3.2. Script 2: Starting Population¶

This script produces the starting population file of DYNAMIS-POP. The output is a CSV file containing all starting population variables. In addition, this script produces a file containing parameters calculated from the starting population, like the number of records, the total population size (sum of weights), as well as a set of parameters containing default values.

3.2.1. The Starting population Variables:¶

   WEIGHT          person weight                    e.g., 8.275     
   BIRTH           time of birth                    e.g., 1966.532    
   SEX             sex                              0 Female, 1 Male
   POR             district of residence            0 .. n
   EDUC            primary education                0 never entered, 1 dropout, 2 completed
   POB             district of birth                0 .. n, (n for is abroad)
   UNION           time of first union (marriage)   e.g. 1988.234
   PARITY          number of children ever born     0, 1, ..
   LASTBIR         time of last birth               e.g., 2012.34
   ETHNO           ethnicity                        0 .. n

3.2.2. Parameters:¶

File size of starting population
Sample size of starting population (calculated from weights)
Write micro-data output file Y/N (default: FALSE)
File name of starting population
Total population size
Time(s) of micro-data output (default: never)
File name micro-data output (a default name)

####################################################################################################
#
#  DYNAMIS-POP Parameter Generation File 2 - Starting Population
#  This file is generic and works for all country contexts.
#  Input file: globals_for_analysis.RData (To generate such a file run the setup script)
#  Last Update: Martin Spielauer 2018-06-29
#
####################################################################################################

####################################################################################################
# Clear work space, load required packages and the input object file
####################################################################################################

rm(list=ls())

library(haven)
library(dplyr)
library(data.table)
library(sp)
library(maptools)
library(survival)
library(fmsb)
library(eha)

load(file="globals_for_analysis.RData")

####################################################################################################
# Generate variables for the starting population file
####################################################################################################

pmc_weight    <- g_residents_dat$M_WEIGHT
pmc_birth     <- g_census_year - g_residents_dat$M_AGE
pmc_sex       <- g_residents_dat$M_MALE
pmc_province  <- g_residents_dat$M_DOR
pmc_educ      <- g_residents_dat$M_EDUC
pmc_pob       <- g_residents_dat$M_DOB

pmc_union     <- rep(9999,length(pmc_weight))
pmc_union[!is.na(g_residents_dat$M_AGEMAR)]   <- pmc_birth[!is.na(g_residents_dat$M_AGEMAR)] +
                                                 g_residents_dat$M_AGEMAR[!is.na(g_residents_dat$M_AGEMAR)]

pmc_parity    <- rep(0,length(pmc_weight))
pmc_parity[!is.na(g_residents_dat$M_PARITY)]  <- g_residents_dat$M_PARITY[!is.na(g_residents_dat$M_PARITY)]  

pmc_lastbir   <- rep(9999,length(pmc_weight))
pmc_lastbir[!is.na(g_residents_dat$M_AGEBIR)] <- g_residents_dat$M_AGEBIR[!is.na(g_residents_dat$M_AGEBIR)] +
                                                 pmc_birth[!is.na(g_residents_dat$M_AGEBIR)]

pmc_group     <- g_residents_dat$M_ETHNO

####################################################################################################
# Generate and write the starting population file
####################################################################################################

cat("WEIGHT, BIRTH, SEX, DISTRICT, EDUC, DISTBIRTH, UNION, PARITY, LASTBIR, ETHNO\n", file=g_startpop_file)
startpop_file <- cbind(pmc_weight, pmc_birth, pmc_sex, pmc_province, pmc_educ, pmc_pob, pmc_union, pmc_parity, pmc_lastbir, pmc_group)
write.table(startpop_file, file = g_startpop_file,sep=", ",col.names=F, row.names=F , append=TRUE)

####################################################################################################
# Calculate model parameters
####################################################################################################

n_popsize     <- sum(pmc_weight)
n_filesize    <- length(pmc_weight)

####################################################################################################
# Write parameter file for starting population parameters
####################################################################################################

parafile      <- file(g_para_startpop, "w")

cat("parameters\n{\n\n", file=parafile)
cat("  long     MicroDataInputFileSize = { ",n_filesize,"}; //EN File size of starting population\n", file=parafile, append=TRUE)
# removed cat("  logical	UseWeightsInFile = TRUE; //EN Use weights in starting population file\n", file=parafile, append=TRUE)
cat("  double	    StartPopSampleSize = 100000; //EN Sample size of starting population\n", file=parafile, append=TRUE)
# removed cat("  logical	ScalePopulation = TRUE; //EN Scale population\n", file=parafile, append=TRUE)
cat("  logical	WriteMicrodata = FALSE; //EN Write micro-data output file Y/N\n", file=parafile, append=TRUE)
cat("  file	    MicroDataInputFile = \"",g_startpop_name,"\"; //EN File name of starting population\n", sep = "", file=parafile, append=TRUE)
cat("  double	  StartPopSize = {",n_popsize,"}; //EN Total Population Size\n",file=parafile, append=TRUE)
cat("  double	  TimeMicroOutput[OUTPUT_TIMES] = { 9999, 9999, 0, }; //EN Time(s) of micro-data output\n",file=parafile, append=TRUE)
cat("  file	    MicroRecordFileName = \"MicroDataOutput.csv\"; //EN File name micro-data output file\n",file=parafile, append=TRUE)
# removed cat("  logical	SelectedOutput[OUTPUT_VARIABLES] = { FALSE, (10) TRUE, }; //EN Output variable selection \n",file=parafile, append=TRUE)
cat("\n};", file=parafile, append=TRUE)

close(parafile)