In gabrielburcea/cvindia: Analysis of symptoms

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  echo = FALSE,
  warning = FALSE,
  message = FALSE
)

library(magrittr)
library(tidyverse)

data_bar_charts <- read_csv("/Users/gabrielburcea/rprojects/data/your.md/cleaned_data_22092020.csv")

country_levels <- c("United Kingdom" = "Great Britain", 
                    "USA" = "United States of America")

data_bar_charts <- data_bar_charts %>%
  dplyr::mutate(country = forcats::fct_recode(country, !!!country_levels))

# get only covid positive and showing symptoms for the purpose of analysis of symptoms reported by comorbidity
# double check
data_covid_exp <- data_bar_charts %>%
  dplyr::filter(covid_tested != "negative")

count_country <- data_bar_charts %>%
  dplyr::select(id, country) %>%
  dplyr::group_by(country) %>%
  tally()  %>% 
  dplyr::mutate(Percent = n/sum(n)*100) %>%
  dplyr::arrange(desc(n))

count_country

obesity_data <- data_covid_exp %>%
  dplyr::select(id, obesity, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, loss_appetite, chest_pain, itchy_eyes, joint_pain) %>%
  tidyr::drop_na()

obesity_count <- obesity_data %>%
  dplyr::filter(obesity == "Yes") %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(yes_no == "Yes") %>%
  group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Obesity\n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_obesity_sympt <-
  ggplot2::ggplot(obesity_count, ggplot2::aes(x = reorder(symptoms, - Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(obesity_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "Counts of symptoms reported by obesity\nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_obesity_sympt

asthma_data <- data_covid_exp %>%
  dplyr::select(id, asthma, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, loss_appetite, chest_pain, itchy_eyes, joint_pain) %>%
  tidyr::drop_na()

asthma_count <- asthma_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(asthma == "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "Asthma across symptoms\n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_asthma_sympt <-
  ggplot2::ggplot(asthma_count, ggplot2::aes(x = reorder(symptoms, - Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(asthma_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "Counts of symptoms reported by asthma\nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_asthma_sympt

diabetes_type_one_data <- data_covid_exp %>%
  dplyr::select(id, diabetes_type_one, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, loss_appetite, chest_pain, itchy_eyes, joint_pain)

diabetes_count <- diabetes_type_one_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(diabetes_type_one == "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Diabetes type  I\n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_diabetes_sympt <-
  ggplot2::ggplot(diabetes_count, ggplot2::aes(x = reorder(symptoms,- Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(diabetes_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "SARS-Covid-19 Symptoms by Diabetes type one\nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_diabetes_sympt

diabetes_type_two_data <- data_covid_exp %>%
  dplyr::select(id, diabetes_type_two, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, loss_appetite, chest_pain, itchy_eyes, joint_pain)

diabetes_two_count <- diabetes_type_two_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(diabetes_type_two == "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Diabetes type  II\n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_diabetes2_sympt <-
  ggplot2::ggplot(diabetes_two_count, ggplot2::aes(x = reorder(symptoms,- Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(diabetes_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "SARS-Covid-19 Symptoms by Diabetes type II\nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_diabetes2_sympt

heart_data <- data_covid_exp %>%
  dplyr::select(id, heart_disease, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, loss_appetite, chest_pain, itchy_eyes, joint_pain)

heart_count <- heart_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(heart_disease == "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Heart disease \n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_asthma_sympt <-
  ggplot2::ggplot(heart_count, ggplot2::aes(x = reorder(symptoms, - Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(heart_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "Counts of symptoms reported by heart disease\nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_asthma_sympt

hypertension_data <- data_covid_exp %>%
  dplyr::select(id, hypertension, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, loss_appetite, chest_pain, itchy_eyes, joint_pain)

hypertension_count <- hypertension_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(hypertension == "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Hypertension \n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_hypertension_sympt <-
  ggplot2::ggplot(hypertension_count, ggplot2::aes(x = reorder(symptoms, - Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(hypertension_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "Counts of symptoms reported by Hypertension \nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_hypertension_sympt

liver_data <- data_covid_exp %>%
  dplyr::select(id,liver_disease, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, loss_appetite, chest_pain, itchy_eyes, joint_pain)

liver_count <- liver_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(liver_disease == "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Liver disease \n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_liver_sympt <-
  ggplot2::ggplot(liver_count, ggplot2::aes(x = reorder(symptoms, - Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(liver_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "Counts of symptoms reported by liver disease \nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_liver_sympt

````




```r
lung_condition_data <- data_covid_exp %>%
  dplyr::select(id, lung_condition, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature,  joint_pain, chest_pain, itchy_eyes, loss_appetite) %>%
  tidyr::drop_na()

lung_count <- lung_condition_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(lung_condition== "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Lung disease \n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_lung_sympt <-
  ggplot2::ggplot(lung_count, ggplot2::aes(x = reorder(symptoms, - Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(lung_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "Counts of symptoms reported by lung disease \nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_lung_sympt

kidney_data <- data_covid_exp %>%
  dplyr::select(id, kidney_disease, chills, cough, diarrhoea, headache, loss_smell_taste, muscle_ache, 
                nasal_congestion, nausea_vomiting, shortness_breath, sore_throat, sputum, temperature, chest_pain, joint_pain, loss_appetite, itchy_eyes) %>%
  tidyr::drop_na()

kidney_count <- kidney_data %>%
  tidyr::pivot_longer(cols = 3:18, 
                      names_to = "symptoms", 
                      values_to = "yes_no") %>%
  dplyr::filter(kidney_disease == "Yes" & yes_no == "Yes") %>%
  dplyr::group_by(symptoms) %>%
  dplyr::tally() %>%
  dplyr::mutate(Percentage = n/sum(n)) %>%
  dplyr::arrange(desc(n))

start_date = as.Date("2020-04-09", tz = "Europe/London")
end_date = as.Date("2020-08-18")
title_stub <- "SARS-Covid-19 Symptoms by Kidney disease \n"
start_date_title <- format(as.Date(start_date), format = "%d %B %Y")
end_date_title <- format(as.Date(end_date), format = "%d %B %Y")
chart_title <- paste0(title_stub, start_date_title, " to ", end_date_title)

plot_kidney_sympt <-
  ggplot2::ggplot(kidney_count, ggplot2::aes(x = reorder(symptoms, - Percentage), y = n, fill = n)) +
  ggplot2::coord_flip() +
  ggplot2::geom_bar(stat = "identity", position = "dodge") +
  ggplot2::scale_fill_viridis_c(option = "magma", direction = -1) +
  ggplot2::scale_x_discrete(limits = unique(kidney_count$symptoms)) +
  #ggplot2::theme(legend.position = "bottom") +
  #ggplot2::guides(fill = ggplot2::guide_legend(nrow = 3)) +
  ggplot2::theme_minimal() +
  ggplot2::labs( title = chart_title,
                 subtitle = "Counts of symptoms reported by kidney disease\nNotes: i) includes responders with both Covid-19 tested positive and those showing symptoms",
                 y = "Counts",
                 x = "Symptoms",
                 caption = "Source: Dataset - Your.md Dataset") +
  ggplot2::theme(
    axis.title.y = ggplot2::element_text(margin = ggplot2::margin(
      t = 0,
      r = 21,
      b = 0,
      l = 0
    )),
    plot.title = ggplot2::element_text(size = 10, face = "bold"),
    plot.subtitle = ggplot2::element_text(size = 9),
    axis.text.x = ggplot2::element_text(angle = 55, hjust = 1)
  )

plot_kidney_sympt