Ciitizen_height_data.Rmd

---
title: "Ciitizen height parameters"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r load libraries}
library(tidyverse)
library(readxl)
library(dplyr)
library(ggplot2)

```

```{r load your data}
#setwd where your file is located

setwd('/Users/tanyabrown/Documents/Ciitizen data')

#read in your files
growth_data <- read_excel('Ciitizen_SLC13A5_1.1_4_26_2021.xlsx',
                          "growth_parameters",
                           col_names = T)
#read in your file
ht_036 <- read_excel('lenageinf.xlsx',
                          "lenageinf",
                           col_names = T)

ht_20 <- read_excel('statage.xls',
                    'statage',
                    col_names = T)

#View the data
#View(growth_data)

```
## R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.

When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:



```{r female height with cdc}
fheight_cdcfxn <- function(measurement)
  {fht_36mo <- filter(ht_036, Sex == 2)
    ht_data <- filter(growth_data, grepl('body_height', growth_parameter)) #sort for measurement
    f_ht_data <- filter(ht_data, grepl('female', sex)) #chooses "female"
    f_ht_data <- arrange(f_ht_data, patient_uuid, growth_parameter_date) #arrange by patient
    f_ht_cm <- f_ht_data %>% 
      select(patient_uuid, growth_parameter, growth_parameter_value, growth_parameter_date, growth_parameter_unit, Agemos) %>% 
    mutate(cm_ht = ifelse(growth_parameter_unit =="m", growth_parameter_value*100,growth_parameter_value)) #convert m to cm
plot1 <- ggplot(fht_36mo, aes(Agemos))+ #takes the CDC data
  geom_smooth(aes(y=P50),
              size = 0.5, 
              se=F, 
              color = 'gray')+
 # geom_dl(aes(label = fht_36mo), method = list ("last.points"), position = identity)+
  geom_smooth(aes(y=P95),
                size  = 0.5,
                se=F,
              color = 'gray')+
  geom_smooth(aes(y=P5),
                size = 0.5,
                se=F,
              color = 'gray')  + 
      geom_point(data = f_ht_cm, aes(Agemos, cm_ht, color = patient_uuid),
                size = 2) +
 scale_colour_discrete(labels = c("Female 1", "Female 2", "Female 3", "Female 4", "Female 5", "Female 6", "Female 7", "Female 8"))+
   labs(title = 'Height', 
        subtitle = 'Female, 0-36 months',
               x = "Age (months)", 
               y = "Height (cm)")+
    theme_bw()+
    theme(legend.title = element_blank())+
      theme(plot.title = element_text(hjust = 0.5),
            plot.subtitle = element_text(hjust = 0.5),
            text = element_text(size = 20))+
      xlim(0,36)+
  ylim(50,100)
 return(plot1)
}

#ggsave("/Users/tanyabrown/Documents/Ciitizen data/Dotplots/DATE.pdf", width = 8, height = 6)


```

```{r male height 0-36 with cdc}

mheight_cdcfxn <- function(measurement)
  {mht_36mo <- filter(ht_036, Sex == 1) #chooses sex in CDC data
    ht_data <- filter(growth_data, grepl('body_height', growth_parameter)) #sort for measurement in Ciitizen data
    m_ht_data <- filter(ht_data, !grepl('female', sex)) #chooses "male"
    m_ht_data <- arrange(m_ht_data, patient_uuid, growth_parameter_date) #arrange by patient
    m_ht_cm <- m_ht_data %>% 
      select(patient_uuid, growth_parameter, growth_parameter_value, growth_parameter_date, growth_parameter_unit, Agemos) %>% 
    mutate(cm_ht = ifelse(growth_parameter_unit =="m", growth_parameter_value*100,growth_parameter_value)) #convert m to cm
plot1 <- ggplot(mht_36mo, aes(Agemos))+ #takes the CDC data
  geom_smooth(aes(y=P50),
              size = 0.5, 
              se=F, 
              color = 'gray')+
  geom_smooth(aes(y=P95),
                size  = 0.5,
                se=F,
              color = 'gray')+
  geom_smooth(aes(y=P5),
                size = 0.5,
              se=F,
              color = 'gray')  + 
#    geom_smooth(data = m_ht_cm, aes(Agemos, cm_ht),
#                size = 2,
#                se=F,
#                color = '#F8766D')+
        geom_point(data = m_ht_cm, aes(Agemos, cm_ht, color = patient_uuid),
                size = 2,
                se=F) +
  scale_colour_discrete(labels = c("Male 1", "Male 2", "Male 3", "Male 4", "Male 5", "Male 6", "Male 7"))+
  theme_bw()+
  theme(legend.title = element_blank())+
  labs(title = 'Height',
       subtitle = 'Male, 0-36 months',
               x = "Age (months)", 
               y = "Height (cm)")+
      theme(plot.title = element_text(hjust = 0.5),
            plot.subtitle = element_text(hjust = 0.5),
            text = element_text(size = 20))+
      xlim(0,36)+
  scale_y_continuous(limits = c(45, 105), breaks = c(50, 60, 70, 80, 90, 100))
#ylim(45, 105)
 return(plot1)
}

