EXTRA_CA_BMIxSmoking2023_05_01.Rmd

---
title: "Extra_CA_BMIxSmoking"
author: "Calvin, Daniel and Eryk"
date: "30/03/2023"
output:
  html_document:
    df_print: paged
---
```{r}
getwd()
setwd("F:/Data Analytics CA/DATACA_LATEST/DATACA_LATEST")
getwd()
list.files()
```

# BMIxSmoking
```{r BMIxSmoking}
library(NHANES)
library(dplyr)
library(ggplot2)

smoking <- read_xpt("SMQ_J.XPT")
bmi <- read_xpt("BMX_J.XPT")
demo <- read_xpt("Demographics.XPT")

smoking_clean <- smoking %>%
  select(SEQN, SMQ040, SMD030) %>%
  filter(!is.na(SMQ040), !is.na(SMD030))

demo_clean <- demo %>%
  select(SEQN, RIAGENDR) %>%
  filter(!is.na(RIAGENDR))

bmi_clean <- bmi %>%
  select(SEQN, BMXBMI) %>%
  filter(!is.na(BMXBMI))

data <- left_join(smoking_clean, bmi_clean, by = "SEQN") %>%
  left_join(demo_clean, by = "SEQN")



ggplot(data %>% filter(SMD030 >= 10, SMD030 <= 100), aes(x = SMD030, fill = factor(SMQ040))) +
  geom_histogram() +
  scale_fill_discrete(labels = c("Non-smoker", "Everyday smoker", "Some day's smoker")) +
  labs(x = "Age started smoking", y = "Count", fill = "Smoking status") +
  facet_wrap(~factor(RIAGENDR), nrow = 1) +
  ggtitle("Distribution of Age Started Smoking by Gender")


ggplot(data %>% filter(SMD030 >= 10, SMD030 <= 100), aes(x = SMD030, y = BMXBMI, color = factor(SMQ040))) +
  geom_point() +
  labs(x = "Age started smoking", y = "BMI", color = "Smoking status") +
  facet_wrap(~factor(RIAGENDR), nrow = 1) +
  scale_color_manual(values = c("1" = "green", "2" = "red", "3" = "blue"), 
                     labels = c("Current smoker", "Former smoker", "Never smoked"))


```