diff --git a/.gitignore b/.gitignore
index 5e16945..821e64f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,6 +4,7 @@ model.log
 __pycache__
 .python-version
 /output/*
+/post_check/*
 metadata/*
 venv/
 .DS_Store
diff --git a/analysis/additional_comorbidities.py b/analysis/additional_comorbidities.py
index f9bd947..1a335e7 100644
--- a/analysis/additional_comorbidities.py
+++ b/analysis/additional_comorbidities.py
@@ -181,12 +181,6 @@ def filter_codes_by_category(codelist, include):
   .is_on_or_after(last_prior_event(codelists
   .copd_resolved_codelist).date))
 )
- 
-#pulmonary fibrosis diagnosis
-has_pulmonary_fibrosis = (
-  has_prior_event(codelists
-  .pulmonary_fibrosis_codelist)
-)
 
 #cystic fibrosis diagnosis
 has_cystic_fibrosis = (
@@ -195,6 +189,21 @@ def filter_codes_by_category(codelist, include):
   .exists_for_patient()
 )
 
+#pulmonary fibrosis diagnosis
+has_pulmonary_fibrosis = (
+  has_prior_event(codelists
+  .pulmonary_fibrosis_codelist)
+)
+
+#Chronic Respiratory Disease
+has_crd = has_prior_event(codelists.crd_codelist)
+
+#other chronic respiratory disease
+has_other_resp = (
+  (has_pulmonary_fibrosis | has_crd) & 
+  (~has_asthma & ~ has_copd & ~ has_cystic_fibrosis)
+)
+
 #diabetes diagnosis
 diab_date = last_prior_event(codelists.diabetes_codelist).date
 dmres_date = last_prior_event(codelists.diabetes_resolved_codelist).date
@@ -248,9 +257,13 @@ def filter_codes_by_category(codelist, include):
   otherwise = False
 )
   
-#Chronic Heart Disease
-has_chd = has_prior_event(codelists.chd_codelist)
-  
+#Chronic Heart Diseases
+has_chd = (
+  (has_prior_event(codelists.chd_codelist)) | 
+  (has_prior_event(codelists.heart_failure_codelist)) |
+  (has_prior_event(codelists.coronary_heart_disease_codelist))
+)
+
 #Chronic Kidney Disease
   
 ###############################################################################
@@ -275,9 +288,6 @@ def filter_codes_by_category(codelist, include):
 #Chronic Neurological Disease including Significant Learning Disorder
 has_cnd = has_prior_event(codelists.cnd_codelist)
 
-#Chronic Respiratory Disease
-has_crd = has_prior_event(codelists.crd_codelist)
-
 #Cancer within 3 years 
 has_cancer = (
   has_prior_event(codelists.cancer_codelist +
@@ -320,12 +330,3 @@ def filter_codes_by_category(codelist, include):
   
 #Sickle Cell Disease
 has_sickle_cell = has_prior_event(codelists.sickle_cell_codelist)
-  
-#Heart Failure
-has_heart_failure = has_prior_event(codelists.heart_failure_codelist)
-  
-#Coronary Heart Disease 
-has_coronary_heart_disease = (
-  has_prior_event(codelists
-  .coronary_heart_disease_codelist)
-)
diff --git a/analysis/cohort_criteria.R b/analysis/cohort_criteria.R
new file mode 100644
index 0000000..3957f68
--- /dev/null
+++ b/analysis/cohort_criteria.R
@@ -0,0 +1,92 @@
+library(tidyverse)
+library(here)
+library(arrow)
+library(ggplot2)
+library(data.table)
+library(gtsummary)
+
+#define study start date and study end date
+source(here("analysis", "design", "design.R"))
+args <- commandArgs(trailingOnly = TRUE)
+if (length(args) == 0) {
+  study_start_date <- "2016-09-01"
+  study_end_date <- "2017-08-31"
+  cohort <- "adults"
+} else {
+  study_start_date <- study_dates[[args[[2]]]]
+  study_end_date <- study_dates[[args[[3]]]]
+  cohort <- args[[1]]
+}
+
+patients_df <- read_csv(
+  here::here("output", "flow_chart", paste0(cohort, "_", year(study_start_date), 
+             "_", year(study_end_date), "_flow_chart", ".csv")))
+
+patients_df <- patients_df %>%
+  mutate(
+    has_imd = ifelse(is.na(patients_df$imd_rounded), F, T),
+    is_female_or_male = ifelse(patients_df$sex == "female" | patients_df$sex == "male", T, F)
+  ) 
+
+if (cohort == "infants" | cohort == "infants_subgroup") {
+  is_appropriate_age = ifelse(patients_df$age >= 0 & patients_df$age <= 23, T, F)
+} else if (cohort == "children_and_adolescents") {
+  is_appropriate_age = ifelse(patients_df$age >= 2 & patients_df$age <= 17, T, F)
+} else if (cohort == "adults") {
+  is_appropriate_age = ifelse(patients_df$age >= 18 & patients_df$age <= 64, T, F)
+} else {
+  is_appropriate_age = ifelse(patients_df$age >= 65, T, F)
+}
+  
+patients_df <- patients_df %>%
+  mutate(is_appropriate_age = is_appropriate_age)
+
+# Define counts based on inclusion and exclusion criteria
+total <- nrow(patients_df)
+registered_count <- sum(patients_df$registered)
+non_registered_count <- total - registered_count
+age_count <- if (cohort == "infants" | cohort == "infants_subgroup") {
+  sum(patients_df$is_appropriate_age)
+  } else {
+  sum(patients_df$is_appropriate_age & patients_df$registered, na.rm = TRUE)
+  }
+not_age_count <- if (cohort == "infants" | cohort == "infants_subgroup") {
+  total - age_count
+} else {
+  registered_count - age_count
+}
+
+if (cohort == "older_adults") {
+  included_count <- sum(patients_df$registered & patients_df$is_female_or_male 
+                        & patients_df$is_appropriate_age & patients_df$has_imd 
+                        & !patients_df$care_home, na.rm = TRUE)
+  excluded_count <- sum(!patients_df$is_female_or_male |!patients_df$has_imd 
+                        | patients_df$care_home, na.rm = TRUE) - not_age_count
+} else if (cohort == "infants" | cohort == "infants_subgroup") {
+  included_count <- sum(patients_df$is_female_or_male 
+                        & patients_df$is_appropriate_age & patients_df$has_imd 
+                        & !patients_df$risk_group_infants 
+                        & !patients_df$severe_immunodeficiency, na.rm = TRUE)
+  excluded_count <- sum(!patients_df$is_female_or_male |!patients_df$has_imd 
+                        | patients_df$risk_group_infants 
+                        | patients_df$severe_immunodeficiency, na.rm = TRUE) - 
+                    not_age_count
+} else {
+  included_count <- sum(patients_df$registered & patients_df$is_female_or_male 
+                        & patients_df$is_appropriate_age & patients_df$has_imd,
+                        na.rm = TRUE)
+  excluded_count <- sum(!patients_df$is_female_or_male 
+                        |!patients_df$has_imd, na.rm = TRUE) - not_age_count
+}
+
+## create output directories ----
+fs::dir_create(here("output", "flow_chart"))
+
+#export flow chart numbers 
+table <- cbind(total, non_registered_count, registered_count,  
+               not_age_count, age_count, excluded_count, included_count)
+table <- table %>%
+  as.data.frame() %>%
+  write_csv(path = paste0(here::here("output", "flow_chart"), "/", 
+            "flow_chart_processed_", cohort, "_", year(study_start_date), "_", 
+            year(study_end_date), ".csv"))
diff --git a/analysis/cohort_description.R b/analysis/cohort_description.R
new file mode 100644
index 0000000..6bf7c15
--- /dev/null
+++ b/analysis/cohort_description.R
@@ -0,0 +1,112 @@
+library(tidyverse)
+library(here)
+library(arrow)
+library(ggplot2)
+library(data.table)
+library(gtsummary)
+
+## create output directories ----
+fs::dir_create(here("analysis"))
+
+#import redaction functions
+source(here("analysis", "functions", "redaction.R"))
+
+#define study start date and study end date
+source(here("analysis", "design", "design.R"))
+args <- commandArgs(trailingOnly = TRUE)
+if (length(args) == 0) {
+  study_start_date <- "2016-09-01"
+  study_end_date <- "2017-08-31"
+  cohort <- "adults"
+  codelist_type <- "specific"
+  investigation_type <- "primary"
+} else {
+  study_start_date <- study_dates[[args[[2]]]]
+  study_end_date <- study_dates[[args[[3]]]]
+  cohort <- args[[1]]
+  codelist_type <- args[[4]]
+  investigation_type <- args[[5]]
+}
+covid_season_min <- as.Date("2019-09-01")
+
+df_input <- read_feather(
+  here::here("output", "data", paste0("input_processed_", cohort, "_", 
+             year(study_start_date), "_", year(study_end_date), "_", 
+             codelist_type, "_", investigation_type,".arrow")))
+
+df_datatable <- as.data.table(df_input)
+
+if (cohort == "infants") {
+  table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
+  table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
+                                              latest_ethnicity_group, imd_quintile, 
+                                              rurality_classification)]
+  setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
+                    "imd_quintile", "rurality_classification"),
+           c("Age Group", "Sex", "Ethnicity", "IMD", "Rurality"))
+} else if (cohort == "children_and_adolescents") {
+  table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
+  table <- df_datatable[registered == TRUE, Reactive_Airway := ifelse(age <= 5, has_asthma_reactive_airway, F)]
+  table <- df_datatable[registered == TRUE, Asthma := ifelse(age > 5, has_asthma_reactive_airway, F)]
+  table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
+                        latest_ethnicity_group, imd_quintile, 
+                        rurality_classification, Asthma, Reactive_Airway,
+                        flu_vaccination)]
+  setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
+                    "imd_quintile", "rurality_classification",
+                    "Reactive_Airway", "flu_vaccination"),
+            c("Age Group", "Sex", "Ethnicity", "IMD", "Rurality",
+              "Reactive Airway", "Flu Vaccine"))
+  if (study_start_date >= covid_season_min) {
+    table[, covid_vaccination_count := df_datatable$covid_vaccination_count]
+    setnames(table, "covid_vaccination_count", "Covid Vaccine Doses")
+  }
+} else {
+  table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
+  table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
+                        latest_ethnicity_group, imd_quintile, 
+                        rurality_classification, smoking_status,
+                        hazardous_drinking, drug_usage, has_asthma, 
+                        has_copd, has_cystic_fibrosis, 
+                        has_other_resp, has_diabetes, has_addisons,
+                        severe_obesity, has_chd, has_ckd, has_cld, has_cnd,
+                        has_cancer, immunosuppressed, has_sickle_cell,  
+                        flu_vaccination)]
+  setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
+                    "imd_quintile", "rurality_classification",
+                    "smoking_status", "hazardous_drinking", "drug_usage",
+                    "has_asthma", "has_copd", "has_cystic_fibrosis", 
+                    "has_other_resp", "has_diabetes", "has_addisons" ,
+                    "severe_obesity", "has_chd", "has_ckd", "has_cld", 
+                    "has_cnd", "has_cancer", "immunosuppressed", 
+                    "has_sickle_cell", "flu_vaccination"),
+            c("Age_Group", "Sex", "Ethnicity", "IMD", "Rurality",
+              "Smoking Status", "Hazardous Drinking", "Drug Usage",
+              "Asthma", "COPD", "Cystic Fibrosis", "Other Chronic Respiratory Diseases",
+              "Diabetes", "Addisons", "Severe Obesity", "Chronic Heart Diseases",
+              "Chronic Kidney Disease", "Chronic Liver Disease", 
+              "Chronic Neurological Disease", "Cancer Within 3 Years",
+              "Immunosuppressed", "Sickle Cell Disease", "Flu Vaccine"))
+  if (study_start_date >= covid_season_min) {
+    table[, covid_vaccination_count := df_datatable$covid_vaccination_count]
+    setnames(table, "covid_vaccination_count", "Covid Vaccine Doses")
+  }
+ }
+
+## create output directories ----
+fs::dir_create(here("output", "table1"))
+
+#export
+table %>%
+  tbl_summary() %>% 
+  as_gt() %>%
+  gt::gtsave(filename = paste0("table1_", cohort, "_", year(study_start_date),
+             "_", year(study_end_date), ".html"), 
+             path = here::here("output", "table1"))
+
+table %>%
+  tbl_summary() %>%
+  as_tibble() %>%
+  write_csv(path = paste0(here::here("output", "table1"), "/", "table1_", 
+            cohort, "_", year(study_start_date), "_",
+            year(study_end_date),".csv"))
diff --git a/analysis/data_processing.R b/analysis/data_processing.R
index a5905c3..c3c5c8b 100644
--- a/analysis/data_processing.R
+++ b/analysis/data_processing.R
@@ -1,9 +1,9 @@
-library("tidyverse")
-library("here")
-library("arrow")
-library("ggplot2")
-library("data.table")
-library("lubridate")
+library(tidyverse)
+library(here)
+library(arrow)
+library(ggplot2)
+library(data.table)
+library(lubridate)
 
