Data608_HW3

library(shiny)
library(dplyr)

## Warning: package 'dplyr' was built under R version 3.4.4

## 
## 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(tidyr)
library(ggplot2)
library(tibble)

file<- "https://raw.githubusercontent.com/VioletaStoyanova/Data608/HW/cleaned-cdc-mortality-1999-2010-2.csv"
download.file(file,destfile = "~/cleaned-cdc-mortality-1999-2010-2.csv")
path<- file.path("cleaned-cdc-mortality-1999-2010-2.csv")
data<- read.csv(file = "https://raw.githubusercontent.com/VioletaStoyanova/Data608/HW/cleaned-cdc-mortality-1999-2010-2.csv", header= TRUE, stringsAsFactors=TRUE, sep = ",")
as_tibble(head(data))

## # A tibble: 6 x 6
##   ICD.Chapter                     State  Year Deaths Population Crude.Rate
## * <fct>                           <fct> <int>  <int>      <int>      <dbl>
## 1 Certain infectious and parasit… AL     1999   1092    4430141       24.6
## 2 Certain infectious and parasit… AL     2000   1188    4447100       26.7
## 3 Certain infectious and parasit… AL     2001   1211    4467634       27.1
## 4 Certain infectious and parasit… AL     2002   1215    4480089       27.1
## 5 Certain infectious and parasit… AL     2003   1350    4503491       30.0
## 6 Certain infectious and parasit… AL     2004   1251    4530729       27.6

round((cor(sapply(data, as.integer), use = "complete.obs")), 3)

##             ICD.Chapter  State   Year Deaths Population Crude.Rate
## ICD.Chapter       1.000  0.000  0.009  0.048      0.024      0.086
## State             0.000  1.000  0.000 -0.026     -0.077      0.010
## Year              0.009  0.000  1.000  0.001      0.027     -0.016
## Deaths            0.048 -0.026  0.001  1.000      0.386      0.626
## Population        0.024 -0.077  0.027  0.386      1.000     -0.032
## Crude.Rate        0.086  0.010 -0.016  0.626     -0.032      1.000

dataQ1 <- data %>%
  filter(Year == 2010) %>%
  group_by(State, ICD.Chapter) %>%
  mutate(Count = sum(Deaths), Crude.Rate = 10^5 * (Count / Population))

## Warning: package 'bindrcpp' was built under R version 3.4.4

head(dataQ1)

## # A tibble: 6 x 7
## # Groups: State, ICD.Chapter [6]
##   ICD.Chapter               State  Year Deaths Population Crude.Rate Count
##   <fct>                     <fct> <int>  <int>      <int>      <dbl> <int>
## 1 Certain infectious and p… AL     2010   1358    4779736       28.4  1358
## 2 Certain infectious and p… AK     2010     88     710231       12.4    88
## 3 Certain infectious and p… AZ     2010   1249    6392017       19.5  1249
## 4 Certain infectious and p… AR     2010    731    2915918       25.1   731
## 5 Certain infectious and p… CA     2010   5090   37253956       13.7  5090
## 6 Certain infectious and p… CO     2010    722    5029196       14.4   722