【发布时间】：2019-04-11 21:42:46
【问题描述】：
我在呼叫中心工作，这些数据是我们自动拨号系统的所有相关数据。从 2019 年开始，我们公司开展了多项活动，以向会员提供多种可能的处方，而不是 1 种。
我们现在遇到的是成员 X 可能有 6 个处方，我们正试图联系他们，而且经常重复。收集所有这些数据的部门查看 IDCARD_MBR_ID 和 TARGET_DOC_ 列的唯一值，而不注意处方药名称。
我的目标是删除重复的处方药。并重新填充任何空出的空间
药物的顺序也不总是相同.. 一个简短的示例可能如下所示：
H0000000001 (member data columns) Target1, Target2
H0000000001 (same member data) Target3, Target1, Target2
我想看到的是：
H0000000001 (member data columns) Target1, Target2,Target3
我已经通过收集处理了我的数据，删除了重复项，将我的目标重新编号为 1-6（所以如果找到 >3，我可以创建一个新行）并将其展开。我的问题是我的传播.. 我得到的东西看起来像这样：
structure(list(IDCARD_MBR_ID = c("H0000000001", "H0000000001",
"H0000000001", "H0000000002", "H0000000002", "H0000000002", "H0000000003",
"H0000000003", "H0000000003", "H0000000004", "H0000000004", "H0000000004",
"H0000000005", "H0000000005", "H0000000005", "H0000000006", "H0000000006",
"H0000000006", "H0000000007", "H0000000007", "H0000000007", "H0000000008",
"H0000000008", "H0000000008", "H0000000009", "H0000000009", "H0000000009",
"H0000000010", "H0000000010", "H0000000010", "H0000000011", "H0000000011",
"H0000000011", "H0000000012", "H0000000012", "H0000000012"),
SDR_PERSON_ID = c("ID000000001", "ID000000001", "ID000000001",
"ID000000002", "ID000000002", "ID000000002", "ID000000003",
"ID000000003", "ID000000003", "ID000000004", "ID000000004",
"ID000000004", "ID000000005", "ID000000005", "ID000000005",
"ID000000006", "ID000000006", "ID000000006", "ID000000007",
"ID000000007", "ID000000007", "ID000000008", "ID000000008",
"ID000000008", "ID000000009", "ID000000009", "ID000000009",
"ID000000010", "ID000000010", "ID000000010", "ID000000011",
"ID000000011", "ID000000011", "ID000000012", "ID000000012",
"ID000000012"), FIRST_NAME = c("First1", "First1", "First1",
"First2", "First2", "First2", "First3", "First3", "First3",
"First4", "First4", "First4", "First5", "First5", "First5",
"First6", "First6", "First6", "First7", "First7", "First7",
"First8", "First8", "First8", "First9", "First9", "First9",
"First10", "First10", "First10", "First11", "First11", "First11",
"First12", "First12", "First12"), LAST_NAME = c("Last1",
"Last1", "Last1", "Last2", "Last2", "Last2", "Last3", "Last3",
"Last3", "Last4", "Last4", "Last4", "Last5", "Last5", "Last5",
"Last6", "Last6", "Last6", "Last7", "Last7", "Last7", "Last8",
"Last8", "Last8", "Last9", "Last9", "Last9", "Last10", "Last10",
"Last10", "Last11", "Last11", "Last11", "Last12", "Last12",
"Last12"), GENDER = c("F", "F", "F", "M", "M", "M", "M",
"M", "M", "F", "F", "F", "F", "F", "F", "F", "F", "F", "M",
"M", "M", "F", "F", "F", "F", "F", "F", "M", "M", "M", "F",
"F", "F", "F", "F", "F"), DOB = c("1901-01-01", "1901-01-01",
"1901-01-01", "1901-01-02", "1901-01-02", "1901-01-02", "1901-01-03",
"1901-01-03", "1901-01-03", "1901-01-04", "1901-01-04", "1901-01-04",
"1901-01-05", "1901-01-05", "1901-01-05", "1901-01-06", "1901-01-06",
"1901-01-06", "1901-01-07", "1901-01-07", "1901-01-07", "1901-01-08",
"1901-01-08", "1901-01-08", "1901-01-09", "1901-01-09", "1901-01-09",
"1901-01-10", "1901-01-10", "1901-01-10", "1901-01-11", "1901-01-11",
"1901-01-11", "1901-01-12", "1901-01-12", "1901-01-12"),
ADDRESS1 = c("123 Testing Way", "123 Testing Way", "123 Testing Way",
"456 Testing Way", "456 Testing Way", "456 Testing Way",
