Merge pull request #59 from OHDSI/develop

hotfix for result uploading

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: Characterization
 Type: Package
 Title: Characterizations of Cohorts
-Version: 2.0.0
-Date: 2024-08-07
+Version: 2.0.1
+Date: 2024-08-21
 Authors@R: c(
 	person("Jenna", "Reps", , "[email protected]", role = c("aut", "cre")),
 	person("Patrick", "Ryan", , "[email protected]", role = c("aut")),

NEWS.md

@@ -1,3 +1,8 @@
+Characterization 2.0.1
+======================
+- edited cohort_type in results to varchar(12)
+- fixed setting id being messed up by readr loading
+
 Characterization 2.0.0
 ======================
 - added tests for all HADES supported dbms

R/RunCharacterization.R

@@ -406,6 +406,14 @@ aggregateCsvs <- function(
     "rechallenge_fail_case_series.csv", "dechallenge_rechallenge.csv"
   )
 
+  colTypes <- c(
+    'ciicc','ciiiicciiccc', 'didciiccd',
+    'didddddddddciicc', 'dciicicc',
+    'icciicccc', 'iiciicciicddddd',
+    '????????',
+    '?????????????????', '????????????????????'
+  )
+
   # this makes sure results are recreated
   firstTracker <- data.frame(
     table = tables,
@@ -430,7 +438,8 @@ aggregateCsvs <- function(
         # TODO do this in batches
         data <- readr::read_csv(
           file = loadPath,
-          show_col_types = F
+          show_col_types = F,
+          col_types = colTypes[csvType == tables]
         )
 
         if (csvType == "analysis_ref.csv") {

inst/settings/resultsDataModelSpecification.csv

@@ -45,7 +45,7 @@ dechallenge_rechallenge,pct_rechallenge_attempt,float,Yes,No,No,No,The percentag
 dechallenge_rechallenge,pct_rechallenge_success,float,Yes,No,No,No,The percentage of rechallenge success
 dechallenge_rechallenge,pct_rechallenge_fail,float,Yes,No,No,No,The percentage of rechallenge fails
 analysis_ref,database_id,varchar(100),Yes,Yes,No,No,The database identifier
-analysis_ref,setting_id,float,Yes,Yes,No,No,The run identifier
+analysis_ref,setting_id,varchar(30),Yes,Yes,No,No,The run identifier
 analysis_ref,analysis_id,int,Yes,Yes,No,No,The analysis identifier
 analysis_ref,analysis_name,varchar,Yes,No,No,No,The analysis name
 analysis_ref,domain_id,varchar,Yes,No,No,No,The domain id
@@ -54,25 +54,25 @@ analysis_ref,end_day,int,Yes,No,No,No,The end day
 analysis_ref,is_binary,varchar(1),Yes,No,No,No,Is this a binary analysis
 analysis_ref,missing_means_zero,varchar(1),Yes,No,No,No,Missing means zero
 covariate_ref,database_id,varchar(100),Yes,Yes,No,No,The database identifier
-covariate_ref,setting_id,float,Yes,Yes,No,No,The run identifier
+covariate_ref,setting_id,varchar(30),Yes,Yes,No,No,The run identifier
 covariate_ref,covariate_id,bigint,Yes,Yes,No,No,The covariate identifier
 covariate_ref,covariate_name,varchar,Yes,No,No,No,The covariate name
 covariate_ref,analysis_id,int,Yes,No,No,No,The analysis identifier
 covariate_ref,concept_id,bigint,Yes,No,No,No,The concept identifier
 covariate_ref,value_as_concept_id,int,N,N,N,N,The value as concept_id for features created from observation or measurement values
 covariate_ref,collisions,int,N,N,N,N,The number of collisions found for the covariate_id
 covariates,database_id,varchar(100),Yes,Yes,No,No,The database identifier
-covariates,setting_id,float,Yes,Yes,No,No,The run identifier
-covariates,cohort_type,varchar(10),Yes,Yes,No,No,The cohort type
+covariates,setting_id,varchar(30),Yes,Yes,No,No,The run identifier
+covariates,cohort_type,varchar(12),Yes,Yes,No,No,The cohort type
 covariates,target_cohort_id,int,Yes,Yes,No,No,The target cohort id
 covariates,outcome_cohort_id,int,Yes,Yes,No,No,The outcome cohort id
 covariates,min_characterization_mean,float,No,Yes,No,No,Minimum fraction for feature extraction
 covariates,covariate_id,bigint,Yes,Yes,No,No,The covaraite id
 covariates,sum_value,int,Yes,No,No,No,The sum value
 covariates,average_value,float,No,No,No,No,The average value
 covariates_continuous,database_id,varchar(100),Yes,Yes,No,No,The database identifier
-covariates_continuous,setting_id,float,Yes,Yes,No,No,The run identifier
-covariates_continuous,cohort_type,varchar(10),Yes,Yes,No,No,The cohort type
+covariates_continuous,setting_id,varchar(30),Yes,Yes,No,No,The run identifier
+covariates_continuous,cohort_type,varchar(12),Yes,Yes,No,No,The cohort type
 covariates_continuous,target_cohort_id,int,Yes,Yes,No,No,The target cohort id
 covariates_continuous,outcome_cohort_id,int,Yes,Yes,No,No,The outcome cohort id
 covariates_continuous,covariate_id,bigint,Yes,Yes,No,No,The covariate identifier
@@ -86,7 +86,7 @@ covariates_continuous,p_10_value,float,No,No,No,No,The 10th percentile
 covariates_continuous,p_25_value,float,No,No,No,No,The 25th percentile
 covariates_continuous,p_75_value,float,No,No,No,No,The 75th percentile
 covariates_continuous,p_90_value,float,No,No,No,No,The 90th percentile
-settings,setting_id,float,Yes,Yes,No,No,The run identifier
+settings,setting_id,varchar(30),Yes,Yes,No,No,The run identifier
 settings,database_id,varchar(100),Yes,Yes,No,No,The database identifier
 settings,covariate_setting_json,varchar,Yes,No,No,No,The covariate settings JSON
 settings,case_covariate_setting_json,varchar,Yes,No,No,No,The during covariate settings JSON
@@ -99,12 +99,12 @@ settings,end_anchor,varchar(15),No,No,No,No,The end anchor
 settings,case_pre_target_duration,int,No,No,No,No,How far to look back before index for case features
 settings,case_post_outcome_duration,int,No,No,No,No,How far to look forward after outcome for case features
 cohort_details,database_id,varchar(100),Yes,Yes,No,No,The database identifier
-cohort_details,setting_id,float,Yes,Yes,No,No,The run identifier
-cohort_details,cohort_type,varchar(10),Yes,Yes,No,No,The cohort type
+cohort_details,setting_id,varchar(30),Yes,Yes,No,No,The run identifier
+cohort_details,cohort_type,varchar(12),Yes,Yes,No,No,The cohort type
 cohort_details,target_cohort_id,int,Yes,Yes,No,No,The target cohort id
 cohort_details,outcome_cohort_id,int,Yes,Yes,No,No,The outcome cohort id
 cohort_counts,database_id,varchar(100),Yes,No,No,No,The database identifier
-cohort_counts,cohort_type,varchar(10),Yes,No,No,No,The cohort type
+cohort_counts,cohort_type,varchar(12),Yes,No,No,No,The cohort type
 cohort_counts,target_cohort_id,int,Yes,No,No,No,The target cohort id
 cohort_counts,outcome_cohort_id,int,Yes,No,No,No,The outcome cohort id
 cohort_counts,risk_window_start,int,No,No,No,No,The risk window start

