Fatal编程技术网
  • r/
  • 计算R中具有特定名称模式的列的行平均值

计算R中具有特定名称模式的列的行平均值

r

计算R中具有特定名称模式的列的行平均值,r,mean,R,Mean,我的数据集如下所示： > head(big_metric[,c(30:37)]) Recall_41365 Accuracy_41361 Precision_41361 Recall_41361 Accuracy_41365 Precision_41365 Recall_41365 Prob 1: 1.0000000 0.9516129 0.9516129 1 0.8189655 0.8189655

我的数据集如下所示：

> head(big_metric[,c(30:37)])
   Recall_41365 Accuracy_41361 Precision_41361 Recall_41361 Accuracy_41365 Precision_41365 Recall_41365 Prob
1:    1.0000000      0.9516129       0.9516129            1      0.8189655       0.8189655            1  0.0
2:    1.0000000      0.9516129       0.9516129            1      0.8189655       0.8189655            1  0.1
3:    1.0000000      0.9516129       0.9516129            1      0.8189655       0.8189655            1  0.2
4:    1.0000000      0.9516129       0.9516129            1      0.8189655       0.8189655            1  0.3
5:    1.0000000      0.9516129       0.9516129            1      0.8189655       0.8189655            1  0.4
6:    0.9936909      0.9516129       0.9516129            1      0.8189655       0.8189655            1  0.5
数据集是
10
行，列
big_metric$Prob
的值从
0
到
0.9
，步骤为
0.1

