Run ALGAE

by Kevin Garwood

The code below was actually the high level method that was written to run the early life analysis for the ALSPAC-Imperial study. Remember that all of ALGAE was written using PostgreSQL.

CREATE OR REPLACE FUNCTION run_imperial_early_analysis()
	RETURNS void AS 
$$
DECLARE
	input_data_directory TEXT;
	output_data_directory TEXT;
	results_directory TEXT;
	
BEGIN

	/*
	 * define the output directory where all the result CSV files
	 * will be exported.  Copy the structure of a results directory
	 * from one of the early or later life analyses that appear in the
	 * test test_environment directory of the download bundle
	 */
	output_data_directory :=
		'C:\algae_protocol\production_environment\alspac\early_life\results';

	/*
	 * Part I: Run cohort-specific routines which load data from CSV 
	 * files into a set of original data tables
	 * 
	 * This method extracts data from all sorts of files and 
	 * creates the original_study_member_data, original_exp_data,
	 * original_geocode_data and original_addr_history_data tables.
	 */
	PERFORM alspac_early_load_data();

	/*
	 * Part II: Run generic early life routines
	 */
	 
	/*
	 * setup scripts does things like sets the default for
	 * blank imputed gestation dates
	 */
	PERFORM setup_scripts(null, null, null, null);	
	/*
	 * This method ensures that the original data tables actually
	 * exist.  It also tries to standardise values whose format
	 * may vary from one cohort to another.  For example, the
	 * way yes/no or null field values are represented.  The
	 * results are stored in a staging table for each original
	 * table.  The rest of the protocol runs off the staging
	 * tables.
	 */
	PERFORM comm_preprocess_staging_tables();
	/*
	 * This method mainly tries to validate aspects of the 
	 * staging tables by attempting to add constraints to fields
	 * eg: primary key, not null etc.
	 */
	PERFORM comm_perform_prelim_system_checks();
	
	
	/*
	 * fin_daily_exposures will probably be populated differently
	 * for each of early life and later life exposures.  In the
	 * later life analysis, annual exposure values are exploded into
	 * daily exposure records having the same value.  Once it is
	 * in the fin_daily_exposures table, the rest of the protocol,
	 * apart from the code that corrects life stages for 
	 * premature births, is not aware of whether the analysis is 
	 * covering early or later life.
	 */
	DROP TABLE IF EXISTS fin_daily_exposures;	
	CREATE TABLE fin_daily_exposures AS 	
	SELECT
		*
	FROM
		staging_exp_data;
	ALTER TABLE fin_daily_exposures ADD PRIMARY KEY (geocode, date_of_year);


	/*
	 * This next block of calls contain methods that are all defined
	 * in the code base.  This is the main place where ALGAE does
	 * its work
	 */
	PERFORM early_calc_life_stages();
	PERFORM comm_set_study_member_sensitivity_data();
	PERFORM comm_process_addr_histories();
	PERFORM comm_set_geocode_sensitivity_data();
	PERFORM comm_set_address_history_sensitivity_data();
	PERFORM common_calc_exposures();
	PERFORM early_calc_exposures();
	PERFORM comm_set_exp_sensitivity_data();
	PERFORM comm_set_stage_sensitivity_data();
	PERFORM comm_determine_life_stage_cov();
	PERFORM comm_determine_moves_cov();
	PERFORM early_life_create_result_tables_and_backup();
	PERFORM early_life_create_reports(output_data_directory);

	/*
	 * Afterwards, there may be other tasks you may want to do,
	 * such as associating various covariates with the locations
	 * that study members occupied at various life stages.
	 * or getting health outcome data that may later be linked to
	 * exposure data
	 */
	PERFORM alspac_early_cohort_specific_results(output_data_directory);

END;
$$   LANGUAGE plpgsql;
--SELECT "run_imperial_early_analysis"();