# OBJECTIVE 3 AND 4 BASELINE SURVEY IN FIJI - 20 JUNE 2019 to ??
library (tidyverse)
library (lubridate)
library (stringr)
rm(list = ls())
#setwd("S:/R-MNHS-SPHPM-EPM-IDEpi/RISE/4. Surveys/3. Objectives/1. FJ/3/20190624_baseline/3. Data/1. raw data")
setwd("Z:/Data Files/Data Files Objective 3")
# DEFINE TODAY FOR DAILY QC - this is the date of data collection
date <- "2019-08-06"
day.qc <- ymd (date)
rm(date)
# HOUSE SURVEY
house <- read_csv (file="RISE_baseline_house_FJ_v1.csv")
# house.water <- read_csv(file="RISE_baseline_house_FJ_v1-house_survey-water_use-water_repeat.csv")
# HOUSEHOLD SURVEY
hhd <- read_csv (file = "RISE_baseline_hhd_FJ_v1.csv")
hhd.child <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-child_loop.csv")
# hhd.activity <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-demographics-activity.csv")
# hhd.daycare <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-demographics-daycare.csv")
# hhd.ethnicity <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-demographics-ethnicity_screen-ethnicity_repeat.csv")
# hhd.marital <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-demographics-marital_status1.csv")
# hhd.read <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-demographics-read.csv")
# hhd.religion <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-demographics-religion_screen-religion_repeat.csv")
# hhd.school <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-demographics-school.csv")
hhd.person <- read_csv (file = "RISE_baseline_hhd_FJ_v1-hhd_survey-person_details1.csv")
write_csv(hhd.child, path = "Z:/Data Files/Data Files Objective 3/Summary/hhd.child.csv")
# CONSENT SURVEY - do not include in daily QC
#consent <- read_csv (file = "consent_ID_final.csv")
consent <- read_csv (file = "consent_FJ_v1.csv")
# consent.form3 <- read_csv (file = "consent_ID_final-consent_form3.csv")
# consent.childname <- read_csv (file = "consent_ID_final-consent3_childname.csv")
#############################################
#############################################
## Correct known errors in the data ##
#############################################
# setwd("S:/R-MNHS-SPHPM-EPM-IDEpi/RISE/4. Surveys/3. Objectives/1. FJ/3/20190624_baseline/3. Data/2. code")
setwd("Z:/R Script/R Script Obj 3")
source("O3_T0_FJ-consent_corrections.R")
setwd("Z:/Data Files/Data Files Objective 3/Summary")
# setwd("S:/R-MNHS-SPHPM-EPM-IDEpi/RISE/4. Surveys/3. Objectives/1. FJ/3/20190624_baseline/3. Data")
setwd("Z:/R Script/R Script Obj 3")
source("O3_T0_FJ-corrections.R")
setwd("Z:/Data Files/Data Files Objective 3/Summary")
##########
### DELETION OF FULL SURVEYS - BEST DONE AFTER MERGE
##########
#KINOYA house # 22 repetition house already done on the 20th form for house and household to be removed.
hhd <- hhd %>%
filter (!(settlement_barcode == "Kinoya" & extract_house_no == 22 & today == "2019-06-24"))
house <- house %>%
filter (!(settlement_barcode == "Kinoya" & extract_house_no == 22 & today == "2019-06-24"))
######
#KINOYA house # 67 repetition house incomplete on 24 redone and completed on 26th. Survey for house and household removed from the 24th.
hhd <- hhd %>%
filter (!(settlement_barcode == "Kinoya" & extract_house_no == 67 & today == "2019-06-24"))
house <- house %>%
filter (!(settlement_barcode == "Kinoya" & extract_house_no == 67 & today == "2019-06-24"))
######
#MUANIVATU house # 55 incorrect house number redone correct house # 89 consent done on 02/07/2019. Survey for house and household removed from the 01/07/2019.
hhd <- hhd %>%
filter (!(settlement_barcode == "Muanivatu" & extract_house_no == 55 & today == "2019-07-01"))
house <- house %>%
filter (!(settlement_barcode == "Muanivatu" & extract_house_no == 55 & today == "2019-07-01"))
######
#MATATA house # 40 incorrect house number redone correct house # 46 consent done on 04/07/2019. Survey for house removed from the 04/07/2019.
