填写缺失的日期并添加“ 0”

时间:2019-03-28 22:09:20

标签: r

以下代码在滑雪季节(12月至3月)中按每年月份产生SLC中的雪崩数量。由于此代码获取每个月的总计,因此不会将雪崩的年份和月总计相加。如何填写表格,以便提供全年的数据?

# write the webscraper
library(XML)
library(RCurl)
library(dplyr)
avalanche<-data.frame()
avalanche.url<-"https://utahavalanchecenter.org/observations?page="
all.pages<-0:202
for(page in all.pages){
  this.url<-paste(avalanche.url, page, sep="")
  this.webpage<-htmlParse(getURL(this.url))
  thispage.avalanche<-readHTMLTable(this.webpage, which=1, header=T,stringsAsFactors=F)
  names(thispage.avalanche)<-c('Date','Region','Location','Observer')
  avalanche<-rbind(avalanche,thispage.avalanche)
}

# subset the data to the Salt Lake Region
avalancheslc<-subset(avalanche, Region=="Salt Lake")
str(avalancheslc)


# convert the dates and get the  total the number of avalanches
avalancheslc <- avalancheslc %>% 
          group_by(Date = format(as.yearmon(Date, "%m/%d/%Y"), "%Y-%m")) %>% 
          summarise(AvalancheTotal = n())
# pipe to only include Dec-Mar of each year
avalancheslc <- avalancheslc %>% filter(as.integer(substr(Date, 6, 7)) %in% c(12, 1:3))
# the data right now looks like this
Date   AvalancheTotal
1980-01        1
1981-02        1
.
.
.



# the data needs to look like this
Date   AvalancheTotal
1980-01        1
1980-02        0
1980-03        0
1980-12        0
1981-01        0
1981-02        1
1981-03        1

1 个答案:

答案 0 :(得分:0)

library("tidyverse")
library("lubridate")

# You data here...

# Simpler version
avalancheslc %>%
  separate(Date, c("year", "month")) %>%
  # Some years might be missing (no avalanches at all)
  # We can fill in those with `full_seq` but
  # `full_seq` works with numbers not characters
  mutate(year = as.integer(year)) %>%
  complete(year = full_seq(year, 1), month,
           fill = list(AvalancheTotal = 0)) %>%
  unite("Date", year, month, sep = "-")

# Alternative version (fills in all months, so needs filtering afterwards)

avalancheslc <- avalancheslc %>%
  # In case `Date` needs parsing
  mutate(Date = parse_date_time(Date, "%y-%m"))

# A full data frame of months
all_months <- avalancheslc %>%
  expand(Date = seq(first(Date), last(Date), by = "month"))

# Join to `avalanches` and fill in with 0s
avalancheslc %>%
  right_join(all_months) %>%
  replace_na(list(AvalancheTotal = 0))