#!/bin/env/Rscript args <- commandArgs(TRUE) input_dir <- args[1] input_dir <- paste0(input_dir, "/") ## input_dir <- "/mnt/beegfs1/data/shared_group_data/syneco/spew_1.2.0/americas/south_america/pry" ## input_dir <- "/mnt/beegfs1/data/shared_group_data/syneco/spew_1.2.0/asia/southern_asia/ind" cur_dir <- input_dir library(spew) library(devtools) library(reshape2) data(iso3) country_name <- iso3$country_name[iso3$iso3 == tolower(basename(input_dir))]
r toupper(country_name)
library(devtools) library(data.table) library(maptools) library(ggmap) library(ggplot2) library(RColorBrewer) #setwd(input_dir) # Params output_dir <- input_dir region <- basename(input_dir) varsToSummarize = list(vars_hh = "base", vars_p = "base") sampSize = 10^4 vars_hh <- NULL doPrint <- FALSE ipums_fs <- spew:::summarizeFileStructure(output_dir, doPrint) ipums_list <- spew:::summarize_ipums(output_dir, ipums_fs, doPrint = doPrint, sampSize = sampSize, readFun = data.table::fread) ipums_sum_list <- ipums_list hh_list <- ipums_list$hh_sum_list
There is/are r ipums_fs$nLevels
level(s) of nested ecosystems in r toupper(country_name)
.
There is/are r nrow(ipums_fs$paths_df)
lowest level sub-regions.
The raw counts, microdata, and shapefiles are from IPUMS-I.
data_path <- input_dir plot_name <- paste0("diags_", region, "-tn.png") map_type <- "toner-lite" savePlot <- FALSE g <- spew:::plot_region_diags(ipums_sum_list, ipums_fs, data_path = data_path, map_type = map_type, savePlot = savePlot, plot_name = plot_name)
The above map shows a sub-sample of the different sub regions. Each region has a sample of up to r prettyNum(sampSize, big.mark = ",")
households.
# Households summary hh_list <- ipums_list$hh_sum_list hh_sum_df <- do.call('rbind', lapply(hh_list, "[[", 1)) hh_sum_df$Region <- toupper(hh_sum_df$region_id) df <- hh_sum_df[, c("Region", "nRecords")] tot <- sum(hh_sum_df$nRecords)
Total Synthetic Households: r prettyNum(tot, big.mark = ",")
Below is a bar chart of the number of households in each region.
cbbPalette <- c("#999999", "#E69F00", "#56B4E9", "#009E73", "#F0E442", "#0072B2", "#D55E00", "#CC79A7") cols <- rep(cbbPalette, length.out = nrow(df)) colScale <- scale_fill_manual(values = cols) g <- ggplot(df, aes(x = Region, y = nRecords, fill = Region)) + geom_bar(stat = "identity") + ggtitle("Household Counts") + labs(x = "Region", y = "Number of Households") + colScale + theme_light() + theme(axis.text.x = element_text(angle = 90), legend.position = "none") print(g)
There are r length(ipums_list$header_hh)
columns in the synthetic household ecosystem. They are:
print(ipums_list$header_hh)
# People summary p_list <- ipums_list$p_sum_list p_sum_df <- do.call('rbind', lapply(p_list, "[[", 1)) p_sum_df$Region <- toupper(p_sum_df$region_id) df <- p_sum_df[, c("Region", "nRecords")] tot <- sum(p_sum_df$nRecords)
Total Synthetic Persons: r prettyNum(tot, big.mark = ",")
```r if( as.character(country_name) %in% c("china", "india", "slovenia", "nigeria"){ print("This population currently does not have summary statistics.") } else{ p_mf <- lapply(p_list, "[[", 2) regions <- df$Region df2<- do.call('cbind', lapply(p_mf, "[[", 1)) df_sf <- data.frame(t(df2)) df_sf <- df_sf / rowSums(df_sf) colnames(df_sf) <- c("Male", "Female") df_sf$Region <- regions cols <- c("darkblue", "lightpink") colScale <- scale_fill_manual(values = cols) df_melt <- melt(df_sf, id.vars = "Region", varnames = c("Male", "Female")) colnames(df_melt)[2:3] <- c("Sex", "Percentage") p <- ggplot(data=df_melt, aes(x=Region, y=Percentage, fill=Sex)) + geom_bar(stat="identity") + coord_flip() + ggtitle("Ratio of Males to Females") + colScale + theme_light() print(p) }
### Column Names There are `r length(ipums_list$header_p)` columns in the synthetic household ecosystem. They are: ```r print(ipums_list$header_p)
This report was generated on r Sys.time()
by spew
, an R
package used to generate populations throughout the world. Please see our spew Github repo and our previously generated regions at epimodels.org. We are a part of the Informatics Services Group MIDAS branch at Carnegie Mellon University and University of Pittsburgh and are supported by 1 U24 GM110707-01 NIH/NIGMS grant. Please send any comments to sventura@stat.cmu.edu.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.