inst/sql/sql_server/ResultTables.sql

@@ -61,7 +61,7 @@ CREATE TABLE @my_schema.@table_prefixdechallenge_rechallenge (
 
 CREATE TABLE @my_schema.@table_prefixanalysis_ref (
     database_id varchar(100) NOT NULL,
-    setting_id float NOT NULL,
+    setting_id varchar(30) NOT NULL,
     analysis_id int NOT NULL,
     analysis_name varchar(max) NOT NULL,
     domain_id varchar(30),
@@ -74,7 +74,7 @@ CREATE TABLE @my_schema.@table_prefixanalysis_ref (
 
 CREATE TABLE @my_schema.@table_prefixcovariate_ref (
     database_id varchar(100) NOT NULL,
-    setting_id float NOT NULL,
+    setting_id varchar(30) NOT NULL,
     covariate_id bigint NOT NULL,
     covariate_name varchar(max) NOT NULL,
     analysis_id int NOT NULL,
@@ -86,8 +86,8 @@ CREATE TABLE @my_schema.@table_prefixcovariate_ref (
 
 CREATE TABLE @my_schema.@table_prefixcovariates (
     database_id varchar(100) NOT NULL,
-    setting_id float NOT NULL,
-    cohort_type varchar(10),
+    setting_id varchar(30) NOT NULL,
+    cohort_type varchar(12),
     target_cohort_id int,
     outcome_cohort_id int,
     min_characterization_mean float,
@@ -99,8 +99,8 @@ CREATE TABLE @my_schema.@table_prefixcovariates (
 
 CREATE TABLE @my_schema.@table_prefixcovariates_continuous (
     database_id varchar(100) NOT NULL,
-    setting_id float NOT NULL,
-    cohort_type varchar(10),
+    setting_id varchar(30) NOT NULL,
+    cohort_type varchar(12),
     target_cohort_id int,
     outcome_cohort_id int,
     covariate_id bigint NOT NULL,
@@ -119,7 +119,7 @@ CREATE TABLE @my_schema.@table_prefixcovariates_continuous (
 
 -- covariateSettings
 CREATE TABLE @my_schema.@table_prefixsettings (
-    setting_id float NOT NULL,
+    setting_id varchar(30) NOT NULL,
     database_id varchar(100) NOT NULL,
     covariate_setting_json varchar(MAX),
     case_covariate_setting_json varchar(MAX),
@@ -137,16 +137,16 @@ CREATE TABLE @my_schema.@table_prefixsettings (
 -- added this table
 CREATE TABLE @my_schema.@table_prefixcohort_details (
     database_id varchar(100) NOT NULL,
-    setting_id float NOT NULL,
-    cohort_type varchar(10),
+    setting_id varchar(30) NOT NULL,
+    cohort_type varchar(12),
     target_cohort_id int,
     outcome_cohort_id int,
     PRIMARY KEY (setting_id, database_id,target_cohort_id,outcome_cohort_id,cohort_type)
 );
 
 CREATE TABLE @my_schema.@table_prefixcohort_counts(
     database_id varchar(100) NOT NULL,
-    cohort_type varchar(10),
+    cohort_type varchar(12),
     target_cohort_id int,
     outcome_cohort_id int,
     risk_window_start int,