r - 如何识别具有多个分组的异常值
问题描述
我正在尝试从特定relabs列的数据集中识别异常值，但我需要在Control列中分别计算它们的值为 1 和 2，其中conc列等于“NK”也分组为Treatment.
带有 reprex 的数据集（应该有 40 个异常值，手动检查）：
df <- wrapr::build_frame(
"ID" , "Treatment", "conc" , "relabs", "Control" |
1 , "A" , "100 µM" , 0.9161 , 0 |
2 , "A" , "100 µM" , 0.8023 , 0 |
3 , "A" , "100 µM" , 0.7189 , 0 |
4 , "A" , "100 µM" , 0.7234 , 0 |
5 , "A" , "100 µM" , 0.6265 , 0 |
6 , "A" , "100 µM" , 0.6237 , 0 |
7 , "A" , "100 µM" , 0.6859 , 0 |
8 , "A" , "100 µM" , 0.8011 , 0 |
9 , "A" , "10 µM" , 1.115 , 0 |
10 , "A" , "10 µM" , 0.8961 , 0 |
11 , "A" , "10 µM" , 0.7925 , 0 |
12 , "A" , "10 µM" , 0.7006 , 0 |
13 , "A" , "10 µM" , 0.6719 , 0 |
14 , "A" , "10 µM" , 0.7363 , 0 |
15 , "A" , "10 µM" , 0.8165 , 0 |
16 , "A" , "10 µM" , 0.8958 , 0 |
17 , "A" , "1 µM" , 1.168 , 0 |
18 , "A" , "1 µM" , 1.066 , 0 |
19 , "A" , "1 µM" , 0.8298 , 0 |
20 , "A" , "1 µM" , 0.9315 , 0 |
21 , "A" , "1 µM" , 0.8067 , 0 |
22 , "A" , "1 µM" , 0.9296 , 0 |
23 , "A" , "1 µM" , 0.8462 , 0 |
24 , "A" , "1 µM" , 1.133 , 0 |
25 , "A" , "NK" , 1.216 , 1 |
26 , "A" , "NK" , 0.9856 , 1 |
27 , "A" , "NK" , 0.8862 , 1 |
28 , "A" , "NK" , 0.9599 , 1 |
29 , "A" , "NK" , 0.8789 , 1 |
30 , "A" , "NK" , 0.9304 , 1 |
31 , "A" , "NK" , 1.057 , 1 |
32 , "A" , "NK" , 1.086 , 1 |
33 , "A" , "10 µM X", 0.9173 , 0 |
34 , "A" , "10 µM X", 0.7754 , 0 |
35 , "A" , "10 µM X", 0.575 , 0 |
36 , "A" , "10 µM X", 0.6619 , 0 |
37 , "A" , "10 µM X", 0.5609 , 0 |
38 , "A" , "10 µM X", 0.5786 , 0 |
39 , "A" , "10 µM X", 0.6024 , 0 |
40 , "A" , "10 µM X", 0.889 , 0 |
41 , "B" , "100 µM" , 0.8515 , 0 |
42 , "B" , "100 µM" , 0.6961 , 0 |
43 , "B" , "100 µM" , 0.6754 , 0 |
44 , "B" , "100 µM" , 0.6816 , 0 |
45 , "B" , "100 µM" , 0.7234 , 0 |
46 , "B" , "100 µM" , 0.6961 , 0 |
47 , "B" , "100 µM" , 0.609 , 0 |
48 , "B" , "100 µM" , 0.7092 , 0 |
49 , "B" , "10 µM" , 0.9482 , 0 |
50 , "B" , "10 µM" , 0.8245 , 0 |
51 , "B" , "10 µM" , 0.8456 , 0 |
52 , "B" , "10 µM" , 0.8181 , 0 |
53 , "B" , "10 µM" , 0.7784 , 0 |
54 , "B" , "10 µM" , 0.7393 , 0 |
55 , "B" , "10 µM" , 0.8035 , 0 |
56 , "B" , "10 µM" , 0.8296 , 0 |
57 , "B" , "1 µM" , 1.237 , 0 |
58 , "B" , "1 µM" , 1.081 , 0 |
59 , "B" , "1 µM" , 0.987 , 0 |
60 , "B" , "1 µM" , 0.8797 , 0 |
61 , "B" , "1 µM" , 0.8077 , 0 |
62 , "B" , "1 µM" , 0.8874 , 0 |
63 , "B" , "1 µM" , 0.8942 , 0 |
64 , "B" , "1 µM" , 1.157 , 0 |
65 , "B" , "NK" , 1.216 , 1 |
