季节性箱形图在R或MATLAB

使用tidyverse和lubridate的解决方案。 tidyverse包括dplyr和tidyr来执行数据处理，并且ggplot2来创建该图。 lubridate是处理数据帧中的日期。

由于您提供的数据集不是很有用，因为它仅包含一月份的一些记录，因此无法创建显示季节差异的箱线图，因此我决定创建一个新的示例数据框。我的示例数据框架的结构与您的数据集相似，应该为您提供一些提示，作为您现实世界问题的出发点。

# Set the seed for reproducibility 
set.seed(123) 
library(tidyverse) 
library(lubridate) 
# Create example data frame 
dt <- data_frame(DATE = seq(ymd("1980-01-01"), ymd("1989-12-31"), by = 1)) %>% 
    mutate(obs1 = rnorm(nrow(.), mean = 0, sd = 1), 
     obs2 = rnorm(nrow(.), mean = 1, sd = 2), 
     obs3 = rnorm(nrow(.), mean = 2, sd = 3)) 
head(dt) 
# # A tibble: 6 x 4 
#   DATE  obs1  obs2  obs3 
#  <date>  <dbl>  <dbl>  <dbl> 
# 1 1980-01-01 -0.56047565 0.7874145 2.7827006 
# 2 1980-01-02 -0.23017749 0.1517417 8.5720252 
# 3 1980-01-03 1.55870831 0.7193725 1.3293478 
# 4 1980-01-04 0.07050839 0.5454177 0.3253155 
# 5 1980-01-05 0.12928774 1.41.1245771 
# 6 1980-01-06 1.71506499 -0.6491910 4.5034395 
tail(dt) 
# # A tibble: 6 x 4 
#   DATE  obs1  obs2  obs3 
#  <date>  <dbl>  <dbl>  <dbl> 
# 1 1989-12-26 -0.3629796 0.6750946 0.8586325 
# 2 1989-12-27 0.1102218 2.8572337 9.8541328 
# 3 1989-12-28 -0.2700741 1.7614026 1.9109596 
# 4 1989-12-29 0.6920973 0.5275611 -0.4756240 
# 5 1989-12-30 0.9282803 1.3811225 1.5222535 
# 6 1989-12-31 0.5931301 -1.6638739 4.1157087 

示例数据框包含10年3个观察组的记录。每列的值都是正态分布，具有不同的平均值和标准偏差。

第一步是通过将数据集从宽格式转换为长格式并添加显示季节信息的列来处理数据帧。

dt2 <- dt %>% 
    # Convert data frame from lwide format to long format 
    gather(Observation, Value, -DATE) %>% 
    # Remove "obs" in the Observation column 
    mutate(Observation = str_replace(Observation, "obs", "")) %>% 
    # Convert the DATE column to date class 
    mutate(DATE = ymd(DATE)) %>% 
    # Create Month column 
    mutate(Month = month(DATE)) %>% 
    # Create Season column 
    mutate(Season = case_when(
    Month %in% c(12, 1, 2)  ~ "winter", 
    Month %in% c(3, 4, 5)  ~ "spring", 
    Month %in% c(6, 7, 8)  ~ "summer", 
    Month %in% c(9, 10, 11)  ~ "fall", 
    TRUE      ~ NA_character_ 
)) 

在那之后，我们就可以使用ggplot2创建箱线图。请注意，我使用stat_summary为每个组添加红线来表示平均值。

# Create a boxplot using ggplot2 
# Specify the aesthetics 
ggplot(dt2, aes(x = Season, y = Value, fill = Observation)) + 
    # Specify the geom to be boxplot 
    geom_boxplot() +     
    # Add a red line to the mean 
    stat_summary(aes(ymax = ..y.., ymin = ..y..), 
       fun.y = "mean", 
       geom = "errorbar",    # Use geom_errorbar to add line as mean 
       color = "red", 
       width = 0.7, 
       position = position_dodge(width = 0.75), # Add the line to each group 
       show.legend = FALSE) 

好吧...第一步是建立可以检测在一个给定的日期落在本赛季的功能。幸运的是，我很早以前就已经开发出了能够在南半球处理季节（这是逆转的）。

该函数没有执行任何完整性检查，因为我已经将它与已经过清理的数据集一起使用，但最终实现一些应该不难（除非您决定在使用它之前对数据集进行清理）。它以矢量化的方式工作，以最大化Matlab中计算的性能。

这里是：

function season = GetSeason(date,southern_hemisphere) 
    if (nargin == 1) 
     southern_hemisphere = false; 
    end 
    [~,month,day] = datevec(date); 
    offset = month + (day/100); 
    winter = (offset < 3.21) | (offset >= 12.22); 
    spring = ~winter & (offset < 6.21); 
    summer = ~winter & ~spring & (offset < 9.23); 
    autumn = ~winter & ~spring & ~summer; 
    offset(spring) = 0; 
    offset(summer) = 1; 
    offset(autumn) = 2; 
    offset(winter) = 3; 
    if (southern_hemisphere) 
     offset = offset + 2; 
    end 
    season = mod(offset,4) + 1; 
end 

