Question

我正在尝试根据部分字符串匹配合并两个相当大的不同大小的数据帧。

df1 $ code包含所有12位数字代码，而df2 $ code包含10-12位数字的混合代码，其中一些较短的代码与df1 $ code中的12位数代码匹配。

因此，我需要合并两个数据帧之间的所有12位数匹配，以及df2中那些具有10-11位代码的子记录与df1匹配的记录。

示例数据框：

df1 <- data.frame(code_1 = c('123456789012', '210987654321', '567890543211', '987656789001', '123456654321', '678905432156', '768927461037', '780125634701', '673940175372', '167438501473'),
              name = c('bob','joe','sally','john','lucy','alan', 'fred','stephanie','greg','tom'))

df2 <- data.frame(code_2 = c('123456789012','2109876543','7890543211','98765678900','12345665432','678905432156'),
              color = c('blue', 'red', 'green', 'purple', 'orange', 'brown'))

df3 (merged)

code_1         code_2         name  color
123456789012   123456789012   bob   blue
210987654321   2109876543     joe   red
567890543211   7890543211     sally green
987656789001   98765678900    john  purple
123456654321   12345665432    lucy  orange
678905432156   678905432156   alan  brown

Answer 1

尝试此SQL连接。

library(sqldf)

sqldf("select a.code_1, b.code_2, a.name, b.color 
       from df2 b left join df1 a on a.code_1 like '%' || b.code_2 || '%'")

，并提供：

        code_1       code_2  name  color
1 123456789012 123456789012   bob   blue
2 210987654321   2109876543   joe    red
3 567890543211   7890543211 sally  green
4 987656789001  98765678900  john purple
5 123456654321  12345665432  lucy orange
6 678905432156 678905432156  alan  brown

更新：更新了答案以反映有争议的更改，以便（1）子字符串可以位于目标字符串中的任何位置，（2）代码列的名称已更改为code_1和code_2。

Answer 2

根据新信息更新。这应该有效：

df2$New <- lapply(df2$code_2, grep, df1$code_1,value=T)

combined <- merge(df1,df2, by.x="code_1", by.y="New")

        code_1  name       code_2  color
1 123456654321  lucy  12345665432 orange
2 123456789012   bob 123456789012   blue
3 210987654321   joe   2109876543    red
4 567890543211 sally   7890543211  green
5 678905432156  alan 678905432156  brown
6 987656789001  john  98765678900 purple

Answer 3

我们可以使用grep + sapply从df2$code中为每个df1$code提取匹配的索引，并从中创建matchID。接下来，我们在merge上matchID获得所需的输出：

df1$matchID = row.names(df1)
df2$matchID = sapply(df2$code, function(x) grep(x, df1$code))

df_merge = merge(df1, df2, by = "matchID")[-1]

请注意，如果df1$code与任何df2$code不匹配，则df2$matchID将为空，因此不会与df1$matchID合并。

<强>结果：

> df2
          code  color matchID
1 123456789012   blue       1
2   2109876543    red       2
3   7890543211  green       3
4  98765678900 purple       4
5  12345665432 orange       5
6 678905432156  brown       6
7  14124124124  black        

> df_merge
        code.x  name       code.y  color
1 123456789012   bob 123456789012   blue
2 210987654321   joe   2109876543    red
3 567890543211 sally   7890543211  green
4 987656789001  john  98765678900 purple
5 123456654321  lucy  12345665432 orange
6 678905432156  alan 678905432156  brown

数据（为了更好的演示添加了不匹配）：

df1 <- data.frame(code = c('123456789012', '210987654321', '567890543211', '987656789001', '123456654321', '678905432156', '768927461037', '780125634701', '673940175372', '167438501473'),
                  name = c('bob','joe','sally','john','lucy','alan', 'fred','stephanie','greg','tom'),
                  stringsAsFactors = FALSE)

df2 <- data.frame(code = c('123456789012','2109876543','7890543211','98765678900','12345665432','678905432156', '14124124124'),
                  color = c('blue', 'red', 'green', 'purple', 'orange', 'brown', 'black'),
                  stringsAsFactors = FALSE)

Answer 4

在python / pandas中，你可以这样做：

from pandas import DataFrame, Series
df1 = DataFrame(dict(
        code1 = ('123456789012', '210987654321', '567890543211', '987656789001', '123456654321', '678905432156', '768927461037', '780125634701', '673940175372', '167438501473'),
        name = ('bob','joe','sally','john','lucy','alan', 'fred','stephanie','greg','tom')))

df2 = DataFrame(dict(
        code2 = ('123456789012','2109876543','7890543211','98765678900','12345665432','678905432156'),
        color = ('blue', 'red', 'green', 'purple', 'orange', 'brown')))

matches = [df1[df1['code1'].str.contains(x)].index[0] for x in df2['code2']]

print(
    df1.assign(subcode=Series(data=df2['code2'], index=matches))
       .merge(df2, left_on='subcode', right_on='code2')
       .drop('subcode', axis='columns')
)

那个转储：

          code1   name         code2   color
0  123456789012    bob  123456789012    blue
1  210987654321    joe    2109876543     red
2  567890543211  sally    7890543211   green
3  987656789001   john   98765678900  purple
4  123456654321   lucy   12345665432  orange
5  678905432156   alan  678905432156   brown

注意：我讨厌使用带有数据帧的循环，但是这个，呃，有用了。

通过部分字符串匹配合并两个数据帧

4 个答案: