R 面_包裹中各组的平均值和观察值
我读了几十篇关于如何在每个R 面_包裹中各组的平均值和观察值,r,ggplot2,facet-wrap,R,Ggplot2,Facet Wrap,我读了几十篇关于如何在每个facet_wrap中添加标签的帖子,但我希望在这里得到一些帮助,因为我一直在添加一个标签,其中包含数据集中的组平均值(λ)和观察数(k)。我使用了其中的大部分,但在以下项目上遇到了困难: 将各组观察结果的正确平均值和数量添加到刻面中 将平均值四舍五入到两位数 将“平均值”标签更改为正确的希腊字母lambda-unicode(u+03BB) 当前绘图输出: 您的代码有一个问题: 您按PIA\u类型划分,但汇总df按PIA\u项目分组 我不确定这是否是根本原因,因为在
facet_wrap
中添加标签的帖子,但我希望在这里得到一些帮助,因为我一直在添加一个标签,其中包含数据集中的组平均值(λ)和观察数(k)。我使用了其中的大部分,但在以下项目上遇到了困难:
您的代码有一个问题:
- 您按
PIA\u类型划分,但汇总df按
PIA\u项目分组
PIA_类型
和PIA_项目
都是相同的,所以我将PIA_类型
更改为两个不同的级别
创建摘要df时,您可以使用n()
计算观察数,使用round
获得正确的位数,并将lambda表示为\U03BB
df_dztpois <- structure(list(PIA_ITEM = structure(c(2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L), .Label = c("RX20 1.5t Type 6209-10", "RX20 1.6t Type 6211",
"RX20 1.6t Type 6221", "RX20 1.8t Type 6213", "RX20 2.0t Type 6215",
"RX20 2.0t Type 6225", "RX20 2.0t Type 6230"), class = "factor"),
PIA_TYPE = c("6211", "6211", "6211", "6211", "6211", "6212",
"6212", "6212", "6212", "6212"), DELY_QTY_WINS = c(75, 62,
57, 57, 67, 57, 53, 70, 70, 60), DELY_QTY_DZTPOIS = c(1.09669678480388e-08,
3.8744657910606e-05, 0.000448728658516301, 0.000448728658516301,
2.24150656988175e-06, 0.000448728658516301, 0.0023318386482722,
3.38775858809732e-07, 3.38775858809732e-07, 0.000108487832825478
)), row.names = c(NA, 10L), class = "data.frame")
library(ggplot2)
library(dplyr)
df_dztpois_summary <- df_dztpois %>%
group_by(PIA_TYPE) %>%
summarize(count = n(),
mean = mean(DELY_QTY_WINS)) %>%
mutate(lab = paste("count = ", count, "\n\U03BB = ", round(mean, digits = 2)))
p <- ggplot(data = df_dztpois, aes(x=DELY_QTY_WINS))
p <- p + geom_line(aes(y=DELY_QTY_DZTPOIS))
p <- p + facet_wrap( ~ PIA_TYPE, nrow=3, scales = "free")
p <- p + xlab("Observation") + ylab("Probability")
p <- p + theme(
legend.position = "bottom",
legend.text = element_text(size = 12),
strip.text.x = element_text(size = 12))
p <- p + labs(title = "Zero-truncated Poisson distribution of order quantity",
subtitle = "Grouped by product (PIA_TYPE)",
caption = "Data source: df_dztpois$DELY_QTY_WINS and df_full$DELY_QTY_DZTPOIS")
p <- p + geom_text(data = df_dztpois_summary, aes(label = lab), x=Inf, y=Inf, hjust=1, vjust=1.2)
p
df_dztpois%
汇总(计数=n(),
平均值=平均值(增量数量赢款))%>%
变异(lab=paste(“count=”,count,“\n\U03BB=”,四舍五入(平均数,位数=2)))
p您的代码有一个问题:
- 您按
PIA\u类型划分,但汇总df按PIA\u项目分组
我不确定这是否是根本原因,因为在您的示例数据中,PIA_类型
和PIA_项目
都是相同的,所以我将PIA_类型
更改为两个不同的级别
创建摘要df时,您可以使用n()
计算观察数,使用round
获得正确的位数,并将lambda表示为\U03BB
df_dztpois <- structure(list(PIA_ITEM = structure(c(2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L), .Label = c("RX20 1.5t Type 6209-10", "RX20 1.6t Type 6211",
"RX20 1.6t Type 6221", "RX20 1.8t Type 6213", "RX20 2.0t Type 6215",
"RX20 2.0t Type 6225", "RX20 2.0t Type 6230"), class = "factor"),
PIA_TYPE = c("6211", "6211", "6211", "6211", "6211", "6212",
"6212", "6212", "6212", "6212"), DELY_QTY_WINS = c(75, 62,
57, 57, 67, 57, 53, 70, 70, 60), DELY_QTY_DZTPOIS = c(1.09669678480388e-08,
3.8744657910606e-05, 0.000448728658516301, 0.000448728658516301,
2.24150656988175e-06, 0.000448728658516301, 0.0023318386482722,
3.38775858809732e-07, 3.38775858809732e-07, 0.000108487832825478
)), row.names = c(NA, 10L), class = "data.frame")
