Merge pull request #29 from pranavanba/main

Minor changes due to renaming of recoverSummarizeR package

Dockerfile

@@ -1,7 +1,7 @@
 FROM ghcr.io/pranavanba/rocker-sage:main
 
 RUN R -e 'install.packages("devtools")'
-RUN R -e 'devtools::install_github("Sage-Bionetworks/recoverSummarizeR")'
+RUN R -e 'devtools::install_github("Sage-Bionetworks/recoverutils")'
 
 RUN apt-get update && apt-get install -y git
 

scripts/egress/egress.R

@@ -14,7 +14,7 @@ latest_commit_tree_url <-
   latest_commit$html_url %>% 
   stringr::str_replace("commit", "tree")
 
-recoverSummarizeR::store_in_syn(
+recoverutils::store_in_syn(
   synFolderID = synFolderID, 
   filepath = file.path(outputConceptsDir, "output_concepts.csv"), 
   used_param = c(ontologyFileID, parquetDirID, selectedVarsFileID), 
@@ -24,12 +24,12 @@ cat(glue::glue("Output concepts stored at {synFolderID}"), "\n\n")
 
 file_name <- "concepts_map.csv"
 write.csv(concept_map, file = file_name, row.names = F)
-store_in_syn(synFolderID, file_name, used_param = ontologyFileID)
+recoverutils::store_in_syn(synFolderID, file_name, used_param = ontologyFileID)
 cat(glue::glue("The input concept map used was stored at {synFolderID} as '{file_name}'"), "\n\n")
 
 file_name <- "selected_vars.csv"
 write.csv(selected_vars, file = file_name, row.names = F)
-store_in_syn(synFolderID, file_name, used_param = selectedVarsFileID)
+recoverutils::store_in_syn(synFolderID, file_name, used_param = selectedVarsFileID)
 cat(glue::glue("The input variable list used was stored at {synFolderID} as '{file_name}'"), "\n\n")
 
 rm(latest_commit,

scripts/fetch-data/fetch_data.R

@@ -1,5 +1,5 @@
 library(synapser)
-library(recoverSummarizeR)
+library(recoverutils)
 library(dplyr)
 
 cat("Fetching data\n")
@@ -8,11 +8,11 @@ synLogin()
 
 # Get input files from synapse
 concept_map <- 
-  syn_file_to_df(ontologyFileID, "CONCEPT_CD") %>% 
+  recoverutils::syn_file_to_df(ontologyFileID, "CONCEPT_CD") %>% 
   filter(CONCEPT_CD!="<null>")
 
 selected_vars <- 
-  syn_file_to_df(selectedVarsFileID) %>% 
+  recoverutils::syn_file_to_df(selectedVarsFileID) %>% 
   mutate(Lower_Bound = suppressWarnings(as.numeric(Lower_Bound)),
          Upper_Bound = suppressWarnings(as.numeric(Upper_Bound)))
 
@@ -49,7 +49,7 @@ system(sync_cmd)
 rm(sync_cmd)
 
 # For use in process-data steps
-concept_replacements_reversed <- vec_reverse(concept_replacements)
+concept_replacements_reversed <- recoverutils::vec_reverse(concept_replacements)
 
 if (!dir.exists(outputConceptsDir)) {
   dir.create(outputConceptsDir)

scripts/process-data/fitbitactivitylogs.R

@@ -53,32 +53,32 @@ for (col_name in names(df_filtered)) {
 # Pivot data frame from long to wide
 df_melted_filtered <- 
   df_filtered %>% 
-  recoverSummarizeR::melt_df(excluded_concepts = excluded_concepts) %>% 
+  recoverutils::melt_df(excluded_concepts = excluded_concepts) %>% 
   select(if("participantidentifier" %in% colnames(.)) "participantidentifier",
          dplyr::matches("(?<!_)date(?!_)", perl = T),
          if("concept" %in% colnames(.)) "concept",
          if("value" %in% colnames(.)) "value") %>% 
   tidyr::drop_na("value") %>% 
   mutate(value = as.numeric(value))
-cat("recoverSummarizeR::melt_df() completed.\n")
+cat("recoverutils::melt_df() completed.\n")
 
