Merge branch 'main' of https://github.com/sarah-colq/covidcast

Author: sarah-colq

.github/workflows/python_ci.yml

@@ -5,9 +5,9 @@ name: Python Lint and Testing
 
 on:
   push:
-    branches: [ main ]
+    branches: [ main, r-pkg-devel ]
   pull_request:
-    branches: [ main ]
+    branches: [ main, r-pkg-devel ]
 
 jobs:
   build:

.github/workflows/r_ci.yml

@@ -10,9 +10,9 @@ name: R
 
 on:
   push:
-    branches: [ main ]
+    branches: [ main, r-pkg-devel ]
   pull_request:
-    branches: [ main ]
+    branches: [ main, r-pkg-devel ]
 
 jobs:
   build:
@@ -27,7 +27,7 @@ jobs:
     steps:
       - uses: actions/checkout@v2
       - name: Set up R ${{ matrix.r-version }}
-        uses: r-lib/actions/setup-r@ffe45a39586f073cc2e9af79c4ba563b657dc6e3
+        uses: r-lib/actions/setup-r@v1
         with:
           r-version: ${{ matrix.r-version }}
       - name: Install linux dependencies  
@@ -39,7 +39,7 @@ jobs:
         uses: actions/cache@v2
         with:
           path: ${{ env.R_LIBS_USER }}
-          key: ${{ runner.os }}-r-1-
+          key: ${{ runner.os }}-r-2-
       - name: Install dependencies
         run: |
           install.packages(c("remotes", "rcmdcheck"))
@@ -48,4 +48,4 @@ jobs:
       - name: Check
         run: |
           rcmdcheck::rcmdcheck(args = c("--no-manual", "--ignore-vignettes", "--as-cran"), build_args = c("--no-build-vignettes"), error_on = "error")
-        shell: Rscript {0}
+        shell: Rscript {0}

R-notebooks/dashboard_functions.R

@@ -13,12 +13,15 @@ plot_28_day_frequency_state  <- function(df_to_plot) {
 
   covidcast_signal_to_plot = make_covidcast_signal(states_present, df_to_plot, "state")
 
-  plot(covidcast_signal_to_plot,
-       title = sprintf(
-         "State frequency in last 28 days (start date: %s)",
-         covidcast_signal_to_plot$time_value[1]
-       ),
-       range = c(0, 28))
+  plot(
+    covidcast_signal_to_plot,
+    title = sprintf(
+      "State frequency in last 28 days (start date: %s); grey = no data for state.",
+      covidcast_signal_to_plot$time_value[1]
+    ),
+    range = c(1, 28),
+    choro_params = list(legend_digits = 0)
+  )
 }
 
 plot_28_day_frequency_county  <- function(df_to_plot) {
@@ -32,9 +35,10 @@ plot_28_day_frequency_county  <- function(df_to_plot) {
   plot(
     covidcast_signal_to_plot,
     title = sprintf(
-      "County frequency in last 28 days (start date: %s)",
+      "County frequency in last 28 days (start date: %s); grey = no data for county.",
       covidcast_signal_to_plot$time_value[1]
     ),
-    range = c(0, 28)
+    range = c(1, 28),
+    choro_params = list(legend_digits = 0)
   )
 }

R-notebooks/jhu_dashboard.Rmd

@@ -0,0 +1,67 @@
+---
+title: "JHU dashboard"
+author: "Delphi Lab"
+date: "`r format(Sys.time(), '%B %d, %Y')`"
+output:
+  html_document:
+    code_folding: hide
+---
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(message = FALSE, warning = FALSE)
+```
+
+```{r}
+library(covidcast)
+library(dplyr)
+library(ggplot2)
+
+date_scale <-
+  scale_x_date(date_breaks = "1 week", date_labels = "%b %d")
+
+twenty_eight_days_ago = Sys.Date() - 28
+```
+
+
+### Coverage
+
+This measures how much county coverage we have in the samples (i.e., how many unique counties are present each day), and how it has recently changed over time.
+
+```{r, fig.width = 7, fig.height = 5}
+
+# Sampling coverage
+df_jhu_counties = covidcast_signal(
+  "jhu-csse",
+  "confirmed_7dav_cumulative_num",
+  start_day = twenty_eight_days_ago,
+  geo_type = "county"
+)
+counties_per_day = df_jhu_counties %>%
+  group_by(time_value) %>%
+  summarize(n = n())
+
+ggplot(counties_per_day, aes(x = time_value, y = n)) +
+  geom_line() + geom_point() + theme_bw() +
+  labs(
+    x = "Date",
+    y = "Number of Counties",
+    title = sprintf(
+      "Unique Counties: %i, mean per day: %i",
+      length(unique(
+        df_jhu_counties$geo_value
+      )),
+      round(mean(counties_per_day$n))
+    )
+  ) + date_scale
+```
+
+## County Coverage Map
+
+This visualizes the county coverage -- how frequently does each county show up in the data over the last 28 days?
+
+```{r, fig.width = 10, fig.height = 8}
+
+source("dashboard_functions.R")
+plot_28_day_frequency_county(df_jhu_counties)
+
+```