 ## create output directories ----
 fs::dir_create(here("analysis"))
@@ -11,16 +11,24 @@ fs::dir_create(here("analysis"))
 #define study start date and study end date
 source(here("analysis", "design", "design.R"))
 args <- commandArgs(trailingOnly = TRUE)
-study_start_date <- study_dates[[args[[2]]]]
-study_end_date <- study_dates[[args[[3]]]]
-cohort <- args[[1]]
-codelist_type <- args[[4]]
-investigation_type <- args[[5]]
+if (length(args) == 0) {
+  study_start_date <- "2016-09-01"
+  study_end_date <- "2017-08-31"
+  cohort <- "adults"
+  codelist_type <- "specific"
+  investigation_type <- "primary"
+} else {
+  study_start_date <- study_dates[[args[[2]]]]
+  study_end_date <- study_dates[[args[[3]]]]
+  cohort <- args[[1]]
+  codelist_type <- args[[4]]
+  investigation_type <- args[[5]]
+}
 
 df_input <- read_feather(
-  here::here("output", paste0("input_", cohort, "_", year(study_start_date),
-              "_", year(study_end_date), "_", codelist_type, "_", 
-              investigation_type,".arrow")))
+  here::here("output", "data", paste0("input_", cohort, "_", 
+             year(study_start_date), "_", year(study_end_date), "_",
+             codelist_type, "_", investigation_type,".arrow")))
 
 #assign ethnicity group
 df_input <- df_input %>%
@@ -140,8 +148,11 @@ df_input <- df_input %>%
 df_input$time_mild <- difftime(df_input$end_time_mild, study_start_date, df_input, "weeks")
 df_input$time_severe <- difftime(df_input$end_time_severe, study_start_date, df_input, "weeks")
 
+## create output directories ----
+fs::dir_create(here("output", "data"))
+
 #write the new input file
-write_feather(df_input, here::here("output", 
+write_feather(df_input, here::here("output", "data", 
   paste0("input_processed_", cohort, "_", year(study_start_date),
          "_", year(study_end_date), "_", codelist_type, 
          "_", investigation_type, ".arrow")))
diff --git a/analysis/dataset_definition.py b/analysis/dataset_definition.py
index f28e900..52294ab 100644
--- a/analysis/dataset_definition.py
+++ b/analysis/dataset_definition.py
@@ -55,6 +55,7 @@
 age_at_end = patients.age_on(study_end_date)
 age_months = (index_date - patients.date_of_birth).months
 age_at_start_months = (study_start_date - patients.date_of_birth).months
+#age_at_end_months = (study_end_date - patients.date_of_birth).months
 
 #get patients who are registered, have sex, age, and imd info
 registered_patients = case(
@@ -71,8 +72,8 @@
   when(cohort == "older_adults").then((age_at_start <= 110) & (age_at_end >= 65)),
   when(cohort == "adults").then((age_at_start <= 64) & (age_at_end >= 18)),
   when(cohort == "children_adolescents").then((age_at_start <= 17) & (age_at_end >= 2)),
-  when(cohort == "infants").then(age_at_start_months <= 23),
-  when(cohort == "infants_subgroup").then(age_at_start_months <= 23)
+  when(cohort == "infants").then((age_at_start_months <= 23) & (age_at_start_months >= 0)),
+  when(cohort == "infants_subgroup").then((age_at_start_months <= 23) & (age_at_start_months >= 0))
 )
 has_imd = (addresses.for_patient_on(index_date).imd_rounded.is_not_null())
 
@@ -849,11 +850,10 @@ def first_infection_event(codelist, where = True):
     filter_codes_by_category, smoking_status,
     hazardous_drinking, drug_usage, has_asthma,
     has_reactive_airway, has_copd,
-    has_pulmonary_fibrosis, has_cystic_fibrosis,
+    has_cystic_fibrosis, has_other_resp,
     has_diabetes, has_addisons, severe_obesity,
     has_chd, has_ckd, has_cld, has_cnd, has_crd,
     has_cancer, immunosuppressed, has_sickle_cell,
-    has_heart_failure, has_coronary_heart_disease
   )
   
   if cohort == "adults" or cohort == "older_adults" :
@@ -863,8 +863,8 @@ def first_infection_event(codelist, where = True):
     dataset.drug_usage = drug_usage
     dataset.has_asthma = has_asthma
     dataset.has_copd = has_copd
-    dataset.has_pulmonary_fibrosis = has_pulmonary_fibrosis
     dataset.has_cystic_fibrosis = has_cystic_fibrosis
+    dataset.has_other_resp = has_other_resp
     dataset.has_diabetes = has_diabetes
     dataset.has_addisons = has_addisons
     dataset.severe_obesity = severe_obesity
@@ -875,8 +875,6 @@ def first_infection_event(codelist, where = True):
     dataset.has_cancer = has_cancer
     dataset.immunosuppressed = immunosuppressed
     dataset.has_sickle_cell = has_sickle_cell
-    dataset.has_heart_failure = has_heart_failure
-    dataset.has_coronary_heart_disease = has_coronary_heart_disease
 
   if cohort == "children_and_adolescents" :
 
diff --git a/analysis/dataset_definition_flow_chart.py b/analysis/dataset_definition_flow_chart.py
index 9e0ca43..457c5da 100644
--- a/analysis/dataset_definition_flow_chart.py
+++ b/analysis/dataset_definition_flow_chart.py
@@ -2,7 +2,7 @@
 from pathlib import Path 
 
 from datetime import date, datetime
-from ehrql import create_dataset, case, when, maximum_of, minimum_of, years, days
+from ehrql import Dataset, case, when, maximum_of, minimum_of, years, days
 from ehrql.tables.tpp import ( 
   patients, 
   medications,
@@ -27,8 +27,7 @@
 
 import codelists
 
-dataset = create_dataset()
-dataset.configure_dummy_data(population_size = 100000)
+dataset = Dataset()
 
 #######################################################################################
 # Import study dates defined in "./analysis/design/study-dates.R" script and then exported
@@ -54,6 +53,7 @@
 age_at_end = patients.age_on(study_end_date)
 age_months = (index_date - patients.date_of_birth).months
 age_at_start_months = (study_start_date - patients.date_of_birth).months
+#age_at_end_months = (study_end_date - patients.date_of_birth).months
 