66 , "B" , "NK" , 0.9856 , 1 |
67 , "B" , "NK" , 0.8862 , 1 |
68 , "B" , "NK" , 0.9599 , 1 |
69 , "B" , "NK" , 0.8789 , 1 |
70 , "B" , "NK" , 0.9304 , 1 |
71 , "B" , "NK" , 1.057 , 1 |
72 , "B" , "NK" , 1.086 , 1 |
73 , "B" , "10 µM X", 0.9173 , 0 |
74 , "B" , "10 µM X", 0.7754 , 0 |
75 , "B" , "10 µM X", 0.575 , 0 |
76 , "B" , "10 µM X", 0.6619 , 0 |
77 , "B" , "10 µM X", 0.5609 , 0 |
78 , "B" , "10 µM X", 0.5786 , 0 |
79 , "B" , "10 µM X", 0.6024 , 0 |
80 , "B" , "10 µM X", 0.889 , 0 |
81 , "C" , "100 µM" , 0.8144 , 0 |
82 , "C" , "100 µM" , 0.7734 , 0 |
83 , "C" , "100 µM" , 0.8364 , 0 |
84 , "C" , "100 µM" , 0.613 , 0 |
85 , "C" , "100 µM" , 0.6863 , 0 |
86 , "C" , "100 µM" , 0.5953 , 0 |
87 , "C" , "100 µM" , 0.5552 , 0 |
88 , "C" , "100 µM" , 0.9572 , 0 |
89 , "C" , "10 µM" , 1.256 , 0 |
90 , "C" , "10 µM" , 1.035 , 0 |
91 , "C" , "10 µM" , 0.9852 , 0 |
92 , "C" , "10 µM" , 0.9186 , 0 |
93 , "C" , "10 µM" , 0.907 , 0 |
94 , "C" , "10 µM" , 0.9979 , 0 |
95 , "C" , "10 µM" , 1.075 , 0 |
96 , "C" , "10 µM" , 1.144 , 0 |
97 , "C" , "1 µM" , 1.218 , 0 |
98 , "C" , "1 µM" , 1.078 , 0 |
99 , "C" , "1 µM" , 0.7224 , 0 |
100 , "C" , "1 µM" , 0.9967 , 0 |
101 , "C" , "1 µM" , 0.9748 , 0 |
102 , "C" , "1 µM" , 0.6157 , 0 |
103 , "C" , "1 µM" , 0.7437 , 0 |
104 , "C" , "1 µM" , 1.191 , 0 |
105 , "C" , "NK" , 1.317 , 1 |
106 , "C" , "NK" , 0.9297 , 1 |
107 , "C" , "NK" , 0.9184 , 1 |
108 , "C" , "NK" , 0.8788 , 1 |
109 , "C" , "NK" , 0.8719 , 1 |
110 , "C" , "NK" , 0.9015 , 1 |
111 , "C" , "NK" , 0.9266 , 1 |
112 , "C" , "NK" , 1.256 , 1 |
113 , "C" , "10 µM X", 0.9173 , 0 |
114 , "C" , "10 µM X", 0.7754 , 0 |
115 , "C" , "10 µM X", 0.575 , 0 |
116 , "C" , "10 µM X", 0.6619 , 0 |
117 , "C" , "10 µM X", 0.5609 , 0 |
118 , "C" , "10 µM X", 0.5786 , 0 |
119 , "C" , "10 µM X", 0.6024 , 0 |
120 , "C" , "10 µM X", 0.889 , 0 |
121 , "D" , "100 µM" , 0.7008 , 0 |
122 , "D" , "100 µM" , 0.7397 , 0 |
123 , "D" , "100 µM" , 0.6957 , 0 |
124 , "D" , "100 µM" , 0.5245 , 0 |
125 , "D" , "100 µM" , 0.5118 , 0 |
126 , "D" , "100 µM" , 0.5568 , 0 |
127 , "D" , "100 µM" , 0.7559 , 0 |
128 , "D" , "100 µM" , 0.8191 , 0 |
129 , "D" , "10 µM" , 1.056 , 0 |
130 , "D" , "10 µM" , 0.8304 , 0 |
131 , "D" , "10 µM" , 0.8152 , 0 |
132 , "D" , "10 µM" , 0.709 , 0 |
133 , "D" , "10 µM" , 0.7035 , 0 |
134 , "D" , "10 µM" , 0.6735 , 0 |
135 , "D" , "10 µM" , 0.7893 , 0 |
136 , "D" , "10 µM" , 0.9783 , 0 |