现在，第一步，你的脚本中，是从一个数据集文件中提取你的观察。为了为您创建完整的演示，我创建了一个Excel数据集。但你也可以使用一个CSV数据集在用Matlab处理的代码或其它格式的文件几乎没有变化：

% detect the dataset columns format 
opts = detectImportOptions('data.xlsx'); 
% impose a specific format for the dataset columns 
opts = setvartype(opts,{'datetime' 'double' 'double' 'double'}); 
% extract data in a table variable 
data = readtable('data.xlsx',opts); 
% sanitize the table variable removing the rows with missing or invalid values 
data = rmmissing(data); 
% sort the table variable rows by date (default first rows, default ascending) 
data = sortrows(data); 

第二次测试包括在获得相应的季节为观察日期：

seasons = GetSeason(data.Date); 

第三步，假设我们只对观测的第一列称为Obs1执行所有这一过程：

spring_1 = data.Obs1(seasons == 1); 
summer_1 = data.Obs1(seasons == 2); 
autumn_1 = data.Obs1(seasons == 3); 
winter_1 = data.Obs1(seasons == 4); 

第四步也是最后一步包括在一个图表中绘制每个季节的一个箱形图（必须将变量groups作为参数传递给boxplot函数，以便知道后者需要绘制多少个箱子并使用哪些值）：

groups = [ 
    ones(size(spring_1)); 
    2 * ones(size(summer_1)); 
    3 * ones(size(autumn_1)); 
    4 * ones(size(winter_1)); 
]; 
figure(); 
boxplot([spring_1; summer_1; autumn_1; winter_1],groups); 
set(gca,'XTickLabel',{'Spring' 'Summer' 'Autumn' 'Winter'}); 

这里是结果：

以饱满的工作代码更新所有意见

opts = detectImportOptions('data.xlsx'); 
opts = setvartype(opts,{'datetime' 'double' 'double' 'double'}); 
data = readtable('data.xlsx',opts); 
data = rmmissing(data); 
data = sortrows(data); 
seasons = GetSeason(data.Date); 
spring_1 = data.Obs1(seasons == 1); 
summer_1 = data.Obs1(seasons == 2); 
autumn_1 = data.Obs1(seasons == 3); 
winter_1 = data.Obs1(seasons == 4); 
spring_2 = data.Obs2(seasons == 1); 
summer_2 = data.Obs2(seasons == 2); 
autumn_2 = data.Obs2(seasons == 3); 
winter_2 = data.Obs2(seasons == 4); 
spring_3 = data.Obs3(seasons == 1); 
summer_3 = data.Obs3(seasons == 2); 
autumn_3 = data.Obs3(seasons == 3); 
winter_3 = data.Obs3(seasons == 4); 
plot_data = [ 
    spring_1; 
    summer_1; 
    autumn_1; 
    winter_1; 
    spring_2; 
    summer_2; 
    autumn_2; 
    winter_2; 
    spring_3; 
    summer_3; 
    autumn_3; 
    winter_3 
]; 
plot_groups = [ 
    (1 * ones(size(spring_1))) (1 * ones(size(spring_1))); 
    (1 * ones(size(summer_1))) (2 * ones(size(summer_1))); 
    (1 * ones(size(autumn_1))) (3 * ones(size(autumn_1))); 
    (1 * ones(size(winter_1))) (4 * ones(size(winter_1))); 
    (2 * ones(size(spring_2))) (5 * ones(size(spring_2))); 
    (2 * ones(size(summer_2))) (6 * ones(size(summer_2))); 
    (2 * ones(size(autumn_2))) (7 * ones(size(autumn_2))); 
    (2 * ones(size(winter_2))) (8 * ones(size(winter_2))); 
    (3 * ones(size(spring_3))) (9 * ones(size(spring_3))); 
    (3 * ones(size(summer_3))) (10 * ones(size(summer_3))); 
    (3 * ones(size(autumn_3))) (11 * ones(size(autumn_3))); 
    (3 * ones(size(winter_3))) (12 * ones(size(winter_3))) 
]; 
labels_obs = {'' '' '' '' '' '' '' '' '' '' '' ''}; 
labels_season = repmat({'Spring' 'Summer' 'Autumn' 'Winter'},1,3); 
figure('Units','normalized','Position',[0.05 0.1 0.9 0.8]); 
boxplot(plot_data,plot_groups, ... 
    'BoxStyle','outline', ... 
    'FactorGap',[5 1], ... 
    'Labels',{labels_obs; labels_season}, ... 
    'Notch','on'); 
colors = repmat('wcyg',1,3); 
h = findobj(gca,'Tag','Box'); 
for i = 1:numel(h) 
    patch(get(h(i),'XData'),get(h(i),'YData'),colors(i),'FaceAlpha',0.5); 
end 
h = findall(allchild(findall(gca,'Type','hggroup')),'Type','text','String',''); 
positions = cell2mat(get(h,'pos')); 
positions_new = num2cell([mean(reshape(positions(:,1),4,[]))' positions(1:4:end,2:end)],2); 
set(h(1:4:end),{'Position'},positions_new,{'String'},{'Observations 3'; 'Observations 2'; 'Observations 1'}) 
h = findall(allchild(findall(gca,'Type','hggroup')),'Type','text','String',''); 
delete(h); 

结果：