r - 将两个不同列表的数据帧融合为 r 中的一个数据帧列表
问题描述
我有两个数据框列表：list1 和 list2。下面是来自 list1 (df1) 和 list2 (df2) 的示例数据框：
> print(df1)
Moment.ext_multi.lane Moment.ext_single.lane Moment.int_multi.lane Moment.int_single.lane
Baseline 0.7109148 0.5367121 0.5874249 0.3718993
Sample1 0.7109148 0.5367121 0.5874249 0.3718993
Sample2 0.7109148 0.5367121 0.5874249 0.3718993
Sample3 0.7109148 0.5367121 0.5874249 0.3718993
Sample4 0.7109148 0.5367121 0.5874249 0.3718993
Sample5 0.7109148 0.5367121 0.5874249 0.3718993
Sample6 0.7109148 0.5367121 0.5874249 0.3718993
Sample7 0.7109148 0.5367121 0.5874249 0.3718993
Sample8 0.7109148 0.5367121 0.5874249 0.3718993
Sample9 0.7109148 0.5367121 0.5874249 0.3718993
Sample10 0.7109148 0.5367121 0.5874249 0.3718993
AASHTO 0.7550000 NA 0.6640000 0.4310000
Mean 0.7109148 0.5367121 0.5874249 0.3718993
> print(df2)
Shear.ext_multi.lane Shear.ext_single.lane Shear.int_multi.lane Shear.int_single.lane
Baseline 0.7109148 0.5367121 0.5874249 0.3718993
Sample1 0.7109148 0.5367121 0.5874249 0.3718993
Sample2 0.7109148 0.5367121 0.5874249 0.3718993
Sample3 0.7109148 0.5367121 0.5874249 0.3718993
Sample4 0.7109148 0.5367121 0.5874249 0.3718993
Sample5 0.7109148 0.5367121 0.5874249 0.3718993
Sample6 0.7109148 0.5367121 0.5874249 0.3718993
Sample7 0.7109148 0.5367121 0.5874249 0.3718993
Sample8 0.7109148 0.5367121 0.5874249 0.3718993
Sample9 0.7109148 0.5367121 0.5874249 0.3718993
Sample10 0.7109148 0.5367121 0.5874249 0.3718993
AASHTO 0.7550000 NA 0.6640000 0.4310000
Mean 0.7109148 0.5367121 0.5874249 0.3718993
我想将这两个列表合并到一个新的数据框列表中，并删除所有 rown 是所有具有称为“平均值”的行名的数据框：list3。
然后我想融合列表的数据，使新列表中的数据框有 4 列。
第一列是 Source，如果原始列表 list1 和列表 2 的行名是“Sample1”到“Sample10”，则 Source 表示 Samples，如果行名是“baseline”，则 Source 表示 Baseline，如果行名是“AASHTO”然后 Source 也表示 AASHTO。
第二列是类型，提取列名称的结尾（从开头删除“Moment.”和“Shear.”，从末尾删除“.lane”）。
第三列是 Moment，包括 list1 的值。
第四列是 Shear，包括 list1 的值。
最终列表 list3 中的预期样本数据帧 (df3) 是：
> print(df2)
Source Type Shear Moment
1 Baseline ext_multi 0.5367121 0.5874249
2 Baseline ext_single 0.5367121 0.5874249
3 Baseline int_multi 0.5367121 0.5874249
4 Baseline int_single 0.5367121 0.5874249
5 AASHTO ext_multi 0.5367121 0.5874249
6 AASHTO ext_single 0.5367121 0.5874249
7 AASHTO int_multi 0.5367121 0.5874249
8 AASHTO int_single 0.5367121 0.5874249
9 AASHTO int_single 0.5367121 0.5874249
5 Sample ext_multi 0.5367121 0.5874249
6 Sample ext_single 0.5367121 0.5874249
7 Sample int_multi 0.5367121 0.5874249
8 Sample int_single 0.5367121 0.5874249
9 Sample int_single 0.5367121 0.5874249
... continues
解决方案
我们可以pivot_longer在两个元素中使用 reshape 为“long”格式list，然后使用map2循环两个 s 的相应元素list并进行连接
lst1new <- map(lst1, ~
.x %>%
rownames_to_column("Source") %>%
pivot_longer(cols = -Source, names_to = 'Type',
values_to = 'Moment') %>%
mutate(Type = str_replace(Type, '^\\w+\\.([^.]+)\\..*', '\\1')))
lst2new <- map(lst2, ~
.x %>%
rownames_to_column("Source") %>%
pivot_longer(cols = -Source, names_to = 'Type',
values_to = 'Shear') %>%
mutate(Type = str_replace(Type, '^\\w+\\.([^.]+)\\..*', '\\1')))
map2(lst1new, lst2new, full_join)
#[[1]]
# A tibble: 52 x 4
# Source Type Moment Shear
# * <chr> <chr> <dbl> <dbl>
# 1 Baseline ext_multi 0.711 0.711
# 2 Baseline ext_single 0.537 0.537
# 3 Baseline int_multi 0.587 0.587
# 4 Baseline int_single 0.372 0.372
# 5 Sample1 ext_multi 0.711 0.711
# 6 Sample1 ext_single 0.537 0.537
# 7 Sample1 int_multi 0.587 0.587
# 8 Sample1 int_single 0.372 0.372
# 9 Sample2 ext_multi 0.711 0.711
#10 Sample2 ext_single 0.537 0.537
# … with 42 more rows
#[[2]]
