如何在 R 中创建桑基图以显示同一节点随时间的变化？
How to create a sankey diagram in R showing changes over time for the same node?
我正在尝试创建我的数据的 Sankey 图 - 下面提供了我的数据输出。
dput(df_new)
structure(list(Hospital = c(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5,
5, 5, 5, 5), Patient = c(21, 21, 21, 21, 21, 21, 21, 21, 21,
21, 21, 21, 22, 22, 22, 22, 22, 22, 23, 23, 23, 23, 23, 23, 24,
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 25, 25, 25, 25, 25,
25, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26,
26, 26, 26, 26, 26, 26, 26, 26, 26, 27, 27, 27, 27, 27, 27, 27,
27, 27, 27, 27, 27), Therapy = c("Etanercept", "Etanercept",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Infliximab",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Infliximab",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Etanercept", "Rituximab", "Rituximab", "Rituximab", "Rituximab",
"Rituximab", "Rituximab", "Adalimumab", "Adalimumab", "Adalimumab",
"Adalimumab", "Adalimumab", "Adalimumab", "Infliximab", "Infliximab",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Etanercept",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Infliximab",
"Infliximab", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Etanercept", "Etanercept", "Rituximab", "Rituximab", "Rituximab",
"Rituximab", "Rituximab", "Rituximab", "Adalimumab", "Adalimumab",
"Adalimumab", "Adalimumab", "Adalimumab", "Adalimumab", "Etanercept",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Infliximab",
"Infliximab"), `First,Second,Third,Fourth,etc` = c(1, 1, 1, 1,
1, 1, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 3, 3, 3, 3, 3, 3, 5, 5, 5, 5, 5, 5, 7, 7, 7, 7, 7, 7, 1,
1, 1, 1, 1, 1, 4, 4, 4, 4, 4, 4), QualityLife = c(3, 4, 4, 4,
2, 2, 2, 5, 6, 6, 6, 8, 1, 3, 3, 4, 4, 5, 3, 5, 6, 6, 7, 7, 2,
3, 3, 3, 3, 3, 3, 5, 5, 5, 5, 5, 2, 3, 3, 3, 4, 4, 1, 3, 3, 3,
1, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 3, 3, 3, 4, 4, 2,
3, 3, 3, 4, 4, 3, 3, 3, 4, 4, 5), FollowUp_time = c(0, 1, 3,
6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6,
12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12,
18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18,
0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18),
Continuous_time = c(0, 1, 3, 6, 12, 18, 18, 19, 21, 24, 30,
36, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12,
18, 36, 37, 39, 42, 48, 54, 0, 1, 3, 6, 12, 18, 0, 1, 3,
6, 12, 18, 54, 55, 57, 60, 66, 72, 90, 91, 93, 96, 102, 108,
126, 127, 129, 132, 138, 144, 0, 1, 3, 6, 12, 18, 72, 73,
75, 78, 84, 90)), row.names = c(NA, -78L), class = "data.frame")
这是一个保健运动。对于每种治疗，患者在 0、1、3、6、12、18 个月时被询问他们的生活质量如何。如果在特定的随访时间，生活质量<特定参数，医生会改变患者的治疗方法，我想在桑基图中显示这一点。我想让一个节点 "Therapy" （具有不同疗法名称的分类变量）随时间重复，x 轴占时间。谁能帮我这个？非常感谢任何帮助。
这是我到目前为止尝试过的：
### install and load packages
install.packages("ggplot2")
install.packages("readxl")
install.packages("ggforce")
# load packages
library(ggplot2)
library(readxl)
library(ggforce)
### read dataset
dataset_new <- read_excel("Made_up_dataset_new.xlsx")
df_new <- as.data.frame(dataset_new)
df_new$Unit <- 1
