-
Notifications
You must be signed in to change notification settings - Fork 0
/
gnuplot.py
1459 lines (1293 loc) · 48.4 KB
/
gnuplot.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/python3
## Tommy Carstensen, 2007-2013
import os, math, sys
import time
## Angstrom {\305}
## degree {\260} ?
## circumflex ?
def scatter_plot_2d(
prefix,
l1=None, l2=None,
d_xtics=None,
logarithmic=False,
errorbars=False,
regression=False, regression_data = None, regression_title = None,
xlabel='',ylabel='',
title=None,
x_min = '', x_max = '',
y_min = '', y_max = '',
terminal = 'postscript',
column1 = '1', column2 = '2',
line_plot = None, ## manual plot line
s_plot = None, ## manual def of stuff to be plotted
bool_remove = True,
lines_extra = None,
prefix_out=None,
bool_execute=True,
bool_title_enhanced=True,
path_gnuplot=None,
bool_timestamp = False,
):
if not path_gnuplot:
path_gnuplot = '/usr/bin/gnuplot'
if not prefix_out:
prefix_out = prefix
d_output = {
'postscript':'ps',
'png':'png',
}
d_terminal = {
'postscript':'%s eps enhanced color "Helvetica" 48' %(terminal),
'png':'png',
}
sett = []
## regression = False ## tmp!!!
if regression == True:
sett += [
## 'set fit logfile "%s.log"\n' %(prefix),
'f(x) = a*x+b\n',
]
## separate set of data to fit to? (e.g. if errorbars is main plot...)
if regression_data:
sett += [
'fit f(x) "%s" via a,b\n' %(regression_data),
]
else:
sett += [
'fit f(x) "%s" via a,b\n' %(prefix),
]
## write file to be plotted if data is provided
if l1 != None and l2 != None and not os.path.isfile(prefix):
lines = ['%s %s\n' %(pair[0],pair[1],) for pair in zip(l1,l2)]
fd = open('%s' %(prefix),'w')
fd.writelines(lines)
fd.close()
sett += [
'set terminal %s\n' %(d_terminal[terminal]),
'set output "%s.%s"\n' %(prefix_out, d_output[terminal]),
'set size 4,4\n', ## scale 400%
'set encoding iso_8859_1\n', ## postscript encoding *necessary* for special characters (e.g. Angstrom)
## 'set title "%s, %s\\njob: %s\\nchains: %s\\ndistance cutoff: %s{\305}" ,4\n' %(plotname, title1, jobid, chains, cutoff_distance),
'set xlabel "%s"\n' %(xlabel),
'set ylabel "%s"\n' %(ylabel),
]
if lines_extra:
sett += lines_extra
if title:
if bool_timestamp == True:
title += '\\n%s' %(time.strftime("%a, %d %b %Y %H:%M:%S", time.gmtime()))
if bool_title_enhanced == True:
sett += ['set title "%s"\n' %(title)]
else:
sett += ['set title "%s" noenhanced\n' %(title)]
if logarithmic == True:
sett += ['set logscale x\n']
if d_xtics:
line_xtic = 'set xtics ('
for xtic in d_xtics.keys():
line_xtic += '"%s" %s, ' %(xtic, d_xtics[xtic])
line_xtic = line_xtic[:-2]+')\n'
sett += [
line_xtic,
'set xtics rotate\n',
]
if not line_plot:
line_plot = 'plot '
if not s_plot:
line_plot += '[%s:%s]' %(x_min,x_max)
line_plot += '[%s:%s]' %(y_min,y_max)
line_plot += '"%s" u %s:%s ' %(prefix,column1,column2,)
else:
line_plot += s_plot
if regression_data:
ps = 3
else:
ps = 2
line_plot += ' lc 0 lt 1 ps %s lw 3 pt 7 t ""' %(
ps,
)
if errorbars == True:
line_plot += ' w errorb'
if regression == True:
line_plot += ', f(x) lt 1 lc 1 lw 10'
if regression_title:
line_plot += ' t "%s"' %(regression_title)
else:
line_plot += ' t ""'
line_plot += '\n'
sett += [line_plot]
fd = open('%s.plt' %(prefix_out),'w')
fd.writelines(sett)
fd.close()
if bool_execute == True:
cmd = '%s %s.plt' %(path_gnuplot,prefix_out)
os.system(cmd)
cmd = 'convert %s.ps %s.png' %(prefix_out, prefix_out,)
os.system(cmd)
## remove postscript if it was generated
if os.path.isfile('%s.ps' %(prefix_out)):
os.remove('%s.ps' %(prefix_out))
if bool_remove == True:
if bool_execute == True:
os.remove('%s.plt' %(prefix_out))
return
def plot_and_convert(
lines, prefix,
x_min='',x_max='',y_min='',y_max='',
xlabel='', ylabel='', title='',
bool_remove = False,
):
if not (
'plot' in ''.join(lines)
or
'sp ' in ''.join(lines)
):
sys.exit(0)
plt = []
plt += [
'set terminal postscript eps enhanced color "Helvetica" 24\n',
'set output "%s.ps"\n' %(prefix),
'set size 5,5\n', ## scale (not text)
'set encoding iso_8859_1\n',
'set autoscale fix\n', ## scale axes to include min and max *only* and *not* the next tic
]
plt += [
'set boxwidth 1\n',
## 'set tics out nomirror\n',
'set xlabel "{/=48 %s}"\n' %(xlabel),
'set ylabel "{/=48 %s}"\n' %(ylabel),
## 'set title "%s" noenhanced\n' %(title),
'set title "%s"\n' %(title),
]
## The `frequency` option makes the data monotonic in x; points with the same
## x-value are replaced by a single point having the summed y-values. The
## resulting points are then connected by straight line segments.
## See also
## smooth.dem
plt += lines
## write gnuplot settings
fd = open('%s.plt' %(prefix),'w')
fd.writelines(plt)
fd.close()
##
## execute gnuplot settings
##
## os.system('/usr/bin/gnuplot %s.plt' %(prefix))
os.system('/nfs/team149/Software/bin/gnuplot %s.plt' %(prefix))
## convert postscript to portable network graphics
if os.path.isfile('%s.png' %(prefix)):
os.remove('%s.png' %(prefix))
os.system('convert %s.ps %s.png' %(prefix,prefix,))
os.remove('%s.ps' %(prefix))
if bool_remove == True:
os.remove('%s.plt' %(prefix))
return
def dict2dat(fn,d,x1,x2,y1,y2,bool_replace_diagonal,l_sequence,bool_log,step=1,):
if l_sequence:
l_x = l_sequence+[len(l_sequence)]
l_y = l_sequence+[len(l_sequence)]
else:
l_x = list(range(x1,x2+step,step,))
l_y = list(range(y1,y2+step,step,))
with open(fn,'w') as f:
for i in range(len(l_x)):
x = l_x[i]
for j in range(len(l_y)):
y = l_y[j]
if bool_replace_diagonal and x == y:
try:
z = float(d[x+1][y])
except:
z = float(d[x-1][y])
else:
try:
z = float(d[x][y])
except:
z = 0
if bool_log == True and z != 0:
z = math.log(z,10)
if not l_sequence:
f.write('%s %s %s\n' %(x,y,z))
else:
f.write('%s %s %s\n' %(i,j,z))
f.write('\n')
return
def contour_plot(
fileprefix=None,
path_dat=None, ## input=file
d_dat=None, ## input=dict
l_dat=None, ## input=lines
title='',xlabel='',ylabel='',zlabel='',
x1=None,x2=None,
y1=None,y2=None,
z1=None,z2=None,
d_xtics = None,
d_ytics = None,
bool_remove = True,
size = 4,
line_splot = None,
col1=0, col2=1, col3=2,
bool_summed = False,
s_sep=' ',
bool_log = False,
bool_replace_diagonal = False,
l_sequence = [],
):