"789 Testing Way", "789 Testing Way", "789 Testing Way",
"1122 Testing Way", "1122 Testing Way", "1122 Testing Way",
"1455 Testing Way", "1455 Testing Way", "1455 Testing Way",
"1788 Testing Way", "1788 Testing Way", "1788 Testing Way",
"2121 Testing Way", "2121 Testing Way", "2121 Testing Way",
"2454 Testing Way", "2454 Testing Way", "2454 Testing Way",
"2787 Testing Way", "2787 Testing Way", "2787 Testing Way",
"3120 Testing Way", "3120 Testing Way", "3120 Testing Way",
"3453 Testing Way", "3453 Testing Way", "3453 Testing Way",
"3786 Testing Way", "3786 Testing Way", "3786 Testing Way"
), ADDRESS2 = c(NA, NA, NA, NA, NA, NA, "APT 302", "APT 302",
"APT 302", "APT 225", "APT 225", "APT 225", NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA), CITY = c("CLARKSVILLE", "CLARKSVILLE",
"CLARKSVILLE", "MONROE", "MONROE", "MONROE", "LOS ANGELES",
"LOS ANGELES", "LOS ANGELES", "TULSA", "TULSA", "TULSA",
"RED BUD", "RED BUD", "RED BUD", "MISSION VIEJO", "MISSION VIEJO",
"MISSION VIEJO", "MILLCREEK", "MILLCREEK", "MILLCREEK", "COLUMBIA",
"COLUMBIA", "COLUMBIA", "HOUSTON", "HOUSTON", "HOUSTON",
"APOPKA", "APOPKA", "APOPKA", "SEALY", "SEALY", "SEALY",
"SEWARD", "SEWARD", "SEWARD"), ST = c("IN", "IN", "IN", "MI",
"MI", "MI", "CA", "CA", "CA", "OK", "OK", "OK", "IL", "IL",
"IL", "CA", "CA", "CA", "UT", "UT", "UT", "MO", "MO", "MO",
"TX", "TX", "TX", "FL", "FL", "FL", "TX", "TX", "TX", "NE",
"NE", "NE"), ZIP = c(47129L, 47129L, 47129L, 48162L, 48162L,
48162L, 90028L, 90028L, 90028L, 74136L, 74136L, 74136L, 62278L,
62278L, 62278L, 92692L, 92692L, 92692L, 84124L, 84124L, 84124L,
65201L, 65201L, 65201L, 77057L, 77057L, 77057L, 32703L, 32703L,
32703L, 77474L, 77474L, 77474L, 68434L, 68434L, 68434L),
EMAIL_ADDRESS = c("Test-mail@test.com", "Test-mail@test.com",
"Test-mail@test.com", NA, NA, NA, NA, NA, NA, NA, NA, NA,
"Test-mail@test.com", "Test-mail@test.com", "Test-mail@test.com",
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, "Test-mail@test.com",
"Test-mail@test.com", "Test-mail@test.com", NA, NA, NA, NA,
NA, NA), PHONE1 = c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L,
4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 7L, 7L, 7L, 8L, 8L, 8L, 9L,
9L, 9L, 10L, 10L, 10L, 11L, 11L, 11L, 12L, 12L, 12L), ARG_CLIENT_NUM = c(6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L), FORMULARYID = c(19430L, 19430L, 19431L,
19431L, 19431L, 19430L, 19430L, 19430L, 19430L, 19430L, 19430L,
19430L, 19430L, 19430L, 19430L, 19431L, 19431L, 19431L, 19430L,
19430L, 19431L, 19431L, 19431L, 19430L, 19430L, 19430L, 19431L,
19430L, 19430L, 19430L, 19430L, 19430L, 19430L, 19430L, 19430L,
19431L), CAMPAIGN_TYPE = c("PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD"), LIS_INDICATOR = c("N",
"N", "N", "N", "N", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "Y",
"Y", "N", "N", "N", "N", "Y", "Y", "N", "N", "N", "N", "N",
"N", "N", "Y", "Y", "N", "Y", "Y", "Y", "Y", "Y", "N"), MONTH = c("February / DIALER",
"February / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "February / DIALER",
"February / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "February / DIALER", "January / DIALER",
"January / DIALER", "February / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "February / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER"), Calltype1 = c("Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings"), Calltype2 = c("Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings"), Calltype3 = c("Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings"), TARGET_DOC_1 = c("A000000000025001",
NA, NA, "A000000000026001", NA, NA, "A000000000027001", NA,
NA, "A000000000028001", NA, NA, "A000000000029001", NA, NA,
"A000000000030001", NA, NA, "A000000000031001", NA, NA, "A000000000032001",
NA, NA, "A000000000033001", NA, NA, "A000000000034001", NA,
NA, "A000000000035001", NA, NA, "A000000000036001", NA, NA
), TARGET_DOC_2 = c(NA, "A000000000013001", NA, NA, "A000000000014001",
NA, NA, "A000000000015001", NA, NA, "A000000000016001", NA,
NA, "A000000000017001", NA, NA, "A000000000018001", NA, NA,
"A000000000019001", NA, NA, "A000000000020001", NA, NA, "A000000000021001",
NA, NA, "A000000000022001", NA, NA, "A000000000023001", NA,
NA, "A000000000024001", NA), TARGET_DOC_3 = c(NA, NA, "A000000000001001",
NA, NA, "A000000000002001", NA, NA, "A000000000003001", NA,
NA, "A000000000004001", NA, NA, "A000000000005001", NA, NA,
"A000000000006001", NA, NA, "A000000000007001", NA, NA, "A000000000008001",
NA, NA, "A000000000009001", NA, NA, "A000000000010001", NA,
NA, "A000000000011001", NA, NA, "A000000000012001"), TARGET_DRUG_ID_1 = c(57237014401,
NA, NA, 65862058301, NA, NA, 57237014301, NA, NA, 68180075701,
NA, NA, 65862058401, NA, NA, 55111033901, NA, NA, 65862058201,
NA, NA, 65862058405, NA, NA, 65862058601, NA, NA, 68180075801,
NA, NA, 65862058601, NA, NA, 68180076001, NA, NA), TARGET_DRUG_ID_2 = c(NA,
57237014401, NA, NA, 65862058301, NA, NA, 57237014301, NA,
NA, 68180075701, NA, NA, 65862058401, NA, NA, 55111033901,
NA, NA, 65862058201, NA, NA, 65862058405, NA, NA, 65862058601,
NA, NA, 68180075801, NA, NA, 65862058601, NA, NA, 68180076001,
NA), TARGET_DRUG_ID_3 = c(NA, NA, 65862058701, NA, NA, 65862058701,
NA, NA, 55111034001, NA, NA, 65862058601, NA, NA, 65862058701,
NA, NA, 55111034001, NA, NA, 65862058401, NA, NA, 65862058405,
NA, NA, 68180047301, NA, NA, 68180075801, NA, NA, 65862058701,
NA, NA, 65862058301), TARGET_NAME_1 = c("Target11", NA, NA,
"Target12", NA, NA, "Target13", NA, NA, "Target14", NA, NA,
"Target15", NA, NA, "Target16", NA, NA, "Target17", NA, NA,
"Target18", NA, NA, "Target19", NA, NA, "Target20", NA, NA,
"Target21", NA, NA, "Target22", NA, NA), TARGET_NAME_2 = c(NA,
"Target21", NA, NA, "Target22", NA, NA, "Target23", NA, NA,
"Target24", NA, NA, "Target25", NA, NA, "Target26", NA, NA,
"Target27", NA, NA, "Target28", NA, NA, "Target29", NA, NA,
"Target30", NA, NA, "Target31", NA, NA, "Target32", NA),
TARGET_NAME_3 = c(NA, NA, "Target31", NA, NA, "Target32",
NA, NA, "Target33", NA, NA, "Target34", NA, NA, "Target35",
NA, NA, "Target36", NA, NA, "Target37", NA, NA, "Target38",
NA, NA, "Target39", NA, NA, "Target40", NA, NA, "Target41",
NA, NA, "Target42")), class = "data.frame", row.names = c(NA,
-36L))}
每组目标都在自己的行中.. 我不知道如何折叠它们并删除 NA，所以我最终得到的结果如下所示：
structure(list(IDCARD_MBR_ID = c("H0000000001", "H0000000002",
"H0000000003", "H0000000004", "H0000000005", "H0000000006", "H0000000007",