R-notebooks/safegraph_dashboard.Rmd

@@ -0,0 +1,67 @@
+---
+title: "Safegraph dashboard"
+author: "Delphi Lab"
+date: "`r format(Sys.time(), '%B %d, %Y')`"
+output:
+  html_document:
+    code_folding: hide
+---
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(message = FALSE, warning = FALSE)
+```
+
+```{r}
+library(covidcast)
+library(dplyr)
+library(ggplot2)
+
+date_scale <-
+  scale_x_date(date_breaks = "1 week", date_labels = "%b %d")
+
+twenty_eight_days_ago = Sys.Date() - 28
+```
+
+
+### Coverage
+
+This measures how much county coverage we have in the samples (i.e., how many unique counties are present each day), and how it has recently changed over time.
+
+```{r, fig.width = 7, fig.height = 5}
+
+# Sampling coverage
+df_safegraph_counties = covidcast_signal(
+  "safegraph",
+  "median_home_dwell_time",
+  start_day = twenty_eight_days_ago,
+  geo_type = "county"
+)
+counties_per_day = df_safegraph_counties %>%
+  group_by(time_value) %>%
+  summarize(n = n())
+
+ggplot(counties_per_day, aes(x = time_value, y = n)) +
+  geom_line() + geom_point() + theme_bw() +
+  labs(
+    x = "Date",
+    y = "Number of Counties",
+    title = sprintf(
+      "Unique Counties: %i, mean per day: %i",
+      length(unique(
+        df_safegraph_counties$geo_value
+      )),
+      round(mean(counties_per_day$n))
+    )
+  ) + date_scale
+```
+
+## County Coverage Map
+
+This visualizes the county coverage -- how frequently does each county show up in the data over the last 28 days?
+
+```{r, fig.width = 10, fig.height = 8}
+
+source("dashboard_functions.R")
+plot_28_day_frequency_county(df_safegraph_counties)
+
+```

R-notebooks/usa_facts_dashboard.Rmd

@@ -0,0 +1,67 @@
+---
+title: "USA facts dashboard"
+author: "Delphi Lab"
+date: "`r format(Sys.time(), '%B %d, %Y')`"
+output:
+  html_document:
+    code_folding: hide
+---
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(message = FALSE, warning = FALSE)
+```
+
+```{r}
+library(covidcast)
+library(dplyr)
+library(ggplot2)
+
+date_scale <-
+  scale_x_date(date_breaks = "1 week", date_labels = "%b %d")
+
+twenty_eight_days_ago = Sys.Date() - 28
+```
+
+
+### Coverage
+
+This measures how much county coverage we have in the samples (i.e., how many unique counties are present each day), and how it has recently changed over time.
+
+```{r, fig.width = 7, fig.height = 5}
+
+# Sampling coverage
+df_usa_facts_counties = covidcast_signal(
+  "usa-facts",
+  "confirmed_cumulative_num",
+  start_day = twenty_eight_days_ago,
+  geo_type = "county"
+)
+counties_per_day = df_usa_facts_counties %>%
+  group_by(time_value) %>%
+  summarize(n = n())
+
+ggplot(counties_per_day, aes(x = time_value, y = n)) +
+  geom_line() + geom_point() + theme_bw() +
+  labs(
+    x = "Date",
+    y = "Number of Counties",
+    title = sprintf(
+      "Unique Counties: %i, mean per day: %i",
+      length(unique(
+        df_usa_facts_counties$geo_value
+      )),
+      round(mean(counties_per_day$n))
+    )
+  ) + date_scale
+```
+
+## County Coverage Map
+
+This visualizes the county coverage -- how frequently does each county show up in the data over the last 28 days?
+
+```{r, fig.width = 10, fig.height = 8}
+
+source("dashboard_functions.R")
+plot_28_day_frequency_county(df_usa_facts_counties)
+
+```

R-packages/covidcast/tests/testthat/setup-options.R

@@ -0,0 +1,6 @@
+# Many tests use hand-made reference data frames. In R < 4.0, columns like
+# `geo_values` and `data_source`, containing strings, are interpreted as
+# factors. To prevent us from having to set stringsAsFactors = FALSE in every
+# test case, set the option while saving the default to restore in the teardown
+# (in teardown-options.R).
+.defaultStringsAsFactors <- options(stringsAsFactors = FALSE)

R-packages/covidcast/tests/testthat/teardown-options.R

@@ -0,0 +1,2 @@
+# see setup-options.R
+options(stringsAsFactors = .defaultStringsAsFactors)