Closed achafetz closed 5 years ago
R review script
library(tidyverse)
library(ICPIutilities)
library(knitr)
options(dplyr.print_min = Inf)
df_ouim <- read_rds("~/ICPI/Data/MER_Structured_Dataset_OU_IM_FY18-19_20190215_v1_1.rds")
#df_psnuim <- read_rds("~/ICPI/Data/MER_Structured_Dataset_PSNU_IM_FY18-19_20190215_v1_1.rds")
# OU.02 Data Quality Check ------------------------------------------------
#indicators
ind_sel <- c("HTS_TST", "HTS_TST_POS", "KP_PREV","OVC_SERV", "PMTCT_ART", "PMTCT_STAT",
"PrEP_NEW", "TB_ART", "TB_STAT", "TX_CURR", "TX_NEW", "VMMC_CIRC")
#ZMB data
df_zmb <- df_ouim %>%
filter(operatingunit == "Zambia",
indicator %in% ind_sel,
standardizeddisaggregate == "Total Numerator",
fundingagency!= "Dedup") %>%
add_cumulative() %>%
rename_official() %>%
mutate(indicator = factor(indicator, ind_sel))
#1. check all agency distributions for all indicators in tab
df_zmb %>%
group_by(indicator, fundingagency) %>%
summarise_at(vars(fy2019cum), ~ sum(., na.rm = TRUE)) %>%
mutate(share = round(fy2019cum / sum(fy2019cum), 2)*100) %>%
ungroup() %>%
select(-fy2019cum) %>%
spread(fundingagency, share)
#2. check another year for all indicators in tab
df_zmb %>%
group_by(indicator, fundingagency) %>%
summarise_at(vars(fy2018apr), ~ sum(., na.rm = TRUE)) %>%
mutate(share = round(fy2018apr / sum(fy2018apr), 2)*100) %>%
ungroup() %>%
select(-fy2018apr) %>%
spread(fundingagency, share)
#3. check another country for all indicators in tab
df_ouim %>%
filter(operatingunit == "Malawi",
indicator %in% ind_sel,
standardizeddisaggregate == "Total Numerator",
fundingagency!= "Dedup") %>%
add_cumulative() %>%
rename_official() %>%
mutate(indicator = factor(indicator, ind_sel)) %>%
group_by(indicator, fundingagency) %>%
summarise_at(vars(fy2019cum), ~ sum(., na.rm = TRUE)) %>%
mutate(share = round(fy2019cum / sum(fy2019cum), 2)*100) %>%
ungroup() %>%
select(-fy2019cum) %>%
spread(fundingagency, share)
Outstanding issues:
Filters
QC checks