df_sankey <- df_new[c("Therapy", "First,Second,Third,Fourth,etc", "Continuous_time","Unit")]
# transform dataframe into appropriate format
df_sankey <- gather_set_data(df_sankey, 1:3)
# define axis-width / sep parameters once here, to be used by each geom layer in the plot
aw <- 0.1
sp <- 0.1
ggplot(df_sankey,
aes(x = x, id = id, split = y, value = Unit)) +
geom_parallel_sets(aes(fill = Therapy), alpha = 0.3,
axis.width = aw, sep = sp) +
geom_parallel_sets_axes(axis.width = aw, sep = sp) +
geom_parallel_sets_labels(colour = "white",
angle = 0, size = 3,
axis.width = aw, sep = sp) +
theme_minimal()
但结果不是我想要的，因为时间在 y 轴上被压缩，而不是在 x 轴上，如果这样有意义吗？请在下面找到我的想法草稿：
感谢任何帮助！
根据下面的答案，我尝试使代码适应我的数据集，我 运行:
df_sankey <- df_new[c("Patient","FirstSecondThird","Therapy")]
head(df_sankey)
df_new$FirstSecondThird <- factor(df_new$FirstSecondThird)
# Plotting it
ggplot(df_sankey, aes(x = FirstSecondThird, stratum = Therapy, alluvium = Patient, fill = Therapy, label = Therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(stat = "alluvium", lode.guidance = "rightleft", color = "darkgray") +
geom_stratum() +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
结果显示如下，但这不是我想要的（正如我在随附的草稿中试图解释的那样，我知道这是非常基本的）：
好吧，您有多种选择。对我有用的第一个解决方案是 ggplot / geom_flow:
# requires(ggplot2)
# requires(ggalluvial)
# faking the data for 20 patients
set.seed(42)
individual <- as.character(rep(1:20,each=5))
timeperiod <- paste0(rep(c(0, 18,36,54,72),20),"_week")
therapy <- factor(sample(c("Etanercept", "Infliximab", "Rituximab", "Adalimumab","Missing"), 100, replace=T))
d <- data.frame(individual, timeperiod, therapy)
head(d)
# Plotting it
ggplot(d, aes(x = timeperiod, stratum = therapy, alluvium = individual, fill = therapy, label = therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(stat = "alluvium", lode.guidance = "rightleft", color = "darkgray") +
geom_stratum() +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
geom_flow 中的参数 stat = "alluvium" 应该允许跟踪单个患者，但如果您愿意，也可以合并流程：
ggplot(d, aes(x = timeperiod, stratum = therapy, alluvium = individual, fill = therapy, label = therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(color = "darkgray") +
geom_stratum() +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
编辑 1：如果您希望某些患者的流量停止（例如治疗已经结束），您可以通过将这些患者设置为 NAs 来轻松实现：
# setting 3 pantients as NA for the last timepoint
d[which(d$individual==3 & d$timeperiod=="72_week"), ]["therapy"] <- NA
d[which(d$individual==6 & d$timeperiod=="72_week"), ]["therapy"] <- NA
d[which(d$individual==9 & d$timeperiod=="72_week"), ]["therapy"] <- NA
# making the plot:
ggplot(d, aes(x = timeperiod, stratum = therapy, alluvium = individual, fill = therapy, label = therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(stat = "alluvium", lode.guidance = "rightleft", color = "darkgray") +
geom_stratum(alpha=0.75) +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
现在，老实说，networkD3 也起作用了，但我只是没能让它看起来足够好。
编辑 2：
您也可以使用 geom_alluvium 代替 geom_flow。它们之间的主要（视觉）区别在于，在 geom_flow 中，流的颜色是从相邻节点（源节点或目标节点）继承的。在 geom_alluvium 中，它是从第一个节点继承的——例如流经节点时不会改变颜色。
如果你想将图表与另一个图表结合起来，最简单的方法似乎是使用 par(mfrow=c(1,2))。
