R - Predict()，重命名列，并且“有 10 行但找到的变量有 20 行”
R - Predict(), renaming columns, and " had 10 rows but variables found have 20 rows "
在其他帖子中，我看到人们提供了针对具体问题的解决方案，但我不明白出现问题的根本原因。
我愿意...
modTest = glm( trainLabels[,1] ~ A + B + C +
D + E + F + G +
H + I, family=binomial(link='logit') )
以上是 20 个标签，9 个向量，每个向量有 20 个值。
然后我尝试预测 10 个未见过的例子。这是 10 行，9 个特征，相同的顺序。
preds = predict( modTest, testFeatures )
我收到错误...
Warning message:
'newdata' had 10 rows but variables found have 20 rows
编辑：简化、删除长特征名称等
> names(trainFeatures)
[1] "Neg" "Pos" "Num" "UN" "UNA" "UNUA" "UP" "UPA" "UPUA"
names(testFeatures)
[1] "Neg" "Pos" "Num" "UN" "UNA" "UNUA" "UP" "UPA" "UPUA"
编辑：Dputs...
为了使用输出，我所做的是...
modTest = glm( trainLabels[,1] ~ as.matrix(trainFeatures) )
preds = predict( modTest, testFeatures )
Warning message:
'newdata' had 10 rows but variables found have 20 rows
不确定为什么我仍然收到该警告。
dput(trainLabels)
structure(list(Neg = c(1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,
0, 0, 0, 1, 1, 1, 0), Pos = c(1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1,
1, 1, 0, 0, 0, 1, 1, 1, 0), Num = c(1, 1, 0, 0, 0, 0, 1, 0, 0,
0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UN = c(1, 1, 0, 0, 0, 0, 1,
0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UNA = c(1, 1, 0, 0, 0,
0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UNUA = c(1, 1,
0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UP = c(1,
1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UPA = c(1,
1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UPUA = c(1,
1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0)), .Names = c("Neg",
"Pos", "Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-20L), class = "data.frame")
dput(trainFeatures)
structure(list(Neg = c(39106, 44664, 114130, 26526, 22122, 19175,
29438, 17741, 17589, 20666, 66024, 168336, 86283, 74826, 88998,
75756, 16041, 17087, 15235, 16659), Pos = c(16129, 21064, 57730,
10314, 18105, 16837, 19300, 16873, 13681, 18414, 27148, 120497,
60031, 49016, 59250, 36264, 15786, 16315, 14556, 16057), Num = c(82994,
121367, 306842, 55458, 69148, 63167, 85891, 58674, 55874, 67505,
152475, 427106, 221043, 190043, 223744, 177388, 51657, 54883,
48378, 54115), UN = c(32343, 35433, 74835, 22271, 17686, 15498,
22416, 14238, 14078, 16800, 54636, 121211, 68079, 59913, 70884,
61408, 13221, 14114, 12647, 13487), UNA = c(95.1499874, 95.0987263,
95.3942596, 95.5444865, 113.1263844, 112.3827424, 111.2684513,
113.2184128, 112.4336258, 114.1739588, 113.5086472, 111.6715378,
112.2842917, 111.9490612, 113.6465561, 111.5254103, 112.2179148,
111.2933853, 112.9056117, 113.1511475), UNUA = c(-94.4280737,
-94.5019854, -94.9246672, -95.0379578, -113.2247115, -112.3497485,
-111.1631387, -113.2051289, -112.1822898, -114.0431466, -113.7435412,
-111.6226818, -112.4077795, -111.9886653, -113.8072166, -111.6138577,
-113.0855995, -112.3075275, -114.2628431, -114.1088453), UP = c(10384,
13015, 24470, 6891, 13445, 12852, 13008, 13093, 9878, 14272,
14938, 77058, 40595, 32518, 39889, 21424, 8322, 8451, 7440, 8071
), UPA = c(58.6289931, 57.73430079, 61.3480343, 57.8297594, 62.1749994,
65.1140073, 62.619361, 63.6791219, 63.412582, 65.1856906, 45.18365794,
71.32918265, 56.04488913, 58.13008276, 53.16603128, 50.36242011,
64.6742956, 64.0982314, 63.4422878, 64.24099034), UPUA = c(88.9216885,
88.3012858, 88.1996008, 88.9910129, 91.0232669, 89.4524702, 91.9122816,
89.8549338, 90.6487273, 88.2063941, 99.9573821, 109.9128868,
103.7989926, 104.0274764, 103.4209936, 101.5065677, 85.8110039,
