Manjari coverage task

.gitignore

@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata

Manjari SHANKAR_Coverage Task.Rmd

@@ -0,0 +1,110 @@
+---
+title: "Coverage_Task"
+author: "Manjari Shankar"
+date: "2023-10-04"
+output: 
+  prettydoc::html_pretty:
+    theme: cayman
+    highlight: github
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## Load packages
+
+```{r message=FALSE, warning=FALSE, include=FALSE}
+pacman::p_load(
+  here,       # relative file pathways  
+  janitor,    # data cleaning and tables
+  lubridate,  # working with dates
+  tidyverse,  # data management and visualization
+  readxl,     # read Excel files
+  stringr,    # working with strings
+  plotly,     # interactive graphs
+  ggplot2,    # plotting and visualizing the data  
+  gganimate,  # animate ggplot
+  scales,     # formatting as percentages
+  flextable   # tabular presentation
+)
+```
+
+## Import datasets
+
+```{r include=FALSE}
+green_blue_fever_raw <- read_xlsx("data_20240120.xlsx", sheet = "Data1", skip = 2)
+pink_fever_raw <- read_xlsx("pink_fever_monthly.xlsx")
+```
+
+## Review & Data cleaning
+
+```{r include=FALSE}
+skimr::skim(pink_fever_raw) # checking variable summaries and types
+skimr::skim(green_blue_fever_raw)
+
+green_blue_fever <- green_blue_fever_raw %>% 
+  janitor:: clean_names() %>% # dataset had names with spaces
+  mutate(bluefever_coverage = bf_coverage * 100, 
+         date = as.Date(date)) %>% # date originally a character variable
+  rename(greenfever_coverage = gf_coverage) %>%
+  select(date, bluefever_coverage, greenfever_coverage)
+
+
+pink_fever <- pink_fever_raw %>%
+  rename(pinkfever_coverage = coverage) %>% # aligning coverage column naming with other dataset
+  mutate(date = make_date(year = year, month = month, day = day)) %>% # adding in date column to align datasets
+  select(date, pinkfever_coverage)
+
+```
+
+## Combining datasets
+
+```{r message=FALSE, warning=FALSE, include=FALSE}
+combined_coverage <- full_join(green_blue_fever, pink_fever, by = c("date" = "date"))
+
+combined_coverage2 <- combined_coverage %>%
+  pivot_longer(
+    cols = -date,
+    names_to = "vaccine",
+    values_to = "vaccination_coverage"
+  ) %>%
+  drop_na()
+```
+
+## Summary by Vaccine
+
+```{r echo=FALSE}
+combined_overview <- combined_coverage2 %>%
+  group_by(vaccine) %>%
+  summarise(Vax_Introduced = first(date), Vax_Last = last(date), pct_change = percent((last(vaccination_coverage)- first(vaccination_coverage))/first(vaccination_coverage)))
+
+qflextable(combined_overview) %>% 
+  theme_booktabs() # shows first and last date of administration and % change since introduction
+```
+
+## Plotting the data
+
+```{r echo=FALSE, message=FALSE, warning=FALSE}
+
+coverage_plot <- combined_coverage2 %>%
+  ggplot() +
+ aes(x = date, y = vaccination_coverage, colour = vaccine) +
+ geom_line(size = 0.8) +
+  scale_x_date(date_breaks = "2 year", date_labels = "%b-%Y", limit=c(as.Date("2000-04-01"),as.Date("2022-12-09"))) +
+ scale_color_hue(direction = 1) +
+ labs(x = "Year", y = "Vaccination Coverage (%)", title = "Vaccination Coverage by Disease", 
+ subtitle = "(Apr-2000:Dec-2022)", color = "Disease") +
+ theme_grey() +
+ theme(plot.title = element_text(face = "bold", 
+ hjust = 0.5), plot.subtitle = element_text(hjust = 0.5),
+ axis.text.x=element_text(angle=90, hjust=0.5)) +
+ ylim(0, 100)
+
+coverage_plot
+```
+
+```{r echo=FALSE, message=FALSE, warning=FALSE}
+coverage_plot +
+  transition_reveal(date) # attempt at animated ggplot
+```

manjari_coverage_task.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX