量化ggplot行之间相似性的方法
Way to quantify similarities in between rows of a ggplot
我有以下数据表：
test <-
number variable value
1 1 V1 0.2635911
2 2 V1 0.2650884
3 3 V1 0.2569116
4 4 V1 0.2616717
5 5 V1 0.2564727
6 6 V1 0.2538608
7 7 V1 0.2633396
8 8 V1 0.2655517
9 9 V1 0.2738706
10 10 V1 0.2689698
11 11 V1 0.2775924
12 12 V1 0.2570329
13 13 V1 0.2628771
14 14 V1 0.2605258
15 15 V1 0.2588198
16 16 V1 0.2706452
17 17 V1 0.2587265
18 18 V1 0.2587265
19 19 V1 0.2613579
20 20 V1 0.2700729
21 21 V1 0.2781541
22 22 V1 0.2908526
23 23 V1 0.2828866
24 24 V1 0.2829607
25 25 V1 0.2800748
26 26 V1 0.2864499
27 27 V1 0.2976331
28 28 V1 0.3076221
29 29 V1 0.3125783
30 30 V1 0.3029413
31 31 V1 0.2921926
32 32 V1 0.2952376
33 33 V1 0.2917149
34 34 V1 0.3095391
35 35 V1 0.3192369
36 36 V1 0.3205008
37 37 V1 0.3210821
38 38 V1 0.3225114
39 39 V1 0.3165967
40 40 V1 0.3311130
41 41 V1 0.3355732
42 1 V2 0.2275850
43 2 V2 0.2268247
44 3 V2 0.2235245
45 4 V2 0.2277341
46 5 V2 0.2224330
47 6 V2 0.2216663
48 7 V2 0.2295579
49 8 V2 0.2303818
50 9 V2 0.2362313
51 10 V2 0.2288778
52 11 V2 0.2415600
53 12 V2 0.2260683
54 13 V2 0.2243258
55 14 V2 0.2217801
56 15 V2 0.2198674
57 16 V2 0.2303736
58 17 V2 0.2222210
59 18 V2 0.2222210
60 19 V2 0.2308805
61 20 V2 0.2408891
62 21 V2 0.2612180
63 22 V2 0.2713836
64 23 V2 0.2680126
65 24 V2 0.2700159
66 25 V2 0.2669348
67 26 V2 0.2668953
68 27 V2 0.2765348
69 28 V2 0.2911455
70 29 V2 0.2959731
71 30 V2 0.2860626
72 31 V2 0.2619870
73 32 V2 0.2623899
74 33 V2 0.2595488
75 34 V2 0.2741101
76 35 V2 0.2826556
77 36 V2 0.2913895
78 37 V2 0.2934421
79 38 V2 0.2842480
80 39 V2 0.2754619
81 40 V2 0.2918188
82 41 V2 0.2943509
83 1 V3 0.2294325
84 2 V3 0.2207675
85 3 V3 0.2276309
86 4 V3 0.2311673
87 5 V3 0.2421844
88 6 V3 0.2393514
89 7 V3 0.2464961
90 8 V3 0.2672072
91 9 V3 0.2706891
92 10 V3 0.2716877
93 11 V3 0.2775320
94 12 V3 0.2882381
95 13 V3 0.2760345
96 14 V3 0.2761454
97 15 V3 0.2686366
98 16 V3 0.2633213
99 17 V3 0.2558415
100 18 V3 0.2558415
101 19 V3 0.2651125
102 20 V3 0.2802660
103 21 V3 0.3130162
104 22 V3 0.3291228
105 23 V3 0.3293683
106 24 V3 0.3309799
107 25 V3 0.3303767
108 26 V3 0.3330788
109 27 V3 0.3427585
110 28 V3 0.3565055
111 29 V3 0.3305404
112 30 V3 0.3437861
113 31 V3 0.3146519
114 32 V3 0.2952635
115 33 V3 0.2902571
116 34 V3 0.3056054
117 35 V3 0.3046384
118 36 V3 0.3240068
119 37 V3 0.3324652
120 38 V3 0.3310975
121 39 V3 0.3256083
122 40 V3 0.3421986
123 41 V3 0.3462222
124 1 V4 0.5916363
125 2 V4 0.5779034
126 3 V4 0.5632020
127 4 V4 0.5467954
128 5 V4 0.5570823
129 6 V4 0.5797311
130 7 V4 0.5811650
131 8 V4 0.5862114
132 9 V4 0.5336045
133 10 V4 0.4983209
134 11 V4 0.5013016
135 12 V4 0.5489596
136 13 V4 0.5328552
137 14 V4 0.5628441
138 15 V4 0.5305244
139 16 V4 0.5396499
140 17 V4 0.5382373
141 18 V4 0.5382373
142 19 V4 0.5657389
143 20 V4 0.6095523
144 21 V4 0.6352541
145 22 V4 0.5622340
146 23 V4 0.5807564
147 24 V4 0.5726391
148 25 V4 0.5724073
149 26 V4 0.6093937
150 27 V4 0.6206982
151 28 V4 0.5944146
152 29 V4 0.6073015
153 30 V4 0.5912288
154 31 V4 0.6116150
155 32 V4 0.5825401
156 33 V4 0.5545265
157 34 V4 0.5916220
158 35 V4 0.6104256
159 36 V4 0.6034211
160 37 V4 0.6224549
161 38 V4 0.6931982
162 39 V4 0.6583044
163 40 V4 0.7277546
164 41 V4 0.7316220
165 1 V5 1.6012750
166 2 V5 1.7232682
167 3 V5 1.6849498
168 4 V5 1.7372409
169 5 V5 1.6904975
170 6 V5 1.6782624
171 7 V5 1.6236781
172 8 V5 1.6440954
173 9 V5 1.6140033
174 10 V5 1.5470975
175 11 V5 1.5507709
176 12 V5 1.4282340
177 13 V5 1.4641920
178 14 V5 1.4392424
179 15 V5 1.3988920
180 16 V5 1.4240200
181 17 V5 1.5839329
182 18 V5 1.5839329
183 19 V5 1.6081716
184 20 V5 1.6432765
185 21 V5 1.7558676
186 22 V5 1.7517093
187 23 V5 1.8167877
188 24 V5 1.7802214
189 25 V5 1.8784713
190 26 V5 1.8622613
191 27 V5 1.7720034
192 28 V5 1.7473988
193 29 V5 1.8420391
194 30 V5 1.6780098
195 31 V5 1.6348314
196 32 V5 1.7805307
197 33 V5 1.8170188
198 34 V5 1.9236170
199 35 V5 1.8752950
200 36 V5 1.8992993
201 37 V5 1.8998148
202 38 V5 1.9408867
203 39 V5 2.0105196
204 40 V5 2.0240603
205 41 V5 1.9986509
206 1 V6 2.7604032
207 2 V6 2.7480095
208 3 V6 2.7097223
209 4 V6 2.6958125
210 5 V6 2.6105382
211 6 V6 2.5355928
212 7 V6 2.4388681
213 8 V6 2.4554528
214 9 V6 2.4891361
215 10 V6 2.5077328
216 11 V6 2.3548875
217 12 V6 2.3558327
218 13 V6 2.4124644
219 14 V6 2.4197325
220 15 V6 2.4519078
221 16 V6 2.4934020
222 17 V6 2.5933631
223 18 V6 2.5933631
224 19 V6 2.4932248
225 20 V6 2.4500380
226 21 V6 2.4430684
227 22 V6 2.5200887
228 23 V6 2.4832765
229 24 V6 2.3941817
230 25 V6 2.3722242
231 26 V6 2.3417260
232 27 V6 2.2805031
233 28 V6 2.4397671
234 29 V6 2.4170213
235 30 V6 2.4760861
236 31 V6 2.4125734
237 32 V6 2.3471103
238 33 V6 2.3429898
239 34 V6 2.4485148
240 35 V6 2.4445050
241 36 V6 2.4393607
242 37 V6 2.4495364
243 38 V6 2.4054107
244 39 V6 2.3577567
245 40 V6 2.3736440
246 41 V6 2.5253512
247 1 V7 2.0602262
248 2 V7 2.0483372
249 3 V7 2.0736990
250 4 V7 2.1315484
251 5 V7 2.1799397
252 6 V7 2.3301890
253 7 V7 2.2959696
254 8 V7 2.2277231
255 9 V7 2.2939646
256 10 V7 2.2176999
257 11 V7 2.2831897
258 12 V7 2.2608763
259 13 V7 2.2078089
260 14 V7 2.2595722
261 15 V7 2.2997794
262 16 V7 2.3210011
263 17 V7 2.3872763
264 18 V7 2.3872763
265 19 V7 2.3771928
266 20 V7 2.4252593
267 21 V7 2.3247052
268 22 V7 2.3791342
269 23 V7 2.3491022
270 24 V7 2.1439292
271 25 V7 2.0383627
272 26 V7 2.0420853
273 27 V7 2.0024845
274 28 V7 1.9494101
275 29 V7 1.8449354
276 30 V7 1.9016126
277 31 V7 1.8161338
278 32 V7 1.8675445
279 33 V7 1.8903949
280 34 V7 1.8955622
281 35 V7 1.9092626
282 36 V7 1.7788932
283 37 V7 1.7412800
284 38 V7 1.6707951