# A tibble: 52 x 4
# Source Type Moment Shear
# * <chr> <chr> <dbl> <dbl>
# 1 Baseline ext_multi 0.711 0.711
# 2 Baseline ext_single 0.537 0.537
# 3 Baseline int_multi 0.587 0.587
# 4 Baseline int_single 0.372 0.372
# 5 Sample1 ext_multi 0.711 0.711
# 6 Sample1 ext_single 0.537 0.537
# 7 Sample1 int_multi 0.587 0.587
# 8 Sample1 int_single 0.372 0.372
# 9 Sample2 ext_multi 0.711 0.711
#10 Sample2 ext_single 0.537 0.537
# … with 42 more rows
如果我们需要删除“示例”中的数字
map2(lst1new, lst2new, ~ full_join(.x, .y) %>%
mutate(Source = str_remove(Source, "\\d+$")))
数据
lst1 <- list(structure(list(Moment.ext_multi.lane = c(0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.755, 0.7109148), Moment.ext_single.lane = c(0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, NA, 0.5367121), Moment.int_multi.lane = c(0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.664, 0.5874249),
Moment.int_single.lane = c(0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.431, 0.3718993)), class = "data.frame", row.names = c("Baseline",
"Sample1", "Sample2", "Sample3", "Sample4", "Sample5", "Sample6",
"Sample7", "Sample8", "Sample9", "Sample10", "AASHTO", "Mean"
)), structure(list(Moment.ext_multi.lane = c(0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.755, 0.7109148), Moment.ext_single.lane = c(0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, NA, 0.5367121), Moment.int_multi.lane = c(0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.664, 0.5874249),
Moment.int_single.lane = c(0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.431, 0.3718993)), class = "data.frame", row.names = c("Baseline",
"Sample1", "Sample2", "Sample3", "Sample4", "Sample5", "Sample6",
"Sample7", "Sample8", "Sample9", "Sample10", "AASHTO", "Mean"
)))
lst2 <- list(structure(list(Shear.ext_multi.lane = c(0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.755, 0.7109148), Shear.ext_single.lane = c(0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, NA, 0.5367121), Shear.int_multi.lane = c(0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.664, 0.5874249),
Shear.int_single.lane = c(0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.431, 0.3718993)), class = "data.frame", row.names = c("Baseline",
"Sample1", "Sample2", "Sample3", "Sample4", "Sample5", "Sample6",
"Sample7", "Sample8", "Sample9", "Sample10", "AASHTO", "Mean"
)), structure(list(Shear.ext_multi.lane = c(0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148, 0.7109148,
0.7109148, 0.7109148, 0.7109148, 0.755, 0.7109148), Shear.ext_single.lane = c(0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121, 0.5367121,
0.5367121, 0.5367121, 0.5367121, 0.5367121, NA, 0.5367121), Shear.int_multi.lane = c(0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.5874249,
0.5874249, 0.5874249, 0.5874249, 0.5874249, 0.664, 0.5874249),
Shear.int_single.lane = c(0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993, 0.3718993,
0.3718993, 0.3718993, 0.431, 0.3718993)), class = "data.frame", row.names = c("Baseline",
"Sample1", "Sample2", "Sample3", "Sample4", "Sample5", "Sample6",
"Sample7", "Sample8", "Sample9", "Sample10", "AASHTO", "Mean"
)))
推荐阅读
- php - 完全丢失 /Applications/XAMPP 文件夹 - 我该如何恢复？（XAMPP 和 Mac OSX 10.15.3）
- makefile - 在 CLion 中使用 CMake 生成然后使用源文件
- javascript - 如何修复加载不以角度显示
- selenium - 如何在元素中获取带引号的文本
- flutter - 如何根据flutter中的下拉选择显示json数据？
- javascript - Javascript .reduce()
- flutter - Flutter 命名路由名称重要吗？
- android - 限制 Firebase 实时数据库查询
- c# - 使用 Core 3.1 HttpClient.SendAsync 获得 304 响应
- swift - 如何检测 MapView (Swift) 中的用户交互