1

我有一个要重塑的数据框；我的重塑代码：

matchedlong <- reshape(matched, direction = 'long',
                       varying = c(29:33, 36:3943),
                       v.names = c("Math34", "TFCIn"),
                       times = 2006:2009, idvar = "schoolnum")

在matched第 36 到 39 列中是合乎逻辑的（TRUE FALSE），但matchedlong它们以某种方式变成了数字....没有明确的数字模式。

这是什么原因造成的？

样本数据：

example.data <- structure(list(Grade_Range_2008 = structure(c(14L, 14L, 40L,
40L, 36L, 13L), .Label = c("3-5, UE", "4-5, UE", "4-8, UE, US",
"5-10, UE, US", "5-8, 10, UE, US", "5-8, UE, US", "5-9, UE, US",
"6-11, US", "6-12, UE, US", "6-7, UE, US", "6-8, 10, UE, US",
"6-8, UE", "6-8, UE, US", "6-9, UE, US", "6, UE", "7-10, US",
"7-8, US", "8-Jun", "8-May", "K-3", "K-3, UE", "K-4, UE", "K-5",
"K-5, UE", "K-6, UE", "K-8", "K-8, UE", "K-8, UE, US", "K, 2-5, UE",
"N/A", "PK-3, UE", "PK-4, UE", "PK-5, 10, UE", "PK-5, 7-9, UE, US",
"PK-5, 8, UE", "PK-5, UE", "PK-6, 10, UE", "PK-6, UE", "PK-8, UE",
"PK-8, UE, US"), class = "factor"), X__of_Yrs_in_school = c(0L,
0L, 0L, 0L, 0L, 0L), Total_Enrollment_2008 = c(348L, 444L, 636L,
495L, 319L, 410L), Free_Lunch_pct_2008 = c(75L, 89L, 94L, 89L,
89L, 91L), Reduced_Lunch_pct_2008 = c(6L, 6L, 3L, 4L, 5L, 4L),
    Stability_pct_2008 = c(89L, 93L, 100L, 98L, 92L, 81L),
Limited_Eng__Prof__pct_2008 = c(8L,
    20L, 8L, 10L, 19L, 19L), Am__Ind_pct_2008 = c(1L, 2L, 0L,
    2L, 0L, 2L), Black_pct_2008 = c(41L, 39L, 28L, 33L, 32L,
    38L), Hispanic_pct_2008 = c(55L, 59L, 70L, 61L, 65L, 57L),
    Asian_pct_2008 = c(2L, 1L, 0L, 2L, 1L, 1L), White_pct_2008 = c(2L,
    0L, 1L, 2L, 1L, 2L), Multi_pct_2008 = c(0L, 0L, 0L, 0L, 0L,
    0L), w_o_Valid_Cert__N_2008 = c(4L, 0L, 1L, 0L, 1L, 1L),
    w_o_Valid_Cert__pct_2008 = c(11L, 0L, 2L, 0L, 3L, 5L),
Teaching_Out_of_Certification_N_ = c(7L,
    7L, 2L, 13L, 3L, 4L), Teaching_Out_of_Certification_pc = c(20L,
    15L, 4L, 25L, 9L, 18L), X_3_yrs__Exp_N_2008 = c(12L, 13L,
    5L, 12L, 5L, 5L), X_3_yrs__Exp_pct_2008 = c(34L, 28L, 11L,
    24L, 15L, 23L), Masters_Plus_N_2008 = c(6L, 11L, 15L, 10L,
    16L, 8L), Masters_Plus___2008 = c(17L, 23L, 32L, 20L, 47L,
    36L), Core_Classes_N_2008 = c(78L, 142L, 49L, 91L, 22L, 49L
    ), Core_Not_Taught_by_HQ_Teachers_p = c(23L, 6L, 2L, 24L,
    9L, 20L), Number_of_Classes_N_2008 = c(93L, 193L, 56L, 119L,
    33L, 68L), Clases_Not_taught_by_App__Cert__ = c(18L, 18L,
    2L, 37L, 3L, 13L), Clases_Not_taught_by_App__Cert_0 = c(19L,
    9L, 4L, 31L, 9L, 19L), Turnover_Rate_of_Teachers_with__ = c(31L,