285 39 V7 1.6438755
286 40 V7 1.6607334
287 41 V7 1.7414011
288 1 V8 1.4733552
289 2 V8 1.4362031
290 3 V8 1.4544211
291 4 V8 1.4581861
292 5 V8 1.5091275
293 6 V8 1.5023336
294 7 V8 1.4620160
295 8 V8 1.5097568
296 9 V8 1.6221026
297 10 V8 1.6092364
298 11 V8 1.7314998
299 12 V8 1.6633172
300 13 V8 1.5910380
301 14 V8 1.5666842
302 15 V8 1.5349787
303 16 V8 1.4716783
304 17 V8 1.4832044
305 18 V8 1.4832044
306 19 V8 1.3647461
307 20 V8 1.3758541
308 21 V8 1.2527031
309 22 V8 1.2535631
310 23 V8 1.2545834
311 24 V8 1.2030473
312 25 V8 1.1877904
313 26 V8 1.1673314
314 27 V8 1.1565594
315 28 V8 1.1913879
316 29 V8 1.1988982
317 30 V8 1.1852045
318 31 V8 1.1457429
319 32 V8 1.1960458
320 33 V8 1.2051532
321 34 V8 1.2331221
322 35 V8 1.2498006
323 36 V8 1.2960149
324 37 V8 1.2848459
325 38 V8 1.2658382
326 39 V8 1.2527976
327 40 V8 1.2304775
328 41 V8 1.2845763
329 1 V9 1.0947622
330 2 V9 1.1116325
331 3 V9 1.1260759
332 4 V9 1.0792304
333 5 V9 1.1135927
334 6 V9 1.0783778
335 7 V9 1.1552650
336 8 V9 1.0407025
337 9 V9 0.9814739
338 10 V9 0.9697538
339 11 V9 0.9738711
340 12 V9 1.0792870
341 13 V9 1.1419961
342 14 V9 1.1458102
343 15 V9 1.1518585
344 16 V9 1.1662038
345 17 V9 1.0965814
346 18 V9 1.0965814
347 19 V9 1.0771700
348 20 V9 1.0742737
349 21 V9 1.0623728
350 22 V9 0.9907468
351 23 V9 0.9523756
352 24 V9 1.0974362
353 25 V9 1.1455644
354 26 V9 1.1711806
355 27 V9 1.1766447
356 28 V9 1.1978350
357 29 V9 1.2063833
358 30 V9 1.2443743
359 31 V9 1.2621440
360 32 V9 1.1956573
361 33 V9 1.1876951
362 34 V9 1.0287512
363 35 V9 0.9414609
364 36 V9 0.9350406
365 37 V9 0.9801132
366 38 V9 0.9911915
367 39 V9 1.0392639
368 40 V9 0.9748509
369 41 V9 0.9681107
370 1 V10 0.7815317
371 2 V10 0.7724668
372 3 V10 0.7829253
373 4 V10 0.7839446
374 5 V10 0.7818569
375 6 V10 0.7467977
376 7 V10 0.8198222
377 8 V10 0.8894059
378 9 V10 0.8871695
379 10 V10 1.0217488
380 11 V10 0.9600032
381 12 V10 1.0234174
382 13 V10 1.0319810
383 14 V10 1.0081507
384 15 V10 1.0491675
385 16 V10 0.9703085
386 17 V10 0.8140696
387 18 V10 0.8140696
388 19 V10 0.9623639
389 20 V10 0.8540813
390 21 V10 0.8742382
391 22 V10 0.8648647
392 23 V10 0.8784826
393 24 V10 1.0928856
394 25 V10 1.0538718
395 26 V10 1.0598224
396 27 V10 1.1073631
397 28 V10 0.9505738
398 29 V10 0.9407248
399 30 V10 1.0043767
400 31 V10 1.2117631
401 32 V10 1.1648705
402 33 V10 1.1723112
403 34 V10 0.9904135
404 35 V10 1.0110657
405 36 V10 1.0342188
406 37 V10 1.0444609
407 38 V10 1.0697553
408 39 V10 1.0667992
409 40 V10 1.0035008
410 41 V10 0.7673388
411 1 V11 0.5392548
412 2 V11 0.5456137
413 3 V11 0.5641490
414 4 V11 0.5203727
415 5 V11 0.5153977
416 6 V11 0.5169318
417 7 V11 0.5534998
418 8 V11 0.5506033
419 9 V11 0.4745199
420 10 V11 0.5158155
421 11 V11 0.5096405
422 12 V11 0.5282389
423 13 V11 0.5144864
424 14 V11 0.5052571