 # Generate i2b2 summaries
 df_summarized <- 
   df_melted_filtered %>% 
   select(all_of(c("participantidentifier", "startdate", "enddate", "concept", "value"))) %>% 
-  recoverSummarizeR::stat_summarize() %>% 
+  recoverutils::stat_summarize() %>% 
   distinct()
-cat("recoverSummarizeR::stat_summarize() completed.\n")
+cat("recoverutils::stat_summarize() completed.\n")
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  process_df(df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
+  recoverutils::process_df(df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
   dplyr::mutate(nval_num = signif(nval_num, 9)) %>% 
   dplyr::arrange(concept) %>% 
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from fitbit variables
 fitbit_participants <- 

scripts/process-data/fitbitdailydata.R

@@ -58,28 +58,28 @@ for (col_name in names(df_filtered)) {
 # Pivot data frame from long to wide
 df_melted_filtered <- 
   df_filtered %>% 
-  recoverSummarizeR::melt_df(excluded_concepts = excluded_concepts) %>% 
+  recoverutils::melt_df(excluded_concepts = excluded_concepts) %>% 
   select(if("participantidentifier" %in% colnames(.)) "participantidentifier",
          dplyr::matches("(?<!_)date(?!_)", perl = T),
          if("concept" %in% colnames(.)) "concept",
          if("value" %in% colnames(.)) "value") %>% 
   tidyr::drop_na("value") %>% 
   mutate(value = as.numeric(value))
-cat("recoverSummarizeR::melt_df() completed.\n")
+cat("recoverutils::melt_df() completed.\n")
 
 # Generate i2b2 summaries
 df_summarized <- 
   df_melted_filtered %>% 
   rename(startdate = dplyr::any_of(c("date", "datetime"))) %>% 
   mutate(enddate = if (!("enddate" %in% names(.))) NA else enddate) %>% 
   select(all_of(c("participantidentifier", "startdate", "enddate", "concept", "value"))) %>% 
-  recoverSummarizeR::stat_summarize() %>% 
+  recoverutils::stat_summarize() %>% 
   distinct()
-cat("recoverSummarizeR::stat_summarize() completed.\n")
+cat("recoverutils::stat_summarize() completed.\n")
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  process_df(df_summarized, 
+  recoverutils::process_df(df_summarized, 
              concept_map, 
              concept_replacements_reversed, 
              concept_map_concepts = "CONCEPT_CD", 
@@ -89,7 +89,7 @@ output_concepts <-
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from fitbit variables
 curr_fitbit_participants <- 

scripts/process-data/fitbitecg.R

@@ -138,14 +138,14 @@ df_melted_filtered <-
   mutate("SinusRhythm" = if_else(resultclassification == "Normal Sinus Rhythm", 1, NA),
          "AtrialFibrillation" = if_else(resultclassification == "Atrial Fibrillation", 1, NA)) %>% 
   select(-c(resultclassification)) %>% 
-  recoverSummarizeR::melt_df(excluded_concepts = excluded_concepts) %>% 
+  recoverutils::melt_df(excluded_concepts = excluded_concepts) %>% 
   select(if("participantidentifier" %in% colnames(.)) "participantidentifier",
          dplyr::matches("(?<!_)date(?!_)", perl = T),
          if("concept" %in% colnames(.)) "concept",
          if("value" %in% colnames(.)) "value") %>% 
   tidyr::drop_na("value") %>% 
   mutate(value = as.numeric(value))
-cat("recoverSummarizeR::melt_df() completed.\n")
+cat("recoverutils::melt_df() completed.\n")
 
 # Generate i2b2 summaries
 df_summarized <- 
@@ -160,7 +160,7 @@ cat("ecg_stat_summarize() completed.\n")
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  recoverSummarizeR::process_df(df_summarized, 
+  recoverutils::process_df(df_summarized, 
                                 concept_map, 
                                 concept_replacements_reversed, 
                                 concept_map_concepts = "CONCEPT_CD", 
@@ -170,7 +170,7 @@ output_concepts <-
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from fitbit variables
 curr_fitbit_participants <- 

scripts/process-data/fitbitintradaycombined.R

@@ -76,34 +76,34 @@ for (col_name in names(df_filtered)) {
 # Pivot data frame from long to wide
 df_melted_filtered <- 
   df_filtered %>% 
-  recoverSummarizeR::melt_df(excluded_concepts = excluded_concepts) %>% 
+  recoverutils::melt_df(excluded_concepts = excluded_concepts) %>% 
   select(if("participantidentifier" %in% colnames(.)) "participantidentifier",
          dplyr::matches("(?<!_)date(?!_)", perl = T),
          if("concept" %in% colnames(.)) "concept",
          if("value" %in% colnames(.)) "value") %>% 
   tidyr::drop_na("value") %>% 
   mutate(value = as.numeric(value))
-cat("recoverSummarizeR::melt_df() completed.\n")
+cat("recoverutils::melt_df() completed.\n")
 
