You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

7.0 KiB

---
output: rmarkdown::github_document
---

```{r, echo=FALSE}
knitr::opts_chunk$set(
collapse = TRUE,
warning = FALSE,
message = FALSE,
comment = "#>",
fig.path = "README_files/README-",
fig.retina = 2
)
```
### :mask: cdcfluview - Retrieve U.S. Flu Season Data from the CDC FluView Portal

[![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/cdcfluview)](https://cran.r-project.org/package=cdcfluview)

**NOTE** If there's a particular data set from http://www.cdc.gov/flu/weekly/fluviewinteractive.htm that you want and that isn't in the package, please file it as an issue and be as specific as you can (screen shot if possible).

-----

The U.S. Centers for Disease Control (CDC) maintains a [portal](http://gis.cdc.gov/grasp/fluview/fluportaldashboard.html) for accessing state, regional and national influenza statistics. The portal's Flash interface makes it difficult and time-consuming to select and retrieve influenza data. This package provides functions to access the data provided by the portal's underlying API.

The following functions are implemented:

- `get_flu_data`: Retrieves state, regional or national influenza statistics from the CDC
- `get_state_data`: Retrieves state/territory-level influenza statistics from the CDC
- `get_weekly_flu_report`: Retrieves (high-level) weekly influenza surveillance report from the CDC
- `get_mortality_surveillance_data` : (fairly self explanatory but also pretty new to the pkg and uses data from: http://www.cdc.gov/flu/weekly/nchs.htm

The following data sets are included:

- `hhs_regions` HHS Region Table (a data frame with 59 rows and 4 variables)
- `census_regions` Census Region Table (a data frame with 51 rows and 2 variables)

### News

- See NEWS
- Version 0.4.0 - [CRAN release](http://cran.r-project.org/web/packages/cdcfluview)
- Version 0.4.0.999 released : another fix for the CDC API (for region parameter); added data files for HHS/Census region lookups; added weekly high-level flu report retrieval
- Version 0.3 released : fix for the CDC API (it changed how year & region params are encoded in the request)
- Version 0.2.1 released : bumped up `httr` version # requirement in `DESCRIPTION` (via Issue [1](https://github.com/hrbrmstr/cdcfluview/issues/1))
- Version 0.2 released : added state-level data retrieval
- Version 0.1 released

### Installation

```{r eval=FALSE}
install.packages("cdcfluview")
# **OR**
devtools::install_github("hrbrmstr/cdcfluview")
```

```{r echo=FALSE, message=FALSE, warning=FALSE, error=FALSE}
options(width=120)
```