425 15 V11 0.5025770
426 16 V11 0.5151202
427 17 V11 0.4558532
428 18 V11 0.4558532
429 19 V11 0.4727876
430 20 V11 0.4582600
431 21 V11 0.4691741
432 22 V11 0.4545345
433 23 V11 0.4649992
434 24 V11 0.4860698
435 25 V11 0.5230827
436 26 V11 0.5100968
437 27 V11 0.5914813
438 28 V11 0.5995068
439 29 V11 0.6245559
440 30 V11 0.6116879
441 31 V11 0.6470981
442 32 V11 0.6347906
443 33 V11 0.6217647
444 34 V11 0.6192189
445 35 V11 0.6655109
446 36 V11 0.6793624
447 37 V11 0.6325885
448 38 V11 0.6239640
449 39 V11 0.6466125
450 40 V11 0.6343966
451 41 V11 0.6147446
452 1 V12 0.3769467
453 2 V12 0.3238852
454 3 V12 0.3327886
455 4 V12 0.3262958
456 5 V12 0.3208774
457 6 V12 0.3169054
458 7 V12 0.3303225
459 8 V12 0.3329080
460 9 V12 0.3232346
461 10 V12 0.3430590
462 11 V12 0.3381513
463 12 V12 0.3404976
464 13 V12 0.3399407
465 14 V12 0.3342554
466 15 V12 0.3329909
467 16 V12 0.3342761
468 17 V12 0.3106927
469 18 V12 0.3106927
470 19 V12 0.3212534
471 20 V12 0.3181768
472 21 V12 0.3302283
473 22 V12 0.3317657
474 23 V12 0.3393688
475 24 V12 0.3456329
476 25 V12 0.3508390
477 26 V12 0.3496786
478 27 V12 0.3753360
479 28 V12 0.3744328
480 29 V12 0.3790487
481 30 V12 0.3746292
482 31 V12 0.3892668
483 32 V12 0.3780193
484 33 V12 0.3666250
485 34 V12 0.3799238
486 35 V12 0.3861426
487 36 V12 0.3984918
488 37 V12 0.3979160
489 38 V12 0.4011035
490 39 V12 0.4064036
491 40 V12 0.4054515
492 41 V12 0.3920580
这给了我这个漂亮的 ggplot:
ggplot(test, mapping = aes(x = variable, y = number, fill = value)) +
geom_raster() +
scale_fill_gradientn(colors = c("blue4", "dodgerblue1", "green3", "yellow", "red"), limits = c(0,3), name = "Value") +
scale_x_discrete(labels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"), name = "", expand = c(0,0)) +
scale_y_continuous(trans = "reverse", label = c(1:41), breaks = c(1:41), name = "", expand = c(0,0))
有什么方法可以量化这 41 行的差异程度吗？我的意思是，我总共有 260 个具有不同数据的此类图，我只想要其中行之间差异最大的一个。所以我试图给这 260 个地块中的每一个都赋予一定的 'similarity' 值，以区分它们中哪一个具有最大的内部差异。
希望这已经够清楚了 ;)
正如您在问题中提到的，您正在使用 data.table，我也会使用它。您可能想要量化数据集的 root mean square error。这与我在评论中给出的建议略有不同，但出于排名目的应该是相似的。
在下面的示例中，假设 question_data 是您问题中数据的引用复制粘贴。
library(data.table)
# Reading in data from question
test <- read.table(text = question_data)
setDT(test)
# Calculating metric
test[, diff := value - mean(value), by = "variable"]
sqrt(sum(test$diff^2))
#> [1] 2.509714
您可以比较行之间的相关性：
library(dplyr)
# put the rows in columns to allow correlation calculation
test <- test %>% pivot_wider(id_cols = variable, names_from = number, values_from = value)
# calculate correlation
test.cor <- cor(test[-1])
min(test.cor)
[1] 0.9231686
which(test.cor == min(test.cor),arr.ind = TRUE)
row col
40 40 12
12 12 40
# remove self correlation (1) before mean calculation
diag(test.cor) <- NA
mean(test.cor, na.rm = T)
[1] 0.9792281