对于每一行，我想计算除
Prob
之外的所有列的
mean
值。
平均值
值将存储在新列中，如下所示：

big\u metric$accurity
：
mean
具有标题模式的列的值
accurity\u 413**

big\u metric$Precision
：
mean
具有标题模式的列的值
Precision\u 413**

big\u metric$Recall
：
mean
具有标题模式的列的值
Recall\u 413**

我对R很陌生，所以如果至少有人能让我走上正轨，那将是一个很大的帮助。欢迎您的任何意见

以下是数据示例：

> dput(big_metric)
structure(list(Accuracy_41365 = c(0.89119171, 0.89119171, 0.89119171, 
0.89119171, 0.89119171, 0.888601036, 0.886010363, 0.883419689, 
0.867875648, 0.870466321), Precision_41365 = c(0.89119171, 0.89119171, 
0.89119171, 0.89119171, 0.89119171, 0.890909091, 0.901069519, 
0.909589041, 0.910364146, 0.92), Recall_41365 = c(1, 1, 1, 1, 
1, 0.997093023, 0.979651163, 0.965116279, 0.944767442, 0.936046512
), Accuracy_41366 = c(0.836898396, 0.836898396, 0.836898396, 
0.836898396, 0.836898396, 0.820855615, 0.839572193, 0.839572193, 
0.831550802, 0.826203209), Precision_41366 = c(0.836898396, 0.836898396, 
0.836898396, 0.836898396, 0.836898396, 0.83423913, 0.856338028, 
0.870967742, 0.87202381, 0.892405063), Recall_41366 = c(1, 1, 
1, 1, 1, 0.980830671, 0.971246006, 0.948881789, 0.936102236, 
0.900958466), Accuracy_41365 = c(0.810344828, 0.810344828, 0.810344828, 
0.810344828, 0.810344828, 0.793103448, 0.801724138, 0.818965517, 
0.801724138, 0.793103448), Precision_41365 = c(0.810344828, 0.810344828, 
0.810344828, 0.810344828, 0.810344828, 0.807017544, 0.825688073, 
0.841121495, 0.838095238, 0.836538462), Recall_41365 = c(1, 1, 
1, 1, 1, 0.978723404, 0.957446809, 0.957446809, 0.936170213, 
0.925531915), Accuracy_41366 = c(0.972477064, 0.972477064, 0.972477064, 
0.972477064, 0.972477064, 0.972477064, 0.926605505, 0.889908257, 
0.844036697, 0.779816514), Precision_41366 = c(0.972477064, 0.972477064, 
0.972477064, 0.972477064, 0.972477064, 0.972477064, 0.99, 1, 
1, 1), Recall_41366 = c(1, 1, 1, 1, 1, 1, 0.933962264, 0.886792453, 
0.839622642, 0.773584906), Accuracy_41361 = c(0.851162791, 0.851162791, 
0.851162791, 0.851162791, 0.851162791, 0.837209302, 0.809302326, 
0.795348837, 0.776744186, 0.795348837), Precision_41361 = c(0.851162791, 
0.851162791, 0.851162791, 0.851162791, 0.851162791, 0.849056604, 
0.858585859, 0.863874346, 0.860962567, 0.879781421), Recall_41361 = c(1, 
1, 1, 1, 1, 0.983606557, 0.928961749, 0.901639344, 0.879781421, 
0.879781421), Accuracy_41366 = c(0.703208556, 0.703208556, 0.703208556, 
0.703208556, 0.703208556, 0.697860963, 0.711229947, 0.703208556, 
0.684491979, 0.687165775), Precision_41366 = c(0.703208556, 0.703208556, 
0.703208556, 0.703208556, 0.703208556, 0.701612903, 0.715877437, 
0.717142857, 0.711370262, 0.715976331), Recall_41366 = c(1, 1, 
1, 1, 1, 0.992395437, 0.977186312, 0.954372624, 0.927756654, 
0.920152091), Accuracy_41361 = c(0.790322581, 0.790322581, 0.790322581, 
0.790322581, 0.790322581, 0.758064516, 0.725806452, 0.661290323, 
0.629032258, 0.612903226), Precision_41361 = c(0.790322581, 0.790322581, 
0.790322581, 0.790322581, 0.790322581, 0.783333333, 0.785714286, 
0.769230769, 0.76, 0.755102041), Recall_41361 = c(1, 1, 1, 1, 
1, 0.959183673, 0.897959184, 0.816326531, 0.775510204, 0.755102041
), Accuracy_41366 = c(0.798165138, 0.798165138, 0.798165138, 
0.798165138, 0.798165138, 0.788990826, 0.76146789, 0.752293578, 
0.724770642, 0.706422018), Precision_41366 = c(0.798165138, 0.798165138, 
0.798165138, 0.798165138, 0.798165138, 0.796296296, 0.796116505, 
0.8, 0.793814433, 0.795698925), Recall_41366 = c(1, 1, 1, 1, 
1, 0.988505747, 0.942528736, 0.91954023, 0.885057471, 0.850574713
), Accuracy_41361 = c(0.874418605, 0.874418605, 0.874418605, 
0.874418605, 0.874418605, 0.860465116, 0.846511628, 0.846511628, 
0.841860465, 0.841860465), Precision_41361 = c(0.874418605, 0.874418605, 
0.874418605, 0.874418605, 0.874418605, 0.872641509, 0.87804878, 
0.885572139, 0.885, 0.896907216), Recall_41361 = c(1, 1, 1, 1, 
1, 0.984042553, 0.957446809, 0.946808511, 0.941489362, 0.925531915
), Accuracy_41365 = c(0.821243523, 0.821243523, 0.821243523, 
0.821243523, 0.821243523, 0.816062176, 0.816062176, 0.810880829, 
0.803108808, 0.792746114), Precision_41365 = c(0.821243523, 0.821243523, 
0.821243523, 0.821243523, 0.821243523, 0.8203125, 0.828877005, 
0.82972973, 0.828337875, 0.831932773), Recall_41365 = c(1, 1, 
1, 1, 1, 0.993690852, 0.977917981, 0.968454259, 0.958990536, 
0.936908517), Accuracy_41361 = c(0.951612903, 0.951612903, 0.951612903, 
0.951612903, 0.951612903, 0.951612903, 0.919354839, 0.919354839, 
0.887096774, 0.870967742), Precision_41361 = c(0.951612903, 0.951612903, 
0.951612903, 0.951612903, 0.951612903, 0.951612903, 0.965517241, 
0.965517241, 0.964285714, 0.981132075), Recall_41361 = c(1, 1, 
1, 1, 1, 1, 0.949152542, 0.949152542, 0.915254237, 0.881355932
), Accuracy_41365 = c(0.818965517, 0.818965517, 0.818965517, 
0.818965517, 0.818965517, 0.818965517, 0.810344828, 0.801724138, 
0.801724138, 0.793103448), Precision_41365 = c(0.818965517, 0.818965517, 
0.818965517, 0.818965517, 0.818965517, 0.818965517, 0.834862385, 
0.839622642, 0.839622642, 0.844660194), Recall_41365 = c(1, 1, 
1, 1, 1, 1, 0.957894737, 0.936842105, 0.936842105, 0.915789474
), Prob = c(0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9)), row.names = c(NA, 
-10L), class = c("data.table", "data.frame"), .internal.selfref = <pointer: 0x00000000052e1ef0>)

>dput（大尺寸）
结构（列表）的精度=c（0.89119171，0.89119171，0.89119171，
0.89119171, 0.89119171, 0.888601036, 0.886010363, 0.883419689, 
0.867875648,0.870466321），精度41365=c（0.89119171,0.89119171，
0.89119171, 0.89119171, 0.89119171, 0.890909091, 0.901069519, 
0.909589041,0.910364146,0.92），召回率41365=c（1,1,1,1，
1, 0.997093023, 0.979651163, 0.965116279, 0.944767442, 0.936046512
)，精度41366=c（0.836898396,0.836898396,0.836898396,0.836898396,，
0.836898396, 0.836898396, 0.820855615, 0.839572193, 0.839572193, 
0.831550802,0.826203209），精度41366=c（0.836898396,0.836898396，
0.836898396, 0.836898396, 0.836898396, 0.83423913, 0.856338028, 
0.870967742,0.87202381,0.892405063），召回率=c（1,1，
1, 1, 1, 0.980830671, 0.971246006, 0.948881789, 0.936102236, 
0.900958466），精度_41365=c（0.810344828，0.810344828，0.810344828，
0.810344828, 0.810344828, 0.793103448, 0.801724138, 0.818965517, 
0.801724138，0.793103448），精度41365=c（0.810344828，0.810344828，
0.810344828, 0.810344828, 0.810344828, 0.807017544, 0.825688073, 
0.841121495,0.838095238,0.836538462），召回率41365=c（1,1，
1, 1, 1, 0.978723404, 0.957446809, 0.957446809, 0.936170213, 
0.925531915），精度_41366=c（0.972477064，0.972477064，0.972477064，
0.972477064, 0.972477064, 0.972477064, 0.926605505, 0.889908257, 
0.844036697，0.779816514），精度41366=c（0.972477064，0.972477064，
0.972477064, 0.972477064, 0.972477064, 0.972477064, 0.99, 1, 
（1,1,1,1,1,1,1,1,1,1,1,0.933962264,0.886792453，
0.839622642,0.773584906），精度41361=c（0.851162791,0.851162791，
0.851162791, 0.851162791, 0.851162791, 0.837209302, 0.809302326, 
0.795348837,0.776744186,0.795348837），精度41361=c（0.851162791，
0.851162791, 0.851162791, 0.851162791, 0.851162791, 0.849056604, 
0.85859,0.863874346,0.860962567,0.879781421），召回率=c（1，
1, 1, 1, 1, 0.983606557, 0.928961749, 0.901639344, 0.879781421, 
0.879781421），精度_41366=c（0.703208556，0.703208556，0.703208556，
0.703208556, 0.703208556, 0.697860963, 0.711229947, 0.703208556, 
0.684491979,0.687165775），精度41366=c（0.703208556,0.703208556，
0.703208556, 0.703208556, 0.703208556, 0.701612903, 0.715877437, 
0.717142857,0.711370262,0.715976331），召回率41366=c（1,1，
1, 1, 1, 0.992395437, 0.977186312, 0.954372624, 0.927756654, 
0.920152091），精度_41361=c（0.790322581，0.790322581，0.790322581，
0.790322581, 0.790322581, 0.758064516, 0.725806452, 0.661290323, 
0.629032258,0.612903226），精度41361=c（0.790322581,0.790322581，
0.790322581, 0.790322581, 0.790322581, 0.783333333, 0.785714286, 
0.769230769,0.76,0.755102041），召回率41361=c（1,1,1,1，
1, 0.959183673, 0.897959184, 0.816326531, 0.775510204, 0.755102041
)，准确度=c（0.798165138，0.798165138，0.798165138，
0.798165138, 0.798165138, 0.788990826, 0.76146789, 0.752293578, 
0.724770642,0.706422018），精度41366=c（0.798165138,0.798165138，
0.798165138, 0.798165138, 0.798165138, 0.796296296, 0.796116505, 
0.8,0.793814433,0.795698925），召回率=c（1,1,1,1，
1, 0.988505747, 0.942528736, 0.91954023, 0.885057471, 0.850574713
)，精度_41361=c（0.874418605，0.874418605，0.874418605，
0.874418605, 0.874418605, 0.860465116, 0.846511628, 0.846511628, 
0.841860465,0.841860465），精度41361=c（0.874418605,0.874418605，
0.874418605, 0.874418605, 0.874418605, 0.872641509, 0.87804878, 
0.885572139,0.885,0.896907216），召回率41361=c（1,1,1,1，
1, 0.984042553, 0.957446809, 0.946808511, 0.941489362, 0.925531915
)，准确度--U 41365=c（0.821243523，0.821243523，0.821243523，
0.821243523, 0.821243523, 0.816062176, 0.816062176, 0.810880829, 
0.8030108808,0.792746114），精度41365=c（0.821243523,0.821243523，
0.821243523, 0.821243523, 0.821243523, 0.8203125, 0.828877005, 
0.82972973,0.828337875,0.831932773），召回率41365=c（1,1，
1, 1, 1, 0.993690852, 0.977917981, 0.968454259, 0.958990536, 
0.936908517），精度_41361=c（0.951612903，0.951612903，0.951612903，
0.951612903, 0.951612903, 0.951612903, 0.919354839, 0.919354839, 
0.887096774,0.870967742），精度41361=c（0.951612903,0.951612903，
0.951612903, 0.951612903, 0.951612903, 0.951612903, 0.965517241, 
0.965517241,0.964285714,0.981132075），召回率41361=c（1,1，
1, 1, 1, 1, 0.949152542, 0.949152542, 0.915254237, 0.881355932
)，精度_41365=c（0.818965517，0.818965517，0.818965517，
0.818965517, 0.818965517, 0.818965517, 0.810344828, 0.801724138, 
0.801724138，0.793103448），精度41365=c（0.818965517，0.818965517，
0.818965517, 0.818965517, 0.818965517, 0.818965517, 0.834862385, 
0.839622642,0.839622642,0.844660194），召回率=c（1,1，
1, 1, 1, 1, 0.957894737, 0.936842105, 0.936842105, 0.915789474
)，Prob=c（0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9）），row.names=c（NA，
-10L），class=c（“data.table”，“data.frame”），.internal.selfref=）
基于
dput
，e 
# find the column names that start with 'Recall', 'Accuracy', 'Precision'
nm1 <- grep("^(Recall|Accuracy|Precision)", names(big_metric), value = TRUE)
# split the dataset with the substring of nm1 into a list
# loop through the list and get the rowMeans
out <- sapply(split.default(big_metric[, ..nm1], sub("_.*", "", nm1)), rowMeans)
# assign that columns to create new columns in the original dataset
big_metric[, colnames(out) := as.data.frame(out)]

out1 <- melt(big_metric[, rn := seq_len(.N)], 
      measure = patterns("^Recall", "^Precision", "^Accuracy"))[, 
     lapply(.SD, mean), rn, .SDcols = value1:value3]
big_metric[, c("Recall", "Precision", "Accuracy") := out1[, 2:4]]

library(matrixStats)
lst1 <- lapply(split.default(big_metric[, ..nm1], sub("_.*", "", nm1)),
   function(x) cbind(Mean = rowMeans(x), SD = rowSds(as.matrix(x))))
out1 <- as.data.frame(do.call(cbind, lst1))
nm2 <- paste0(rep(c("Recall", "Precision", "Accuracy"), each = 2), names(out1))
big_metric[, (nm2) := out1]