In Thaliehln/timci: Data management and visualisation for the TIMCI project

write("Export SPA healthcare provider interview data and run corresponding quality checks", stderr())

spa_hcpi_data <- process_spa_hcpi_data(spa_hcpi_data)
n_raw_spa_hcpi_data <- nrow(spa_hcpi_data)
db_name <- "SPA healthcare provider interview"

There are r n_raw_spa_hcpi_data records in the raw r db_name database.

Non-valid participant IDs [compliance check `r qc_spa_hcpi_nonvalid_ids`]\n\n

qc_description <- "Healthcare providers who are interviewed as part of the SPA should have been observed during their consultation. If there is no observation recorded for a provider, their ID is considered as non-valid."
qc_rule <- "Keep only records for which the healthcare provider ID (X-Fxxxx-Hxx) has been found in the locked SPA sick child observation database."
qc_type <- "nonvalid_ids"
df <- spa_hcpi_data
idcol1 <- "hcp_id"
refdf <- locked_spa_sco_data
idcol2 <- "hcp_identification-hcpid"
qc_text <- "healthcare provider ID not valid"
qc_idx <- qc_spa_hcpi_nonvalid_ids
qc_export_label <- "nonvalid_hcpid"
qc_export_description <- "non-valid participant ID"
cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

locked_spa_hcpi_data <- cleaned_df

Duplicate management [compliance check `r qc_spa_hcpi_duplicates`]\n\n

qc_description <- "Keep duplicated records and investigate the reason for duplicates."
qc_rule <- action_alert_no_modification
qc_type <- "duplicates"
df <- locked_spa_hcpi_data
col_id <- "hcp_id"
col_date <- "interview_start"
cleaning <- "none"
qc_text <- "duplicated IDs"
qc_idx <- qc_spa_hcpi_duplicates
qc_export_label <- "duplicated_spa_hcpi"
qc_export_description <- "SPA healthcare provider interviews are duplicated"
cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

n_locked_spa_hcpi_data <- nrow(locked_spa_hcpi_data)

Data cleaning summary\n\n

There are r n_locked_spa_hcpi_data records in the locked r db_name database.

Data export\n\n

timci::dataset_export(spa_hcpi_data,
                      "12",
                      "timci_spa_provider_interview_data",
                      params$spa_dir,
                      "Raw SPA healthcare provider interview data")

timci::dataset_export(locked_spa_hcpi_data,
                      "12",
                      "timci_spa_provider_interview_data",
                      locked_db_dir,
                      "Cleaned SPA healthcare provider interview data")