最小相关性表明两个最不同的行有多么不同。
平均相关性说明所有行之间的平均差异。
我有以下数据表：
test <-
number variable value
1 1 V1 0.2635911
2 2 V1 0.2650884
3 3 V1 0.2569116
4 4 V1 0.2616717
5 5 V1 0.2564727
6 6 V1 0.2538608
7 7 V1 0.2633396
8 8 V1 0.2655517
9 9 V1 0.2738706
10 10 V1 0.2689698
11 11 V1 0.2775924
12 12 V1 0.2570329
13 13 V1 0.2628771
14 14 V1 0.2605258
15 15 V1 0.2588198
16 16 V1 0.2706452
17 17 V1 0.2587265
18 18 V1 0.2587265
19 19 V1 0.2613579
20 20 V1 0.2700729
21 21 V1 0.2781541
22 22 V1 0.2908526
23 23 V1 0.2828866
24 24 V1 0.2829607
25 25 V1 0.2800748
26 26 V1 0.2864499
27 27 V1 0.2976331
28 28 V1 0.3076221
29 29 V1 0.3125783
30 30 V1 0.3029413
31 31 V1 0.2921926
32 32 V1 0.2952376
33 33 V1 0.2917149
34 34 V1 0.3095391
35 35 V1 0.3192369
36 36 V1 0.3205008
37 37 V1 0.3210821
38 38 V1 0.3225114
39 39 V1 0.3165967
40 40 V1 0.3311130
41 41 V1 0.3355732
42 1 V2 0.2275850
43 2 V2 0.2268247
44 3 V2 0.2235245
45 4 V2 0.2277341
46 5 V2 0.2224330
47 6 V2 0.2216663
48 7 V2 0.2295579
49 8 V2 0.2303818
50 9 V2 0.2362313
51 10 V2 0.2288778
52 11 V2 0.2415600
53 12 V2 0.2260683
54 13 V2 0.2243258
55 14 V2 0.2217801
56 15 V2 0.2198674
57 16 V2 0.2303736
58 17 V2 0.2222210
59 18 V2 0.2222210
60 19 V2 0.2308805
61 20 V2 0.2408891
62 21 V2 0.2612180
63 22 V2 0.2713836
64 23 V2 0.2680126
65 24 V2 0.2700159
66 25 V2 0.2669348
67 26 V2 0.2668953
68 27 V2 0.2765348
69 28 V2 0.2911455
70 29 V2 0.2959731
71 30 V2 0.2860626
72 31 V2 0.2619870
73 32 V2 0.2623899
74 33 V2 0.2595488
75 34 V2 0.2741101
76 35 V2 0.2826556
77 36 V2 0.2913895
78 37 V2 0.2934421
79 38 V2 0.2842480
80 39 V2 0.2754619
81 40 V2 0.2918188
82 41 V2 0.2943509
83 1 V3 0.2294325
84 2 V3 0.2207675
85 3 V3 0.2276309
86 4 V3 0.2311673
87 5 V3 0.2421844
88 6 V3 0.2393514
89 7 V3 0.2464961
90 8 V3 0.2672072
91 9 V3 0.2706891
92 10 V3 0.2716877
93 11 V3 0.2775320
94 12 V3 0.2882381
95 13 V3 0.2760345
96 14 V3 0.2761454
97 15 V3 0.2686366
98 16 V3 0.2633213
99 17 V3 0.2558415
100 18 V3 0.2558415
101 19 V3 0.2651125
102 20 V3 0.2802660
103 21 V3 0.3130162
104 22 V3 0.3291228
105 23 V3 0.3293683
106 24 V3 0.3309799
107 25 V3 0.3303767
108 26 V3 0.3330788
109 27 V3 0.3427585
110 28 V3 0.3565055
111 29 V3 0.3305404
112 30 V3 0.3437861
113 31 V3 0.3146519
114 32 V3 0.2952635
115 33 V3 0.2902571
116 34 V3 0.3056054
117 35 V3 0.3046384
118 36 V3 0.3240068
119 37 V3 0.3324652
120 38 V3 0.3310975
121 39 V3 0.3256083
122 40 V3 0.3421986
123 41 V3 0.3462222
124 1 V4 0.5916363
125 2 V4 0.5779034
126 3 V4 0.5632020
127 4 V4 0.5467954
128 5 V4 0.5570823
129 6 V4 0.5797311
130 7 V4 0.5811650
131 8 V4 0.5862114
132 9 V4 0.5336045
133 10 V4 0.4983209
134 11 V4 0.5013016
135 12 V4 0.5489596
136 13 V4 0.5328552
137 14 V4 0.5628441
138 15 V4 0.5305244
139 16 V4 0.5396499
140 17 V4 0.5382373
141 18 V4 0.5382373
142 19 V4 0.5657389
143 20 V4 0.6095523
144 21 V4 0.6352541