library(ggplot2)
library(dplyr)
df_dztpois_summary <- df_dztpois %>%
group_by(PIA_TYPE) %>%
summarize(count = n(),
mean = mean(DELY_QTY_WINS)) %>%
mutate(lab = paste("count = ", count, "\n\U03BB = ", round(mean, digits = 2)))
p <- ggplot(data = df_dztpois, aes(x=DELY_QTY_WINS))
p <- p + geom_line(aes(y=DELY_QTY_DZTPOIS))
p <- p + facet_wrap( ~ PIA_TYPE, nrow=3, scales = "free")
p <- p + xlab("Observation") + ylab("Probability")
p <- p + theme(
legend.position = "bottom",
legend.text = element_text(size = 12),
strip.text.x = element_text(size = 12))
p <- p + labs(title = "Zero-truncated Poisson distribution of order quantity",
subtitle = "Grouped by product (PIA_TYPE)",
caption = "Data source: df_dztpois$DELY_QTY_WINS and df_full$DELY_QTY_DZTPOIS")
p <- p + geom_text(data = df_dztpois_summary, aes(label = lab), x=Inf, y=Inf, hjust=1, vjust=1.2)
p
df_dztpois%
汇总(计数=n(),
平均值=平均值(增量数量赢款))%>%
变异(lab=paste(“count=”,count,“\n\U03BB=”,四舍五入(平均数,位数=2)))
pdf_-dztpois_摘要
不包含PIA_类型
,因此它不包含标签应显示在哪个方面的任何信息。df_-dztpois_摘要
不包含PIA_类型
,因此,它不包含任何关于标签应该出现在哪个方面的信息。感谢您的及时回答。我注意到我在总结和方面的错误,但正如你所说的,它们只是一个又长又短的版本。n()
对我不起作用,我得到了一个错误:`n()`只能在dplyr谓词中使用。`结果表明,重新启动R解决了n()问题。再次感谢!谢谢你的及时答复。我注意到我在总结和方面的错误,但正如你所说的,它们只是一个又长又短的版本。n()
对我不起作用,我得到了一个错误:`n()`只能在dplyr谓词中使用。`结果表明,重新启动R解决了n()问题。再次感谢!
> str(df_dztpois)
'data.frame': 959 obs. of 4 variables:
$ PIA_ITEM : Factor w/ 7 levels "RX20 1.5t Type 6209-10",..: 2 2 2 2 2 2 2 2 2 2 ...
$ PIA_TYPE : chr "6211" "6211" "6211" "6211" ...
$ DELY_QTY_WINS : num 75 62 57 57 67 57 53 70 70 60 ...
$ DELY_QTY_DZTPOIS: num 1.10e-08 3.87e-05 4.49e-04 4.49e-04 2.24e-06 ...
df_dztpois <- structure(list(PIA_ITEM = structure(c(2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L), .Label = c("RX20 1.5t Type 6209-10", "RX20 1.6t Type 6211",
"RX20 1.6t Type 6221", "RX20 1.8t Type 6213", "RX20 2.0t Type 6215",
"RX20 2.0t Type 6225", "RX20 2.0t Type 6230"), class = "factor"),
PIA_TYPE = c("6211", "6211", "6211", "6211", "6211", "6212",
"6212", "6212", "6212", "6212"), DELY_QTY_WINS = c(75, 62,
57, 57, 67, 57, 53, 70, 70, 60), DELY_QTY_DZTPOIS = c(1.09669678480388e-08,
3.8744657910606e-05, 0.000448728658516301, 0.000448728658516301,
2.24150656988175e-06, 0.000448728658516301, 0.0023318386482722,
3.38775858809732e-07, 3.38775858809732e-07, 0.000108487832825478
)), row.names = c(NA, 10L), class = "data.frame")
library(ggplot2)
library(dplyr)
df_dztpois_summary <- df_dztpois %>%
group_by(PIA_TYPE) %>%
summarize(count = n(),
mean = mean(DELY_QTY_WINS)) %>%
mutate(lab = paste("count = ", count, "\n\U03BB = ", round(mean, digits = 2)))
p <- ggplot(data = df_dztpois, aes(x=DELY_QTY_WINS))
p <- p + geom_line(aes(y=DELY_QTY_DZTPOIS))
p <- p + facet_wrap( ~ PIA_TYPE, nrow=3, scales = "free")
p <- p + xlab("Observation") + ylab("Probability")
p <- p + theme(
legend.position = "bottom",
legend.text = element_text(size = 12),
strip.text.x = element_text(size = 12))
p <- p + labs(title = "Zero-truncated Poisson distribution of order quantity",
subtitle = "Grouped by product (PIA_TYPE)",
caption = "Data source: df_dztpois$DELY_QTY_WINS and df_full$DELY_QTY_DZTPOIS")
p <- p + geom_text(data = df_dztpois_summary, aes(label = lab), x=Inf, y=Inf, hjust=1, vjust=1.2)
p