可能用到的包
library(tidyverse)
## Warning: 程序包'tidyverse'是用R版本4.4.3 来建造的
## Warning: 程序包'ggplot2'是用R版本4.4.3 来建造的
## Warning: 程序包'tibble'是用R版本4.4.3 来建造的
## Warning: 程序包'tidyr'是用R版本4.4.3 来建造的
## Warning: 程序包'readr'是用R版本4.4.3 来建造的
## Warning: 程序包'purrr'是用R版本4.4.3 来建造的
## Warning: 程序包'dplyr'是用R版本4.4.3 来建造的
## Warning: 程序包'stringr'是用R版本4.4.3 来建造的
## Warning: 程序包'forcats'是用R版本4.4.3 来建造的
## Warning: 程序包'lubridate'是用R版本4.4.3 来建造的
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(lubridate)
导入数据“madision_weather.csv”
madision_weather <- read_csv("C:/Rcourse/data/data/madision_weather.csv")
## Rows: 98538 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): station, name
## dbl (12): latitude, longitude, elevation, year, month, day, prcp, snow, snwd...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
数据说明
- station: 气象站唯一识别标识
- name: 气象站名称
- latitude: 气象站纬度
- longitude: 气象站经度
- elevation: 气象站海拔
- date: 日期
- year: 年
- month: 月
- day: 日
- prcp: 降水量
- snow: 降雪量
- snwd: 积雪厚度
- tmax: 最高温度(华氏度)
- tmin: 最低温度(华氏度)
- tavg: 日平均气温(华氏度)
1.报告数据维度(多少行，多少列)并输出数据的前10行
madision_weather <- read_csv("C:/Rcourse/data/data/madision_weather.csv") # 确保文件路径正确
## Rows: 98538 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): station, name
## dbl (12): latitude, longitude, elevation, year, month, day, prcp, snow, snwd...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
dim(madision_weather)
## [1] 98538 14
head(madision_weather, 10)
## # A tibble: 10 × 14
## station name latitude longitude elevation year month day prcp snow
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 1 0 NA
## 2 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 2 0 NA
## 3 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 3 0.15 NA
## 4 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 4 0.02 NA
## 5 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 5 0.01 NA
## 6 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 6 0.25 NA
## 7 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 7 0.04 NA
## 8 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 8 0.05 NA
## 9 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 9 0 NA
## 10 USC00470273 UW AR… 43.0 -89.4 265. 1971 10 10 0 NA
## # ℹ 4 more variables: snwd <dbl>, tavg <dbl>, tmax <dbl>, tmin <dbl>
2.Madision总共有几个气象站？并输出每个气象站的详细信息（包括纬度、经度、海拔）
madision_weather %>%
distinct(station, name, latitude, longitude, elevation)
## # A tibble: 4 × 5
## station name latitude longitude elevation
## <chr> <chr> <dbl> <dbl> <dbl>
## 1 USC00470273 UW ARBORETUM MADISON, WI US 43.0 -89.4 265.
## 2 USW00014837 MADISON DANE CO REGIONAL AIRPORT, WI… 43.1 -89.3 262.
## 3 USC00471416 CHARMANY FARM, WI US 43.1 -89.5 319.
## 4 USC00474966 MADISON WEATHER BUREAU CITY, WI US 43.1 -89.4 297.
3.查看”USC00471416”气象站2020年降水量、降雪量、积雪厚度的缺失数量
madision_weather %>%
filter(station == "USC00471416", year == 2020) %>%
summarise(prcp_na = sum(is.na(prcp)),
snow_na = sum(is.na(snow)),
snwd_na = sum(is.na(snwd)))
## # A tibble: 1 × 3
## prcp_na snow_na snwd_na
## <int> <int> <int>
## 1 5 2 0
4.查看每个气象站统计的起始日期(命名：first_date)和最后日期(命名：last_date)，气象站有记录的天数(命名:days_n)，应该记录的天数(命名：days_possible)，缺失的天数(命名:days_missing)
- 提示：days_possible = as.numeric(last_date - first_date) + 1
(两个date类型的变量相减，可以算出来二者之间间隔了多少天，只不过此时是一个datediff
类型的变量，通过as.numeric()函数可以将其转换为数值型变量)
madision_weather <- madision_weather %>%
mutate(date = make_date(year, month, day))
madision_weather %>%
group_by(station) %>%
summarise(
first_date = min(date, na.rm = TRUE),
last_date = max(date, na.rm = TRUE),
days_n = n(),
days_possible = as.numeric(last_date - first_date) + 1,
days_missing = days_possible - days_n
)
## # A tibble: 4 × 6
## station first_date last_date days_n days_possible days_missing
## <chr> <date> <date> <int> <dbl> <dbl>
## 1 USC00470273 1971-10-01 2021-12-31 18179 18355 176
## 2 USC00471416 1959-08-01 2021-12-31 21410 22799 1389
## 3 USC00474966 1884-01-01 1963-05-31 28906 29005 99
## 4 USW00014837 1939-10-01 2021-12-31 30043 30043 0
5.将3个温度指标(tmax,tmin,tavg)从华氏度换算成摄氏度，并替代原来的变量(C
= 5*(F-32)/9, C为摄氏度，F为华氏度)
madision_weather <- madision_weather %>%
mutate(across(c(tmax, tmin, tavg), ~ 5*(. -32)/9, .names = "{.col}"))