 # Generate i2b2 summaries
 df_summarized <- 
   df_melted_filtered %>% 
   rename(startdate = dplyr::any_of(c("date", "datetime"))) %>% 
   mutate(enddate = if (!("enddate" %in% names(.))) NA else enddate) %>% 
   select(all_of(c("participantidentifier", "startdate", "enddate", "concept", "value"))) %>% 
-  recoverSummarizeR::stat_summarize() %>% 
+  recoverutils::stat_summarize() %>% 
   distinct()
-cat("recoverSummarizeR::stat_summarize() completed.\n")
+cat("recoverutils::stat_summarize() completed.\n")
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  process_df(df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
+  recoverutils::process_df(df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
   dplyr::mutate(nval_num = signif(nval_num, 9)) %>% 
   dplyr::arrange(concept) %>% 
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from fitbit variables
 curr_fitbit_participants <- 

scripts/process-data/fitbitsleeplogs.R

@@ -336,7 +336,7 @@ for (col_name in names(df_filtered)) {
 # Pivot data frames from long to wide
 df_melted_filtered <- 
   df_filtered %>% 
-  recoverSummarizeR::melt_df(excluded_concepts = excluded_concepts) %>% 
+  recoverutils::melt_df(excluded_concepts = excluded_concepts) %>% 
   select(if("participantidentifier" %in% colnames(.)) "participantidentifier",
          dplyr::matches("(?<!_)date(?!_)", perl = T),
          if("concept" %in% colnames(.)) "concept",
@@ -368,7 +368,7 @@ numepisodes_df_melted_filtered_weekly <-
   tidyr::drop_na("value") %>%
   mutate(value = as.numeric(value))
 
-cat("recoverSummarizeR::melt_df() completed.\n")
+cat("recoverutils::melt_df() completed.\n")
 
 # Generate i2b2 summaries
 df_summarized <- 
@@ -403,13 +403,13 @@ cat("sleeplogs_stat_summarize() completed.\n")
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  process_df(final_df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
+  recoverutils::process_df(final_df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
   dplyr::mutate(nval_num = signif(nval_num, 9)) %>% 
   dplyr::arrange(concept) %>% 
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from fitbit variables
 curr_fitbit_participants <- 

scripts/process-data/healthkitv2activitysummaries.R

@@ -46,32 +46,32 @@ for (col_name in names(df_filtered)) {
 
 df_melted_filtered <- 
   df_filtered %>% 
-  recoverSummarizeR::melt_df(excluded_concepts = excluded_concepts) %>% 
+  recoverutils::melt_df(excluded_concepts = excluded_concepts) %>% 
   select(if("participantidentifier" %in% colnames(.)) "participantidentifier",
          dplyr::matches("(?<!_)date(?!_)", perl = T),
          if("concept" %in% colnames(.)) "concept",
          if("value" %in% colnames(.)) "value") %>% 
   tidyr::drop_na("value") %>% 
   mutate(value = as.numeric(value))
-cat("recoverSummarizeR::melt_df() completed.\n")
+cat("recoverutils::melt_df() completed.\n")
 
 df_summarized <- 
   df_melted_filtered %>% 
   rename(startdate = dplyr::any_of(c("date", "datetime"))) %>% 
   mutate(enddate = if (!("enddate" %in% names(.))) NA else enddate) %>% 
   select(all_of(c("participantidentifier", "startdate", "enddate", "concept", "value"))) %>% 
-  recoverSummarizeR::stat_summarize() %>% 
+  recoverutils::stat_summarize() %>% 
   distinct()
-cat("recoverSummarizeR::stat_summarize() completed.\n")
+cat("recoverutils::stat_summarize() completed.\n")
 
 output_concepts <- 
-  process_df(df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
+  recoverutils::process_df(df_summarized, concept_map, concept_replacements_reversed, concept_map_concepts = "CONCEPT_CD", concept_map_units = "UNITS_CD") %>% 
   dplyr::mutate(nval_num = signif(nval_num, 9)) %>% 
   dplyr::arrange(concept) %>% 
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 output_concepts %>% 
   write.csv(file.path(outputConceptsDir, glue::glue("{dataset}.csv")), row.names = F)