hhd <- hhd %>%
filter (!(settlement_barcode == "Matata" & extract_house_no == 40 & today == "2019-07-04"))
house <- house %>%
filter (!(settlement_barcode == "Matata" & extract_house_no == 40 & today == "2019-07-04"))
#############################################
#############################################
## Clean variables ##
#############################################
#############################################
# setwd("S:/R-MNHS-SPHPM-EPM-IDEpi/Current/RISE/4. Surveys/2.Consent and House ID/2. ID/2. Data/2. code")
# source("consentfj-clean.R")
# setwd("S:/R-MNHS-SPHPM-EPM-IDEpi/Current/RISE/4. Surveys/2.Consent and House ID/2. ID/2. Data")
# need to fix dates to allow for return visits with survey left open (can't use "today")
fix_date <- function(x_date){
x_date <- ifelse(!is.na(ymd_hms(x_date)), ymd_hms(x_date),
ifelse(!is.na(dmy_hms(x_date)), dmy_hms(x_date), mdy_hms(x_date))) # Check the format and return the correct integer-date
x_date <- as.POSIXct(x_date, origin = "1970-01-01", tz = "UTC") # Convert the integer-date to a consistent format
}
house$time <- date(fix_date(house$time9))
hhd$time <- date(fix_date(hhd$time9))
#############################################
#############################################
# SUBSET - ONLY DATA COLLECTED TODAY
#############################################
#############################################
subhouse <- subset (house, today == day.qc,
select = c (extract_settlement, settlement_barcode,
extract_house_no, survey_status))
subhhd <- subset (hhd, today == day.qc,
select = c (extract_settlement, settlement_barcode,extract_house_no,
survey_status))
#############################################
#############################################
# DAILY QC REPORT
#############################################
#############################################
#############################################
####### what settlements were visited ************
# need to merge settlements from both house and household surveys because there
# might not always be a house survey
settlement_house <- subhouse %>%
select (settlement_barcode)
settlement_hhd <- subhhd %>%
select (settlement_barcode)
# append
settlement_group <- rbind(settlement_house, settlement_hhd)
# then group
settlement <- settlement_group %>%
arrange (settlement_barcode) %>%
group_by (settlement_barcode) %>%
summarize (count = n ())
settlement.list <- pull (settlement, var = settlement_barcode)
#############################################
# HOUSE SURVEYS
#number started
nrow(subhouse)
#number completed
house.complete <- subhouse %>%
filter (survey_status == 1)
house.incomplete <- subhouse %>%
filter (is.na(survey_status))
#############################################
# HOUSEHOLD SURVEYS
#number started
nrow(subhhd)
#number completed
hhd.complete <- subhhd %>%
filter (survey_status == 1)
#############################################
# HOUSE SURVEYS WITH NO HOUSEHOLD SURVEY?
#SURVEY DURATION
time_hhd <- hhd %>%
select (extract_settlement, settlement_barcode, extract_house_no, house_status, time, duration, time1, duration1, time14, duration14,
survey_status, house_status, gift_yn) %>%
mutate (duration_min = duration/60) %>%
filter (time == day.qc)
time_hhd_avg <- mean(time_hhd$duration_min)
time_hhd_min <- min(time_hhd$duration_min)
time_hhd_max <- max(time_hhd$duration_min)
summary(time_hhd$duration_min)
time_house <- house %>%
select(extract_settlement, settlement_barcode, extract_house_no, house_status, survey_continue_yes, survey_status,
time, duration, time1, duration1, time10, duration10, roofing) %>%
mutate (duration_min = duration/60) %>%
filter (time == day.qc)
time_house_avg <- mean(time_house$duration_min)
time_house_min <- min(time_house$duration_min)
time_house_max <- max(time_house$duration_min)
summary(time_house$duration_min)
#NUMBER OF SURVEYS COMPLETED PER CFW
cfw_house <- house %>%
filter (time == day.qc) %>%
select (settlement_barcode, extract_house_no, name_surveyor, duration, house_status, survey_continue_yes, survey_status) %>%
mutate (duration_min = duration/60) %>%
filter (survey_continue_yes == 1)
cfw_house_count <- cfw_house %>%
group_by(name_surveyor) %>%
summarise (house= n())
cfw_house_count_avg <- mean(cfw_house_count$house)
cfw_house_count_min <- min(cfw_house_count$house)
cfw_house_count_max <- max(cfw_house_count$house)
cfw_hhd <- hhd %>%
filter (time == day.qc) %>%
select (settlement_barcode, extract_house_no, name_surveyor, duration, survey_status, house_status, gift_yn) %>%
mutate (duration_min = duration/60) %>%
filter (house_status == 1)
cfw_hhd_count <- cfw_hhd %>%
group_by(name_surveyor) %>%
summarise (hhd = n())
cfw_hhd_count_avg <- mean(cfw_hhd_count$hhd)
cfw_hhd_count_min <- min(cfw_hhd_count$hhd)
cfw_hhd_count_max <- max(cfw_hhd_count$hhd)
#CROSS CHECK WITH FULL LIST OF HHDS
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.