R examples

install.R

+install.packages("knitr")
+
+install.packages("tidyverse")
+
+install.packages("data.table")

notebooks/examples-Rmd/covidtracking-example.Rmd

+---
+title: "covidtracking-example"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+```{r}
+library(jsonlite)
+library(ggplot2)
+options(repr.plot.width=14, repr.plot.height=8)
+library(data.table)
+```
+## Look at the metadata
+
+```{r}
+metadata_df <- fromJSON("../../data/covidtracking/states-metadata.json")
+head(metadata_df)
+```
+
+## Look at the data
+
+```{r}
+data_df <- fromJSON("../../data/covidtracking/states-daily.json")
+head(data_df)
+```
+
+```{r}
+data_df$date <- as.Date(paste(data_df$date), format="%Y%m%d")
+head(data_df)
+```
+
+## Daily counts and totals
+
+```{r}
+# compute daily differences
+data_df <- data.table(data_df)
+tdf <- data.table(data_df)
+setkey(tdf, state, date)
+head(tdf)
+```
+
+```{r}
+tdf[, diff_positive := positive - shift(positive), by = .(state)]
+tdf_state <- tdf[state == "WA"]
+tdf_state
+```
+
+```{r}
+ggplot(data = tdf_state, aes(x = date, y = diff_positive)) +
+  labs(title = "WA", y = "Daily positive") +
+  geom_bar(stat = "identity", position =  position_dodge(width=1))
+```
+
+## Counts per 100k
+
+```{r}
+data_df <- as.data.table(data_df)
+pop_df <- fread("../../data/geodata/us_pop_fung_2019.csv")
+setkey(pop_df, ST)
+head(pop_df)
+```
+
+```{r}
+most_recent_test_date <- max(data_df$date)
+most_recent_df <- data_df[date == most_recent_test_date]
+paste("Most recent test date", most_recent_test_date)
+paste(nrow(most_recent_df), "states/territories have data on this date.")
+```
+
+```{r}
+most_recent_df <- merge(most_recent_df, pop_df, by.x = "state", by.y = "ST", all = TRUE)
+head(most_recent_df)
+```
+
+```{r}
+most_recent_df[, total_100k := total / Population * 100000]
+head(most_recent_df[, .(date, state, total_100k)])
+```
+
+```{r}
+setkey(most_recent_df, total_100k)
+head(most_recent_df)
+```
+
+```{r}
+most_recent_df[, state := factor(state, levels = c(state))]
+```
+
+```{r}
+ggplot(data = most_recent_df, aes(x = state, y = total_100k)) +
+  labs(title = "Tests per 100k", y = "total/100k") +
+  geom_bar(stat="identity", position=position_dodge(width=1)) +
+  theme(axis.text.x = element_text(angle = 90))
+```
+

notebooks/examples-Rmd/italy-with-r.Rmd

+---
+title: "italy-with-r"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## Read the data
+
+```{r}
+library(readr)
+d <- read_csv("../../data/covid-19-italy/dpc-covid19-ita-andamento-nazionale.csv")
+d
+```
+
+```{r}
+names(d)
+```
+
+## Create a plot
+
+```{r}
+library(ggplot2)
+
+ggplot(d, aes(x = data, y = totale_casi)) + 
+  geom_point() +
+  geom_line(col = "blue") +
+  xlab("Date") +
+  ylab("Number of cases")
+```
+