具有多个条件的子集 Data.Frame

Question

最终目标：

为从第 1:167 行开始的日期范围内的 StressCumulative、BaseCumulative、StressQoQ 和 BaseQoQ 的每个区域创建一个图。

问题：

我在对我的 data.frame 进行子集化时遇到了困难。我的问题是我进行子集化的条件是合乎逻辑的，因此只会返回条件之后的第一个元素。

subset_region_1 <- subset.data.frame(HPF, HPF$region == 1, select = BaseCumulative, HPF$StressCumulative, StressQoQ, BaseQoQ)

Warning messages:
1: In if (drop) warningc("drop ignored") :
  the condition has length > 1 and only the first element will be used
2: drop ignored 

这仅返回第一列 BaseCumulative。

数据：

在这里，您可以了解我正在处理的内容。这是我要从中提取子集的表。我的 data.frame 格式很高

我想创建一个子集，以便在第 1:167 行的日期范围内绘制 BaseCumulative、StressCumulative、BaseQoQ 和 StressQoQ 变量的图表。日期列对所有 100 个区域使用相同的日期。我的问题是，当我在 ggplot 中绘图时，我收到一个错误，即我的 aes 映射大小不同。完整表的 date = 18370 行长，但值每 167 行重复一次（对于每个唯一区域）。此外，BaseCumulative 变量也是 18370 行长，但对所有区域都是唯一的，即每 167 行。我想知道如何按区域进行子集化，同时为我有兴趣测量的变量获取正确的行大小。

数据点：

#Rows 1-3 (Region 1 Sample): 
dput(head(HPF[1:3, ]))
    structure(list(region = c(1, 1, 1), path = c(1, 1, 1), date = c(20140215, 
    20140515, 20140815), index_value = c(1, 1.033852765, 1.041697122
    ), index = 0:2, counter = 1:3, BaseQoQ = c(NA, 0.033852765, 0.00758749917354029
    ), BaseCumulative = c(100, 103.3852765, 104.1697122), StressCumulative = c(110, 
    113.3852765, 114.1697122), StressQoQ = c(NA, 0.0307752409090909, 
    0.00691832065162346)), .Names = c("region", "path", "date", "index_value", 
    "index", "counter", "BaseQoQ", "BaseCumulative", "StressCumulative", 
    "StressQoQ"), row.names = c(NA, -3L), class = c("tbl_df", "tbl", 
    "data.frame"))

#Rows 168:200 (Region 2 Sample):
dput(head(HPF[168:200, ]))
    structure(list(region = c(2, 2, 2, 2, 2, 2), path = c(1, 1, 1, 
    1, 1, 1), date = c(20140215, 20140515, 20140815, 20141115, 20150215, 
    20150515), index_value = c(1, 1.014162265, 1.01964828, 1.009372314, 
    1.007210703, 1.018695493), index = 0:5, counter = 1:6, BaseQoQ = c(NA, 
    0.014162265, 0.00540940556489744, -0.0100779515854232, -0.0021415398163972, 
    0.0114025694582001), BaseCumulative = c(100, 101.4162265, 101.964828, 
    100.9372314, 100.7210703, 101.8695493), StressCumulative = c(110, 
    111.4162265, 111.964828, 110.9372314, 110.7210703, 101.8695493
    ), StressQoQ = c(NA, 0.0128747863636363, 0.00492389230216839, 
    -0.00917785181610786, -0.00194849914020834, -0.0799443229370588
    )), .Names = c("region", "path", "date", "index_value", "index", 
    "counter", "BaseQoQ", "BaseCumulative", "StressCumulative", "StressQoQ"
    ), row.names = c(NA, -6L), class = c("tbl_df", "tbl", "data.frame"
    ))

问题：

除了指定 region == # 之外，我如何对其他列进行子集化？我尝试了以下方法，但问题是日期的值循环并且我的图表不正确：

ggplot(HPF, aes(x = date, y= BaseCumulative, linetype = factor(region == 1))) + 
  geom_line() +
  theme_light()

此外，如果我尝试在 ggplot 中进行子集化，例如：

ggplot(HPF[HPF$region == 1, ], aes(x = HPF$date[1:167, ], y= HPF$BaseCumulative[1:167, ], linetype = factor(region == 1))) + 
      geom_line() +
      theme_light()

感谢任何帮助。

Answer 1

我不完全确定你想在情节中展示什么；这就是你所追求的吗？

library(tidyverse);
df %>%
    gather(what, value, 7:10) %>%
    ggplot(aes(date, value, colour = what)) + geom_line() + theme_light()

说明：将数据从宽格式转换为长格式，然后将what 作为colour（或linetype）美学传递，以便在一个图中为7, 8, 9, 10 列获得不同的线图。

---

如果您想为region 单独绘制图，您可以添加+ facet_wrap(~ as.factor(region))，例如

df %>%
    gather(what, value, 7:10) %>%
    ggplot(aes(date, value, colour = what)) + geom_line() + theme_light() + facet_wrap(~ as.factor(region))

---

样本数据

df1 <- structure(list(region = c(1, 1, 1), path = c(1, 1, 1), date = c(20140215,
    20140515, 20140815), index_value = c(1, 1.033852765, 1.041697122
    ), index = 0:2, counter = 1:3, BaseQoQ = c(NA, 0.033852765, 0.00758749917354029
    ), BaseCumulative = c(100, 103.3852765, 104.1697122), StressCumulative = c(110,
    113.3852765, 114.1697122), StressQoQ = c(NA, 0.0307752409090909,
    0.00691832065162346)), .Names = c("region", "path", "date", "index_value",
    "index", "counter", "BaseQoQ", "BaseCumulative", "StressCumulative",
    "StressQoQ"), row.names = c(NA, -3L), class = c("tbl_df", "tbl",
    "data.frame"));

df2 <- structure(list(region = c(2, 2, 2, 2, 2, 2), path = c(1, 1, 1,
    1, 1, 1), date = c(20140215, 20140515, 20140815, 20141115, 20150215,
    20150515), index_value = c(1, 1.014162265, 1.01964828, 1.009372314,
    1.007210703, 1.018695493), index = 0:5, counter = 1:6, BaseQoQ = c(NA,
    0.014162265, 0.00540940556489744, -0.0100779515854232, -0.0021415398163972,
    0.0114025694582001), BaseCumulative = c(100, 101.4162265, 101.964828,
    100.9372314, 100.7210703, 101.8695493), StressCumulative = c(110,
    111.4162265, 111.964828, 110.9372314, 110.7210703, 101.8695493
    ), StressQoQ = c(NA, 0.0128747863636363, 0.00492389230216839,
    -0.00917785181610786, -0.00194849914020834, -0.0799443229370588
    )), .Names = c("region", "path", "date", "index_value", "index",
    "counter", "BaseQoQ", "BaseCumulative", "StressCumulative", "StressQoQ"
    ), row.names = c(NA, -6L), class = c("tbl_df", "tbl", "data.frame"
    ))

df <- rbind.data.frame(df1, df2);