## at some point I should make it possible
## to just feed this function with 2 lists and zip the data automatically...
## this function is currently a bit of a mess...
if not line_splot:
if not fileprefix:
fileprefix = 'contour'
if d_dat:
if not x1:
x1 = min(list(d_dat.keys()))
if not x2:
x2 = max(list(d_dat.keys()))
if not y1:
y1 = min(list(d_dat[x1].keys()))
if not y2:
y2 = max(list(d_dat[x1].keys()))
dict2dat(
'%s.dat' %(fileprefix),d_dat,x1,x2,y1,y2,
bool_replace_diagonal,l_sequence,
bool_log,
)
elif path_dat:
fileprefix = path_dat
if bool_summed == False:
d = {}
with open(path_dat,'r') as file_dat:
for line_dat in file_dat:
l_dat = line_dat.strip().split(s_sep)
if l_dat == ['']: continue ## blank line
x = int(l_dat[col1])
y = int(l_dat[col2])
if x1 == None and x2 == None and y1 == None and y2 == None:
x1 = x
x2 = x
y1 = y
y2 = y
else:
if x < x1: x1 = x
elif x > x2: x2 = x
if y < y1: y1 = y
elif y > y2: y2 = y
v3 = float(l_dat[col3])
if bool_log == True and v3 != 0:
v3 = math.log(v3,10)
try:
d[x][y] += v3
except:
try:
d[x][y] = v3
except:
d[x] = {y:v3}
dict2dat(
'%s.dat' %(path_dat),d,x1,x2,y1,y2,bool_replace_diagonal,
l_sequence,bool_log,
)
elif l_dat:
fd = open('%s.dat' %(fileprefix), 'w')
fd.writelines(l_dat)
fd.close()
else:
stopnoinput
## write gnuplot settings to txt file
lines = ['set size square\n'] ## scale square
lines += [
'set terminal postscript eps enhanced color "Helvetica" 48\n',
'set output "%s.ps"\n' %(fileprefix),
'set size %i,%i\n' %(size,size), ## scale 400%
]
if not line_splot:
lines += [
'set view map\n', ## change orientation of plot
'set style data pm3d\n', ## set by default?
'set style function pm3d\n', ## set by default?
]
lines += [
'set autoscale fix\n', ## scale axes
'set encoding iso_8859_1\n', ## postscript encoding for special characters
'set title "%s"\n' %(title),
]
if xlabel:
lines += ['set xlabel "%s"\n' %(xlabel),]
if ylabel:
lines += ['set ylabel "%s"\n' %(ylabel),]
if zlabel:
lines += ['set cblabel "%s"\n' %(zlabel),]
lines += ['set zlabel "%s"\n' %(zlabel),]
if z1 != None or z2 != None:
## set colorbox range
line = 'set cbrange ['
if z1: line += '%s' %(z1,z2)
line += ':'
if z2: line += '%s' %(z2)
line += ']\n'
lines += [line]
if not line_splot:
lines += [
## 'set palette model CMY rgbformulae 7,5,15\n',
'set pm3d map corners2color c1\n', ## generate a 2D surface rather than 3D points
]
if d_xtics:
line_xtic = 'set xtics ('
for xtic in d_xtics.keys():
line_xtic += '"%s" %s, ' %(xtic, d_xtics[xtic])
line_xtic = line_xtic[:-2]+')\n'
lines += [
line_xtic,
'set xtics rotate\n',
## 'set xtics rotate by -90 offset 0,-1.5\n', ## tmp!!!
]
if d_ytics:
line = 'set ytics ('
for tic in d_ytics.keys():
line += '"%s" %s, ' %(tic, d_ytics[tic])
line = line[:-2]+')\n'