"H0000000008", "H0000000009", "H0000000010", "H0000000011", "H0000000012"
), SDR_PERSON_ID = c("ID000000001", "ID000000002", "ID000000003",
"ID000000004", "ID000000005", "ID000000006", "ID000000007", "ID000000008",
"ID000000009", "ID000000010", "ID000000011", "ID000000012"),
FIRST_NAME = c("First1", "First2", "First3", "First4", "First5",
"First6", "First7", "First8", "First9", "First10", "First11",
"First12"), LAST_NAME = c("Last1", "Last2", "Last3", "Last4",
"Last5", "Last6", "Last7", "Last8", "Last9", "Last10", "Last11",
"Last12"), GENDER = c("F", "M", "M", "F", "F", "F", "M",
"F", "F", "M", "F", "F"), DOB = c("1/1/1901", "1/2/1901",
"1/3/1901", "1/4/1901", "1/5/1901", "1/6/1901", "1/7/1901",
"1/8/1901", "1/9/1901", "1/10/1901", "1/11/1901", "1/12/1901"
), ADDRESS1 = c("123 Testing Way", "456 Testing Way", "789 Testing Way",
"1122 Testing Way", "1455 Testing Way", "1788 Testing Way",
"2121 Testing Way", "2454 Testing Way", "2787 Testing Way",
"3120 Testing Way", "3453 Testing Way", "3786 Testing Way"
), ADDRESS2 = c(NA, NA, "APT 302", "APT 225", NA, NA, NA,
NA, NA, NA, NA, NA), CITY = c("CLARKSVILLE", "MONROE", "LOS ANGELES",
"TULSA", "RED BUD", "MISSION VIEJO", "MILLCREEK", "COLUMBIA",
"HOUSTON", "APOPKA", "SEALY", "SEWARD"), ST = c("IN", "MI",
"CA", "OK", "IL", "CA", "UT", "MO", "TX", "FL", "TX", "NE"
), ZIP = c(47129L, 48162L, 90028L, 74136L, 62278L, 92692L,
84124L, 65201L, 77057L, 32703L, 77474L, 68434L), EMAIL_ADDRESS = c("Test-mail@test.com",
NA, NA, NA, "Test-mail@test.com", NA, NA, NA, NA, "Test-mail@test.com",
NA, NA), PHONE1 = 1:12, ARG_CLIENT_NUM = c(6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L), FORMULARYID = c(19430L,
19431L, 19430L, 19430L, 19430L, 19431L, 19430L, 19431L, 19430L,
19430L, 19430L, 19430L), CAMPAIGN_TYPE = c("PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD",
"PDP_Lean MAPD", "PDP_Lean MAPD", "PDP_Lean MAPD"), LIS_INDICATOR = c("N",
"N", "Y", "Y", "Y", "N", "Y", "N", "N", "Y", "Y", "Y"), MONTH = c("February / DIALER",
"January / DIALER", "February / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER", "January / DIALER",
"January / DIALER", "January / DIALER"), Calltype1 = c("Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings"), Calltype2 = c("Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings"), Calltype3 = c("Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings", "Cost Savings",
"Cost Savings", "Cost Savings", "Cost Savings"), TARGET_DOC_1 = c("A000000000025001",
"A000000000026001", "A000000000027001", "A000000000028001",
"A000000000029001", "A000000000030001", "A000000000031001",
"A000000000032001", "A000000000033001", "A000000000034001",
"A000000000035001", "A000000000036001"), TARGET_DOC_2 = c("A000000000013001",
"A000000000014001", "A000000000015001", "A000000000016001",
"A000000000017001", "A000000000018001", "A000000000019001",
"A000000000020001", "A000000000021001", "A000000000022001",
"A000000000023001", "A000000000024001"), TARGET_DOC_3 = c("A000000000001001",
"A000000000002001", "A000000000003001", "A000000000004001",
"A000000000005001", "A000000000006001", "A000000000007001",
"A000000000008001", "A000000000009001", "A000000000010001",
"A000000000011001", "A000000000012001"), TARGET_DRUG_ID_1 = c(57237014401,