### Usage

```{r state2015, message=FALSE, warning=FALSE, fig.height=10, fig.width=6}
library(cdcfluview)
library(ggplot2)
library(dplyr)
library(statebins)

# current verison
packageVersion("cdcfluview")

flu <- get_flu_data("hhs", sub_region=1:10, "ilinet", years=2014)
glimpse(flu)

state_flu <- get_state_data(years=2015)
glimpse(state_flu)

gg <- ggplot(flu, aes(x=WEEK, y=`% WEIGHTED ILI`, group=REGION))
gg <- gg + geom_line()
gg <- gg + facet_wrap(~REGION, ncol=2)
gg <- gg + theme_bw()
gg
```

```{r mortality, message=FALSE, warning=FALSE, fig.height=6, fig.width=10}
msd <- get_mortality_surveillance_data()

mutate(msd$by_state, ym=as.Date(sprintf("%04d-%02d-1", Year, Week), "%Y-%U-%u")) %>%
select(state, wk=ym, death_pct=`Percent of Deaths Due to Pneumonia and Influenza`) %>%
mutate(death_pct=death_pct/100) -> df

gg <- ggplot() + geom_smooth(data=df, aes(wk, death_pct, group=state),
se=FALSE, color="#2b2b2b", size=0.25)

gb <- ggplot_build(gg)

gb$data[[1]] %>%
arrange(desc(x)) %>%
group_by(group) %>%
slice(1) %>%
ungroup() %>%
arrange(desc(y)) %>%
head(1) -> top

top_state <- sort(unique(msd$by_state$state))[top$group]

gg <- gg + geom_text(data=top, aes(as.Date(x, origin="1970-01-01"), y, label=top_state),
hjust=1, family="Arial Narrow", size=3, nudge_x=-5, nudge_y=-0.001)
gg <- gg + scale_x_date(expand=c(0,0))
gg <- gg + scale_y_continuous(label=scales::percent)
gg <- gg + labs(x=NULL, y=NULL,
title="Percent of In-State Deaths Due to Pneumonia and Pnfluenza (2010-Present)")
gg <- gg + theme_bw(base_family="Arial Narrow")
gg <- gg + theme(axis.text.x=element_text(margin=margin(0,0,0,0)))
gg <- gg + theme(axis.text.y=element_text(margin=margin(0,0,0,0)))
gg <- gg + theme(axis.ticks=element_blank())
gg <- gg + theme(plot.title=element_text(face="bold", size=16))
gg
```

```{r region, eval=FALSE, include=FALSE, warning=FALSE, error=FALSE, message=FALSE}
dat <- get_flu_data(region="hhs",
sub_region=1:10,
data_source="ilinet",
years=2000:2014)

dat %>%
mutate(REGION=factor(REGION,
levels=unique(REGION),
labels=c("Boston", "New York",
"Philadelphia", "Atlanta",
"Chicago", "Dallas",
"Kansas City", "Denver",
"San Francisco", "Seattle"),
ordered=TRUE)) %>%
mutate(season_week=ifelse(WEEK>=40, WEEK-40, WEEK),
season=ifelse(WEEK<40,
sprintf("%d-%d", YEAR-1, YEAR),
sprintf("%d-%d", YEAR, YEAR+1))) -> dat

prev_years <- dat %>% filter(season != "2014-2015")
curr_year <- dat %>% filter(season == "2014-2015")

curr_week <- tail(dat, 1)$season_week

gg <- ggplot()
gg <- gg + geom_point(data=prev_years,
aes(x=season_week, y=`% WEIGHTED ILI`, group=season),
color="#969696", size=1, alpha=0.25)
gg <- gg + geom_point(data=curr_year,
aes(x=season_week, y=`% WEIGHTED ILI`, group=season),
color="red", size=1.25, alpha=1)
gg <- gg + geom_line(data=curr_year,
aes(x=season_week, y=`% WEIGHTED ILI`, group=season),
size=1.25, color="#d7301f")
gg <- gg + geom_vline(xintercept=curr_week, color="#d7301f", size=0.5, linetype="dashed", alpha=0.5)
gg <- gg + facet_wrap(~REGION, ncol=3)
gg <- gg + labs(x=NULL, y="Weighted ILI Index",
title="ILINet - 1999-2015 year weighted flu index history by CDC region\nWeek Ending Jan 3, 2015 (Red == 2014-2015 season)\n")
gg <- gg + theme_bw()
gg <- gg + theme(panel.grid=element_blank())
gg <- gg + theme(strip.background=element_blank())
gg <- gg + theme(axis.ticks.x=element_blank())
gg <- gg + theme(axis.text.x=element_blank())
```

```{r bins, message=FALSE, fig.height=5, fig.width=7}
gg_s <- state_flu %>%
filter(WEEKEND=="Jan-02-2016") %>%
select(state=STATENAME, value=ACTIVITY.LEVEL) %>%
filter(!(state %in% c("Puerto Rico", "New York City"))) %>% # need to add PR to statebins
mutate(value=as.numeric(gsub("Level ", "", value))) %>%
statebins(brewer_pal="RdPu", breaks=4,
labels=c("Minimal", "Low", "Moderate", "High"),
legend_position="bottom", legend_title="ILI Activity Level") +
ggtitle("CDC State FluView (2015-01-03)")
gg_s
```

### Test Results

```{r message=FALSE}
library(cdcfluview)
library(testthat)

date()

test_dir("tests/")
```