lines += [
line,
## 'set xtics rotate by -90 offset 0,-1.5\n', ## tmp!!!
]
if line_splot:
lines += [line_splot]
else:
line = 'splot '
line += '['
if x1: line += str(x1)
line += ':'
if x2: line += str(x2)
line += ']'
line += '['
if y1: line += str(y1)
line += ':'
if y2: line += str(y2)
line += ']'
line += '"%s.dat" title ""\n' %(fileprefix) ## splot gnuplot data file
lines += [line]
fd = open('%s.plt' %(fileprefix), 'w')
fd.writelines(lines)
fd.close()
## plot data with gnuplot splot
os.system('/usr/bin/gnuplot %s.plt' %(fileprefix))
## convert postscript to portable network graphics
print('convert')
os.system('convert %s.ps %s.png' %(fileprefix, fileprefix))
os.remove('%s.ps' %(fileprefix))
if bool_remove == True:
if line_splot == None:
os.remove('%s.dat' %(fileprefix))
os.remove('%s.plt' %(fileprefix))
return
def histogram2(
fileprefix,
l_data = None,
x_min = None, x_max = None,
y_max = '',
x_step = None, ## width of boxes
xlabel = None, ylabel = None, title = None,
bool_remove = True,
tic_step = None, ## tics on axis
s_plot = None,
column = '$1',
lines_extra = None,
color = 'blue',
prefix_out = None,
bool_timestamp = False,
):
if not prefix_out:
prefix_out = fileprefix
if l_data:
lines = ['%f\n' %(y) for y in l_data]
fd = open('%s' %(fileprefix),'w')
fd.writelines(lines)
fd.close()
elif s_plot == None and not os.path.isfile(fileprefix):
print('nothing to plot', fileprefix)
return
if bool_timestamp == True:
title += '\\n%s' %(time.strftime("%a, %d %b %Y %H:%M:%S", time.gmtime()))
sett = []
sett += [
'set terminal postscript eps enhanced color "Helvetica" 24\n',
'set output "%s.ps"\n' %(prefix_out),
'set size 2,2\n', ## scale 400%
'set encoding iso_8859_1\n',
'set autoscale fix\n', ## scale axes to include min and max *only* and *not* the next tic
]
if x_min != None and x_max != None:
sett += [
'min=%f\n' %(float(x_min)),
'max=%f\n' %(float(x_max)),
'set xrange [min:max]\n',
]
if tic_step:
sett += ['set xtics min,%f,max\n' %(tic_step),] ## min and max must be floats...
elif x_max != None:
sett += ['set xrange [:%f]\n' %(float(x_max))]
sett += [
'width=%s #interval width\n' %(x_step),
'#function used to map a value to the intervals\n',
'hist(x,width)=width*floor(x/width)+width/2.0\n',
'set yrange [0:]\n',
'#to put an empty boundary around the\n',
'#data inside an autoscaled graph.\n',
## 'set offset graph 0.05,0.05,0.05,0.0\n',
## 'set xtics min,(max-min)/%i,max\n' %(n_tics), ## min and max must be floats...
'set boxwidth width*0.9\n',
'set style fill solid 0.5 #fillstyle\n',
'set tics out nomirror\n',
'set xlabel "{/=36 %s}"\n' %(xlabel),
## 'set title "%s" noenhanced\n' %(title),
'set title "%s"\n' %(title),
## 'set ylabel "Frequency"\n',
'#count and plot\n',
## 'unset ytics\n',
]
if ylabel:
sett += ['set ylabel "{/=36 %s}"\n' %(ylabel),]
if lines_extra:
sett += lines_extra
## The `frequency` option makes the data monotonic in x; points with the same
## x-value are replaced by a single point having the summed y-values. The
## resulting points are then connected by straight line segments.
## See also
## smooth.dem
if s_plot == None:
sett += [
'plot [:][:%s]"%s" u (hist(%s,width)):(1.0) smooth freq w boxes lc rgb"%s" notitle\n' %(
y_max, fileprefix, column, color,
),
]
else:
sett += [s_plot]
## write gnuplot settings
fd = open('%s.plt' %(prefix_out),'w')
fd.writelines(sett)
fd.close()
##
## execute gnuplot settings
##
os.system('/usr/bin/gnuplot %s.plt' %(prefix_out))
## convert postscript to portable network graphics
if os.path.isfile('%s.png' %(prefix_out)):
os.remove('%s.png' %(prefix_out))
os.system('convert %s.ps %s.png' %(prefix_out,prefix_out,))
os.remove('%s.ps' %(prefix_out))
if bool_remove == True:
os.remove('%s.plt' %(prefix_out))
return
def histogram(
fileprefix,
d_data = None, l_xtics = None,
l_data = None,
ylabel=None,xlabel=None,l_plotdatafiles=[],title=None,
x_min = None, x_max = None, x_step = None,
y_min = '', y_max = '',
):
##
## write data
##
if l_data == None:
yrange = []
gnuplotdata = []
for i in range(len(l_xtics)):
res_name = l_xtics[i]
for y in d_data[res_name]:
gnuplotdata += ['%f %f\n' %(float(i),y)]
yrange += [y]
y_min = min(yrange)
y_max = max(yrange)
fd = open('%s.dat' %(fileprefix),'w')
fd.writelines(gnuplotdata)
fd.close()
elif l_data != None:
d_count = {}
for x in l_data:
xbin = x_step*int(x/x_step)
if not xbin in d_count.keys():
d_count[xbin] = 0
d_count[xbin] += 1
gnuplotdata = []
for xbin in range(int(x_min/x_step),int(x_max/x_step)+1,):
xbin *= x_step
if xbin in d_count.keys():
count = d_count[xbin]
else:
count = 0
gnuplotdata += ['%f %i\n' %(xbin,count,)]
fd = open('%s.dat' %(fileprefix),'w')
fd.writelines(gnuplotdata)
fd.close()
if l_xtics != None:
l_xtics = [xbin for xbin in range(int(x_min/x_step),int(x_max/x_step)+1,)]
else:
stop
##
## calculate statistics
##
if l_xtics != None:
gnuplot_statistics = []
for i in range(len(l_xtics)):
res_name = l_xtics[i]
n = len(d_data[res_name])
if n <= 1:
continue
sumx = 0
sumxx = 0
for x in d_data[res_name]:
sumx += x
sumxx += x**2
average = sumx/n
SS = sumxx-(sumx**2)/n
MSE = SS / (n-1)
if MSE < 0:
SE = 0 ## temp!!! check the equation!!!
else:
SE = math.sqrt(MSE/n)
gnuplot_statistics += ['%f %f %f\n' %(float(i),average,SE)]
## write statistics
fd = open('gnuplot.statistics','w')
fd.writelines(gnuplot_statistics)
fd.close()
##
## write gnuplot settings
##
sett = []
sett += [
'set terminal postscript eps enhanced color "Helvetica" 24\n',
'set output "gnuplot.ps"\n',
'set size 4,4\n', ## scale 400%
'set autoscale fix\n', ## scale axes to include min and max *only* and *not* the next tic
'set style fill\n',
## 'set style histogram\n',
## 'set style data histograms\n',
]
if title:
sett += [
'set title "%s"\n' %(title),
]
if xlabel:
sett += [