65862058301, 57237014301, 68180075701, 65862058401, 55111033901,
65862058201, 65862058405, 65862058601, 68180075801, 65862058601,
68180076001), TARGET_DRUG_ID_2 = c(57237014401, 65862058301,
57237014301, 68180075701, 65862058401, 55111033901, 65862058201,
65862058405, 65862058601, 68180075801, 65862058601, 68180076001
), TARGET_DRUG_ID_3 = c(65862058701, 65862058701, 55111034001,
65862058601, 65862058701, 55111034001, 65862058401, 65862058405,
68180047301, 68180075801, 65862058701, 65862058301), TARGET_NAME_1 = c("Target11",
"Target12", "Target13", "Target14", "Target15", "Target16",
"Target17", "Target18", "Target19", "Target20", "Target21",
"Target22"), TARGET_NAME_2 = c("Target21", "Target22", "Target23",
"Target24", "Target25", "Target26", "Target27", "Target28",
"Target29", "Target30", "Target31", "Target32"), TARGET_NAME_3 = c("Target31",
"Target32", "Target33", "Target34", "Target35", "Target36",
"Target37", "Target38", "Target39", "Target40", "Target41",
"Target42")), class = "data.frame", row.names = c(NA, -12L
))
我一直在研究类似的问题，例如： 折叠重复的行 Collapse duplicated rows with different values in few columns using R
我最大的问题是我的列数太多了（必然..所有行都需要保持在一起以保持完整性）我很快就会迷路。
编辑 1：添加 DF 的“head(12)”（注意 DF 非常宽，很难粘贴以保持格式。这是受问题影响的列）...另外，不知道为什么在这个测试数据有些不适用，有些不适用。在我的真实数据中，它们是真正的缺失值不适用。
Calltype3 TARGET_DOC_1 TARGET_DOC_2 TARGET_DOC_3 TARGET_DRUG_ID_1 TARGET_DRUG_ID_2 TARGET_DRUG_ID_3
1 Cost Savings A000000000025001 <NA> <NA> 57237014401 NA NA
2 Cost Savings <NA> A000000000013001 <NA> NA 57237014401 NA
3 Cost Savings <NA> <NA> A000000000001001 NA NA 65862058701
4 Cost Savings A000000000026001 <NA> <NA> 65862058301 NA NA
5 Cost Savings <NA> A000000000014001 <NA> NA 65862058301 NA
6 Cost Savings <NA> <NA> A000000000002001 NA NA 65862058701
7 Cost Savings A000000000027001 <NA> <NA> 57237014301 NA NA
8 Cost Savings <NA> A000000000015001 <NA> NA 57237014301 NA
9 Cost Savings <NA> <NA> A000000000003001 NA NA 55111034001
10 Cost Savings A000000000028001 <NA> <NA> 68180075701 NA NA
11 Cost Savings <NA> A000000000016001 <NA> NA 68180075701 NA
12 Cost Savings <NA> <NA> A000000000004001 NA NA 65862058601
TARGET_NAME_1 TARGET_NAME_2 TARGET_NAME_3
1 Target11 <NA> <NA>
2 <NA> Target21 <NA>
3 <NA> <NA> Target31
4 Target12 <NA> <NA>
5 <NA> Target22 <NA>
6 <NA> <NA> Target32
7 Target13 <NA> <NA>
8 <NA> Target23 <NA>
9 <NA> <NA> Target33
10 Target14 <NA> <NA>
11 <NA> Target24 <NA>
12 <NA> <NA> Target34
编辑 4：根据 Humpelstielzchen 的建议，我运行了这个： 我的点差 DF = spread1
spread2 <- spread1 %>%
group_by(IDCARD_MBR_ID) %>%
mutate(MONTH = MONTH[row_number()==1],
FORMULARYID = FORMULARYID[row_number()==1],
LIS_INDICATOR = LIS_INDICATOR[row_number() ==1]) %>%
group_by_at(vars(-starts_with("TARGET"))) %>%
summarise_at(vars(starts_with("TARGET")), list(. = ~.[which(!is.na(.))[1]]))
而且它似乎工作正常；我有一个超过 100 万个起始行的数据框，这帮助我减少到了 ~600k；我需要一点时间来验证准确性，但看起来很棒！
【问题讨论】：
-
对于这么长的
structure对象，您能显示数据的样子吗（例如head()）？ -
我会争取尽快拿到head()；我在我父母家吃晚饭，但是当我回到家时，我会看看.. 上面的 R 结构已经是一个缩短的 Head(24) （但有 30 多列）.. 我想要足够的行来显示我所指的模式在没有完全压倒任何人的情况下.. 看来我需要进一步缩短它:)
-
不，您不需要缩短它们。使用
head打印出来时只需发布前几行，这样其他人就可以看到格式，而无需将structure复制并粘贴到他们自己的R工作区中 -
我添加了 head(12).. 格式很难在 DF 上保持这么宽，所以我只将受影响的 DF 最右侧的列发布。
-
看看这个stackoverflow.com/a/52524260/786542。可能会有所帮助
标签： r data.table tidyr microsoft-r