137 , "D" , "1 µM" , 1.294 , 0 |
138 , "D" , "1 µM" , 0.9011 , 0 |
139 , "D" , "1 µM" , 0.9489 , 0 |
140 , "D" , "1 µM" , 0.7918 , 0 |
141 , "D" , "1 µM" , 0.7772 , 0 |
142 , "D" , "1 µM" , 0.759 , 0 |
143 , "D" , "1 µM" , 0.8787 , 0 |
144 , "D" , "1 µM" , 1.132 , 0 |
145 , "D" , "10 µM X", 0.9173 , 0 |
146 , "D" , "10 µM X", 0.7754 , 0 |
147 , "D" , "10 µM X", 0.575 , 0 |
148 , "D" , "10 µM X", 0.6619 , 0 |
149 , "D" , "10 µM X", 0.5609 , 0 |
150 , "D" , "10 µM X", 0.5786 , 0 |
151 , "D" , "10 µM X", 0.6024 , 0 |
152 , "D" , "10 µM X", 0.889 , 0 |
153 , "D" , "NK" , 1.317 , 1 |
154 , "D" , "NK" , 0.9297 , 1 |
155 , "D" , "NK" , 0.9184 , 1 |
156 , "D" , "NK" , 0.8788 , 1 |
157 , "D" , "NK" , 0.8719 , 1 |
158 , "D" , "NK" , 0.9015 , 1 |
159 , "D" , "NK" , 0.9266 , 1 |
160 , "D" , "NK" , 1.256 , 1 |
161 , "E" , "100 µM" , 0.9406 , 0 |
162 , "E" , "100 µM" , 0.7404 , 0 |
163 , "E" , "100 µM" , 0.7166 , 0 |
164 , "E" , "100 µM" , 0.5353 , 0 |
165 , "E" , "100 µM" , 0.6104 , 0 |
166 , "E" , "100 µM" , 0.555 , 0 |
167 , "E" , "100 µM" , 0.6529 , 0 |
168 , "E" , "100 µM" , 0.8834 , 0 |
169 , "E" , "10 µM" , 0.9397 , 0 |
170 , "E" , "10 µM" , 0.8172 , 0 |
171 , "E" , "10 µM" , 0.7854 , 0 |
172 , "E" , "10 µM" , 0.8047 , 0 |
173 , "E" , "10 µM" , 0.7185 , 0 |
174 , "E" , "10 µM" , 0.7277 , 0 |
175 , "E" , "10 µM" , 0.852 , 0 |
176 , "E" , "10 µM" , 0.9809 , 0 |
177 , "E" , "1 µM" , 1.295 , 0 |
178 , "E" , "1 µM" , 1.138 , 0 |
179 , "E" , "1 µM" , 0.86 , 0 |
180 , "E" , "1 µM" , 0.9272 , 0 |
181 , "E" , "1 µM" , 0.8434 , 0 |
182 , "E" , "1 µM" , 0.92 , 0 |
183 , "E" , "1 µM" , 0.8568 , 0 |
184 , "E" , "1 µM" , 1.184 , 0 |
185 , "E" , "10 µM X", 0.9173 , 0 |
186 , "E" , "10 µM X", 0.7754 , 0 |
187 , "E" , "10 µM X", 0.575 , 0 |
188 , "E" , "10 µM X", 0.6619 , 0 |
189 , "E" , "10 µM X", 0.5609 , 0 |
190 , "E" , "10 µM X", 0.5786 , 0 |
191 , "E" , "10 µM X", 0.6024 , 0 |
192 , "E" , "10 µM X", 0.889 , 0 |
193 , "E" , "NK" , 1.317 , 1 |
194 , "E" , "NK" , 0.9297 , 1 |
195 , "E" , "NK" , 0.9184 , 1 |
196 , "E" , "NK" , 0.8788 , 1 |
197 , "E" , "NK" , 0.8719 , 1 |
198 , "E" , "NK" , 0.9015 , 1 |
199 , "E" , "NK" , 0.9266 , 1 |
200 , "E" , "NK" , 1.256 , 1 |
201 , "A" , "NK" , 1.317 , 2 |
202 , "A" , "NK" , 0.9297 , 2 |
203 , "A" , "NK" , 0.9184 , 2 |
204 , "A" , "NK" , 0.8788 , 2 |
205 , "A" , "NK" , 0.8719 , 2 |
206 , "A" , "NK" , 0.9015 , 2 |
207 , "A" , "NK" , 0.9266 , 2 |