145 22 V4 0.5622340
146 23 V4 0.5807564
147 24 V4 0.5726391
148 25 V4 0.5724073
149 26 V4 0.6093937
150 27 V4 0.6206982
151 28 V4 0.5944146
152 29 V4 0.6073015
153 30 V4 0.5912288
154 31 V4 0.6116150
155 32 V4 0.5825401
156 33 V4 0.5545265
157 34 V4 0.5916220
158 35 V4 0.6104256
159 36 V4 0.6034211
160 37 V4 0.6224549
161 38 V4 0.6931982
162 39 V4 0.6583044
163 40 V4 0.7277546
164 41 V4 0.7316220
165 1 V5 1.6012750
166 2 V5 1.7232682
167 3 V5 1.6849498
168 4 V5 1.7372409
169 5 V5 1.6904975
170 6 V5 1.6782624
171 7 V5 1.6236781
172 8 V5 1.6440954
173 9 V5 1.6140033
174 10 V5 1.5470975
175 11 V5 1.5507709
176 12 V5 1.4282340
177 13 V5 1.4641920
178 14 V5 1.4392424
179 15 V5 1.3988920
180 16 V5 1.4240200
181 17 V5 1.5839329
182 18 V5 1.5839329
183 19 V5 1.6081716
184 20 V5 1.6432765
185 21 V5 1.7558676
186 22 V5 1.7517093
187 23 V5 1.8167877
188 24 V5 1.7802214
189 25 V5 1.8784713
190 26 V5 1.8622613
191 27 V5 1.7720034
192 28 V5 1.7473988
193 29 V5 1.8420391
194 30 V5 1.6780098
195 31 V5 1.6348314
196 32 V5 1.7805307
197 33 V5 1.8170188
198 34 V5 1.9236170
199 35 V5 1.8752950
200 36 V5 1.8992993
201 37 V5 1.8998148
202 38 V5 1.9408867
203 39 V5 2.0105196
204 40 V5 2.0240603
205 41 V5 1.9986509
206 1 V6 2.7604032
207 2 V6 2.7480095
208 3 V6 2.7097223
209 4 V6 2.6958125
210 5 V6 2.6105382
211 6 V6 2.5355928
212 7 V6 2.4388681
213 8 V6 2.4554528
214 9 V6 2.4891361
215 10 V6 2.5077328
216 11 V6 2.3548875
217 12 V6 2.3558327
218 13 V6 2.4124644
219 14 V6 2.4197325
220 15 V6 2.4519078
221 16 V6 2.4934020
222 17 V6 2.5933631
223 18 V6 2.5933631
224 19 V6 2.4932248
225 20 V6 2.4500380
226 21 V6 2.4430684
227 22 V6 2.5200887
228 23 V6 2.4832765
229 24 V6 2.3941817
230 25 V6 2.3722242
231 26 V6 2.3417260
232 27 V6 2.2805031
233 28 V6 2.4397671
234 29 V6 2.4170213
235 30 V6 2.4760861
236 31 V6 2.4125734
237 32 V6 2.3471103
238 33 V6 2.3429898
239 34 V6 2.4485148
240 35 V6 2.4445050
241 36 V6 2.4393607
242 37 V6 2.4495364
243 38 V6 2.4054107
244 39 V6 2.3577567
245 40 V6 2.3736440
246 41 V6 2.5253512
247 1 V7 2.0602262
248 2 V7 2.0483372
249 3 V7 2.0736990
250 4 V7 2.1315484
251 5 V7 2.1799397
252 6 V7 2.3301890
253 7 V7 2.2959696
254 8 V7 2.2277231
255 9 V7 2.2939646
256 10 V7 2.2176999
257 11 V7 2.2831897
258 12 V7 2.2608763
259 13 V7 2.2078089
260 14 V7 2.2595722
261 15 V7 2.2997794
262 16 V7 2.3210011
263 17 V7 2.3872763
264 18 V7 2.3872763
265 19 V7 2.3771928
266 20 V7 2.4252593
267 21 V7 2.3247052
268 22 V7 2.3791342
269 23 V7 2.3491022
270 24 V7 2.1439292
271 25 V7 2.0383627
272 26 V7 2.0420853
273 27 V7 2.0024845
274 28 V7 1.9494101
275 29 V7 1.8449354
276 30 V7 1.9016126
277 31 V7 1.8161338
278 32 V7 1.8675445
279 33 V7 1.8903949
280 34 V7 1.8955622
281 35 V7 1.9092626
282 36 V7 1.7788932
283 37 V7 1.7412800
284 38 V7 1.6707951
285 39 V7 1.6438755
286 40 V7 1.6607334
