title: "Homework 2" author: "Christina Ferguson" date: "r Sys.Date ()" output: html_document ---

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

Purpose: The purpose of this script is to practice importing data and manipulate data

Part 1, Question 1: Import data

{r} #Part 1, Question 1: Import data library ("rio") diet <- read.csv("diet_data-2.csv")

Part 1, Question 2: Check dimensions

```{r}

Part 1, Question 2: Check dimensions

datadimensions <- dim(diet) print(datadimensions)

library(dplyr) glimpse(diet) ```

Part 1, Question 3: Create data frame for adults >20 years old

```{r} library(dplyr)

filtered_diet <- diet %>% filter(age >= 20) ```

Part 2, Question 1: Create a new age categorical variable

```{r}

Part2, Question 1: Create a new age categorical variable

library(dplyr)

filtereddiet <- filtereddiet %>% mutate(agecategory = floor(age / 10) * 10) glimpse(filtereddiet) ```

Part 2, Question 2: Create a new binary variable for good or bad dietary quality

```{r}

Part 2 Question 2: Create a new binary variable for good or bad dietary quality

library(dplyr)

filtereddiet <- filtereddiet %>% mutate(dietaryquality = ifelse(hei > 80, "Good", "Bad")) ```

Reviewing

{r} glimpse(filtered_diet)

Part2, Question 3A: Create two level categorical variables for physical activity: Met and Did Not Meet

```{r}

library(dplyr)

filtereddiet <- filtereddiet %>% mutate(physical_activity = ifelse(mvpa >= 150, "Met", "Did Not Meet")) ```

Reviewing

{r} glimpse(filtered_diet)

Part 2, Question 3B: Creating three levels of Physical Activity

```{r} library(dplyr)

filtereddiet <- filtereddiet %>% mutate(threelevelphysicalactivity = casewhen( mvpa > 150 ~ "Sufficient Physical Activity", mvpa > 0 & mvpa <= 150 ~ "Insufficient Physical Activity", mvpa == 0 ~ "No Reported Physical Activity" ))

```

Creating a data frame to only visualize the three levels matches and the two corresponding variables

{r} new_data_frame <- filtered_diet %>% select(mvpa, three_level_physical_activity, physical_activity)

Viewing new data frame

{r} View(new_data_frame)

Part 2, Question 4: Create dummy variables for race

```{r} library(dplyr)

filtereddiet <- filtereddiet %>% mutate( racedummy = casewhen( race == 1 ~ "non-Hispanic White", race == 2 ~ "non-Hispanic Black", race == 3 ~ "Hispanic", race == 4 ~ "Other"
))

```

Part 2, Question 5:Label variables & values using the Diet Data Codebook

{r} install.packages("labelled") library(labelled)

Changing Variables

```{r} library(labelled)

varlabel(filtereddiet) <-list( work = "Employment status", edu = "Education", age = "Age yrs", poverty = "Poverty Status", mvpa = "Physical activity (min/wk)", sleepduration = "Sleep duration (hrs/night)", eatwindow = "Food intake window (hrs)", eatwindow10hr = "10 hr food intake window", hei = "Healthy eating index", gender = "Gender", bmi = "Body Mass Index", race = "Race/ethnicity" ) ```

Changing Values for Edu

```{r} library(labelled)

vallabels(filtereddiet$edu) <- c( "Less than high school" = 1, "High school/GED" = 2, "More than high school" = 3 ) ```

Changing values for Work

```{r} library(labelled)

vallabels(filtereddiet$work) <- c( "not working" = 0, "part-time" = 1, "full-time" = 2 ) ```

Changing values for poverty

```{r} library(labelled)

vallabels(filtereddiet$poverty) <- c( "low-income" = 0, "middle income" = 1, "high income" = 2 ) ```

Changing values for eat window

```{r} library(labelled)

vallabels(filtereddiet$eatwindow10hr) <- c( "No" = 0, "Yes" = 1 ) ```

Changing values for gender

```{r} library(labelled)

vallabels(filtereddiet$eatwindow10hr) <- c( "Men" = 1, "Women" = 2 ) ```