'set xlabel "%s"\n' %(xlabel),
]
sett += [
'set ylabel "{/=48 %s}"\n' %(ylabel),
]
if l_xtics != None:
line_xtic = 'set xtics ('
for xtic in l_xtics:
line_xtic += '"%s" %s, ' %(xtic, l_xtics.index(xtic))
line_xtic = line_xtic[:-2]+')\n'
sett += [
line_xtic,
'set xtics rotate\n',
]
sett += [
'plot ',
## '[-1:%i][%f:%f] "gnuplot.data" lt 0 ps 2 pt 2 t ""' %(len(l_xtics)+1, ymin, ymax),
'[%f:%f][%s:%s] "%s.dat" u 1:2 lt 0 t ""' %(
x_min, x_max, y_min, y_max, fileprefix,
),
]
if l_xtics:
sett += [
', ',
'"gnuplot.statistics" u 2 lt 1 lc 0 ps 0 pt 0 w errorb t ""',
]
for plotdatafile in l_plotdatafiles:
sett += [
', ',
'"%s" lt 0 lc 1 ps 3 pt 7 t ""\n' %(plotdatafile),
]
sett += ['\n']
## unset ytics
if ylabel == None:
sett += [
'unset ytics\n',
]
## write gnuplot settings
fd = open('%s.plt' %(fileprefix),'w')
fd.writelines(sett)
fd.close()
##
## execute gnuplot settings
##
os.system('/usr/bin/gnuplot gnuplot.plt')
## convert postscript to portable network graphics
os.system('convert gnuplot.ps %s.png' %(fileprefix))
os.remove('gnuplot.ps')
os.remove('%s.dat' %(fileprefix))
os.remove('%s.plt' %(fileprefix))
if l_xtics != None:
os.remove('gnuplot.statistics')
return
def bisection(r1,r2,A):
bisection = .5
d = r1
## the area of the intersection
## as a function of the distance between the centers of the circles
## is monotonic
## and thus a numerical solution can be found for d
## using a method of bisection
while True:
## http://en.wikipedia.org/wiki/Circular_segment
## a) d=d1+d2
## b) d1**2=r1**2-(c/2)**2
## c) d2**2=r2**2-(c/2)**2
## d1**2-r1**2=d2**2-r2**2
## d1**2=d2**2+r1**2-r2**2
## d1**2+d1**2+2d1d2=d1**2+d2**2+2d1d2+r1**2-r2**2
## 2d1(d1+d2)=(d1+d2)**2+r1**2-r2**2
## d1 = (d**2+r1**2-r2**2)/2d
d1 = (d**2+r1**2-r2**2)/(2*d)
d2 = (d**2+r2**2-r1**2)/(2*d)
alpha1 = 2*math.acos(d1/r1)
alpha2 = 2*math.acos(d2/r2)
## A = circular sector - triangular portion
## A = (pi*r**2 * angle/2pi) - ((r**2 sinangle)/2))
## A = .5r**2(angle-sinangle)
A_intersection = (
## area of circular segment 1
.5*(r1**2)*(alpha1-math.sin(alpha1))
+
## area of circular segment 2
.5*(r2**2)*(alpha2-math.sin(alpha2))
)
## ## http://mathworld.wolfram.com/Circle-CircleIntersection.html
## for x in xrange(1000000):
## A_intersection = (
## (r1**2)*math.acos((d**2+r1**2-r2**2)/(2*d*r1))
## +
## (r2**2)*math.acos((d**2+r2**2-r1**2)/(2*d*r2))
## -
## .5*math.sqrt((-d+r1+r2)*(d+r1-r2)*(d-r1+r2)*(d+r1+r2))
## )
diff = A_intersection - A
if abs(diff) < 0.001:
break
elif diff > 0:
d += bisection*r2
bisection *= .5
pass
else:
d -= bisection*r2
bisection *= .5
pass
continue
return d,d1,d2
def venn2(
f1=None,f2=None,
l1=None,l2=None,
i1=None,i2=None,i3=None,
text1='a',text2='b',
suffix = 'venn2',
verbose = False,
):
## Tommy Carstensen, November 2012
'''
draw area proportional Venn diagram for 2 sets
set object circle only works with gnuplot 4.3 and higher
alternatively plot a parametric function with gnuplot 4.2 and lower...