 #get patients who are registered, have sex, age, and imd info
 registered_patients = case(
@@ -70,8 +70,8 @@
   when(cohort == "older_adults").then((age_at_start <= 110) & (age_at_end >= 65)),
   when(cohort == "adults").then((age_at_start <= 64) & (age_at_end >= 18)),
   when(cohort == "children_adolescents").then((age_at_start <= 17) & (age_at_end >= 2)),
-  when(cohort == "infants").then(age_at_start_months <= 23),
-  when(cohort == "infants_subgroup").then(age_at_start_months <= 23)
+  when(cohort == "infants").then((age_at_start_months <= 23) & (age_at_start_months >= 0)),
+  when(cohort == "infants_subgroup").then((age_at_start_months <= 23) & (age_at_start_months >= 0))
 )
 has_imd = (addresses.for_patient_on(index_date).imd_rounded.is_not_null())
 
@@ -215,6 +215,5 @@ def first_infection_event(codelist, where = True):
   when(cohort == "infants_subgroup").then(age_at_start_months)
 )
 
-dataset.is_female_or_male = is_female_or_male
-dataset.is_appropriate_age = is_appropriate_age
-dataset.has_imd = has_imd
+#get patients IMD rank
+dataset.imd_rounded = addresses.for_patient_on(index_date).imd_rounded
diff --git a/analysis/dummydata/dummydata_adults.R b/analysis/dummydata/dummydata_adults.R
index 196c53d..435c788 100644
--- a/analysis/dummydata/dummydata_adults.R
+++ b/analysis/dummydata/dummydata_adults.R
@@ -1,13 +1,13 @@
 ##create a dummy dataset
 
-library("tidyverse")
-library("arrow")
-library("here")
-library("glue")
-library("EnvStats")
+library(tidyverse)
+library(arrow)
+library(here)
+library(glue)
+library(EnvStats)
 
-remotes::install_github("https://github.com/wjchulme/dd4d")
-library("dd4d")
+#remotes::install_github("https://github.com/wjchulme/dd4d")
+library(dd4d)
 
 ## create output directories ----
 fs::dir_create(here("analysis", "dummydata"))
@@ -110,7 +110,7 @@ sim_list = lst(
       "4",
       "5",
       "6"
-    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0))
+    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0.05))
   ),
   
   #household ID (to determine composition)
@@ -156,16 +156,16 @@ sim_list = lst(
                                        I(smoking_status == "Former")*-0.1))
   ),
   
-  #pulmonary fibrosis
-  has_pulmonary_fibrosis = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.001)
-  ),
-  
   #cystic fibrosis
   has_cystic_fibrosis = bn_node(
     ~ rbernoulli(n = ..n, p = 0.02)
   ),
   
+  #other chronic respiratory diseases
+  has_other_resp = bn_node(
+    ~ rbernoulli(n = ..n, p = 0.01)
+  ),
+  
   #diabetes
   has_diabetes = bn_node(
     ~ rbernoulli(n = ..n, p = plogis(-1 + age*0.02 + I(sex == "female")*-0.2))
@@ -181,9 +181,9 @@ sim_list = lst(
     ~ rbernoulli(n = ..n, p = 0.1)
   ),
   
-  #chronic heart disease
+  #chronic heart diseases
   has_chd = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.01)
+    ~ rbernoulli(n = ..n, p = 0.08)
   ),
   
   #chronic kidney disease
@@ -221,16 +221,6 @@ sim_list = lst(
     ~ rbernoulli(n = ..n, p = 0.01)
   ),
   
-  #heart failure
-  has_heart_failure = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.015)
-  ),
-  
-  #coronary heart disease
-  has_coronary_heart_disease = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.1)
-  ),
-  
   #flu vaccination
   flu_vaccination = bn_node(
     ~ rbernoulli(n = ..n, p = 0.75)
diff --git a/analysis/dummydata/dummydata_children_and_adolescents.R b/analysis/dummydata/dummydata_children_and_adolescents.R
index 1a9f966..6fe6f8e 100644
--- a/analysis/dummydata/dummydata_children_and_adolescents.R
+++ b/analysis/dummydata/dummydata_children_and_adolescents.R
@@ -1,13 +1,13 @@
 ##create a dummy dataset
 
-library("tidyverse")
-library("arrow")
-library("here")
-library("glue")
-library("EnvStats")
+library(tidyverse)
+library(arrow)
+library(here)
+library(glue)
+library(EnvStats)
 
-remotes::install_github("https://github.com/wjchulme/dd4d")
-library("dd4d")
+#remotes::install_github("https://github.com/wjchulme/dd4d")
+library(dd4d)
 
 ## create output directories ----
 fs::dir_create(here("analysis", "dummydata"))
@@ -110,7 +110,7 @@ sim_list = lst(
       "4",
       "5",
       "6"
-    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0))
+    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0.05))
   ),
   
   #household ID (to determine composition)
diff --git a/analysis/dummydata/dummydata_infants.R b/analysis/dummydata/dummydata_infants.R
index 2485d30..e55b416 100644
--- a/analysis/dummydata/dummydata_infants.R
+++ b/analysis/dummydata/dummydata_infants.R
@@ -1,13 +1,13 @@
 ##create a dummy dataset
 
-library("tidyverse")
-library("arrow")
-library("here")
-library("glue")
-library("EnvStats")
+library(tidyverse)
+library(arrow)
+library(here)
+library(glue)
+library(EnvStats)
 
-remotes::install_github("https://github.com/wjchulme/dd4d")
-library("dd4d")
+#remotes::install_github("https://github.com/wjchulme/dd4d")
+library(dd4d)
 
 ## create output directories ----
 fs::dir_create(here("analysis", "dummydata"))
@@ -113,7 +113,7 @@ sim_list = lst(
       "4",
       "5",
       "6"
-    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0))
+    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0.05))
   ),
   
   #household ID (to determine composition)
@@ -258,6 +258,18 @@ sim_list = lst(
   #date
   all_cause_mortality_day = bn_node(
     ~ as.integer(runif(n = ..n, index_day, index_day + 365))
+  ),
+  
+  ##exclusion criteria
+  
+  #part of risk group
+  risk_group_infants = bn_node(
+    ~ rbernoulli(n = ..n, p = 0.1)
+  ),
+  
+  #severe immunodeficiency
+  severe_immunodeficiency = bn_node(
+    ~ rbernoulli(n = ..n, p = 0.1)
   )
   
 )
diff --git a/analysis/dummydata/dummydata_infants_subgroup.R b/analysis/dummydata/dummydata_infants_subgroup.R
index cd26b63..9b91c2c 100644
--- a/analysis/dummydata/dummydata_infants_subgroup.R
+++ b/analysis/dummydata/dummydata_infants_subgroup.R
@@ -1,13 +1,13 @@
 ##create a dummy dataset
 
-library("tidyverse")
-library("arrow")
-library("here")
-library("glue")
-library("EnvStats")
+library(tidyverse)
+library(arrow)
+library(here)
+library(glue)
+library(EnvStats)
 
-remotes::install_github("https://github.com/wjchulme/dd4d")
-library("dd4d")
+#remotes::install_github("https://github.com/wjchulme/dd4d")
+library(dd4d)
 
 ## create output directories ----
 fs::dir_create(here("analysis", "dummydata"))
@@ -113,7 +113,7 @@ sim_list = lst(
       "4",
       "5",
       "6"
-    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0))
+    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0.05))
   ),
   
   #household ID (to determine composition)
@@ -305,6 +305,18 @@ sim_list = lst(
   #date
   all_cause_mortality_day = bn_node(
     ~ as.integer(runif(n = ..n, index_day, index_day + 365))
+  ),
+  
+  ##exclusion criteria
+  
+  #part of risk group
+  risk_group_infants = bn_node(
+    ~ rbernoulli(n = ..n, p = 0.1)
+  ),
+  
+  #severe immunodeficiency
+  severe_immunodeficiency = bn_node(
+    ~ rbernoulli(n = ..n, p = 0.1)
   )
   
 )
diff --git a/analysis/dummydata/dummydata_older_adults.R b/analysis/dummydata/dummydata_older_adults.R
index eed7df7..759731d 100644
--- a/analysis/dummydata/dummydata_older_adults.R
+++ b/analysis/dummydata/dummydata_older_adults.R
@@ -1,13 +1,13 @@
 ##create a dummy dataset
 
-library("tidyverse")
-library("arrow")
-library("here")
-library("glue")
-library("EnvStats")
+library(tidyverse)
+library(arrow)
+library(here)
+library(glue)
+library(EnvStats)
 
-remotes::install_github("https://github.com/wjchulme/dd4d")
-library("dd4d")
+#remotes::install_github("https://github.com/wjchulme/dd4d")
+library(dd4d)
 
 ## create output directories ----
 fs::dir_create(here("analysis", "dummydata"))
@@ -110,7 +110,7 @@ sim_list = lst(
       "4",
       "5",
       "6"
-    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0))
+    ), p = c(0.81, 0.03, 0.1, 0.04, 0.02, 0.05))
   ),
   
   #household ID (to determine composition)
@@ -156,16 +156,16 @@ sim_list = lst(
                                        I(smoking_status == "Former")*-0.1))
   ),
   
-  #pulmonary fibrosis
-  has_pulmonary_fibrosis = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.001)
-  ),
-  
   #cystic fibrosis
   has_cystic_fibrosis = bn_node(
     ~ rbernoulli(n = ..n, p = 0.02)
   ),
   
+  #other chronic respiratory diseases
+  has_other_resp = bn_node(
+    ~ rbernoulli(n = ..n, p = 0.01)
+  ),
+  
   #diabetes
   has_diabetes = bn_node(
     ~ rbernoulli(n = ..n, p = plogis(-1 + age*0.02 + I(sex == "female")*-0.2))
@@ -181,9 +181,9 @@ sim_list = lst(
     ~ rbernoulli(n = ..n, p = 0.1)
   ),
   
-  #chronic heart disease
+  #chronic heart diseases
   has_chd = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.01)
+    ~ rbernoulli(n = ..n, p = 0.08)
   ),
   
   #chronic kidney disease
@@ -221,16 +221,6 @@ sim_list = lst(
     ~ rbernoulli(n = ..n, p = 0.01)
   ),
   
-  #heart failure
-  has_heart_failure = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.015)
-  ),
-  
-  #coronary heart disease
-  has_coronary_heart_disease = bn_node(
-    ~ rbernoulli(n = ..n, p = 0.1)
-  ),
-  
   #flu vaccination
   flu_vaccination = bn_node(
     ~ rbernoulli(n = ..n, p = 0.75)
@@ -375,6 +365,13 @@ sim_list = lst(
   #date
   all_cause_mortality_day = bn_node(
     ~ as.integer(runif(n = ..n, index_day, index_day + 365))
+  ),
+  
+  ##exclusion criteria
+  
+  #care home resident
+  care_home = bn_node(
+    ~ rbernoulli(n = ..n, p = 0.1)
   )
   
 )
diff --git a/analysis/dummydata/dummyextract_adults_2016_2017.arrow b/analysis/dummydata/dummyextract_adults_2016_2017.arrow
index 8abf466..667e680 100644
Binary files a/analysis/dummydata/dummyextract_adults_2016_2017.arrow and b/analysis/dummydata/dummyextract_adults_2016_2017.arrow differ
diff --git a/analysis/dummydata/dummyextract_children_adolescents_2016_2017.arrow b/analysis/dummydata/dummyextract_children_adolescents_2016_2017.arrow
deleted file mode 100644
index 411271e..0000000
Binary files a/analysis/dummydata/dummyextract_children_adolescents_2016_2017.arrow and /dev/null differ
diff --git a/analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow b/analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
index a176d57..e1a931f 100644
Binary files a/analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow and b/analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow differ
diff --git a/analysis/dummydata/dummyextract_infants_2016_2017.arrow b/analysis/dummydata/dummyextract_infants_2016_2017.arrow
index e2ddef1..97f52c0 100644
Binary files a/analysis/dummydata/dummyextract_infants_2016_2017.arrow and b/analysis/dummydata/dummyextract_infants_2016_2017.arrow differ
diff --git a/analysis/dummydata/dummyextract_infants_subgroup_2016_2017.arrow b/analysis/dummydata/dummyextract_infants_subgroup_2016_2017.arrow
index d4113f3..b1b1af4 100644
Binary files a/analysis/dummydata/dummyextract_infants_subgroup_2016_2017.arrow and b/analysis/dummydata/dummyextract_infants_subgroup_2016_2017.arrow differ
diff --git a/analysis/dummydata/dummyextract_older_adults_2016_2017.arrow b/analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
index e6d21d9..7ed895f 100644
Binary files a/analysis/dummydata/dummyextract_older_adults_2016_2017.arrow and b/analysis/dummydata/dummyextract_older_adults_2016_2017.arrow differ
diff --git a/analysis/flow_chart.R b/analysis/flow_chart.R
deleted file mode 100644
index 853421c..0000000
--- a/analysis/flow_chart.R
+++ /dev/null
@@ -1,121 +0,0 @@
-library("tidyverse")
-library("here")
-library("arrow")
-library("ggplot2")
-library("data.table")
-library("gtsummary")
-
-#define study start date and study end date
-source(here("analysis", "design", "design.R"))
-args <- commandArgs(trailingOnly = TRUE)
-study_start_date <- study_dates[[args[[2]]]]
-study_end_date <- study_dates[[args[[3]]]]
-cohort <- args[[1]]
-
-patients_df <- read_feather(
-  here::here("output", paste0(cohort, "_", year(study_start_date), "_", 
-                              year(study_end_date), "_flow_chart", ".arrow")))
-
-
-library(Gmisc, quietly = TRUE)
-library(glue)
-library(htmlTable)
-library(grid)
-library(magrittr)
-
-# Define counts based on inclusion and exclusion criteria
-registered_count <- sum(patients_df$registered)
-gender_count <- sum(patients_df$is_female_or_male)
-age_count <- sum(patients_df$is_appropriate_age & registered_count)
-imd_count <- sum(patients_df$has_imd)
-included_count <- sum(patients_df$registered & patients_df$is_female_or_male & patients_df$is_appropriate_age & patients_df$has_imd)
-care_home_count <- sum(patients_df$registered & patients_df$is_appropriate_age & patients_df$care_home)
-demographic_excl_count <- sum(patients_df$registered & patients_df$is_appropriate_age & !patients_df$care_home &!patients_df$is_female_or_male |!patients_df$has_imd)
-
-org_cohort <- boxGrob(glue("Total Patients",
-                           "n = {pop}",
-                           pop = txtInt(nrow(patients_df)),
-                           .sep = "\n"))
-
-follow_up <- boxGrob(glue("At least one year of follow-up before {start}",
-                           "n = {follow}",
-                           start = study_start_date,
-                           follow = txtInt(registered_count),
-                           .sep = "\n"))
-
-follow_up_excl <- boxGrob(glue("Less than one year of prior follow-up",
-                               "n = {follow_e}",
-                               follow_e = txtInt(nrow(patients_df) - registered_count),
-                               .sep = "\n"))
-
-age <- boxGrob(glue("Aged 65 or over",
-                    "n = {age}",
-                    age = txtInt(age_count),
-                    .sep = "\n"))
-
-age_excl <- boxGrob(glue("Aged under 65 on {start}",
-                         "n = {age_e}",
-                         start = study_start_date,
-                         age_e = txtInt(nrow(patients_df) - age_count),
-                         .sep = "\n"))
-
-not_care_home <- boxGrob(glue("Not in long-term care facility",
-                              "n = {nocare}",
-                              nocare = txtInt(age_count - care_home_count),
-                              .sep = "\n"))
-
-care_home <- boxGrob(glue("In long-term care facility",
-                          "n = {care}",
-                          care = txtInt(care_home_count),
-                          .sep = "\n"))
-
-demographic_excl <- boxGrob(glue("Missing deomgraphic information",
-                                 "n = {excl}",
-                                 excl = txtInt(demographic_excl_count),
-                                 .sep = "\n"))
-
-included <- boxGrob(glue("Included",
-                         "n = {incl}",
-                         incl = txtInt(included_count),
-                         .sep = "\n"))
-
-grid.newpage()
-vert <- spreadVertical(org_cohort = org_cohort, follow_up = follow_up, 
-                       age = age, not_care_home = not_care_home, 
-                       included = included, .from = org_cohort,
-                       .to = included, .type = "center")
-vert$excluded <- NULL
-
-follow_up_excl <- moveBox(follow_up_excl,
-                          x = 0.82,
-                          y = coords(vert$follow_up)$top + distance(vert$age, vert$follow_up, half = TRUE, center = FALSE))
-
-age_excl <- moveBox(age_excl,
-                    x = 0.82,
-                    y = coords(vert$age)$top + distance(vert$not_care_home, vert$age, half = TRUE, center = FALSE))
-
-care_home <- moveBox(care_home,
-                     x = 0.82,
-                     y = coords(vert$not_care_home)$top + distance(vert$included, vert$not_care_home, half = TRUE, center = FALSE))
-
-demographic_excl <- moveBox(demographic_excl,
-                            x = 0.82,
-                            y = coords(vert$included)$top + distance(vert$included, vert$not_care_home, half = TRUE, center = FALSE))
-
-
-for (i in 1:(length(vert) - 1)) {
-  connectGrob(vert[[i]], vert[[i + 1]], type = "vert") %>%
-    print
-}
-
-connectGrob(vert$org_cohort, follow_up_excl, type = "L")
-connectGrob(vert$follow_up, age_excl, type = "L")
-connectGrob(vert$age, care_home, type = "L")
-connectGrob(vert$not_care_home,  demographic_excl, type = "L")
-
-# Print boxes
-vert
-follow_up_excl
-age_excl
-care_home
-demographic_excl
diff --git a/analysis/report.R b/analysis/report.R
index fc0ef87..eb181d1 100644
--- a/analysis/report.R
+++ b/analysis/report.R
@@ -1,9 +1,9 @@
-library("tidyverse")
-library("here")
-library("arrow")
-library("ggplot2")
-library("data.table")
-library("gtsummary")
+library(tidyverse)
+library(here)
+library(arrow)
+library(ggplot2)
+library(data.table)
+library(gtsummary)
 
 ## create output directories ----
 fs::dir_create(here("analysis"))
@@ -14,11 +14,19 @@ source(here("analysis", "functions", "redaction.R"))
 #define study start date and study end date
 source(here("analysis", "design", "design.R"))
 args <- commandArgs(trailingOnly = TRUE)
-study_start_date <- study_dates[[args[[2]]]]
-study_end_date <- study_dates[[args[[3]]]]
-cohort <- args[[1]]
-codelist_type <- args[[4]]
-investigation_type <- args[[5]]
+if (length(args) == 0) {
+  study_start_date <- "2016-09-01"
+  study_end_date <- "2017-08-31"
+  cohort <- "adults"
+  codelist_type <- "specific"
+  investigation_type <- "primary"
+} else {
+  study_start_date <- study_dates[[args[[2]]]]
+  study_end_date <- study_dates[[args[[3]]]]
+  cohort <- args[[1]]
+  codelist_type <- args[[4]]
+  investigation_type <- args[[5]]
+}
 covid_season_min <- as.Date("2019-09-01")
 