287 41 V7 1.7414011
288 1 V8 1.4733552
289 2 V8 1.4362031
290 3 V8 1.4544211
291 4 V8 1.4581861
292 5 V8 1.5091275
293 6 V8 1.5023336
294 7 V8 1.4620160
295 8 V8 1.5097568
296 9 V8 1.6221026
297 10 V8 1.6092364
298 11 V8 1.7314998
299 12 V8 1.6633172
300 13 V8 1.5910380
301 14 V8 1.5666842
302 15 V8 1.5349787
303 16 V8 1.4716783
304 17 V8 1.4832044
305 18 V8 1.4832044
306 19 V8 1.3647461
307 20 V8 1.3758541
308 21 V8 1.2527031
309 22 V8 1.2535631
310 23 V8 1.2545834
311 24 V8 1.2030473
312 25 V8 1.1877904
313 26 V8 1.1673314
314 27 V8 1.1565594
315 28 V8 1.1913879
316 29 V8 1.1988982
317 30 V8 1.1852045
318 31 V8 1.1457429
319 32 V8 1.1960458
320 33 V8 1.2051532
321 34 V8 1.2331221
322 35 V8 1.2498006
323 36 V8 1.2960149
324 37 V8 1.2848459
325 38 V8 1.2658382
326 39 V8 1.2527976
327 40 V8 1.2304775
328 41 V8 1.2845763
329 1 V9 1.0947622
330 2 V9 1.1116325
331 3 V9 1.1260759
332 4 V9 1.0792304
333 5 V9 1.1135927
334 6 V9 1.0783778
335 7 V9 1.1552650
336 8 V9 1.0407025
337 9 V9 0.9814739
338 10 V9 0.9697538
339 11 V9 0.9738711
340 12 V9 1.0792870
341 13 V9 1.1419961
342 14 V9 1.1458102
343 15 V9 1.1518585
344 16 V9 1.1662038
345 17 V9 1.0965814
346 18 V9 1.0965814
347 19 V9 1.0771700
348 20 V9 1.0742737
349 21 V9 1.0623728
350 22 V9 0.9907468
351 23 V9 0.9523756
352 24 V9 1.0974362
353 25 V9 1.1455644
354 26 V9 1.1711806
355 27 V9 1.1766447
356 28 V9 1.1978350
357 29 V9 1.2063833
358 30 V9 1.2443743
359 31 V9 1.2621440
360 32 V9 1.1956573
361 33 V9 1.1876951
362 34 V9 1.0287512
363 35 V9 0.9414609
364 36 V9 0.9350406
365 37 V9 0.9801132
366 38 V9 0.9911915
367 39 V9 1.0392639
368 40 V9 0.9748509
369 41 V9 0.9681107
370 1 V10 0.7815317
371 2 V10 0.7724668
372 3 V10 0.7829253
373 4 V10 0.7839446
374 5 V10 0.7818569
375 6 V10 0.7467977
376 7 V10 0.8198222
377 8 V10 0.8894059
378 9 V10 0.8871695
379 10 V10 1.0217488
380 11 V10 0.9600032
381 12 V10 1.0234174
382 13 V10 1.0319810
383 14 V10 1.0081507
384 15 V10 1.0491675
385 16 V10 0.9703085
386 17 V10 0.8140696
387 18 V10 0.8140696
388 19 V10 0.9623639
389 20 V10 0.8540813
390 21 V10 0.8742382
391 22 V10 0.8648647
392 23 V10 0.8784826
393 24 V10 1.0928856
394 25 V10 1.0538718
395 26 V10 1.0598224
396 27 V10 1.1073631
397 28 V10 0.9505738
398 29 V10 0.9407248
399 30 V10 1.0043767
400 31 V10 1.2117631
401 32 V10 1.1648705
402 33 V10 1.1723112
403 34 V10 0.9904135
404 35 V10 1.0110657
405 36 V10 1.0342188
406 37 V10 1.0444609
407 38 V10 1.0697553
408 39 V10 1.0667992
409 40 V10 1.0035008
410 41 V10 0.7673388
411 1 V11 0.5392548
412 2 V11 0.5456137
413 3 V11 0.5641490
414 4 V11 0.5203727
415 5 V11 0.5153977
416 6 V11 0.5169318
417 7 V11 0.5534998
418 8 V11 0.5506033
419 9 V11 0.4745199
420 10 V11 0.5158155
421 11 V11 0.5096405
422 12 V11 0.5282389
423 13 V11 0.5144864
424 14 V11 0.5052571
425 15 V11 0.5025770
426 16 V11 0.5151202