the postscript terminal does not support transparency
'''
if f1 != None:
fd = open(f1,'r')
l1 = fd.readlines()
fd.close()
fd = open(f2,'r')
l2 = fd.readlines()
fd.close()
## working with sets is definitely not the fastest method!!!
if l1 != None:
## circles
set_circle1 = set(l1)
set_circle2 = set(l2)
## circle-circle intersections
set_intersection12 = set_circle1&set_circle2
## lengths
i10 = i1 = len(set_circle1)
i01 = i2 = len(set_circle2)
i11 = i3 = len(set_intersection12)
## radii of circles
R1 = math.sqrt((i1)/math.pi)
R2 = math.sqrt((i2)/math.pi)
## area of intersections between circles
A_intersect12 = i3
if verbose == True:
print(R1, R2, R3)
##
## find distances between circle centers yielding correct area
## http://mathworld.wolfram.com/Circle-CircleIntersection.html
##
## distance between circle centers
d,d1,d2 = bisection(R1,R2,A_intersect12,)
## height = r(1-cos(alpha/2))
## lengths of sides of triangle between centers of circles
a = s110 = s12 = d
## coordinate centers of circles
c1 = [0,0,]
c2 = [a,0,]
sett = []
sett += [
'set terminal pngcairo transparent enhanced size 1440,1080\n',
## transparency does not work for the postscript terminal...
'set output "venn2_%s.png"\n' %(suffix),
'set size 1,1\n', ## scale 400%
'set autoscale fix\n', ## scale axes to include min and max *only* and *not* the next tic
## remove borders and tics
'set noborder\n',
'set noxtics\n',
'set noytics\n',
## avoid elongated circles...
## 'set size square\n',
'set size ratio -1\n', ## http://stackoverflow.com/questions/11138012/drawing-a-circle-of-radius-r-around-a-point
## add labels
'set label 1 "%s (%i)" at %s, %s front nopoint tc rgbcolor "red" left font "Verdana,24" noenhanced\n' %(
## text1, i1+i4+i5+i7, -0.7*R1, 0.7*R1,
text1, i1, 'graph(0.05)','graph(0.95)',
),
'set label 2 "%s (%i)" at %s, %s front nopoint tc rgb "green" right font "Verdana,24" noenhanced\n' %(
## text2, i2+i4+i6+i7, a+0.7*R2, 0.7*R2,
text2, i2, 'graph(0.95)','graph(0.95)',
),
]
## dual intersection (pos needs to be fixed...)
sett += [
'set label 4 "%i" at %f, %f front nopoint tc rgb "black" center font "Verdana,24" noenhanced\n' %(
i3, d1, 0,
),
]
sett += [
'set obj 1 circle center 0,0 size %f fc rgb "red" fs transparent solid 0.5 noborder\n' %(R1,),
'set obj 2 circle center %f,0 size %f fc rgb "green" fs transparent solid 0.5 noborder\n' %(c2[0],R2,),
'set yrange [%f:%f]\n' %(0-max(R1,R2),0+max(R1,R2),),
'plot [%f:%f][%f:%f] NaN notitle\n' %(
c1[0]-R1,c2[0]+R2,
-max(R1,R2),max(R1,R2),
),
]
## write gnuplot settings
fd = open('%s.plt' %(suffix),'w')
fd.writelines(sett)
fd.close()
##
## execute gnuplot settings
##
os.system('/nfs/team149/Software/bin/gnuplot %s.plt' %(suffix))
os.remove('%s.plt' %(suffix))
return
def venn3(
f1=None,f2=None,f3=None,
l1=None,l2=None,l3=None,
i1=None,i2=None,i3=None,i4=None,i5=None,i6=None,i7=None,
text1='a',text2='b',text3='c',
suffix = '',
verbose=False,
bool_labels=True,
bool_sorted=False,
):
## Tommy Carstensen, August 2012, July 2013
'''
draw area proportional Venn diagram for 3 sets
set object circle only works with gnuplot 4.3 and higher
alternatively plot a parametric function with gnuplot 4.2 and lower...
