学会使用和操作时间数据课程目录

Chapter1. R里的时间和数据
Chapter2. 操作和剖析时间数据
Chapter3. 对时间数据进行计算
Chapter4. 问题实践

Chapter2. 操作和剖析时间数据

使用lubridate包

有一个很便利的包可以用来操作时间数据的格式。
比方说ymd表示年月日，dmy表示日月年。

library(lubridate)
# Parse x 
x <- "2010 September 20th" # 2010-09-20
ymd(x)
[1] "2010-09-20"
# Parse y 
y <- "02.01.2010"  # 2010-01-02
dmy(y)
[1] "2010-01-02"
# Parse z 
z <- "Sep, 12th 2010 14:00"  # 2010-09-12T14:00
mdy_hm(z)
[1] "2010-09-12 14:00:00 UTC"

# Specify order to include both "mdy" and "dmy"
two_orders <- c("October 7, 2001", "October 13, 2002", "April 13, 2003", 
  "17 April 2005", "23 April 2017")
parse_date_time(two_orders, orders = c("mdy","dmy"))
[1] "2001-10-07 UTC" "2002-10-13 UTC" "2003-04-13 UTC" "2005-04-17 UTC"
[5] "2017-04-23 UTC"
# Specify order to include "dOmY", "OmY" and "Y"
short_dates <- c("11 December 1282", "May 1372", "1253")
parse_date_time(short_dates, orders = c("dOmY","OmY","Y"))
[1] "1282-12-11 UTC" "1372-05-01 UTC" "1253-01-01 UTC"
# Specify an order string to parse x
x <- "Monday June 1st 2010 at 4pm"
parse_date_time(x, orders = "AmdyIp")
[1] "2010-06-01 16:00:00 UTC"
# Specify order to include both "mdy" and "dmy"
two_orders <- c("October 7, 2001", "October 13, 2002", "April 13, 2003", 
  "17 April 2005", "23 April 2017")
parse_date_time(two_orders, orders = c("mdy","dmy"))
[1] "2001-10-07 UTC" "2002-10-13 UTC" "2003-04-13 UTC" "2005-04-17 UTC"
[5] "2017-04-23 UTC"
# Specify order to include "dOmY", "OmY" and "Y"
short_dates <- c("11 December 1282", "May 1372", "1253")
parse_date_time(short_dates, orders = c("dOmY","OmY","Y"))
[1] "1282-12-11 UTC" "1372-05-01 UTC" "1253-01-01 UTC"

这里总结一下常用的字母符号代表的意思。

再来一个练习，读取一个csv文件，将其中的date列定义为ymd的日期格式，然后组合其他变量进行可视化。

library(lubridate)
library(readr)
library(dplyr)
library(ggplot2)

# Parse date 
akl_daily <- akl_daily_raw %>%
  mutate(date = ymd(date))
# Print akl_daily
akl_daily
# A tibble: 3,661 x 7
   date       max_temp min_temp mean_temp mean_rh events cloud_cover
   <date>        <int>    <int>     <int>   <int> <chr>        <int>
 1 2007-09-01       60       51        56      75 <NA>             4
 2 2007-09-02       60       53        56      82 Rain             4
 3 2007-09-03       57       51        54      78 <NA>             6
 4 2007-09-04       64       50        57      80 Rain             6
 5 2007-09-05       53       48        50      90 Rain             7
 6 2007-09-06       57       42        50      69 <NA>             1
 7 2007-09-07       59       41        50      77 <NA>             4
 8 2007-09-08       59       46        52      80 <NA>             5
 9 2007-09-09       55       50        52      88 Rain             7
10 2007-09-10       59       50        54      82 Rain             4
# ... with 3,651 more rows
# Plot to check work
ggplot(akl_daily, aes(x = date, y = max_temp)) +
  geom_line() 
Warning message: Removed 1 row(s) containing missing values (geom_path).

library(lubridate)
library(readr)
library(dplyr)
library(ggplot2)

# Import "akl_weather_hourly_2016.csv"
akl_hourly_raw <- read_csv("akl_weather_hourly_2016.csv")

# Print akl_hourly_raw
akl_hourly_raw

# Use make_date() to combine year, month and mday 
akl_hourly  <- akl_hourly_raw  %>% 
  mutate(date = make_date(year = year, month = month, day = mday))

# Parse datetime_string 
akl_hourly <- akl_hourly  %>% 
  mutate(
    datetime_string = paste(date, time, sep = "T"),
    datetime = ymd_hms(datetime_string)
  )

# Print date, time and datetime columns of akl_hourly
akl_hourly %>% select(date, time, datetime)

# Plot to check work
ggplot(akl_hourly, aes(x = datetime, y = temperature)) +
  geom_line()