scripts/process-data/healthkitv2electrocardiogram.R

@@ -143,14 +143,14 @@ df_melted_filtered <-
   mutate("SinusRhythm" = if_else(classification == "SinusRhythm", 1, NA),
          "AtrialFibrillation" = if_else(classification == "AtrialFibrillation", 1, NA)) %>% 
   select(-c(classification)) %>% 
-  recoverSummarizeR::melt_df(excluded_concepts = excluded_concepts) %>% 
+  recoverutils::melt_df(excluded_concepts = excluded_concepts) %>% 
   select(if("participantidentifier" %in% colnames(.)) "participantidentifier",
          dplyr::matches("(?<!_)date(?!_)", perl = T),
          if("concept" %in% colnames(.)) "concept",
          if("value" %in% colnames(.)) "value") %>% 
   tidyr::drop_na("value") %>% 
   mutate(value = as.numeric(value))
-cat("recoverSummarizeR::melt_df() completed.\n")
+cat("recoverutils::melt_df() completed.\n")
 
 # Generate i2b2 summaries
 df_summarized <- 
@@ -163,7 +163,7 @@ cat("ecg_stat_summarize() completed.\n")
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  recoverSummarizeR::process_df(df_summarized, 
+  recoverutils::process_df(df_summarized, 
                                 concept_map, 
                                 concept_replacements_reversed, 
                                 concept_map_concepts = "CONCEPT_CD", 
@@ -173,7 +173,7 @@ output_concepts <-
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from healthkit variables
 curr_hk_participants <- 

scripts/process-data/healthkitv2samples.R

@@ -80,9 +80,9 @@ df_summarized <-
   df_melted_filtered %>% 
   rename(enddate = "date") %>% 
   select(all_of(c("participantidentifier", "startdate", "enddate", "concept", "value"))) %>% 
-  recoverSummarizeR::stat_summarize() %>% 
+  recoverutils::stat_summarize() %>% 
   distinct()
-cat("recoverSummarizeR::stat_summarize() completed.\n")
+cat("recoverutils::stat_summarize() completed.\n")
 
 tmp_concept_replacements <- c("respiratoryrate" = "breathingrate",
                               "heartratevariability" = "hrv",
@@ -91,7 +91,7 @@ tmp_concept_replacements <- c("respiratoryrate" = "breathingrate",
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  process_df(df_summarized, 
+  recoverutils::process_df(df_summarized, 
              concept_map, 
              concept_replacements_reversed = tmp_concept_replacements, 
              concept_map_concepts = "CONCEPT_CD", 
@@ -101,7 +101,7 @@ output_concepts <-
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from healthkit variables
 curr_hk_participants <- 

scripts/process-data/healthkitv2statistics.R

@@ -55,15 +55,15 @@ df_summarized <-
   df_melted_filtered %>% 
   rename(enddate = "date") %>% 
   select(all_of(c("participantidentifier", "startdate", "enddate", "concept", "value"))) %>% 
-  recoverSummarizeR::stat_summarize() %>% 
+  recoverutils::stat_summarize() %>% 
   distinct()
-cat("recoverSummarizeR::stat_summarize() completed.\n")
+cat("recoverutils::stat_summarize() completed.\n")
 
 tmp_concept_replacements <- c("dailysteps" = "steps")
 
 # Add i2b2 columns from concept map (ontology file) and clean the output
 output_concepts <- 
-  process_df(df_summarized, 
+  recoverutils::process_df(df_summarized, 
              concept_map, 
              concept_replacements_reversed = tmp_concept_replacements, 
              concept_map_concepts = "CONCEPT_CD", 
@@ -73,7 +73,7 @@ output_concepts <-
   dplyr::mutate(dplyr::across(.cols = dplyr::everything(), .fns = as.character)) %>% 
   replace(is.na(.), "<null>") %>% 
   dplyr::filter(nval_num != "<null>" | tval_char != "<null>")
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Identify the participants who have output concepts derived from healthkit variables
 curr_hk_participants <- 

scripts/process-data/participant_devices.R

@@ -86,7 +86,7 @@ output_concepts <-
   dplyr::select(participantidentifier, startdate, enddate, 
                 concept, valtype_cd, nval_num, tval_char, UNITS_CD) %>% 
   dplyr::rename(units_cd = UNITS_CD)
-cat("recoverSummarizeR::process_df() completed.\n")
+cat("recoverutils::process_df() completed.\n")
 
 # Write the output
 output_concepts %>%