我正在尝试创建我的数据的 Sankey 图 - 下面提供了我的数据输出。
dput(df_new)
structure(list(Hospital = c(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5,
5, 5, 5, 5), Patient = c(21, 21, 21, 21, 21, 21, 21, 21, 21,
21, 21, 21, 22, 22, 22, 22, 22, 22, 23, 23, 23, 23, 23, 23, 24,
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 25, 25, 25, 25, 25,
25, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26,
26, 26, 26, 26, 26, 26, 26, 26, 26, 27, 27, 27, 27, 27, 27, 27,
27, 27, 27, 27, 27), Therapy = c("Etanercept", "Etanercept",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Infliximab",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Infliximab",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Etanercept", "Rituximab", "Rituximab", "Rituximab", "Rituximab",
"Rituximab", "Rituximab", "Adalimumab", "Adalimumab", "Adalimumab",
"Adalimumab", "Adalimumab", "Adalimumab", "Infliximab", "Infliximab",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Etanercept",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Infliximab",
"Infliximab", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Etanercept", "Etanercept", "Rituximab", "Rituximab", "Rituximab",
"Rituximab", "Rituximab", "Rituximab", "Adalimumab", "Adalimumab",
"Adalimumab", "Adalimumab", "Adalimumab", "Adalimumab", "Etanercept",
"Etanercept", "Etanercept", "Etanercept", "Etanercept", "Etanercept",
"Infliximab", "Infliximab", "Infliximab", "Infliximab", "Infliximab",
"Infliximab"), `First,Second,Third,Fourth,etc` = c(1, 1, 1, 1,
1, 1, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 3, 3, 3, 3, 3, 3, 5, 5, 5, 5, 5, 5, 7, 7, 7, 7, 7, 7, 1,
1, 1, 1, 1, 1, 4, 4, 4, 4, 4, 4), QualityLife = c(3, 4, 4, 4,
2, 2, 2, 5, 6, 6, 6, 8, 1, 3, 3, 4, 4, 5, 3, 5, 6, 6, 7, 7, 2,
3, 3, 3, 3, 3, 3, 5, 5, 5, 5, 5, 2, 3, 3, 3, 4, 4, 1, 3, 3, 3,
1, 2, 2, 3, 3, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 3, 3, 3, 4, 4, 2,
3, 3, 3, 4, 4, 3, 3, 3, 4, 4, 5), FollowUp_time = c(0, 1, 3,
6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6,
12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12,
18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18,
0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18),
Continuous_time = c(0, 1, 3, 6, 12, 18, 18, 19, 21, 24, 30,
36, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12, 18, 0, 1, 3, 6, 12,
18, 36, 37, 39, 42, 48, 54, 0, 1, 3, 6, 12, 18, 0, 1, 3,
6, 12, 18, 54, 55, 57, 60, 66, 72, 90, 91, 93, 96, 102, 108,
126, 127, 129, 132, 138, 144, 0, 1, 3, 6, 12, 18, 72, 73,
75, 78, 84, 90)), row.names = c(NA, -78L), class = "data.frame")
这是一个保健运动。对于每种治疗，患者在 0、1、3、6、12、18 个月时被询问他们的生活质量如何。如果在特定的随访时间，生活质量<特定参数，医生会改变患者的治疗方法，我想在桑基图中显示这一点。我想让一个节点 "Therapy" （具有不同疗法名称的分类变量）随时间重复，x 轴占时间。谁能帮我这个？非常感谢任何帮助。
这是我到目前为止尝试过的：
### install and load packages
install.packages("ggplot2")
install.packages("readxl")
install.packages("ggforce")
# load packages
library(ggplot2)
library(readxl)
library(ggforce)
### read dataset
dataset_new <- read_excel("Made_up_dataset_new.xlsx")
df_new <- as.data.frame(dataset_new)
df_new$Unit <- 1