87.0786241, 86.1020646, 86.8835026)), .Names = c("Neg", "Pos",
"Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-20L), class = "data.frame")
dput(testLabels)
structure(list(Neg = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1), Pos = c(0,
1, 1, 1, 0, 1, 1, 1, 1, 1), Num = c(0, 1, 1, 1, 0, 1, 1, 1, 1,
1), UN = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1), UNA = c(0, 1, 1, 1,
0, 1, 1, 1, 1, 1), UNUA = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1), UP = c(0,
1, 1, 1, 0, 1, 1, 1, 1, 1), UPA = c(0, 1, 1, 1, 0, 1, 1, 1, 1,
1), UPUA = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1)), .Names = c("Neg",
"Pos", "Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-10L), class = "data.frame")
> dput(testFeatures)
structure(list(Neg = c(51404, 32447, 24642, 95979, 15743, 90843,
13813, 11496, 12871, 13546), Pos = c(23350, 13525, 19941, 49984,
10867, 64404, 13324, 11302, 12918, 13118), Num = c(121342, 68160,
77219, 248890, 49259, 232645, 43707, 35674, 40734, 42979), UN = c(40766,
27363, 19590, 71772, 12615, 71496, 11529, 9739, 10810, 11346),
UNA = c(95.2486872, 93.4642772, 111.3853297, 112.6770471,
110.0845355, 113.6696598, 111.8409793, 116.0476022, 120.3481302,
111.9496978), UNUA = c(-94.6150698, -92.5605373, -111.1994432,
-112.4947319, -109.7130777, -113.8083912, -112.5678322, -116.5407619,
-121.4756386, -113.4991191), UP = c(14285, 9043, 14862, 31626,
7491, 43903, 7021, 5559, 6149, 6789), UPA = c(61.25585053,
62.6231081, 64.191128, 64.6397131, 63.4911744, 58.4792454,
63.5063289, 60.5667637, 60.3857056, 64.1569975), UPUA = c(88.4605419,
88.2790682, 90.0217465, 88.8441004, 91.0222662, 105.0494229,
85.8914139, 86.7685668, 84.8304901, 86.9786109)), .Names = c("Neg",
"Pos", "Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-10L), class = "data.frame")
所以，我 运行 使用您提供的所有数据编写代码并得到很好的结果。这是模型拟合：
modTest = glm(trainLabels[,1] ~ Neg + Pos + Num +
UN + UNA + UNUA + UP +
UPA + UPUA, family=binomial(link='logit'),
data = trainFeatues)
以下是测试数据的预测值：
predict( modTest, testFeatures)
1 2 3 4 5 6 7 8
4.6711576 -1.3572345 -2.0639104 18.7625539 -7.6961149 0.4317324 -0.8983256 -8.2052158
9 10
-1.5968013 10.8357174
注意：替代规范可以是这样的：
modTest = glm(trainLabels[,1] ~ trainFeatues$Neg + trainFeatues$Pos +
trainFeatues$Num + trainFeatues$UN + trainFeatues$UNA +
trainFeatues$UNUA + trainFeatues$UP + trainFeatues$UPA +
trainFeatues$UPUA, family=binomial(link='logit'))
但是拟合模型如下：
modTest$coefficients
(Intercept) trainFeatues$Neg trainFeatues$Pos trainFeatues$Num trainFeatues$UN
4.027803e+01 8.874801e-04 -3.000123e-03 1.277138e-04 -4.521793e-04
trainFeatues$UNA trainFeatues$UNUA trainFeatues$UP trainFeatues$UPA trainFeatues$UPUA
-1.519463e+01 -1.480503e+01 2.930261e-03 4.741432e-01 -3.690940e-01
当您输入训练数据进行预测时，这会导致问题，因为上面拟合的特征与输入的新数据不匹配进行预测。导致：
predict( modTest, testFeatures)
1 2 3 4 5 6 7
0.21651890 3.23450117 -2.16298672 -0.06949967 -0.91026504 -0.91484739 -1.69209826
8 9 10 11 12 13 14
-2.45603982 -6.35855600 -1.84871546 -0.25027815 2.72625440 -0.50422297 -1.76701963
15 16 17 18 19 20
0.05033351 0.65101666 0.27680835 1.79176029 6.79618311 -0.16186455
Warning message:
'newdata' had 10 rows but variables found have 20 rows
在其他帖子中，我看到人们提供了针对具体问题的解决方案，但我不明白出现问题的根本原因。
我愿意...
modTest = glm( trainLabels[,1] ~ A + B + C +
D + E + F + G +
H + I, family=binomial(link='logit') )
以上是 20 个标签，9 个向量，每个向量有 20 个值。
然后我尝试预测 10 个未见过的例子。这是 10 行，9 个特征，相同的顺序。
preds = predict( modTest, testFeatures )
我收到错误...
Warning message:
'newdata' had 10 rows but variables found have 20 rows
编辑：简化、删除长特征名称等
> names(trainFeatures)
[1] "Neg" "Pos" "Num" "UN" "UNA" "UNUA" "UP" "UPA" "UPUA"
names(testFeatures)
[1] "Neg" "Pos" "Num" "UN" "UNA" "UNUA" "UP" "UPA" "UPUA"
编辑：Dputs...
为了使用输出，我所做的是...
modTest = glm( trainLabels[,1] ~ as.matrix(trainFeatures) )
preds = predict( modTest, testFeatures )
Warning message:
'newdata' had 10 rows but variables found have 20 rows
不确定为什么我仍然收到该警告。
dput(trainLabels)
structure(list(Neg = c(1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1,
0, 0, 0, 1, 1, 1, 0), Pos = c(1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1,
1, 1, 0, 0, 0, 1, 1, 1, 0), Num = c(1, 1, 0, 0, 0, 0, 1, 0, 0,
0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UN = c(1, 1, 0, 0, 0, 0, 1,
0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UNA = c(1, 1, 0, 0, 0,
0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UNUA = c(1, 1,
0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UP = c(1,
1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UPA = c(1,
1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0), UPUA = c(1,
1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0)), .Names = c("Neg",
"Pos", "Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-20L), class = "data.frame")
dput(trainFeatures)
structure(list(Neg = c(39106, 44664, 114130, 26526, 22122, 19175,
29438, 17741, 17589, 20666, 66024, 168336, 86283, 74826, 88998,
75756, 16041, 17087, 15235, 16659), Pos = c(16129, 21064, 57730,
10314, 18105, 16837, 19300, 16873, 13681, 18414, 27148, 120497,
60031, 49016, 59250, 36264, 15786, 16315, 14556, 16057), Num = c(82994,
121367, 306842, 55458, 69148, 63167, 85891, 58674, 55874, 67505,
152475, 427106, 221043, 190043, 223744, 177388, 51657, 54883,
48378, 54115), UN = c(32343, 35433, 74835, 22271, 17686, 15498,
22416, 14238, 14078, 16800, 54636, 121211, 68079, 59913, 70884,
61408, 13221, 14114, 12647, 13487), UNA = c(95.1499874, 95.0987263,
95.3942596, 95.5444865, 113.1263844, 112.3827424, 111.2684513,
113.2184128, 112.4336258, 114.1739588, 113.5086472, 111.6715378,
112.2842917, 111.9490612, 113.6465561, 111.5254103, 112.2179148,
111.2933853, 112.9056117, 113.1511475), UNUA = c(-94.4280737,
-94.5019854, -94.9246672, -95.0379578, -113.2247115, -112.3497485,
-111.1631387, -113.2051289, -112.1822898, -114.0431466, -113.7435412,
-111.6226818, -112.4077795, -111.9886653, -113.8072166, -111.6138577,
-113.0855995, -112.3075275, -114.2628431, -114.1088453), UP = c(10384,
13015, 24470, 6891, 13445, 12852, 13008, 13093, 9878, 14272,
14938, 77058, 40595, 32518, 39889, 21424, 8322, 8451, 7440, 8071
), UPA = c(58.6289931, 57.73430079, 61.3480343, 57.8297594, 62.1749994,
65.1140073, 62.619361, 63.6791219, 63.412582, 65.1856906, 45.18365794,
71.32918265, 56.04488913, 58.13008276, 53.16603128, 50.36242011,
64.6742956, 64.0982314, 63.4422878, 64.24099034), UPUA = c(88.9216885,
88.3012858, 88.1996008, 88.9910129, 91.0232669, 89.4524702, 91.9122816,
89.8549338, 90.6487273, 88.2063941, 99.9573821, 109.9128868,
103.7989926, 104.0274764, 103.4209936, 101.5065677, 85.8110039,