6.①Madision地区2000年的最高气温和最低气温是多少，分别是哪一天哪一个气象站观测到的？②计算2000年每个气象站最高气温和最低气温的差值并排序
# ①
madision_weather <- madision_weather %>%
mutate(date = make_date(year, month, day))
madision_weather %>%
filter(year == 2000) %>%
filter(
tmax == max(tmax, na.rm = TRUE) |
tmin == min(tmin, na.rm = TRUE)
) %>%
select(date, station, tmax, tmin)
## # A tibble: 2 × 4
## date station tmax tmin
## <date> <chr> <dbl> <dbl>
## 1 2000-09-02 USC00470273 33.9 20
## 2 2000-12-25 USW00014837 -12.8 -29.4
madision_weather %>%
filter(year == 2000) %>%
group_by(station) %>%
summarise(
max_tmax = max(tmax, na.rm = TRUE),
min_tmin = min(tmin, na.rm = TRUE),
t_diff = max_tmax - min_tmin
) %>%
arrange(desc(t_diff))
## # A tibble: 3 × 4
## station max_tmax min_tmin t_diff
## <chr> <dbl> <dbl> <dbl>
## 1 USW00014837 33.3 -29.4 62.8
## 2 USC00470273 33.9 -28.3 62.2
## 3 USC00471416 32.8 -21.1 53.9
7.筛选出平均气温最高的10年，这10年中有多少年是2000年以后的？
madision_weather %>%
group_by(year) %>%
summarise(mean_tavg = mean(tavg, na.rm = TRUE)) %>%
slice_max(mean_tavg, n = 10) %>%
summarise(post_2000 = sum(year > 2000))
## # A tibble: 1 × 1
## post_2000
## <int>
## 1 4
8.为数据集添加日温差变量(命名:tdiff)，“是否下雪”指示变量（命名:is_snow,提示：降雪量大于0)
madision_weather <- madision_weather %>%
mutate(tdiff = tmax - tmin,
is_snow = snow > 0)
9.计算各气象站的平均气温(命名:station_tavg)和平均温差(命名:station_tdiff)，并按气象站的海拔排序。
madision_weather %>%
group_by(station, elevation) %>%
summarise(station_tavg = mean(tavg, na.rm = TRUE),
station_tdiff = mean(tdiff, na.rm = TRUE)) %>%
arrange(elevation)
## `summarise()` has grouped output by 'station'. You can override using the
## `.groups` argument.
## # A tibble: 4 × 4
## # Groups: station [4]
## station elevation station_tavg station_tdiff
## <chr> <dbl> <dbl> <dbl>
## 1 USW00014837 262. 8.02 11.2
## 2 USC00470273 265. 7.95 12.4
## 3 USC00474966 297. 7.99 9.07
## 4 USC00471416 319. 7.98 10.6
10.以气象站”USC00470273”的数据代表madision地区的天气，将数据聚合到年层面，并计算年降水量(prcp_year)、年降雪量(snow_year)、降雪天数(snow_days)、年均气温(tavg_year),保存数据并命名为madision_weather_panel。
madision_weather_panel <- madision_weather %>%
filter(station == "USC00470273") %>%
group_by(year) %>%
summarise(
prcp_year = sum(prcp, na.rm = TRUE),
snow_year = sum(snow, na.rm = TRUE),
snow_days = sum(is_snow, na.rm = TRUE),
tavg_year = mean(tavg, na.rm = TRUE)
)
11.根据上题得到的数据，研究Madision的气温逐年变化趋势。
lm(tavg_year ~ year, data = madision_weather_panel) %>% summary()
##
## Call:
## lm(formula = tavg_year ~ year, data = madision_weather_panel)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.80575 -0.64707 0.01282 0.71645 1.94078
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -90.33559 20.91056 -4.320 7.59e-05 ***
## year 0.04921 0.01048 4.697 2.17e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.101 on 49 degrees of freedom
## Multiple R-squared: 0.3105, Adjusted R-squared: 0.2964
## F-statistic: 22.06 on 1 and 49 DF, p-value: 2.168e-05
12.这里定义了季节划分函数并添加季节列，请你计算每个季节的平均降水量、平均降雪量、平均气温，并从降水量、降雪量、气温几个指标中选择一个指标，绘制季节变化折线图
get_season <- function(month) {
case_when(
month %in% 3:5 ~ "Spring",
month %in% 6:8 ~ "Summer",
month %in% 9:11 ~ "Fall",
TRUE ~ "Winter"
)
}
madision_weather_season <- madision_weather %>%
mutate(season = get_season(month))
season_stats <- madision_weather_season %>%
group_by(season) %>%
summarise(
mean_prcp = mean(prcp, na.rm = TRUE),
mean_snow = mean(snow, na.rm = TRUE),
mean_tavg = mean(tavg, na.rm = TRUE)
)
# 示例绘图（气温季节变化）
ggplot(season_stats, aes(x = season, y = mean_tavg, group = 1)) +
geom_line() +
labs(title = "Seasonal Temperature Variation")
13.根据本次作业出现的各种数据，提出一个你感兴趣的问题并进行简单研究。
madision_weather %>%
group_by(station) %>%
summarise(
elevation = first(elevation),
mean_tdiff = mean(tdiff, na.rm = TRUE)
) %>%
lm(mean_tdiff ~ elevation, data = .) %>% summary()
##
## Call:
## lm(formula = mean_tdiff ~ elevation, data = .)
##
## Residuals:
## 1 2 3 4
## 0.9087 0.8152 -1.4128 -0.3111
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 19.56647 8.14714 2.402 0.138
## elevation -0.03060 0.02843 -1.077 0.394
##
## Residual standard error: 1.338 on 2 degrees of freedom
## Multiple R-squared: 0.3669, Adjusted R-squared: 0.0503
## F-statistic: 1.159 on 1 and 2 DF, p-value: 0.3943