 # roundmid_any <- function(x, to=6){
@@ -27,153 +35,22 @@ covid_season_min <- as.Date("2019-09-01")
 # }
 
 df_input <- read_feather(
-  here::here("output", paste0("input_processed_", cohort, "_", year(study_start_date),
-             "_", year(study_end_date), "_", codelist_type, "_", 
-             investigation_type,".arrow")))
-
-# lab <- ifelse(cohort == "infants", "Age (Months)", 
-#        ifelse(cohort == "infants_subgroup", "Age (Months)", "Age (Years)"))
-# 
-# plot_age <- ggplot(data = df_input, aes(age, frequency(age))) + geom_col(width = 0.9) +
-#   xlab(lab) + ylab("Frequency")
-# 
-# ggsave(
-#   plot = plot_age,
-#   filename = paste0("descriptive_", cohort, "_", year(study_start_date),
-#     "_", year(study_end_date), "_", codelist_type, "_", 
-#     investigation_type,".png"), path = here::here("output"),
-# )
-
-df_datatable <- as.data.table(df_input)
+  here::here("output", "data", paste0("input_processed_", cohort, "_", 
+             year(study_start_date), "_", year(study_end_date), "_", 
+             codelist_type, "_", investigation_type,".arrow")))
 
-if (cohort == "infants") {
-  table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
-  table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
-                        latest_ethnicity_group, imd_quintile, 
-                        rurality_classification)]
-  setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
-                    "imd_quintile", "rurality_classification"),
-           c("Age Group", "Sex", "Ethnicity", "IMD", "Rurality"))
-} else if (cohort == "children_and_adolescents") {
-  if(investigation_type == "primary") {
-    table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
-    table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
-                          latest_ethnicity_group, imd_quintile, 
-                          rurality_classification, flu_vaccination)]
-    setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
-                      "imd_quintile", "rurality_classification",
-                      "flu_vaccination"),
-              c("Age Group", "Sex", "Ethnicity", "IMD", "Rurality",
-              "Flu Vaccine"))
-    if (study_start_date >= covid_season_min) {
-      table[, covid_vaccination_count := df_datatable$covid_vaccination_count]
-      setnames(table, "covid_vaccination_count", "Covid Vaccine Doses")
-    }
-  } else {
-    table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
-    table <- df_datatable[registered == TRUE, Reactive_Airway := ifelse(age <= 5, has_asthma_reactive_airway, F)]
-    table <- df_datatable[registered == TRUE, Asthma := ifelse(age > 5, has_asthma_reactive_airway, F)]
-    table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
-                          latest_ethnicity_group, imd_quintile, 
-                          rurality_classification, Asthma, Reactive_Airway,
-                          flu_vaccination)]
-    setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
-                      "imd_quintile", "rurality_classification",
-                      "Reactive_Airway", "flu_vaccination"),
-             c("Age Group", "Sex", "Ethnicity", "IMD", "Rurality",
-               "Reactive Airway", "Flu Vaccine"))
-    if (study_start_date >= covid_season_min) {
-      table[, covid_vaccination_count := df_datatable$covid_vaccination_count]
-      setnames(table, "covid_vaccination_count", "Covid Vaccine Doses")
-    }
-  }
-} else {
-  if (investigation_type == "primary") {
-    table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
-    table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
-                          latest_ethnicity_group, imd_quintile, 
-                          rurality_classification, flu_vaccination)]
-    setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
-                      "imd_quintile", "rurality_classification",
-                      "flu_vaccination"),
-             c("Age Group", "Sex", "Ethnicity", "IMD", "Rurality",
-               "Flu Vaccine"))
-    if (study_start_date >= covid_season_min) {
-      table[, covid_vaccination_count := df_datatable$covid_vaccination_count]
-      setnames(table, "covid_vaccination_count", "Covid Vaccine Doses")
-    }
-  } else {
-    table <- df_datatable[registered == TRUE, Total := n_distinct(patient_id)]
-    table <- df_datatable[registered == TRUE, .(Total, age_band, sex, 
-                          latest_ethnicity_group, imd_quintile, 
-                          rurality_classification, smoking_status,
-                          hazardous_drinking, drug_usage, has_asthma, 
-                          has_copd, has_pulmonary_fibrosis, 
-                          has_cystic_fibrosis, has_diabetes, has_addisons,
-                          severe_obesity, has_chd, has_ckd, has_cld, has_cnd,
-                          has_cancer, immunosuppressed, has_sickle_cell, 
-                          has_heart_failure, has_coronary_heart_disease, 
-                          flu_vaccination)]
-    setnames(table, c("age_band", "sex", "latest_ethnicity_group", 
-                      "imd_quintile", "rurality_classification",
-                      "smoking_status", "hazardous_drinking", "drug_usage",
-                      "has_asthma", "has_copd", "has_pulmonary_fibrosis", 
-                      "has_cystic_fibrosis", "has_diabetes", "has_addisons" ,
-                      "severe_obesity", "has_chd", "has_ckd", "has_cld", 
-                      "has_cnd", "has_cancer", "immunosuppressed", 
-                      "has_sickle_cell", "has_heart_failure",
-                      "has_coronary_heart_disease", "flu_vaccination"),
-             c("Age_Group", "Sex", "Ethnicity", "IMD", "Rurality",
-               "Smoking Status", "Hazardous Drinking", "Drug Usage",
-               "Asthma", "COPD", "Pulmonary Fibrosis", "Cystic Fibrosis",
-               "Diabetes", "Addisons", "Severe Obesity", "Chronic Heart Disease",
-               "Chronic Kidney Disease", "Chronic Liver Disease", 
-               "Chronic Neurological Disease", "Cancer Within 3 Years",
-               "Immunosuppressed", "Sickle Cell Disease", "Heart Failure",
-               "Coronary Heart Disease", "Flu Vaccine"))
-    if (study_start_date >= covid_season_min) {
-      table[, covid_vaccination_count := df_datatable$covid_vaccination_count]
-      setnames(table, "covid_vaccination_count", "Covid Vaccine Doses")
-    }
-  }
-}
+## create output directories ----
+fs::dir_create(here("output", "models"))
 
-table %>%
-  tbl_summary() %>% 
-  as_gt() %>%
-  gt::gtsave(filename = paste0("table1_", cohort, "_", year(study_start_date),
-              "_", year(study_end_date), "_", codelist_type, "_", 
-              investigation_type,".html"), path = here::here("output"))
+lab <- ifelse(cohort == "infants", "Age (Months)",
+       ifelse(cohort == "infants_subgroup", "Age (Months)", "Age (Years)"))
 
-table %>%
-  tbl_summary() %>%
-  as_tibble() %>%
-  write_csv(path = paste0(here::here("output"), "/", "table1_", cohort, "_", year(study_start_date),
-            "_", year(study_end_date), "_", codelist_type, "_",
-            investigation_type,".csv"))
+plot_age <- ggplot(data = df_input, aes(age, frequency(age))) + geom_col(width = 0.9) +
+  xlab(lab) + ylab("Frequency")
 
-# table_sum <- tbl_summary(table)
-# table_redacted <- redact_tblsummary(table_sum, 7)
-# var_labels <- colnames(table_sum)
-# raw_stats <- table_sum$meta_data %>%
-#   select(var_label, df_stats) %>%
-#   unnest(df_stats)
-# threshold = 7
-# raw_stats_redacted <- raw_stats %>%
-#   mutate(
-#     n = roundmid_any(n, threshold),
-#     N = roundmid_any(N, threshold),
-#     p = n / N,
-#     N_miss = roundmid_any(N_miss, threshold),
-#     N_obs = roundmid_any(N_obs, threshold),
-#     p_miss = N_miss / N_obs,
-#     N_nonmiss = roundmid_any(N_nonmiss, threshold),
-#     p_nonmiss = N_nonmiss / N_obs,
-#     var_label = factor(var_label, levels = map_chr(var_labels[-c(1, 2)], ~ last(as.character(.)))),
-#     variable_levels = replace_na(as.character(variable_levels), "")
-#   )
-# 
-# raw_stats_redacted %>%
-#   write.csv(filename = paste0("table1_raw_", cohort, "_", year(study_start_date),
-#              "_", year(study_end_date), "_", codelist_type, "_", 
-#              investigation_type,".xlsx"), path = here::here("output"))
+ggsave(
+  plot = plot_age,
+  filename = paste0("descriptive_", cohort, "_", year(study_start_date),
+    "_", year(study_end_date), "_", codelist_type, "_",
+    investigation_type,".png"), path = here::here("output", "models"),
+)
diff --git a/analysis/table_collation.R b/analysis/table_collation.R
new file mode 100644
index 0000000..c3a30db
--- /dev/null
+++ b/analysis/table_collation.R
@@ -0,0 +1,53 @@
+library(tidyverse)
+library(here)
+library(arrow)
+library(ggplot2)
+
+#define cohort
+args <- commandArgs(trailingOnly = TRUE)
+if (length(args) == 0) {
+  cohort <- "adults"
+} else {
+  cohort <- args[[1]]
+}
+
+# import flow chart info by cohort
+collated_table1 = rbind(
+  read_csv(here::here("output", paste0("flow_chart_processed_", cohort, 
+                      "_2016_2017.csv"))) %>% mutate(subset = "2016_17"),
+  read_csv(here::here("output", paste0("flow_chart_processed_", cohort, 
+                      "_2017_2018.csv"))) %>% mutate(subset = "2017_18"),
+  read_csv(here::here("output", paste0("flow_chart_processed_", cohort, 
+                      "_2018_2019.csv"))) %>% mutate(subset = "2018_19"),
+  read_csv(here::here("output", paste0("flow_chart_processed_", cohort, 
+                      "_2019_2020.csv"))) %>% mutate(subset = "2019_20"),
+  read_csv(here::here("output", paste0("flow_chart_processed_", cohort, 
+                      "_2020_2021.csv"))) %>% mutate(subset = "2020_21"),
+  read_csv(here::here("output", paste0("flow_chart_processed_", cohort, 
+                      "_2021_2022.csv"))) %>% mutate(subset = "2021_22"),
+  read_csv(here::here("output", paste0("flow_chart_processed_", cohort, 
+                      "_2022_2023.csv"))) %>% mutate(subset = "2022_23")
+)
+
+#save as csv
+write_csv(collated_table1, paste0(here::here("output"), "/", "table1_collated", 
+                                  cohort, "_", year(study_start_date), "_", year(study_end_date),".csv"))
+
+# import table 1 by cohort
+collated_table1 = rbind(
+  read_csv(here::here("output", paste0("table1_", cohort, "_2016_2017.csv"))) %>% mutate(subset = "2016_17"),
+  read_csv(here::here("output", paste0("table1_", cohort, "_2017_2018.csv"))) %>% mutate(subset = "2017_18"),
+  read_csv(here::here("output", paste0("table1_", cohort, "_2018_2019.csv"))) %>% mutate(subset = "2018_19"),
+  read_csv(here::here("output", paste0("table1_", cohort, "_2019_2020.csv"))) %>% mutate(subset = "2019_20"),
+  read_csv(here::here("output", paste0("table1_", cohort, "_2020_2021.csv"))) %>% mutate(subset = "2020_21"),
+  read_csv(here::here("output", paste0("table1_", cohort, "_2021_2022.csv"))) %>% mutate(subset = "2021_22"),
+  read_csv(here::here("output", paste0("table1_", cohort, "_2022_2023.csv"))) %>% mutate(subset = "2022_23")
+)
+
+## create output directories ----
+fs::dir_create(here("output", "table1"))
+
+#save as csv
+write_csv(collated_table1, paste0(here::here("output", "table1"), "/", 
+          "table1_collated", cohort, "_", year(study_start_date), "_", 
+          year(study_end_date),".csv"))
diff --git a/project.yaml b/project.yaml
index fe5b6b2..c36a939 100644
--- a/project.yaml
+++ b/project.yaml
@@ -8,336 +8,406 @@ actions:
 