df_sankey <- df_new[c("Therapy", "First,Second,Third,Fourth,etc", "Continuous_time","Unit")]
# transform dataframe into appropriate format
df_sankey <- gather_set_data(df_sankey, 1:3)
# define axis-width / sep parameters once here, to be used by each geom layer in the plot
aw <- 0.1
sp <- 0.1
ggplot(df_sankey,
aes(x = x, id = id, split = y, value = Unit)) +
geom_parallel_sets(aes(fill = Therapy), alpha = 0.3,
axis.width = aw, sep = sp) +
geom_parallel_sets_axes(axis.width = aw, sep = sp) +
geom_parallel_sets_labels(colour = "white",
angle = 0, size = 3,
axis.width = aw, sep = sp) +
theme_minimal()
但结果不是我想要的，因为时间在 y 轴上被压缩，而不是在 x 轴上，如果这样有意义吗？请在下面找到我的想法草稿：
感谢任何帮助！
根据下面的答案，我尝试使代码适应我的数据集，我 运行:
df_sankey <- df_new[c("Patient","FirstSecondThird","Therapy")]
head(df_sankey)
df_new$FirstSecondThird <- factor(df_new$FirstSecondThird)
# Plotting it
ggplot(df_sankey, aes(x = FirstSecondThird, stratum = Therapy, alluvium = Patient, fill = Therapy, label = Therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(stat = "alluvium", lode.guidance = "rightleft", color = "darkgray") +
geom_stratum() +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
结果显示如下，但这不是我想要的（正如我在随附的草稿中试图解释的那样，我知道这是非常基本的）：
好吧，您有多种选择。对我有用的第一个解决方案是 ggplot / geom_flow:
# requires(ggplot2)
# requires(ggalluvial)
# faking the data for 20 patients
set.seed(42)
individual <- as.character(rep(1:20,each=5))
timeperiod <- paste0(rep(c(0, 18,36,54,72),20),"_week")
therapy <- factor(sample(c("Etanercept", "Infliximab", "Rituximab", "Adalimumab","Missing"), 100, replace=T))
d <- data.frame(individual, timeperiod, therapy)
head(d)
# Plotting it
ggplot(d, aes(x = timeperiod, stratum = therapy, alluvium = individual, fill = therapy, label = therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(stat = "alluvium", lode.guidance = "rightleft", color = "darkgray") +
geom_stratum() +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
geom_flow 中的参数 stat = "alluvium" 应该允许跟踪单个患者，但如果您愿意，也可以合并流程：
ggplot(d, aes(x = timeperiod, stratum = therapy, alluvium = individual, fill = therapy, label = therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(color = "darkgray") +
geom_stratum() +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
编辑 1：如果您希望某些患者的流量停止（例如治疗已经结束），您可以通过将这些患者设置为 NAs 来轻松实现：
# setting 3 pantients as NA for the last timepoint
d[which(d$individual==3 & d$timeperiod=="72_week"), ]["therapy"] <- NA
d[which(d$individual==6 & d$timeperiod=="72_week"), ]["therapy"] <- NA
d[which(d$individual==9 & d$timeperiod=="72_week"), ]["therapy"] <- NA
# making the plot:
ggplot(d, aes(x = timeperiod, stratum = therapy, alluvium = individual, fill = therapy, label = therapy)) +
scale_fill_brewer(type = "qual", palette = "Set2") +
geom_flow(stat = "alluvium", lode.guidance = "rightleft", color = "darkgray") +
geom_stratum(alpha=0.75) +
theme(legend.position = "bottom") +
ggtitle("Treatment across observation period")
networkD3 也起作用了，但我只是没能让它看起来足够好。
编辑 2：
您也可以使用
geom_alluvium代替geom_flow。它们之间的主要（视觉）区别在于，在geom_flow中，流的颜色是从相邻节点（源节点或目标节点）继承的。在geom_alluvium中，它是从第一个节点继承的——例如流经节点时不会改变颜色。如果你想将图表与另一个图表结合起来，最简单的方法似乎是使用
par(mfrow=c(1,2))。