- **28 new variables** added
+- **74 variables enhanced** with expanded database support
+- **6 new R functions** for validation and utilities
+- **34 critical dependencies** reviewed and validated
+
+### Variable changes
+**New variables (28):** ADL_score_6, ADM_MOI_I, ADM_YOI_I, ALCDTYP_A, DHH_MS, DHH_MS_A, GEOGPRV_ONCO, HUI06, HUI07, HUI07A, HUI08, HUI09, HWTDBMI, HWTDHTM, HWTDWTK, MAM_037, PACFLEI, RAC_6D, SDCDGT_A, SDCDGT_B, and others.
+
+**Variables enhanced with _i database support (74):** ADL_01 through ADL_07, ALCDTTM, ALW_2A1 through ALW_2A7, and others.
+
+### Code changes
+**New R functions:** adl_score_6.R, csv-helpers.R, csv-utils.R, DemPoRT_ICES_code.R, schema-validation.R, test code.R
+
+### Critical dependencies
+All 34 variables affecting derived functions reviewed and confirmed compatible.
+
 # cchsflow 2.0.1
 2022-05-05
 

R/RACDPAL.R

@@ -1,79 +1,84 @@
-#' @title Participation and Activity Limitation 
-#' 
+#' @title Participation and Activity Limitation
+#'
 #' @description This is a derived variable used in the CCHS (RACDPAL) to
 #'  classify respondents according to the frequency with which they experience
 #'  activity limitations due to disability.
-#'  
+#'
 #' @details This derived variable is generated in CCHS cycles 2003-2014. The
 #'  2001 CCHS cycle, however, contains the same base variables used to derive
 #'  this variable. To include respondents in the 2001 CCHS cycle, this custom
 #'  function was created using the same derivation conditions used in later
 #'  cycles.
-#' 
+#'
 #' @param RAC_1 Has difficulty with activities due to disability
-#' 
+#'
 #' @param RAC_2A Reduction in activities at home due to disability
-#' 
+#'
 #' @param RAC_2B Reduction in activities at school or work due to disability
-#' 
+#'
 #' @param RAC_2C Reduction in other activities
-#' 
+#'
 #' @return the CCHS derived variable RACDPAL with 3 categories:
 #'  \enumerate{
 #'   \item Sometimes
 #'   \item Often
 #'   \item Never
 #'   }
-#' 
-#' @examples 
-#' # Using RACDPAL_fun() to transform RACDPAL in 2001. 
+#'
+#' @examples
+#' # Using RACDPAL_fun() to transform RACDPAL in 2001.
 #' # RACDPAL_fun() is specified in variable_details.csv along with the
 #' # CCHS variables and cycles included.
-#'  
+#'
 #' # To transform RACDPAL, use rec_with_table() for each the 2001 cycle
 #' # and specify RACDPAL, along with the various ADL variables.
-#' 
+#'
 #' library(cchsflow)
-#' 
+#'
 #' RACDPAL_2001 <- rec_with_table(
 #'   cchs2001_p, c(
 #'     "RAC_1", "RAC_2A", "RAC_2B", "RAC_2C", "RACDPAL"
 #'   )
 #' )
-#' 
+#'
 #' head(RACDPAL_2001)
-#' 
+#'
 #' # Note: In other CCHS cycles you only need to specify RACDPAL as the variable
 #' # was included in those survey cycles.
-#' 
+#'
 #' # Using RACDPAL_fun() with user inputted data.
-#' 
+#'
 #' # Let's say you're an individual that sometimes has difficulties with
 #' # activities due to disability, sometimes has a reduction in activities at
 #' # home, often has a reduction at school or work, and never has a reduction
 #' # in other activities. Your participation and activity limitation can be
 #' # determined as follows:
-#' 
+#'
 #' library(cchsflow)
 #' RACDPAL <- RACDPAL_fun(1, 1, 2, 3)
 #' print(RACDPAL)
-#' 
+#'
 #' @export
 
-RACDPAL_fun <- function(RAC_1, RAC_2A, RAC_2B, RAC_2C){
+RACDPAL_fun <- function(RAC_1, RAC_2A, RAC_2B, RAC_2C) {
   # Check to see if all values are in range
-  if_else2((RAC_1 %in% 1:3) & (RAC_2A %in% 1:3) & (RAC_2B %in% 1:4) &
-             (RAC_2C %in% 1:3),
-           # Check if respondents said reductions impacted them often
-           if_else2(RAC_1 == 2 | RAC_2A == 2 | RAC_2B == 2 | RAC_2C == 2, 2,
-                    # Check if respondents said reductions impacted them
-                    # sometimes
-                    if_else2(RAC_1 == 1 | RAC_2A == 1 | RAC_2B == 1 |
-                               RAC_2C == 1, 1,
-                             # Check if respondents said reductions never
-                             # impacted them
-                             if_else2(RAC_1 == 3 & RAC_2A == 3 &
-                                        (RAC_2B %in% 3:4) &
-                                        RAC_2C == 3, 3, "NA(b)"))), "NA(b)"
+  if_else2(
+    (RAC_1 %in% 1:3) & (RAC_2A %in% 1:3) & (RAC_2B %in% 1:4) &
+      (RAC_2C %in% 1:3),
+    # Check if respondents said reductions impacted them often
+    if_else2(
+      RAC_1 == 2 | RAC_2A == 2 | RAC_2B == 2 | RAC_2C == 2, 2,
+      # Check if respondents said reductions impacted them
+      # sometimes
+      if_else2(
+        RAC_1 == 1 | RAC_2A == 1 | RAC_2B == 1 |
+          RAC_2C == 1, 1,
+        # Check if respondents said reductions never
+        # impacted them
+        if_else2(RAC_1 == 3 & RAC_2A == 3 &
+          (RAC_2B %in% 3:4) &
+          RAC_2C == 3, 3, "NA(b)")
+      )
+    ), "NA(b)"
   )
-}
+}