 ### exploratory analysis 
 
+##  season 1 (2016/17) - cohort inclusion
+
   generate_flow_chart_data_older_adults_s1:
     run: >
       ehrql:v1 generate-dataset analysis/dataset_definition_flow_chart.py
-      --output output/older_adults_2016_2017_flow_chart.arrow
+      --output output/flow_chart/older_adults_2016_2017_flow_chart.csv
+      --dummy-data-file analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
       -- older_adults season1_start_date season1_end_date
     outputs:
       highly_sensitive:
-        dataset: output/older_adults_2016_2017_flow_chart.arrow
-
-# ### primary analysis
-# 
-# ##  season 1 (2016/17)
-# 
-#   generate_dataset_older_adults_s1_spec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_older_adults_2016_2017_specific_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
-#       -- older_adults season1_start_date season1_end_date specific primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_older_adults_2016_2017_specific_primary.arrow
-# 
-#   process_dataset_older_adults_s1_spec:
-#     run: r:latest analysis/data_processing.R older_adults season1_start_date season1_end_date specific primary
-#     needs: [generate_dataset_older_adults_s1_spec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_older_adults_2016_2017_specific_primary.arrow
-# 
-#   describe_dataset_older_adults_s1_spec:
-#     run: r:latest analysis/report.R older_adults season1_start_date season1_end_date specific primary
-#     needs: [process_dataset_older_adults_s1_spec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_older_adults_2016_2017_specific_primary.png
-#         html: output/table1_older_adults_2016_2017_specific_primary.html
-#         csv: output/table1_older_adults_2016_2017_specific_primary.csv
-# 
-#   generate_dataset_adults_s1_spec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_adults_2016_2017_specific_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_adults_2016_2017.arrow
-#       -- adults season1_start_date season1_end_date specific primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_adults_2016_2017_specific_primary.arrow
-# 
-#   process_dataset_adults_s1_spec:
-#     run: r:latest analysis/data_processing.R adults season1_start_date season1_end_date specific primary
-#     needs: [generate_dataset_adults_s1_spec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_adults_2016_2017_specific_primary.arrow
-# 
-#   describe_dataset_adults_s1_spec:
-#     run: r:latest analysis/report.R adults season1_start_date season1_end_date specific primary
-#     needs: [process_dataset_adults_s1_spec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_adults_2016_2017_specific_primary.png
-#         html: output/table1_adults_2016_2017_specific_primary.html
-#         csv: output/table1_adults_2016_2017_specific_primary.csv
-# 
-#   generate_dataset_children_and_adolescents_s1_spec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_children_and_adolescents_2016_2017_specific_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
-#       -- children_and_adolescents season1_start_date season1_end_date specific primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_children_and_adolescents_2016_2017_specific_primary.arrow
-# 
-#   process_dataset_children_and_adolescents_s1_spec:
-#     run: r:latest analysis/data_processing.R children_and_adolescents season1_start_date season1_end_date specific primary
-#     needs: [generate_dataset_children_and_adolescents_s1_spec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_children_and_adolescents_2016_2017_specific_primary.arrow
-# 
-#   describe_dataset_children_and_adolescents_s1_spec:
-#     run: r:latest analysis/report.R children_and_adolescents season1_start_date season1_end_date specific primary
-#     needs: [process_dataset_children_and_adolescents_s1_spec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_children_and_adolescents_2016_2017_specific_primary.png
-#         html: output/table1_children_and_adolescents_2016_2017_specific_primary.html
-#         csv: output/table1_children_and_adolescents_2016_2017_specific_primary.csv
-# 
-#   generate_dataset_infants_s1_spec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_infants_2016_2017_specific_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_infants_2016_2017.arrow
-#       -- infants season1_start_date season1_end_date specific primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_infants_2016_2017_specific_primary.arrow
-# 
-#   process_dataset_infants_s1_spec:
-#     run: r:latest analysis/data_processing.R infants season1_start_date season1_end_date specific primary
-#     needs: [generate_dataset_infants_s1_spec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_infants_2016_2017_specific_primary.arrow
-# 
-#   describe_dataset_infants_s1_spec:
-#     run: r:latest analysis/report.R infants season1_start_date season1_end_date specific primary
-#     needs: [process_dataset_infants_s1_spec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_infants_2016_2017_specific_primary.png
-#         html: output/table1_infants_2016_2017_specific_primary.html
-#         csv: output/table1_infants_2016_2017_specific_primary.csv
-# 
-# ### sensitivity analysis
-# 
-# ##  season 1 (2016/17)
-# 
-#   generate_dataset_older_adults_s1_sens:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_older_adults_2016_2017_sensitive_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
-#       -- older_adults season1_start_date season1_end_date sensitive primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_older_adults_2016_2017_sensitive_primary.arrow
-# 
-#   process_dataset_older_adults_s1_sens:
-#     run: r:latest analysis/data_processing.R older_adults season1_start_date season1_end_date sensitive primary
-#     needs: [generate_dataset_older_adults_s1_sens]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_older_adults_2016_2017_sensitive_primary.arrow
-# 
-#   describe_dataset_older_adults_s1_sens:
-#     run: r:latest analysis/report.R older_adults season1_start_date season1_end_date sensitive primary
-#     needs: [process_dataset_older_adults_s1_sens]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_older_adults_2016_2017_sensitive_primary.png
-#         html: output/table1_older_adults_2016_2017_sensitive_primary.html
-#         csv: output/table1_older_adults_2016_2017_sensitive_primary.csv
-# 
-#   generate_dataset_adults_s1_sens:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_adults_2016_2017_sensitive_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_adults_2016_2017.arrow
-#       -- adults season1_start_date season1_end_date sensitive primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_adults_2016_2017_sensitive_primary.arrow
-# 
-#   process_dataset_adults_s1_sens:
-#     run: r:latest analysis/data_processing.R adults season1_start_date season1_end_date sensitive primary
-#     needs: [generate_dataset_adults_s1_sens]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_adults_2016_2017_sensitive_primary.arrow
-# 
-#   describe_dataset_adults_s1_sens:
-#     run: r:latest analysis/report.R adults season1_start_date season1_end_date sensitive primary
-#     needs: [process_dataset_adults_s1_sens]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_adults_2016_2017_sensitive_primary.png
-#         html: output/table1_adults_2016_2017_sensitive_primary.html
-#         csv: output/table1_adults_2016_2017_sensitive_primary.csv
-# 
-#   generate_dataset_children_and_adolescents_s1_sens:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_children_and_adolescents_2016_2017_sensitive_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
-#       -- children_and_adolescents season1_start_date season1_end_date sensitive primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_children_and_adolescents_2016_2017_sensitive_primary.arrow
-# 
-#   process_dataset_children_and_adolescents_s1_sens:
-#     run: r:latest analysis/data_processing.R children_and_adolescents season1_start_date season1_end_date sensitive primary
-#     needs: [generate_dataset_children_and_adolescents_s1_sens]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_children_and_adolescents_2016_2017_sensitive_primary.arrow
-# 
-#   describe_dataset_children_and_adolescents_s1_sens:
-#     run: r:latest analysis/report.R children_and_adolescents season1_start_date season1_end_date sensitive primary
-#     needs: [process_dataset_children_and_adolescents_s1_sens]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_children_and_adolescents_2016_2017_sensitive_primary.png
-#         html: output/table1_children_and_adolescents_2016_2017_sensitive_primary.html
-#         csv: output/table1_children_and_adolescents_2016_2017_sensitive_primary.csv
-# 
-#   generate_dataset_infants_s1_sens:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_infants_2016_2017_sensitive_primary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_infants_2016_2017.arrow
-#       -- infants season1_start_date season1_end_date sensitive primary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_infants_2016_2017_sensitive_primary.arrow
-# 
-#   process_dataset_infants_s1_sens:
-#     run: r:latest analysis/data_processing.R infants season1_start_date season1_end_date sensitive primary
-#     needs: [generate_dataset_infants_s1_sens]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_infants_2016_2017_sensitive_primary.arrow
-# 
-#   describe_dataset_infants_s1_sens:
-#     run: r:latest analysis/report.R infants season1_start_date season1_end_date sensitive primary
-#     needs: [process_dataset_infants_s1_sens]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_infants_2016_2017_sensitive_primary.png
-#         html: output/table1_infants_2016_2017_sensitive_primary.html
-#         csv: output/table1_infants_2016_2017_sensitive_primary.csv
-# 
-# ### secondary analysis
-# 
-# ##  season 1 (2016/17)
-# 
-#   generate_dataset_older_adults_s1_sens_sec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_older_adults_2016_2017_sensitive_secondary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
-#       -- older_adults season1_start_date season1_end_date sensitive secondary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_older_adults_2016_2017_sensitive_secondary.arrow
-# 
-#   process_dataset_older_adults_s1_sens_sec:
-#     run: r:latest analysis/data_processing.R older_adults season1_start_date season1_end_date sensitive secondary
-#     needs: [generate_dataset_older_adults_s1_sens_sec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_older_adults_2016_2017_sensitive_secondary.arrow
-#  
-#   describe_dataset_older_adults_s1_sens_sec:
-#     run: r:latest analysis/report.R older_adults season1_start_date season1_end_date sensitive secondary
-#     needs: [process_dataset_older_adults_s1_sens_sec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_older_adults_2016_2017_sensitive_secondary.png
-#         html: output/table1_older_adults_2016_2017_sensitive_secondary.html
-#         csv: output/table1_older_adults_2016_2017_sensitive_secondary.csv
-# 
-#   generate_dataset_adults_s1_sens_sec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_adults_2016_2017_sensitive_secondary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_adults_2016_2017.arrow
-#       -- adults season1_start_date season1_end_date sensitive secondary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_adults_2016_2017_sensitive_secondary.arrow
-# 
-#   process_dataset_adults_s1_sens_sec:
-#     run: r:latest analysis/data_processing.R adults season1_start_date season1_end_date sensitive secondary
-#     needs: [generate_dataset_adults_s1_sens_sec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_adults_2016_2017_sensitive_secondary.arrow
-#  
-#   describe_dataset_adults_s1_sens_sec:
-#     run: r:latest analysis/report.R adults season1_start_date season1_end_date sensitive secondary
-#     needs: [process_dataset_adults_s1_sens_sec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_adults_2016_2017_sensitive_secondary.png
-#         html: output/table1_adults_2016_2017_sensitive_secondary.html
-#         csv: output/table1_adults_2016_2017_sensitive_secondary.csv
-# 
-#   generate_dataset_children_and_adolescents_s1_sens_sec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_children_and_adolescents_2016_2017_sensitive_secondary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
-#       -- children_and_adolescents season1_start_date season1_end_date sensitive secondary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_children_and_adolescents_2016_2017_sensitive_secondary.arrow
-# 
-#   process_dataset_children_and_adolescents_s1_sens_sec:
-#     run: r:latest analysis/data_processing.R children_and_adolescents season1_start_date season1_end_date sensitive secondary
-#     needs: [generate_dataset_children_and_adolescents_s1_sens_sec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_children_and_adolescents_2016_2017_sensitive_secondary.arrow
-#  
-#   describe_dataset_children_and_adolescents_s1_sens_sec:
-#     run: r:latest analysis/report.R children_and_adolescents season1_start_date season1_end_date sensitive secondary
-#     needs: [process_dataset_children_and_adolescents_s1_sens_sec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_children_and_adolescents_2016_2017_sensitive_secondary.png
-#         html: output/table1_children_and_adolescents_2016_2017_sensitive_secondary.html
-#         csv: output/table1_children_and_adolescents_2016_2017_sensitive_secondary.csv
-# 
-#   generate_dataset_infants_s1_sens_sec:
-#     run: >
-#       ehrql:v1 generate-dataset analysis/dataset_definition.py
-#       --output output/input_infants_2016_2017_sensitive_secondary.arrow
-#       --dummy-data-file analysis/dummydata/dummyextract_infants_2016_2017.arrow
-#       -- infants season1_start_date season1_end_date sensitive secondary
-#     outputs:
-#       highly_sensitive:
-#         dataset: output/input_infants_2016_2017_sensitive_secondary.arrow
-# 
-#   process_dataset_infants_s1_sens_sec:
-#     run: r:latest analysis/data_processing.R infants season1_start_date season1_end_date sensitive secondary
-#     needs: [generate_dataset_infants_s1_sens_sec]
-#     outputs:
-#       highly_sensitive:
-#         cohort: output/input_processed_infants_2016_2017_sensitive_secondary.arrow
-# 
-#   describe_dataset_infants_s1_sens_sec:
-#     run: r:latest analysis/report.R infants season1_start_date season1_end_date sensitive secondary
-#     needs: [process_dataset_infants_s1_sens_sec]
-#     outputs:
-#       moderately_sensitive:
-#         png: output/descriptive_infants_2016_2017_sensitive_secondary.png
-#         html: output/table1_infants_2016_2017_sensitive_secondary.html
-#         csv: output/table1_infants_2016_2017_sensitive_secondary.csv
-#   
\ No newline at end of file
+        dataset: output/flow_chart/older_adults_2016_2017_flow_chart.csv
+  
+  process_flow_chart_older_adults_s1:
+    run: r:latest analysis/cohort_criteria.R older_adults season1_start_date season1_end_date 
+    needs: [generate_flow_chart_data_older_adults_s1]
+    outputs:
+      highly_sensitive:
+        cohort: output/flow_chart/flow_chart_processed_older_adults_2016_2017.csv
+
+  generate_flow_chart_data_adults_s1:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition_flow_chart.py
+      --output output/flow_chart/adults_2016_2017_flow_chart.csv
+      --dummy-data-file analysis/dummydata/dummyextract_adults_2016_2017.arrow
+      -- adults season1_start_date season1_end_date
+    outputs:
+      highly_sensitive:
+        dataset: output/flow_chart/adults_2016_2017_flow_chart.csv
+
+  process_flow_chart_adults_s1:
+    run: r:latest analysis/cohort_criteria.R adults season1_start_date season1_end_date 
+    needs: [generate_flow_chart_data_adults_s1]
+    outputs:
+      highly_sensitive:
+        cohort: output/flow_chart/flow_chart_processed_adults_2016_2017.csv
+
+  generate_flow_chart_data_children_and_adolescents_s1:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition_flow_chart.py
+      --output output/flow_chart/children_and_adolescents_2016_2017_flow_chart.csv
+      --dummy-data-file analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
+      -- children_and_adolescents season1_start_date season1_end_date
+    outputs:
+      highly_sensitive:
+        dataset: output/flow_chart/children_and_adolescents_2016_2017_flow_chart.csv
+
+  process_flow_chart_children_and_adolescents_s1:
+    run: r:latest analysis/cohort_criteria.R children_and_adolescents season1_start_date season1_end_date 
+    needs: [generate_flow_chart_data_children_and_adolescents_s1]
+    outputs:
+      highly_sensitive:
+        cohort: output/flow_chart/flow_chart_processed_children_and_adolescents_2016_2017.csv
+
+  generate_flow_chart_data_infants_s1:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition_flow_chart.py
+      --output output/flow_chart/infants_2016_2017_flow_chart.csv
+      --dummy-data-file analysis/dummydata/dummyextract_infants_2016_2017.arrow
+      -- infants season1_start_date season1_end_date
+    outputs:
+      highly_sensitive:
+        dataset: output/flow_chart/infants_2016_2017_flow_chart.csv
+
+  process_flow_chart_infants_s1:
+    run: r:latest analysis/cohort_criteria.R infants season1_start_date season1_end_date 
+    needs: [generate_flow_chart_data_infants_s1]
+    outputs:
+      highly_sensitive:
+        cohort: output/flow_chart/flow_chart_processed_infants_2016_2017.csv
+
+## season 1 (2016/17) - cohort description 
+
+  describe_cohort_older_adults_s1:
+    run: r:latest analysis/cohort_description.R older_adults season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_older_adults_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        html: output/table1/table1_older_adults_2016_2017.html
+        csv: output/table1/table1_older_adults_2016_2017.csv
+
+  describe_cohort_adults_s1:
+    run: r:latest analysis/cohort_description.R adults season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_adults_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        html: output/table1/table1_adults_2016_2017.html
+        csv: output/table1/table1_adults_2016_2017.csv
+
+  describe_cohort_children_and_adolescents_s1:
+    run: r:latest analysis/cohort_description.R children_and_adolescents season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_children_and_adolescents_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        html: output/table1/table1_children_and_adolescents_2016_2017.html
+        csv: output/table1/table1_children_and_adolescents_2016_2017.csv
+
+  describe_cohort_infants_s1:
+    run: r:latest analysis/cohort_description.R infants season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_infants_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        html: output/table1/table1_infants_2016_2017.html
+        csv: output/table1/table1_infants_2016_2017.csv
+  
+### primary analysis
+
+##  season 1 (2016/17)
+
+  generate_dataset_older_adults_s1_spec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_older_adults_2016_2017_specific_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
+      -- older_adults season1_start_date season1_end_date specific primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_older_adults_2016_2017_specific_primary.arrow
+
+  process_dataset_older_adults_s1_spec:
+    run: r:latest analysis/data_processing.R older_adults season1_start_date season1_end_date specific primary
+    needs: [generate_dataset_older_adults_s1_spec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_older_adults_2016_2017_specific_primary.arrow
+
+  describe_dataset_older_adults_s1_spec:
+    run: r:latest analysis/report.R older_adults season1_start_date season1_end_date specific primary
+    needs: [process_dataset_older_adults_s1_spec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_older_adults_2016_2017_specific_primary.png
+
+  generate_dataset_adults_s1_spec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_adults_2016_2017_specific_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_adults_2016_2017.arrow
+      -- adults season1_start_date season1_end_date specific primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_adults_2016_2017_specific_primary.arrow
+
+  process_dataset_adults_s1_spec:
+    run: r:latest analysis/data_processing.R adults season1_start_date season1_end_date specific primary
+    needs: [generate_dataset_adults_s1_spec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_adults_2016_2017_specific_primary.arrow
+
+  describe_dataset_adults_s1_spec:
+    run: r:latest analysis/report.R adults season1_start_date season1_end_date specific primary