208 , "A" , "NK" , 1.256 , 2 |
209 , "B" , "NK" , 1.317 , 2 |
210 , "B" , "NK" , 0.9297 , 2 |
211 , "B" , "NK" , 0.9184 , 2 |
212 , "B" , "NK" , 0.8788 , 2 |
213 , "B" , "NK" , 0.8719 , 2 |
214 , "B" , "NK" , 0.9015 , 2 |
215 , "B" , "NK" , 0.9266 , 2 |
216 , "B" , "NK" , 1.256 , 2 |
217 , "C" , "NK" , 1.216 , 2 |
218 , "C" , "NK" , 0.9856 , 2 |
219 , "C" , "NK" , 0.8862 , 2 |
220 , "C" , "NK" , 0.9599 , 2 |
221 , "C" , "NK" , 0.8789 , 2 |
222 , "C" , "NK" , 0.9304 , 2 |
223 , "C" , "NK" , 1.057 , 2 |
224 , "C" , "NK" , 1.086 , 2 |
225 , "D" , "NK" , 1.216 , 2 |
226 , "D" , "NK" , 0.9856 , 2 |
227 , "D" , "NK" , 0.8862 , 2 |
228 , "D" , "NK" , 0.9599 , 2 |
229 , "D" , "NK" , 0.8789 , 2 |
230 , "D" , "NK" , 0.9304 , 2 |
231 , "D" , "NK" , 1.057 , 2 |
232 , "D" , "NK" , 1.086 , 2 |
233 , "E" , "NK" , 1.216 , 2 |
234 , "E" , "NK" , 0.9856 , 2 |
235 , "E" , "NK" , 0.8862 , 2 |
236 , "E" , "NK" , 0.9599 , 2 |
237 , "E" , "NK" , 0.8789 , 2 |
238 , "E" , "NK" , 0.9304 , 2 |
239 , "E" , "NK" , 1.057 , 2 |
240 , "E" , "NK" , 1.086 , 2 )
我应该得到的数据集：
df <- wrapr::build_frame(
"ID" , "Treatment", "conc" , "relabs" |
1 , "A" , "100 µM" , 0.9869 |
2 , "A" , "100 µM" , 0.8644 |
3 , "A" , "100 µM" , 0.7745 |
4 , "A" , "100 µM" , 0.7793 |
5 , "A" , "100 µM" , 0.675 |
6 , "A" , "100 µM" , 0.6719 |
7 , "A" , "100 µM" , 0.739 |
8 , "A" , "100 µM" , 0.8631 |
9 , "A" , "10 µM" , 0.9654 |
10 , "A" , "10 µM" , 0.8538 |
11 , "A" , "10 µM" , 0.7548 |
12 , "A" , "10 µM" , 0.7239 |
13 , "A" , "10 µM" , 0.7933 |
14 , "A" , "10 µM" , 0.8797 |
15 , "A" , "10 µM" , 0.9651 |
16 , "A" , "1 µM" , 0.894 |
17 , "A" , "1 µM" , 1.004 |
18 , "A" , "1 µM" , 0.8691 |
19 , "A" , "1 µM" , 1.002 |
20 , "A" , "1 µM" , 0.9117 |
21 , "A" , "10 µM X", 1.014 |
22 , "A" , "10 µM X", 0.8573 |
23 , "A" , "10 µM X", 0.6358 |
24 , "A" , "10 µM X", 0.7318 |
25 , "A" , "10 µM X", 0.6201 |
26 , "A" , "10 µM X", 0.6397 |
27 , "A" , "10 µM X", 0.666 |
28 , "A" , "10 µM X", 0.9829 |
29 , "A" , "NK" , 1.062 |
30 , "A" , "NK" , 0.9548 |
31 , "A" , "NK" , 1.034 |
32 , "A" , "NK" , 0.9469 |
33 , "A" , "NK" , 1.002 |
34 , "A" , "NK" , 1.028 |
35 , "A" , "NK" , 1.015 |
36 , "A" , "NK" , 0.9716 |
37 , "A" , "NK" , 0.964 |
38 , "A" , "NK" , 0.9967 |
39 , "A" , "NK" , 1.024 |
40 , "B" , "100 µM" , 0.9174 |
41 , "B" , "100 µM" , 0.75 |
42 , "B" , "100 µM" , 0.7277 |
43 , "B" , "100 µM" , 0.7344 |
44 , "B" , "100 µM" , 0.7794 |
45 , "B" , "100 µM" , 0.7499 |
46 , "B" , "100 µM" , 0.6561 |
47 , "B" , "100 µM" , 0.7641 |
48 , "B" , "10 µM" , 1.022 |
49 , "B" , "10 µM" , 0.8883 |
50 , "B" , "10 µM" , 0.911 |
51 , "B" , "10 µM" , 0.8814 |
52 , "B" , "10 µM" , 0.8387 |
53 , "B" , "10 µM" , 0.7965 |
54 , "B" , "10 µM" , 0.8656 |
55 , "B" , "10 µM" , 0.8938 |
56 , "B" , "1 µM" , 1.063 |
57 , "B" , "1 µM" , 0.9478 |
58 , "B" , "1 µM" , 0.8702 |
59 , "B" , "1 µM" , 0.9561 |
60 , "B" , "1 µM" , 0.9634 |
61 , "B" , "NK" , 1.062 |
62 , "B" , "NK" , 0.9548 |
63 , "B" , "NK" , 1.034 |
64 , "B" , "NK" , 0.9469 |
65 , "B" , "NK" , 1.002 |
66 , "B" , "NK" , 1.028 |
67 , "B" , "NK" , 1.015 |
68 , "B" , "NK" , 0.9716 |
69 , "B" , "NK" , 0.964 |
70 , "B" , "NK" , 0.9967 |
71 , "B" , "NK" , 1.024 |
72 , "B" , "10 µM X", 1.014 |
73 , "B" , "10 µM X", 0.8573 |
74 , "B" , "10 µM X", 0.6358 |
75 , "B" , "10 µM X", 0.7318 |
76 , "B" , "10 µM X", 0.6201 |
77 , "B" , "10 µM X", 0.6397 |
78 , "B" , "10 µM X", 0.666 |
79 , "B" , "10 µM X", 0.9829 |
80 , "C" , "100 µM" , 0.9005 |
81 , "C" , "100 µM" , 0.8551 |
82 , "C" , "100 µM" , 0.9248 |
83 , "C" , "100 µM" , 0.6778 |
84 , "C" , "100 µM" , 0.7588 |
85 , "C" , "100 µM" , 0.6582 |
86 , "C" , "100 µM" , 0.6138 |
87 , "C" , "100 µM" , 1.058 |
88 , "C" , "10 µM" , 1.144 |
89 , "C" , "10 µM" , 1.089 |
90 , "C" , "10 µM" , 1.016 |
91 , "C" , "10 µM" , 1.003 |
92 , "C" , "10 µM" , 1.103 |
93 , "C" , "10 µM" , 1.188 |
94 , "C" , "1 µM" , 1.192 |
95 , "C" , "1 µM" , 0.7987 |
96 , "C" , "1 µM" , 1.102 |
97 , "C" , "1 µM" , 1.078 |
98 , "C" , "1 µM" , 0.6808 |
99 , "C" , "1 µM" , 0.8223 |
100 , "C" , "NK" , 1.028 |
101 , "C" , "NK" , 1.015 |
102 , "C" , "NK" , 0.9716 |
103 , "C" , "NK" , 0.964 |
104 , "C" , "NK" , 0.9967 |
105 , "C" , "NK" , 1.024 |
106 , "C" , "NK" , 1.062 |
107 , "C" , "NK" , 0.9548 |
108 , "C" , "NK" , 1.034 |
109 , "C" , "NK" , 0.9469 |
110 , "C" , "NK" , 1.002 |
111 , "C" , "10 µM X", 1.014 |
112 , "C" , "10 µM X", 0.8573 |
113 , "C" , "10 µM X", 0.6358 |
114 , "C" , "10 µM X", 0.7318 |
115 , "C" , "10 µM X", 0.6201 |
116 , "C" , "10 µM X", 0.6397 |
117 , "C" , "10 µM X", 0.666 |
118 , "C" , "10 µM X", 0.9829 |
119 , "D" , "100 µM" , 0.7748 |
120 , "D" , "100 µM" , 0.8178 |
121 , "D" , "100 µM" , 0.7692 |
122 , "D" , "100 µM" , 0.5798 |
123 , "D" , "100 µM" , 0.5658 |
124 , "D" , "100 µM" , 0.6157 |
125 , "D" , "100 µM" , 0.8357 |
126 , "D" , "100 µM" , 0.9056 |
127 , "D" , "10 µM" , 1.168 |
128 , "D" , "10 µM" , 0.9181 |
129 , "D" , "10 µM" , 0.9013 |
130 , "D" , "10 µM" , 0.7839 |
131 , "D" , "10 µM" , 0.7778 |
132 , "D" , "10 µM" , 0.7447 |
133 , "D" , "10 µM" , 0.8727 |
134 , "D" , "10 µM" , 1.082 |
135 , "D" , "1 µM" , 0.9963 |
136 , "D" , "1 µM" , 1.049 |
137 , "D" , "1 µM" , 0.8755 |
138 , "D" , "1 µM" , 0.8593 |
139 , "D" , "1 µM" , 0.8392 |
140 , "D" , "1 µM" , 0.9715 |
141 , "D" , "1 µM" , 1.251 |
142 , "D" , "10 µM X", 1.014 |
143 , "D" , "10 µM X", 0.8573 |
144 , "D" , "10 µM X", 0.6358 |
145 , "D" , "10 µM X", 0.7318 |
146 , "D" , "10 µM X", 0.6201 |
147 , "D" , "10 µM X", 0.6397 |
148 , "D" , "10 µM X", 0.666 |
149 , "D" , "10 µM X", 0.9829 |
150 , "D" , "NK" , 1.028 |
151 , "D" , "NK" , 1.015 |
152 , "D" , "NK" , 0.9716 |
153 , "D" , "NK" , 0.964 |
154 , "D" , "NK" , 0.9967 |
155 , "D" , "NK" , 1.024 |
156 , "D" , "NK" , 1.062 |
157 , "D" , "NK" , 0.9548 |
158 , "D" , "NK" , 1.034 |
159 , "D" , "NK" , 0.9469 |
160 , "D" , "NK" , 1.002 |
161 , "E" , "100 µM" , 1.04 |
162 , "E" , "100 µM" , 0.8186 |
163 , "E" , "100 µM" , 0.7923 |
164 , "E" , "100 µM" , 0.5918 |
165 , "E" , "100 µM" , 0.6749 |
166 , "E" , "100 µM" , 0.6136 |
167 , "E" , "100 µM" , 0.7218 |
168 , "E" , "100 µM" , 0.9768 |
169 , "E" , "10 µM" , 1.039 |
170 , "E" , "10 µM" , 0.9035 |
171 , "E" , "10 µM" , 0.8684 |
172 , "E" , "10 µM" , 0.8898 |
173 , "E" , "10 µM" , 0.7944 |
174 , "E" , "10 µM" , 0.8046 |
175 , "E" , "10 µM" , 0.942 |
176 , "E" , "10 µM" , 1.085 |
177 , "E" , "1 µM" , 0.9508 |
178 , "E" , "1 µM" , 1.025 |
179 , "E" , "1 µM" , 0.9325 |
180 , "E" , "1 µM" , 1.017 |
181 , "E" , "1 µM" , 0.9473 |
182 , "E" , "10 µM X", 1.014 |
183 , "E" , "10 µM X", 0.8573 |
184 , "E" , "10 µM X", 0.6358 |
185 , "E" , "10 µM X", 0.7318 |
186 , "E" , "10 µM X", 0.6201 |
187 , "E" , "10 µM X", 0.6397 |
188 , "E" , "10 µM X", 0.666 |
189 , "E" , "10 µM X", 0.9829 |
190 , "E" , "NK" , 1.028 |
191 , "E" , "NK" , 1.015 |
192 , "E" , "NK" , 0.9716 |
193 , "E" , "NK" , 0.964 |
194 , "E" , "NK" , 0.9967 |
195 , "E" , "NK" , 1.024 |
196 , "E" , "NK" , 1.062 |
197 , "E" , "NK" , 0.9548 |
198 , "E" , "NK" , 1.034 |
199 , "E" , "NK" , 0.9469 |
200 , "E" , "NK" , 1.002 )
我使用函数 identify_outliers by Treatmentandconc它运行良好，但我也需要这个函数从我的数据集中分别从conc“NK”和Control“1”和“2”计算异常值，而不是组合，然后排除所有异常值anti_join。
我当前的代码，它没有分别计算来自“NK”和“1”和“2”的异常值。Identify_outliers来自rstatix。
df_outliers <-
df %>%
group_by(Treatment, conc) %>%
identify_outliers("relabs")
df_outliers
我通过以下方式排除异常值anti_join：
df_wo_outliers <-
df %>%
anti_join(df_outliers, by = "ID") %>%
view()
我有很多数据，所以如果我能弄清楚如何用 R 来做，我不想手动做。
有没有办法计算异常值 和 分组Treatment，conc以及如果Treatment等于“NK”并且控制是“1”和“2”，则单独计算它？
在excel中手动计算异常值：
解决方案
** 更新 **
如果我们使用你的data，我们会在所有组中发现 9 个异常值。我不确定你是如何确定 40 的。但这种group_by方法基本上是有效的。
library(dplyr)
library(rstatix)
data <- as_tibble(data) # for printing
df_outliers <-
data %>%
group_by(Treatment, conc) %>%
identify_outliers(relabs)
data %>%
anti_join(df_outliers, by = "ID")
#> # A tibble: 231 x 5
#> ID Treatment conc relabs Control
#> <dbl> <chr> <chr> <dbl> <dbl>
#> 1 1 A 100 µM 0.916 0
#> 2 2 A 100 µM 0.802 0
#> 3 3 A 100 µM 0.719 0
#> 4 4 A 100 µM 0.723 0
#> 5 5 A 100 µM 0.626 0
#> 6 6 A 100 µM 0.624 0
#> 7 7 A 100 µM 0.686 0
#> 8 8 A 100 µM 0.801 0
#> 9 9 A 10 µM 1.12 0
#> 10 10 A 10 µM 0.896 0
#> # … with 221 more rows
由reprex 包（v0.3.0）于 2021-09-26 创建
旧答案
rstatix::identify_outliers效果很好，dplyr::group_by但要做到这一点，我们首先需要数据中的异常值。下面我更改了数据以显示如何identify_outliers工作。
library(dplyr)
library(rstatix)
set.seed(1)
# setup:
# lets make the data set bigger
# and introduce some outliers in each group by making `relab` larger
df2 <- df %>%
slice_sample(n = 10000,
replace = TRUE) %>%
group_by(Treatment, conc) %>%
mutate(row_id = row_number(),
relabs = ifelse(row_id == 1, rnorm(1) * 100, relabs))
df_outliers <-
df2 %>%
# df2 is already grouped so we don't need this here:
# group_by(Treatment, conc) %>%
identify_outliers(relabs)
df2 %>%
anti_join(df_outliers, by = c("ID", "row_id"))
#> # A tibble: 9,990 x 6
#> # Groups: Treatment, conc [10]
#> ID Treatment conc relabs Control row_id
#> <dbl> <chr> <chr> <dbl> <dbl> <int>
#> 1 1 A NK 0.91 1 2
#> 2 2 A NK 0.83 2 3
#> 3 19 B NK 0.98 1 2
#> 4 1 A NK 0.91 1 4
#> 5 21 B 10X 0.66 0 2
#> 6 10 A 100 0.12 0 2
#> 7 14 B NK 0.93 2 3
#> 8 10 A 100 0.12 0 3
#> 9 7 A NK 0.73 1 5
#> 10 15 B 10X 0.62 0 3
#> # … with 9,980 more rows
由reprex 包（v0.3.0）于 2021-09-26 创建
推荐阅读
- python - Python中的列表按整数降序排序
- python - 如何更新显示的值而不是每次在 Python 中打印？
- mysql - @mysql/xdevapi 在插入数据时返回无效的输入表达式（MySQL 8）
- php - X-cart css 和类别图像没有改变
- bash - Unix如何将fuser命令输出存储到变量中
- asp.net - 哪个更合适：Windows 服务还是 WCF 服务？
- android - 使用 Retrofit 进行两次 API 调用以形成一个对象
- python - 从python中的xarray格式获取值
- ios - 如何将编程按钮声明为 var
- ios - 绑定 Objective-C 包时出错