MSNA_2021_Monitoring_report.Rmd

---
title: "Reach OPT MSNA 2021"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = FALSE, cache = FALSE,comment = NA, message = FALSE, warning=FALSE, fig.align = 'center' )
```
```{r, include=FALSE}
library(dplyr)
library(lubridate)
library(readxl)
library(kableExtra)
library(knitr)
library(readr)
library(openxlsx)
library(sf)
library(raster)
library(Hmisc)
source("functions/audit_function_full.R")
source("functions/function_handler.R")

WGS84 <- crs("+init=epsg:4326")
UTM38N <- crs("+init=epsg:32638")

assessment_start_date <- as.Date("2021-05-17")

# set min time and max # interviews per day

time_limit <- 15
flag_time_limit <- 30
max_interv <- 10

# read data from excel file
##df <- read_excel("input/raw_data/Final__V10__REACH_oPt_Kobo_MSNA_May_2021_V8_27052021_-_all_versions_-_False_-_2021-06-07-08-58-28.xlsx", sheet = "MSNA_I_2021")
  
df <- read_excel("input/raw_data/Final__V10__REACH_oPt_Kobo_MSNA_May_2021_V8_27052021_-_all_versions_-_False_-_2021-06-07-08-58-28.xlsx", sheet = "MSNA_I_2021")

  ###########################################################################################################
# time check from audit files
# today
df$today <- as.Date(df$start, "%Y-%m-%d")

df <- time_check_audit(audit_dir_path = "audit/", df,  "_uuid", time_limit = time_limit)


# df <- time_check(df, time_limit)
df <- df %>% 
  mutate(time_validity = case_when(interview_duration < flag_time_limit & 
                                     interview_duration > time_limit ~ "Flagged", TRUE ~ time_validity))

###########################################################################################################

# when survey does not continue to hh member calculation, these surveys are not valid

df <- df %>% 
  mutate(not_eligible = case_when(is.na(hh_size) ~ "yes",
                                      TRUE ~ "no"))

# remove ineligible surveys
df %<>% filter(consent == "yes" & not_eligible == "no")
```
```{r,include=FALSE}
########## SAMPLE FRAMES ########################
# 
westbank_sample <- read_csv("input/sample/Final_sampling_frame_WestBank_95_9_CS 8_B 15.csv")

westbank_sample <- westbank_sample %>% 
                    rename(num_surveys = "Survey")

westbank_sample_summarized <- westbank_sample %>% 
                    group_by(gov_name) %>% 
                    summarise(num_surveys = sum(num_surveys))
                    
                     
                  

gaza_sample <- read_csv("input/sample/Final_sampling_summary_Gaza.csv") 

gaza_sample_summarized <- gaza_sample %>% 
                          rename(num_surveys = "# surveys") %>% 
                          group_by(Stratification) %>% 
                          summarise(num_surveys = sum(num_surveys))
                          

east_Jerusalem_sample <- read_excel("input/sample/Final_sampling_frame_EJ_95_9_CS 5_B 15.xlsx")
ej_summarized_sample <- east_Jerusalem_sample %>% 
                        rename(num_surveys = "Survey") %>% 
                        group_by(Location) %>% 
                        summarise(num_surveys = sum(num_surveys))
  



```

```{r}
##########################################################################################
# Deleted interviews column
df <- df %>% 
  mutate(
    deleted = case_when(
      time_validity == "Deleted" | consent == "no" | not_eligible == "yes" ~ "yes",
      TRUE ~ "no"))

```

```{r}
########################################################################################

### Interview method 

interview_method <- df %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Location = location,
         interview_type = dc_method) %>% 
 group_by(Location, interview_type) %>% tally(name = "Number_of_interviews")
interview_method
interview_method_date <- df %>% 
  dplyr::filter(today > assessment_start_date) %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Location = location,
         interview_type = dc_method) %>% 
   group_by(interview_type, Date) %>% tally(name = "Number_of_interviews")
interview_method_date