+    needs: [process_dataset_adults_s1_spec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_adults_2016_2017_specific_primary.png
+
+  generate_dataset_children_and_adolescents_s1_spec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_children_and_adolescents_2016_2017_specific_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
+      -- children_and_adolescents season1_start_date season1_end_date specific primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_children_and_adolescents_2016_2017_specific_primary.arrow
+
+  process_dataset_children_and_adolescents_s1_spec:
+    run: r:latest analysis/data_processing.R children_and_adolescents season1_start_date season1_end_date specific primary
+    needs: [generate_dataset_children_and_adolescents_s1_spec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_children_and_adolescents_2016_2017_specific_primary.arrow
+
+  describe_dataset_children_and_adolescents_s1_spec:
+    run: r:latest analysis/report.R children_and_adolescents season1_start_date season1_end_date specific primary
+    needs: [process_dataset_children_and_adolescents_s1_spec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_children_and_adolescents_2016_2017_specific_primary.png
+
+  generate_dataset_infants_s1_spec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_infants_2016_2017_specific_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_infants_2016_2017.arrow
+      -- infants season1_start_date season1_end_date specific primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_infants_2016_2017_specific_primary.arrow
+
+  process_dataset_infants_s1_spec:
+    run: r:latest analysis/data_processing.R infants season1_start_date season1_end_date specific primary
+    needs: [generate_dataset_infants_s1_spec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_infants_2016_2017_specific_primary.arrow
+
+  describe_dataset_infants_s1_spec:
+    run: r:latest analysis/report.R infants season1_start_date season1_end_date specific primary
+    needs: [process_dataset_infants_s1_spec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_infants_2016_2017_specific_primary.png
+
+### sensitivity analysis
+
+##  season 1 (2016/17)
+
+  generate_dataset_older_adults_s1_sens:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_older_adults_2016_2017_sensitive_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
+      -- older_adults season1_start_date season1_end_date sensitive primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_older_adults_2016_2017_sensitive_primary.arrow
+
+  process_dataset_older_adults_s1_sens:
+    run: r:latest analysis/data_processing.R older_adults season1_start_date season1_end_date sensitive primary
+    needs: [generate_dataset_older_adults_s1_sens]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_older_adults_2016_2017_sensitive_primary.arrow
+
+  describe_dataset_older_adults_s1_sens:
+    run: r:latest analysis/report.R older_adults season1_start_date season1_end_date sensitive primary
+    needs: [process_dataset_older_adults_s1_sens]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_older_adults_2016_2017_sensitive_primary.png
+
+  generate_dataset_adults_s1_sens:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_adults_2016_2017_sensitive_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_adults_2016_2017.arrow
+      -- adults season1_start_date season1_end_date sensitive primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_adults_2016_2017_sensitive_primary.arrow
+
+  process_dataset_adults_s1_sens:
+    run: r:latest analysis/data_processing.R adults season1_start_date season1_end_date sensitive primary
+    needs: [generate_dataset_adults_s1_sens]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_adults_2016_2017_sensitive_primary.arrow
+
+  describe_dataset_adults_s1_sens:
+    run: r:latest analysis/report.R adults season1_start_date season1_end_date sensitive primary
+    needs: [process_dataset_adults_s1_sens]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_adults_2016_2017_sensitive_primary.png
+
+  generate_dataset_children_and_adolescents_s1_sens:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_children_and_adolescents_2016_2017_sensitive_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
+      -- children_and_adolescents season1_start_date season1_end_date sensitive primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_children_and_adolescents_2016_2017_sensitive_primary.arrow
+
+  process_dataset_children_and_adolescents_s1_sens:
+    run: r:latest analysis/data_processing.R children_and_adolescents season1_start_date season1_end_date sensitive primary
+    needs: [generate_dataset_children_and_adolescents_s1_sens]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_children_and_adolescents_2016_2017_sensitive_primary.arrow
+
+  describe_dataset_children_and_adolescents_s1_sens:
+    run: r:latest analysis/report.R children_and_adolescents season1_start_date season1_end_date sensitive primary
+    needs: [process_dataset_children_and_adolescents_s1_sens]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_children_and_adolescents_2016_2017_sensitive_primary.png
+
+  generate_dataset_infants_s1_sens:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_infants_2016_2017_sensitive_primary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_infants_2016_2017.arrow
+      -- infants season1_start_date season1_end_date sensitive primary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_infants_2016_2017_sensitive_primary.arrow
+
+  process_dataset_infants_s1_sens:
+    run: r:latest analysis/data_processing.R infants season1_start_date season1_end_date sensitive primary
+    needs: [generate_dataset_infants_s1_sens]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_infants_2016_2017_sensitive_primary.arrow
+
+  describe_dataset_infants_s1_sens:
+    run: r:latest analysis/report.R infants season1_start_date season1_end_date sensitive primary
+    needs: [process_dataset_infants_s1_sens]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_infants_2016_2017_sensitive_primary.png
+
+### secondary analysis
+
+##  season 1 (2016/17)
+
+  generate_dataset_older_adults_s1_sens_sec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_older_adults_2016_2017_sensitive_secondary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_older_adults_2016_2017.arrow
+      -- older_adults season1_start_date season1_end_date sensitive secondary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_older_adults_2016_2017_sensitive_secondary.arrow
+
+  process_dataset_older_adults_s1_sens_sec:
+    run: r:latest analysis/data_processing.R older_adults season1_start_date season1_end_date sensitive secondary
+    needs: [generate_dataset_older_adults_s1_sens_sec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_older_adults_2016_2017_sensitive_secondary.arrow
+
+  describe_dataset_older_adults_s1_sens_sec:
+    run: r:latest analysis/report.R older_adults season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_older_adults_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_older_adults_2016_2017_sensitive_secondary.png
+  
+  generate_dataset_adults_s1_sens_sec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_adults_2016_2017_sensitive_secondary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_adults_2016_2017.arrow
+      -- adults season1_start_date season1_end_date sensitive secondary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_adults_2016_2017_sensitive_secondary.arrow
+
+  process_dataset_adults_s1_sens_sec:
+    run: r:latest analysis/data_processing.R adults season1_start_date season1_end_date sensitive secondary
+    needs: [generate_dataset_adults_s1_sens_sec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_adults_2016_2017_sensitive_secondary.arrow
+
+  describe_dataset_adults_s1_sens_sec:
+    run: r:latest analysis/report.R adults season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_adults_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_adults_2016_2017_sensitive_secondary.png
+  
+  generate_dataset_children_and_adolescents_s1_sens_sec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_children_and_adolescents_2016_2017_sensitive_secondary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_children_and_adolescents_2016_2017.arrow
+      -- children_and_adolescents season1_start_date season1_end_date sensitive secondary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_children_and_adolescents_2016_2017_sensitive_secondary.arrow
+
+  process_dataset_children_and_adolescents_s1_sens_sec:
+    run: r:latest analysis/data_processing.R children_and_adolescents season1_start_date season1_end_date sensitive secondary
+    needs: [generate_dataset_children_and_adolescents_s1_sens_sec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_children_and_adolescents_2016_2017_sensitive_secondary.arrow
+
+  describe_dataset_children_and_adolescents_s1_sens_sec:
+    run: r:latest analysis/report.R children_and_adolescents season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_children_and_adolescents_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_children_and_adolescents_2016_2017_sensitive_secondary.png
+  
+  generate_dataset_infants_s1_sens_sec:
+    run: >
+      ehrql:v1 generate-dataset analysis/dataset_definition.py
+      --output output/data/input_infants_2016_2017_sensitive_secondary.arrow
+      --dummy-data-file analysis/dummydata/dummyextract_infants_2016_2017.arrow
+      -- infants season1_start_date season1_end_date sensitive secondary
+    outputs:
+      highly_sensitive:
+        dataset: output/data/input_infants_2016_2017_sensitive_secondary.arrow
+
+  process_dataset_infants_s1_sens_sec:
+    run: r:latest analysis/data_processing.R infants season1_start_date season1_end_date sensitive secondary
+    needs: [generate_dataset_infants_s1_sens_sec]
+    outputs:
+      highly_sensitive:
+        cohort: output/data/input_processed_infants_2016_2017_sensitive_secondary.arrow
+
+  describe_dataset_infants_s1_sens_sec:
+    run: r:latest analysis/report.R infants season1_start_date season1_end_date sensitive secondary
+    needs: [process_dataset_infants_s1_sens_sec]
+    outputs:
+      moderately_sensitive:
+        png: output/models/descriptive_infants_2016_2017_sensitive_secondary.png
\ No newline at end of file