In [9]:
library(DataComputing)
library(rvest)
library(lubridate)
page = "List_of_nuclear_reactors"
xpath = '//*[@id="mw-content-text"]/table'
table_list <- page %>%
read_html() %>%
html_nodes(xpath = xpath) %>%
html_table(fill = TRUE)
In [10]:
table <- table_list[[23]]
head(table)
Out[10]:
In [11]:
names(table)
Out[11]:
In [13]:
new_names <- c("name", "reactor_no", "type", "model",
"status", "net", "gross", "construction_start",
"operation_start", "closure")
names(table) <- new_names
table <- table %>% filter(row_number() != 1)
head(table)
Out[13]:
In [15]:
table %>%
separate(construction_start, into=c("day", "month", "year"), sep=" ") %>%
mutate(year=as.numeric(year)) %>%
ggplot(aes(y=net, x=year, color=type)) + geom_point() + labs(x="construction start")
In [16]:
table %>%
separate(construction_start, into=c("day1", "month1", "year1"), sep=" ") %>%
separate(operation_start, into=c("day2", "month2", "year2"), sep=" ") %>%
mutate(year1=as.numeric(year1), year2=as.numeric(year2)) %>%
ggplot() + geom_segment(aes(x=year1, xend=year2, y=name, yend=name)) + labs(x="construction start", y="reactor site")
ls
less lifeexpectancy.csv
wc -l lifeexpectancy.csv
head -1 lifeexpectancy.csv #column 152, 177, 202
cut -f 1,152,177,202 -d ',' lifeexpectancy.csv
cut -f 1,152,177,202 -d ',' lifeexpectancy.csv | egrep "[0-9]" > lifeexpectancy.clean.csv
R CMD BATCH makemaps-1.R lifeexpectancy.clean.csv | tee message.txt
ls plots