#ggsave("/Users/tanyabrown/Documents/Ciitizen data/Dotplots/NAME.pdf", width = 8, height = 6)

```

```{r male height 2-20 with cdc}

mht_yrfxn <- function(measurement)
  {mht_20 <- filter(ht_20, Sex == 1) #chooses sex in CDC data
    ht_data <- filter(growth_data, grepl('body_height', growth_parameter)) #sort for measurement in Ciitizen data
    m_ht_data <- filter(ht_data, !grepl('female', sex)) #chooses "male"
    m_ht_data <- arrange(m_ht_data, patient_uuid, growth_parameter_date) #arrange by patient
    m_ht_cm <- m_ht_data %>% 
      select(patient_uuid, growth_parameter, growth_parameter_value, growth_parameter_date, growth_parameter_unit, Ageyr) %>% 
    mutate(cm_ht = ifelse(growth_parameter_unit =="m", growth_parameter_value*100,growth_parameter_value)) #convert m to cm
plot1 <- ggplot(mht_20, aes(Ageyr))+ #takes the CDC data
  geom_smooth(aes(y=P50),
              size = 0.5, 
              se=F, 
              color = 'gray')+
  geom_smooth(aes(y=P95),
                size  = 0.5,
                se=F,
              color = 'gray')+
  geom_smooth(aes(y=P5),
                size =0.5,
              se=F,
              color = 'gray')  + 
     geom_point(data = m_ht_cm, aes(Ageyr, cm_ht, color = patient_uuid),
                size = 2)+
 scale_colour_discrete(labels = c("Male 1", "Male 2", "Male 3", "Male 4", "Male 5", "Male 6", "Male 7"))+
   labs(title = 'Height', 
        subtitle = 'Male, 2-20 years',
               x = "Age (years)", 
               y = "Height (cm)")+
  ylim(85, 190)+
  theme_bw()+
  theme(legend.title = element_blank())+
      theme(plot.title = element_text(hjust = 0.5),
            plot.subtitle = element_text(hjust = 0.5),
            text = element_text(size = 20))+
      xlim(2,20)
 return(plot1)
}

#ggsave("/Users/tanyabrown/Documents/Ciitizen data/", width = 8, height = 6)
```

```{r female height 2-20 with cdc}

fht_yrfxn <- function(measurement)
  {fht_20 <- filter(ht_20, Sex == 2) #chooses sex in CDC data
    ht_data <- filter(growth_data, grepl('body_height', growth_parameter)) #sort for measurement in Ciitizen data
    f_ht_data <- filter(ht_data, grepl('female', sex)) #chooses "male"
    f_ht_data <- arrange(f_ht_data, patient_uuid, growth_parameter_date) #arrange by patient
    f_ht_cm <- f_ht_data %>% 
      select(patient_uuid, growth_parameter, growth_parameter_value, growth_parameter_date, growth_parameter_unit, Ageyr) %>% 
    mutate(cm_ht = ifelse(growth_parameter_unit =="m", growth_parameter_value*100,growth_parameter_value)) #convert m to cm
plot1 <- ggplot(fht_20, aes(Ageyr))+ #takes the CDC data
  geom_smooth(aes(y=P50),
              size = 0.5, 
              se=F, 
              color = 'gray')+
  geom_smooth(aes(y=P95),
                size  = 0.5,
                se=F,
              color = 'gray')+
  geom_smooth(aes(y=P5),
                size = 0.5,
              se=F,
              color = 'gray')  + 
    geom_point(data = f_ht_cm, aes(Ageyr, cm_ht, color = patient_uuid),
                size = 2)+
                #se=F,
                #color = '#00BFC4')+
   scale_colour_discrete(labels = c("Female 1", "Female 2", "Female 3", "Female 4", "Female 5", "Female 6", "Female 7", "Female 8"))+
 #ylim(80,180)+ 
  scale_y_continuous(limits = c(80,180, 10))+
   xlim(2,20)+
  ylim(80, 175)+
   labs(title = 'Height', 
        subtitle = 'Female, 2-20 years',
               x = "Age (years)", 
               y = "Height (cm)")+
  theme_bw()+
  theme(legend.title = element_blank())+
      theme(plot.title = element_text(hjust = 0.5),
            plot.subtitle = element_text(hjust = 0.5),
            text = element_text(size = 20))
 return(plot1)
}

#ggsave("/Users/tanyabrown/Documents/Ciitizen data/Dotplots/NAME.png", width = 8, height = 6)

```