427 17 V11 0.4558532
428 18 V11 0.4558532
429 19 V11 0.4727876
430 20 V11 0.4582600
431 21 V11 0.4691741
432 22 V11 0.4545345
433 23 V11 0.4649992
434 24 V11 0.4860698
435 25 V11 0.5230827
436 26 V11 0.5100968
437 27 V11 0.5914813
438 28 V11 0.5995068
439 29 V11 0.6245559
440 30 V11 0.6116879
441 31 V11 0.6470981
442 32 V11 0.6347906
443 33 V11 0.6217647
444 34 V11 0.6192189
445 35 V11 0.6655109
446 36 V11 0.6793624
447 37 V11 0.6325885
448 38 V11 0.6239640
449 39 V11 0.6466125
450 40 V11 0.6343966
451 41 V11 0.6147446
452 1 V12 0.3769467
453 2 V12 0.3238852
454 3 V12 0.3327886
455 4 V12 0.3262958
456 5 V12 0.3208774
457 6 V12 0.3169054
458 7 V12 0.3303225
459 8 V12 0.3329080
460 9 V12 0.3232346
461 10 V12 0.3430590
462 11 V12 0.3381513
463 12 V12 0.3404976
464 13 V12 0.3399407
465 14 V12 0.3342554
466 15 V12 0.3329909
467 16 V12 0.3342761
468 17 V12 0.3106927
469 18 V12 0.3106927
470 19 V12 0.3212534
471 20 V12 0.3181768
472 21 V12 0.3302283
473 22 V12 0.3317657
474 23 V12 0.3393688
475 24 V12 0.3456329
476 25 V12 0.3508390
477 26 V12 0.3496786
478 27 V12 0.3753360
479 28 V12 0.3744328
480 29 V12 0.3790487
481 30 V12 0.3746292
482 31 V12 0.3892668
483 32 V12 0.3780193
484 33 V12 0.3666250
485 34 V12 0.3799238
486 35 V12 0.3861426
487 36 V12 0.3984918
488 37 V12 0.3979160
489 38 V12 0.4011035
490 39 V12 0.4064036
491 40 V12 0.4054515
492 41 V12 0.3920580
这给了我这个漂亮的 ggplot:
ggplot(test, mapping = aes(x = variable, y = number, fill = value)) +
geom_raster() +
scale_fill_gradientn(colors = c("blue4", "dodgerblue1", "green3", "yellow", "red"), limits = c(0,3), name = "Value") +
scale_x_discrete(labels = c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"), name = "", expand = c(0,0)) +
scale_y_continuous(trans = "reverse", label = c(1:41), breaks = c(1:41), name = "", expand = c(0,0))
有什么方法可以量化这 41 行的差异程度吗？我的意思是，我总共有 260 个具有不同数据的此类图，我只想要其中行之间差异最大的一个。所以我试图给这 260 个地块中的每一个都赋予一定的 'similarity' 值，以区分它们中哪一个具有最大的内部差异。
希望这已经够清楚了 ;)
正如您在问题中提到的，您正在使用 data.table，我也会使用它。您可能想要量化数据集的 root mean square error。这与我在评论中给出的建议略有不同，但出于排名目的应该是相似的。
在下面的示例中，假设 question_data 是您问题中数据的引用复制粘贴。
library(data.table)
# Reading in data from question
test <- read.table(text = question_data)
setDT(test)
# Calculating metric
test[, diff := value - mean(value), by = "variable"]
sqrt(sum(test$diff^2))
#> [1] 2.509714
您可以比较行之间的相关性：
library(dplyr)
# put the rows in columns to allow correlation calculation
test <- test %>% pivot_wider(id_cols = variable, names_from = number, values_from = value)
# calculate correlation
test.cor <- cor(test[-1])
min(test.cor)
[1] 0.9231686
which(test.cor == min(test.cor),arr.ind = TRUE)
row col
40 40 12
12 12 40
# remove self correlation (1) before mean calculation
diag(test.cor) <- NA
mean(test.cor, na.rm = T)
[1] 0.9792281
最小相关性表明两个最不同的行有多么不同。
平均相关性说明所有行之间的平均差异。