library(plotly)
survey_method_graph <- plot_ly(interview_method_date, x = ~Date, y = ~Number_of_interviews, name = 'Number of Interviews Per Day', type = 'scatter', mode = 'lines',
        line = list(color = 'rgb(205, 12, 24)', width = 4)) 
# interview_method Wide format
interview_method_wide <- tidyr::pivot_wider(interview_method, 
                                            names_from = interview_type, 
                                            values_from = Number_of_interviews,
                                            values_fill = list(Number_of_interviews = 0))%>% 
  dplyr::select(Location, `Face to Face` = in_person, Phone = remote )

interview_method_wide
```
```{r}
### Interview method Westbank 


interview_method_wb <- df %>%
  filter(!is.na(hh_location_wb)) %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Governorate = hh_location_wb,
         interview_type = dc_method
  ) %>% 
 group_by(Governorate, interview_type) %>% tally(name = "Number_of_interviews")

interview_method_wb

interview_method_date_wb <- df %>% 
  dplyr::filter(today > assessment_start_date & !is.na(hh_location_wb)) %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Governorate = hh_location_wb,
         interview_type = dc_method) %>% 
   group_by(interview_type, Date) %>% tally(name = "Number_of_interviews")

interview_method_date_wb

library(plotly)
survey_method_graph_wb <- plot_ly(interview_method_date_wb, x = ~Date, y = ~Number_of_interviews, name = 'Number of Interviews West Bank', type = 'scatter', mode = 'lines',
        line = list(color = 'rgb(205, 12, 24)', width = 4)) 
survey_method_graph_wb
# interview_method Wide format

interview_method_wide_wb <- tidyr::pivot_wider(interview_method_wb, 
                                            names_from = interview_type, 
                                            values_from = Number_of_interviews,
                                            values_fill = list(Number_of_interviews = 0))

survey_method_graph_wb
```

```{r}
### Interview method Gaza


interview_method_gaza <- df %>%
  filter(!is.na(hh_location_gaza)) %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Municipality = hh_location_gaza,
         interview_type = dc_method
  ) %>% 
 group_by(Municipality, interview_type) %>% tally(name = "Number_of_interviews")

interview_method_gaza

interview_method_date_gaza <- df %>% 
  dplyr::filter(today > assessment_start_date & !is.na(hh_location_gaza)) %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Municipality = hh_location_gaza,
         interview_type = dc_method) %>% 
   group_by(interview_type, Date) %>% tally(name = "Number_of_interviews")
interview_method_date_gaza

library(plotly)
survey_method_graph_gaza <- plot_ly(interview_method_date_gaza, x = ~Date, y = ~Number_of_interviews, name = 'Number of Interviews Gaza', type = 'scatter', mode = 'lines',
        line = list(color = 'rgb(205, 12, 24)', width = 4)) 
survey_method_graph_gaza 
# interview_method Wide format
interview_method_wide_gaza <- tidyr::pivot_wider(interview_method_gaza, 
                                            names_from = interview_type, 
                                            values_from = Number_of_interviews,
                                            values_fill = list(Number_of_interviews = 0))

interview_method_wide_gaza
```
```{r}
### Interview method East Jerusalem


interview_method_EJ <- df %>%
  filter(location == "ej") %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Location = location,
         interview_type = dc_method
  ) %>% 
 group_by(Location, interview_type) %>% tally(name = "Number_of_interviews")
interview_method_EJ

interview_method_date_EJ <- df %>% 
  dplyr::filter(today > assessment_start_date & location == "ej") %>% 
  dplyr::select(Date = today,
         Enumerator = enumerator_num,
         Location = location,
         interview_type = dc_method) %>% 
   group_by(interview_type, Date) %>% tally(name = "Number_of_interviews")
interview_method_date_EJ

library(plotly)
survey_method_graph_EJ <- plot_ly(interview_method_date_EJ, x = ~Date, y = ~Number_of_interviews, name = 'Number of Interviews EJ', type = 'scatter', mode = 'lines',
        line = list(color = 'rgb(205, 12, 24)', width = 4)) 
survey_method_graph_EJ
# interview_method Wide format
interview_method_wide_EJ <- tidyr::pivot_wider(interview_method_EJ, 
                                            names_from = interview_type, 
                                            values_from = Number_of_interviews,
                                            values_fill = list(Number_of_interviews = 0))
interview_method_wide_EJ

```