    56L, 20L, 32L, 0L, 50L), Turnover_Rate_all_Teachers_pct_2 = c(42L,
    29L, 17L, 30L, 14L, 49L), Math_Level_3_4_pct_2006 = c(5.1,
    16.4, 58.2, 34.4, 48.9, 12.4), Math_Level_3_4_pct_2007 = c(15.2,
    22.1, 65.7, 29.9, 70.5, 22.6), Math_Level_3_4_pct_2008 = c(29.9,
    43.2, 69.8, 41.2, 78.9, 38.5), Math_Level_3_4_pct_2009 = c(50.7,
    49.7, 80.7, 47.1, 83.9, 51.6), Att__pct_2005 = c(0.83, 0.86,
    0.89, 0.9, 0.89, 0.87), Susp__pct_2005 = c(6L, 15L, 1L, 4L,
    0L, 3L), schoolnum = c(4013, 4045, 4096, 4101, 4102, 4117
    ), In_2006 = c(FALSE, FALSE, FALSE, FALSE, FALSE, FALSE),
    In_2007 = c(FALSE, FALSE, FALSE, FALSE, FALSE, FALSE), In_2008 = c(FALSE,
    FALSE, FALSE, FALSE, FALSE, FALSE), In_2009 = c(FALSE, FALSE,
    FALSE, FALSE, FALSE, FALSE), weights = c(1, 1, 1, 1, 1, 1
    )), .Names = c("Grade_Range_2008", "X__of_Yrs_in_school",
"Total_Enrollment_2008", "Free_Lunch_pct_2008", "Reduced_Lunch_pct_2008",
"Stability_pct_2008", "Limited_Eng__Prof__pct_2008", "Am__Ind_pct_2008",
"Black_pct_2008", "Hispanic_pct_2008", "Asian_pct_2008", "White_pct_2008",
"Multi_pct_2008", "w_o_Valid_Cert__N_2008", "w_o_Valid_Cert__pct_2008",
"Teaching_Out_of_Certification_N_", "Teaching_Out_of_Certification_pc",
"X_3_yrs__Exp_N_2008", "X_3_yrs__Exp_pct_2008", "Masters_Plus_N_2008",
"Masters_Plus___2008", "Core_Classes_N_2008",
"Core_Not_Taught_by_HQ_Teachers_p",
"Number_of_Classes_N_2008", "Clases_Not_taught_by_App__Cert__",
"Clases_Not_taught_by_App__Cert_0", "Turnover_Rate_of_Teachers_with__",
"Turnover_Rate_all_Teachers_pct_2", "Math_Level_3_4_pct_2006",
"Math_Level_3_4_pct_2007", "Math_Level_3_4_pct_2008",
"Math_Level_3_4_pct_2009",
"Att__pct_2005", "Susp__pct_2005", "schoolnum", "In_2006", "In_2007",
"In_2008", "In_2009", "weights"), row.names = c(1L, 4L, 7L, 8L,
11L, 12L), class = "data.frame")
4

1 回答 1

4

一列必须是一种数据类型；你不能混合逻辑和数字。

不确定如何对多种不同的数据类型进行“长时间”分析，因为通常这些是具有不同分组的相同变量。如果需要，请先尝试将逻辑值转换为数字（使用as.numeric）。

当您不使用该reshape软件包时，Hadley 在他对melt()执行相同任务的函数的讨论中指出了这一点（例如，请参阅本文）：

在[熔体]的当前实现中，熔体只有一个假设：所有测量值必须属于同一类型，例如，数字、因子、日期。我们需要这个假设，因为熔融数据存储在 R 数据框中，值列只能是一种类型。大多数情况下，这不是问题，因为在转换输出中组合不同类型的变量有意义的情况很少。

编辑：

我认为您可能正在尝试同时做两件事。这是你想要的吗？

a <- reshape(example.data[,-c(36:39)], direction = 'long', varying = c(29:32), v.names = c("Math34"), times = 2006:2009, idvar = "schoolnum")
b <- reshape(example.data[,-c(29:32)], direction = 'long', varying = c(36:39)-4, v.names = c("TFCIn"), times = 2006:2009, idvar = "schoolnum")
c <- merge(a,b)
于 2009-12-09T20:17:51.187 回答