87.0786241, 86.1020646, 86.8835026)), .Names = c("Neg", "Pos",
"Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-20L), class = "data.frame")
dput(testLabels)
structure(list(Neg = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1), Pos = c(0,
1, 1, 1, 0, 1, 1, 1, 1, 1), Num = c(0, 1, 1, 1, 0, 1, 1, 1, 1,
1), UN = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1), UNA = c(0, 1, 1, 1,
0, 1, 1, 1, 1, 1), UNUA = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1), UP = c(0,
1, 1, 1, 0, 1, 1, 1, 1, 1), UPA = c(0, 1, 1, 1, 0, 1, 1, 1, 1,
1), UPUA = c(0, 1, 1, 1, 0, 1, 1, 1, 1, 1)), .Names = c("Neg",
"Pos", "Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-10L), class = "data.frame")
> dput(testFeatures)
structure(list(Neg = c(51404, 32447, 24642, 95979, 15743, 90843,
13813, 11496, 12871, 13546), Pos = c(23350, 13525, 19941, 49984,
10867, 64404, 13324, 11302, 12918, 13118), Num = c(121342, 68160,
77219, 248890, 49259, 232645, 43707, 35674, 40734, 42979), UN = c(40766,
27363, 19590, 71772, 12615, 71496, 11529, 9739, 10810, 11346),
UNA = c(95.2486872, 93.4642772, 111.3853297, 112.6770471,
110.0845355, 113.6696598, 111.8409793, 116.0476022, 120.3481302,
111.9496978), UNUA = c(-94.6150698, -92.5605373, -111.1994432,
-112.4947319, -109.7130777, -113.8083912, -112.5678322, -116.5407619,
-121.4756386, -113.4991191), UP = c(14285, 9043, 14862, 31626,
7491, 43903, 7021, 5559, 6149, 6789), UPA = c(61.25585053,
62.6231081, 64.191128, 64.6397131, 63.4911744, 58.4792454,
63.5063289, 60.5667637, 60.3857056, 64.1569975), UPUA = c(88.4605419,
88.2790682, 90.0217465, 88.8441004, 91.0222662, 105.0494229,
85.8914139, 86.7685668, 84.8304901, 86.9786109)), .Names = c("Neg",
"Pos", "Num", "UN", "UNA", "UNUA", "UP", "UPA", "UPUA"), row.names = c(NA,
-10L), class = "data.frame")
所以，我 运行 使用您提供的所有数据编写代码并得到很好的结果。这是模型拟合：
modTest = glm(trainLabels[,1] ~ Neg + Pos + Num +
UN + UNA + UNUA + UP +
UPA + UPUA, family=binomial(link='logit'),
data = trainFeatues)
以下是测试数据的预测值：
predict( modTest, testFeatures)
1 2 3 4 5 6 7 8
4.6711576 -1.3572345 -2.0639104 18.7625539 -7.6961149 0.4317324 -0.8983256 -8.2052158
9 10
-1.5968013 10.8357174
注意：替代规范可以是这样的：
modTest = glm(trainLabels[,1] ~ trainFeatues$Neg + trainFeatues$Pos +
trainFeatues$Num + trainFeatues$UN + trainFeatues$UNA +
trainFeatues$UNUA + trainFeatues$UP + trainFeatues$UPA +
trainFeatues$UPUA, family=binomial(link='logit'))
但是拟合模型如下：
modTest$coefficients
(Intercept) trainFeatues$Neg trainFeatues$Pos trainFeatues$Num trainFeatues$UN
4.027803e+01 8.874801e-04 -3.000123e-03 1.277138e-04 -4.521793e-04
trainFeatues$UNA trainFeatues$UNUA trainFeatues$UP trainFeatues$UPA trainFeatues$UPUA
-1.519463e+01 -1.480503e+01 2.930261e-03 4.741432e-01 -3.690940e-01
当您输入训练数据进行预测时，这会导致问题，因为上面拟合的特征与输入的新数据不匹配进行预测。导致：
predict( modTest, testFeatures)
1 2 3 4 5 6 7
0.21651890 3.23450117 -2.16298672 -0.06949967 -0.91026504 -0.91484739 -1.69209826
8 9 10 11 12 13 14
-2.45603982 -6.35855600 -1.84871546 -0.25027815 2.72625440 -0.50422297 -1.76701963
15 16 17 18 19 20
0.05033351 0.65101666 0.27680835 1.79176029 6.79618311 -0.16186455
Warning message:
'newdata' had 10 rows but variables found have 20 rows