热图重新排列列

Question

我正在用 R 语言创建一个热图，并且是该语言的新手。尝试重新排序此热图上的 y 轴，以使每年出现次数最多的城市显示在顶部，而在底部显示最少，但会出现大量错误，即使我越过了它们也没有改变任何东西。我已经尝试了很多东西，所以认为这可能值得一问。

唯一相关的变量名：Month_num 和 Australian_City。这是我得到的：

# I've included my discarded ideas too, as comments
require(ggplot2)
require(dplyr)

add_count(flights, Australian_City)
ggplot(flights, aes(x=Month_num %>% reorder(count.Freq), y=Australian_City)) + geom_bin2d() + scale_x_discrete(labels=c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")) + labs(x="Month", y="Flights per city") + ggtitle("Monthly International Flights Per City")

#city_counts = flights %>% group_by(Australian_City) %>% count()
#ave(age, gender, FUN = length))
#flights %>% mutate(num_by_city=ave(Australian_City, FUN=length))
#flights$Australian_City <- flights$Australian_City %>% reorder(flights$n)
#flights <- transform(flights, count=table(Australian_City)[Australian_City])
#flights %>% mutate(num_by_city= case_when(city_counts$Australian_City==Australian_City ~ city_counts$n))
#flights %>% mutate(visit_count = sum(flights$))

我可以看到其中一个被丢弃的想法有效，但我不知道如何:(。Month_num 和Australian_City 都是因子，但月份存储为整数1 到12。任何帮助将不胜感激！

Answer 1

我试图重现你的情况。 创建数据集：

require(ggplot2)
require(dplyr)
library(tidyr)

Adelaide <- sample(1:300, 12, replace=TRUE)
Darwin <- sample(1:300, 12, replace=TRUE)
Calms <- sample(1:300, 12, replace=TRUE)
Canberra <- sample(1:300, 12, replace=TRUE)
Melbourne <- sample(1:300, 12, replace=TRUE)

data <- data.frame(Adelaide, Darwin, Calms, Canberra, Melbourne)
data$Month <- format(ISOdatetime(2000,1:12,1,0,0,0),"%b")

       Adelaide Darwin Calms Canberra Melbourne Month
1        91    148    10      246        45   gen
2       175    156   247      118         1   feb
3       244    232    18      287        74   mar
4       123      5    75      194       136   apr
5       142    267    19      155        75   mag
6       166    292   263      266       187   giu
7        18     72    61       83       197   lug
8       294     97    69       15         3   ago
9       234    135    80        8       267   set
10      181    134    54       64       203   ott
11      232    197    50      145        39   nov
12      177     20    68       32       299   dic

然后收集它：

data <- gather(data, "City","Count",1:5) # change 5 with your actual number of cities
data$Month <- as.character(data$Month)
data$Month <- factor(data$Month, levels=unique(data$Month))

data$City <- as.character(data$City)
data$City <- factor(data$City, levels=unique(data$City))

     Month   City   Count
1    gen  Adelaide    91
2    feb  Adelaide   175
3    mar  Adelaide   244
4    apr  Adelaide   123
5    mag  Adelaide   142
6    giu  Adelaide   166
7    lug  Adelaide    18
8    ago  Adelaide   294
9    set  Adelaide   234
10   ott  Adelaide   181
11   nov  Adelaide   232
12   dic  Adelaide   177
13   gen    Darwin   148
14   feb    Darwin   156
15   mar    Darwin   232
16   apr    Darwin     5
17   mag    Darwin   267
18   giu    Darwin   292
..   ...    .....    ...

然后绘制热图（未排序）：

ggplot(data, aes(x= Month, y = City , fill= Count)) + geom_tile()

最后，您可以按照每年出现次数最多的城市显示在顶部的方式排列行：

     Calms  Melbourne  Canberra    Darwin  Adelaide 
     1014      1526      1613      1755      2077 

ggplot(data, aes(x= Month, y = reorder(City, Count) , fill= Count)) + geom_tile()