Question

我有一个大约186,000行的大数据框，有27个变量。特定变量“价格”具有一些不正确的值。我需要为NA设置不正确的值，以便分析将忽略这些值，而其他值则可以。

我已将问题简化如下。输入输出也可供参考

dfCSV = structure(list(isin = structure(c(115L, 68L, 100L, 98L, 67L, 
78L, 81L), .Label = c("IN0019780025", "IN0019780074", "IN0019790024", 
"IN0019800021", "IN0019810020", "IN0019820037", "IN0019820128", 
"IN0019830010", "IN0019830143", "IN0019840035", "IN0019840084", 
"IN0019850034", "IN0019850059", "IN0019860033", "IN0019870073", 
"IN0019880031", "IN0019890030", "IN0019900045", "IN0019910036", 
"IN0019910044", "IN0019910127", "IN0019910192", "IN0019950164", 
"IN0019960056", "IN0019960098", "IN0019970014", "IN0019970121", 
"IN0019980021", "IN0019980047", "IN0019980062", "IN0019980096", 
"IN0019980120", "IN0019980153", "IN0019980187", "IN0019980229", 
"IN0019980286", "IN0019980336", "IN0019980344", "IN0019990012", 
"IN0019990038", "IN0019990129", "IN0019990137", "IN0020000025", 
"IN0020000033", "IN0020000041", "IN0020000066", "IN0020000074", 
"IN0020000082", "IN0020000090", "IN0020000108", "IN0020000116", 
"IN0020000124", "IN0020000132", "IN0020010016", "IN0020010024", 
"IN0020010032", "IN0020010040", "IN0020010057", "IN0020010065", 
"IN0020010073", "IN0020010081", "IN0020010099", "IN0020010107", 
"IN0020020015", "IN0020020023", "IN0020020031", "IN0020020049", 
"IN0020020056", "IN0020020064", "IN0020020072", "IN0020020080", 
"IN0020020098", "IN0020020106", "IN0020020122", "IN0020020130", 
"IN0020020155", "IN0020020163", "IN0020020171", "IN0020020213", 
"IN0020020221", "IN0020020247", "IN0020030014", "IN0020030022", 
"IN0020030030", "IN0020030048", "IN0020030055", "IN0020030063", 
"IN0020030097", "IN0020039015", "IN0020039031", "IN0020040013", 
"IN0020040039", "IN0020050012", "IN0020060037", "IN0020060045", 
"IN0020060078", "IN0020060086", "IN0020060219", "IN0020060318", 
"IN0020070010", "IN0020070028", "IN0020070036", "IN0020070044", 
"IN0020070051", "IN0020070069", "IN0020070077", "IN0020080019", 
"IN0020080043", "IN0020080050", "IN0020080068", "IN0020090018", 
"IN0020090026", "IN0020090034", "IN0020090042", "IN0020090059", 
"IN0020090067", "IN0020100015", "IN0020100023", "IN0020100031", 
"IN0020110014", "IN0020110022", "IN0020110030", "IN0020110048", 
"IN0020110055", "IN0020110063", "IN0020110071", "IN0020120013", 
"IN0020120021", "IN0020120039", "IN0020120047", "IN0020120054", 
"IN0020120062"), class = "factor"), tr_date = structure(c(14673, 
13272, 13731, 13515, 13578, 14705, 14155), class = "Date"), ytm = c(40.4806, 
85.041, 80.1207, 75.1705, 82.2098, 70.2422, 10.3402), price = c(25, 
10, 10, 10.19, 9.535, 9.18, 64)), .Names = c("isin", "tr_date", 
"ytm", "price"), row.names = c(11358L, 25878L, 29827L, 43679L, 
75310L, 124470L, 156240L), class = "data.frame")

以下行产生正确的输出，其中前六行的价格不正确。

> dfCSV[dfCSV$price < 66, c("isin", "tr_date", "ytm", "price")]
               isin    tr_date     ytm  price
11358  IN0020090059 2010-03-05 40.4806 25.000
25878  IN0020020056 2006-05-04 85.0410 10.000
29827  IN0020070010 2007-08-06 80.1207 10.000
43679  IN0020060219 2007-01-02 75.1705 10.190
75310  IN0020020049 2007-03-06 82.2098  9.535
124470 IN0020020171 2010-04-06 70.2422  9.180
156240 IN0020020247 2008-10-03 10.3402 64.000

将错误的价格设置为-1，输出符合预期

> dfCSV$price[dfCSV$price < 50] = -1
> dfCSV[dfCSV$price < 66, c("isin", "tr_date", "ytm", "price")]
               isin    tr_date     ytm price
11358  IN0020090059 2010-03-05 40.4806    -1
25878  IN0020020056 2006-05-04 85.0410    -1
29827  IN0020070010 2007-08-06 80.1207    -1
43679  IN0020060219 2007-01-02 75.1705    -1
75310  IN0020020049 2007-03-06 82.2098    -1
124470 IN0020020171 2010-04-06 70.2422    -1
156240 IN0020020247 2008-10-03 10.3402    64

现在不正确的价格（在这种情况下为-1）设置为NA并且地狱破裂了。

> dfCSV$price[dfCSV$price == -1] = NA
> dfCSV[dfCSV$price < 66, c("isin", "tr_date", "ytm", "price")]
               isin    tr_date     ytm price
NA             <NA>       <NA>      NA    NA
NA.1           <NA>       <NA>      NA    NA
NA.2           <NA>       <NA>      NA    NA
NA.3           <NA>       <NA>      NA    NA
NA.4           <NA>       <NA>      NA    NA
NA.5           <NA>       <NA>      NA    NA
156240 IN0020020247 2008-10-03 10.3402    64

我的问题是我在这里做错了什么导致行消失而不是将价格点作为NA。

我看到了一些建议使用lapply的帖子。就我而言，我只需要更改给定变量中的部分价格。在R中处理这个将有点棘手，而不是R-ish。我相信那里有一个优雅的解决方案。这将是了解更多R的好方法。

请帮我解决这个问题。问候

基肖尔

Answer 1

如果您与NA进行比较，则结果为NA，而不是TRUE或FALSE。这搞砸了你的子集。您可以使用dfCSV$price < 66 | is.na(dfCSV$price)（请注意NA | TRUE返回TRUE）。

dfCSV[dfCSV$price < 66 | is.na(dfCSV$price), c("isin", "tr_date", "ytm", "price")]
#                isin    tr_date     ytm price
# 11358  IN0020090059 2010-03-05 40.4806    NA
# 25878  IN0020020056 2006-05-04 85.0410    NA
# 29827  IN0020070010 2007-08-06 80.1207    NA
# 43679  IN0020060219 2007-01-02 75.1705    NA
# 75310  IN0020020049 2007-03-06 82.2098    NA
# 124470 IN0020020171 2010-04-06 70.2422    NA
# 156240 IN0020020247 2008-10-03 10.3402    64

将大数据帧列的某些元素设置为NA会将数据帧的所有列设置为NA

1 个答案: