Homework #2

library(readr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tibble)
jy_csv <- read.csv("C:/Users/Jessica/Desktop/712/health_data.csv")

head(jy_csv)

tail (jy_csv)

glimpse(jy_csv)

## Observations: 5
## Variables: 12
## $ Geo_FIPS    <int> 36001, 36031, 36061, 36063, 36069
## $ Geo_NAME    <fct> Albany County, Essex County, New York County, Niag...
## $ Geo_QNAME   <fct> "Albany County, New York ", "Essex County, New Yor...
## $ Geo_STATE   <int> 36, 36, 36, 36, 36
## $ Geo_COUNTY  <int> 1, 31, 61, 63, 69
## $ SE_T011_001 <dbl> 13.6, 14.3, 13.2, 15.8, 13.9
## $ SE_T011_002 <dbl> 18.7, 18.7, 21.3, 18.5, 19.6
## $ SE_T012_001 <dbl> 4.955115, 1.995570, 0.000000, 5.272294, 2.899159
## $ SE_T012_002 <dbl> 85.59618, 100.00000, 98.43317, 87.75806, 83.03731
## $ SE_T012_003 <dbl> 27.2, 28.5, 14.7, 30.2, 29.5
## $ SE_T012_004 <dbl> 22.0, 27.3, 17.6, 21.8, 17.4
## $ SE_T012_005 <dbl> 30.51945, 33.00669, 60.32939, 35.05148, 25.14412

names(jy_csv)

##  [1] "Geo_FIPS"    "Geo_NAME"    "Geo_QNAME"   "Geo_STATE"   "Geo_COUNTY" 
##  [6] "SE_T011_001" "SE_T011_002" "SE_T012_001" "SE_T012_002" "SE_T012_003"
## [11] "SE_T012_004" "SE_T012_005"

health <- rename(jy_csv,
                 county_name = Geo_NAME,
                current_smokers = SE_T011_001,
                drinking_adult = SE_T011_002,
                limited_access_to_healthyfoods = SE_T012_001,
                access_to_exercise_opportunities = SE_T012_002, 
                obese_person_twenty_andover = SE_T012_003,
                physically_inacive_person_twentyandup = SE_T012_004, 
                children_elligible_for_free_lunch_eighteenorless = SE_T012_005)

health <- select(health, 
                 county_name,
                 current_smokers,
                 drinking_adult,
                limited_access_to_healthyfoods, 
                  access_to_exercise_opportunities,
                  obese_person_twenty_andover,
                  physically_inacive_person_twentyandup,
                  children_elligible_for_free_lunch_eighteenorless)

head(health)

tail (health)

glimpse(health)

## Observations: 5
## Variables: 8
## $ county_name                                      <fct> Albany County...
## $ current_smokers                                  <dbl> 13.6, 14.3, 1...
## $ drinking_adult                                   <dbl> 18.7, 18.7, 2...
## $ limited_access_to_healthyfoods                   <dbl> 4.955115, 1.9...
## $ access_to_exercise_opportunities                 <dbl> 85.59618, 100...
## $ obese_person_twenty_andover                      <dbl> 27.2, 28.5, 1...
## $ physically_inacive_person_twentyandup            <dbl> 22.0, 27.3, 1...
## $ children_elligible_for_free_lunch_eighteenorless <dbl> 30.51945, 33....

names(health)

## [1] "county_name"                                     
## [2] "current_smokers"                                 
## [3] "drinking_adult"                                  
## [4] "limited_access_to_healthyfoods"                  
## [5] "access_to_exercise_opportunities"                
## [6] "obese_person_twenty_andover"                     
## [7] "physically_inacive_person_twentyandup"           
## [8] "children_elligible_for_free_lunch_eighteenorless"

avgsmoke <- summarize(health, smoker = mean(current_smokers))
avgdrinker <- summarize(health,drinker = mean(drinking_adult))

avgsmoke

avgdrinker

Homework #2

Jessica Yin