the postscript terminal does not support transparency
'''
if f1 != None:
for fn in (f1,f2,f3):
cmd = 'cat %s' %(fn)
if bool_sorted == False:
cmd += ' | sort'
cmd += ' > %s.sorted' %(fn)
execmd(cmd)
## intersection set
cmd = 'comm -12 %s.sorted %s.sorted > 11x' %(f1,f2)
execmd(cmd)
cmd = 'comm -23 %s.sorted %s.sorted > 10x' %(f1,f2)
execmd(cmd)
cmd = 'comm -13 %s.sorted %s.sorted > 01x' %(f1,f2)
execmd(cmd)
## union set
cmd = 'cat %s.sorted %s.sorted > 00x' %(f1,f2) ## 00x is a misleading name for a union set...
execmd(cmd)
i111 = int(os.popen('comm -12 %s.sorted 11x | wc -l' %(f3)).read())
i110 = int(os.popen('comm -13 %s.sorted 11x | wc -l' %(f3)).read())
i001 = int(os.popen('comm -23 %s.sorted 00x | wc -l' %(f3)).read())
i010 = int(os.popen('comm -13 %s.sorted 01x | wc -l' %(f3)).read())
i100 = int(os.popen('comm -13 %s.sorted 10x | wc -l' %(f3)).read())
i011 = int(os.popen('comm -12 %s.sorted 01x | wc -l' %(f3)).read())
i101 = int(os.popen('comm -12 %s.sorted 10x | wc -l' %(f3)).read())
## fd = open(f1,'r')
## l1 = fd.readlines()
## fd.close()
## fd = open(f2,'r')
## l2 = fd.readlines()
## fd.close()
## fd = open(f3,'r')
## l3 = fd.readlines()
## fd.close()
## working with sets is definitely not the fastest method!!!
if l1 != None:
## circles
set_circle1 = set(l1)
set_circle2 = set(l2)
set_circle3 = set(l3)
## circle-circle intersections
set_intersection12 = set_circle1&set_circle2
set_intersection13 = set_circle1&set_circle3
set_intersection23 = set_circle2&set_circle3
set7 = set_intersection12&set_intersection13&set_intersection23
## subtract intersections
set4 = set_intersection12-set7
set5 = set_intersection13-set7
set6 = set_intersection23-set7
set1 = set_circle1-set4-set5-set7
set2 = set_circle2-set4-set6-set7
set3 = set_circle3-set5-set6-set7
## lengths
i100 = i1 = len(set1)
i010 = i2 = len(set2)
i001 = i3 = len(set3)
i12 = i110 = i4 = len(set4)
i13 = i101 = i5 = len(set5)
i23 = i011 = i6 = len(set6)
i123 = i111 = i7 = len(set7)
sum1 = i100+i110+i101+i111
sum2 = i010+i110+i011+i111
sum3 = i001+i101+i011+i111
sum4 = i110
sum5 = i101
sum6 = i011
sum7 = i111
## radii of circles
R1 = math.sqrt((i100+i110+i101+i111)/math.pi)
R2 = math.sqrt((i010+i110+i011+i111)/math.pi)
R3 = math.sqrt((i001+i101+i011+i111)/math.pi)
## area of intersections between circles
A_intersect12 = i110+i111
A_intersect13 = i101+i111
A_intersect23 = i011+i111
if verbose == True:
print(R1, R2, R3)
## r_max = max(R1, R2, R3)
## R1 /= r_max
## R2 /= r_max
## R3 /= r_max
## A_intersect12 /= math.pi*r_max**2
## A_intersect13 /= math.pi*r_max**2
## A_intersect23 /= math.pi*r_max**2
##
## find distances between circle centers yielding correct area
## http://mathworld.wolfram.com/Circle-CircleIntersection.html
##
## list of distances between circle centers
l_d = []
for r1,r2,A in [
[R1,R2,A_intersect12,],
[R1,R3,A_intersect13,],
[R2,R3,A_intersect23,],
]:
d,d1,d2 = bisection(r1,r2,A)
## append distance to list of distance between circle centers
l_d += [[d,d1,d2,]]