我试图从我使用weatherData包的个人气象站获取每小时的总降水量值。我遇到的问题是每五分钟收集一次数据,并且值会重复,直到降水值发生变化。我已经尝试了重复的'功能,但我没有降水时删除大量数据,这使我很难得到每小时降水的摘要。
请参阅以下代码
## Load required libraries
library(weatherData)
library(ggplot2)
library(scales)
library(plyr)
library(reshape2)
library(gridExtra)
library(lubridate)
library(weathermetrics)
library(zoo)
# Get data for PWS using weatherData package
pws <- getWeatherForDate("IPENANGB2", "2014-09-01","2014-09-30", station_type = "id",opt_detailed=T, opt_custom_columns=T, custom_columns=c(1,2,6,7,10))
# Rename columns
colnames(pws)<-c("time","time1","tempc","wdd","wspd","prcp")
## Adding date columns
pws$time<-as.POSIXct(pws$time1,format="%Y-%m-%d %H:%M:%S",tz="Australia/Perth")
pws$year <- as.numeric(format(pws$time,"%Y"))
pws$date <-as.Date(pws$time,format="%Y-%m-%d",tz="Australia/Perth")
pws$year <- as.numeric(as.POSIXlt(pws$date)$year+1900)
pws$month <- as.numeric(as.POSIXlt(pws$date)$mon+1)
pws$monthf <- factor(pws$month,levels=as.character(1:12),labels=c("Jan","Feb","Mar","Apr","May","Jun","Jul","Aug","Sep","Oct","Nov","Dec"),ordered=TRUE)
pws$weekday <- as.POSIXlt(pws$date)$wday
pws$weekdayf <- factor(pws$weekday,levels=rev(0:6),labels=rev(c("Mon","Tue","Wed","Thu","Fri","Sat","Sun")),ordered=TRUE)
pws$yearmonth <- as.yearmon(pws$date)
pws$yearmonthf <- factor(pws$yearmonth)
pws$week <- as.numeric(format(as.Date(pws$date),"%W"))
pws$weekf<- factor(pws$week)
pws$jday<-yday(pws$date)
pws$hour <- as.numeric(format(strptime(pws$time, format = "%Y-%m-%d %H:%M"),format = "%H"))
pws$min <- as.numeric(format(strptime(pws$time, format = "%Y-%m-%d %H:%M"),format = "%M"))
# Remove duplicate values
pws.df <- pws[!duplicated(pws$prcp),]
答案 0 :(得分:1)
假设你想得到每小时的tempc,wdd,wspd,prcp:
# used packages
library(weatherData)
library(lubridate)
library(dplyr)
library(stringr)
# read data
pws <- getWeatherForDate("IPENANGB2",
"2014-09-01",
"2014-09-30",
station_type = "id",
opt_detailed = T,
opt_custom_columns = T,
custom_columns = c(1, 2, 6, 7, 10))
# rename columns
colnames(pws) <- c("time", "time1", "tempc", "wdd", "wspd", "prcp")
# cleaning dataset and adding some columns
useful_pws <-
pws %>%
select(2:6) %>%
filter(!str_detect(time1, "<br>")) %>%
mutate(time1 = ymd_hms(time1),
year = year(time1),
month = month(time1),
day = day(time1),
hour = hour(time1)) %>%
tbl_df()
# summarising dataset
useful_pws %>%
select(-time1) %>%
group_by(year, month, day, hour) %>%
summarise(tempc = mean(tempc, na.rm = TRUE),
wdd = mean(wdd, na.rm = TRUE),
wspd = mean(wspd, na.rm = TRUE),
prcp = mean(prcp, na.rm = TRUE))