-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathprepNew.sh
2351 lines (1948 loc) · 114 KB
/
prepNew.sh
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
#!/bin/bash
####################
#new ver R
####################
##################################################################################################################
# report stats for the ICSE submission Table 1-2
##################################################################################################################
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb java C rb PY JS ; do zcat PtAPkgR$la.s| perl -e 'while(<STDIN>){chop();($p,$t,$a,@ms)=split(/;/);$as{$a}++;$ps{$p}++;$ls{$#ms}++, $n++;} print STDERR "'$la';$n;".(scalar(keys %as)).";".(scalar(keys %ps))."\n"; for $nl (keys %ls){print "$nl;$ls{$nl}\n"}' | gzip > PtAPkgR$la.nm; done
######################
#lang;chages;authors;projects
F;1628760;24898;15623
jl;1297134;18666;35723
R;6822662;361754;516678
ipy;12160775;793261;1154120
pl;18780774;480615;547115
Rust;13599452;95712;148327
Dart;7036000;116317;164360
Kotlin;28129485;281469;429071
TypeScript;239416852;1605563;2253291
Cs;220871444;2092316;3092761
Go;123432323;490967;662355
Scala;36361141;176414;210175
rb;74618824;1222886;2343825
JS;55609812;3362191;7347050
PY;612708423;4795735;6820899
C;1780602124;3656965;4704446
java;1106084606;5063200;7512800
#lang;apis
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb java C rb PY JS ;do zcat PtAPkgR$la.s| perl -e 'while(<STDIN>){chop();($p,$t,$a,@ms)=split(/;/);for $m (@ms){$mm{$m}++;}} print "'$la';".(scalar(keys %mm))."\n";'; done
F;59349
jl;104725
R;85255
ipy;687085
pl;58942
Rust;818686
Dart;467863
Kotlin;6233673
TypeScript;7324019
Cs;6648357
Go;245102
Scala;3571593
java;85079403
JS;1105918
PY;17227676
rb;669297
C;2553521
#quantiles on the number of APIs per blob counting % of delta with <=30 APIs
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb java C rb PY JS; do zcat PtAPkgR$la.nm|lsort 1G -t\; -k2 -rn | awk -F\; '{n+=$2; c[$1]=$2} END {num=0;for (k=0;k<=30;k++){num+=c[k]};print "'$la'",num/n,n,$1}'; done
F 0.984606 1628760 106
jl 0.988739 1297134 108
R 0.998431 6822662 117
ipy 0.990262 12160775 1158
pl 0.999785 18780774 109
Rust 0.992667 13599452 118
Dart 0.993704 7036000 165
Kotlin 0.964331 28129485 1096
TypeScript 0.989924 239416852 1013
Cs 0.997572 220871444 150
Go 0.995657 123432323 1207
Scala 0.990467 36361141 1288
rb 0.997044 74618824 1002
java 0.916324 1106084606 1004
C 0.986453 1780602124 1007
rb 0.997044 74618824 1002
PY 0.989345 612708423 1001
JS 0.667983 55609812 10014
##################################################################################################################
##################################################################################################################
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do zcat PtAPkgR$la.s | perl -e 'while(<STDIN>){chop();($p,$t,$a)=split(/;/);$pre=0; $pre=1 if $t>= 1518784533+3600*24*365.25; $pn{$p}{$pre}++; $an{$a}{$pre}++;}; for my $p (keys %pn){print "p;$p;$pn{$p}{1};$pn{$p}{0}\n";} for my $a (keys %an){print "a;$a;$an{$a}{1};$an{$a}{0}\n";}' | gzip > PtAPkgR$la.cnt
done
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do zcat PtAPkgR$la.cnt| grep ^a | awk -F\; '{if($4>100 && $3>100)print $0}' > PtAPkgR$la.cnt100
done
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do cut -d\; -f2 PtAPkgR$la.cnt100
done | lsort 1G -u | gzip > AuR100.gz
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do zcat PtAPkgR$la.s
done | perl ~/bin/grepField.perl AuR100.gz 3 | gzip > PtAPkgRAllA100.s
#fit in da5:/data/play/forks
ls -f /da0_data/play/*thruMaps/b2cPtaPkgR*.s| while read f; do la=$(echo $f|sed 's|.*b2cPtaPkgR||;s|\.[0-9]*\.s$||'); zcat $f | cut -d\; -f3- | ~/lookup/grepField.perl eap 1 | awk '{print "'$la';"$0}'; done | gzip > eap.api
zcat eap.api | perl ~/lookup/mp.perl 3 /da0_data/basemaps/gz/a2AQ.s | gzip > eAp.api
python3 fitXldRea.py eAp.api 200 30 20 5 1550908281 eAp eAp
python3 fitXldRea.py eA.api 200 30 20 5 1550908281 eA eA
#prepare api prediction
#first count delta for authors
zcat /da4_data/play/api/eAp.api|cut -d\; -f4|lsort 100G |uniq -c | sed 's|^\s*||;s|\s|;|' |perl -ane 's/\r//g;print'| gzip > eAp.c2a.gz
zcat eAp.c2a.gz|perl -ane 'chop();($n,$a)=split(/;/);print "$a\n" if $n >=100 && $n < 25000;' | gzip > eAp.a100
zcat /da4_data/play/api/eAp.api| ~/bin/grepField.perl eAp.a100 4 | gzip > /da4_data/play/api/eAp.api100
python3 fitXldRea.py eAp.api100 200 30 20 5 1518784533 eAp100 eAp100
##################################################################################################################
# report stats for the ICSE submission Table 3
##################################################################################################################
#need eAp.api
perl prepPredApi.perl | gzip > eAp.sAD
python3 measureAPIvR.py| gzip > measureAPIvR.gz
f='measureAPIvR.gz'
aa = read.table("eAp.c2a.gz",sep=";",quote="",comment.char="");
amed = as.character(aa[aa[,1]>100&aa[,1]<25000,2]);
x = read.table(f,sep=";",quote="",comment.char="");
ind = match(x[,1], amed,nomatch=0);
a = tapply(x$V5[ind>0], list(x$V1[ind>0],x$V3[ind>0],x$V2[ind>0]), mean,na.rm=T);
a1 = tapply(x$V5[ind>-1], list(x$V1[ind>-1],x$V3[ind>-1],x$V2[ind>-1]), mean,na.rm=T);
las=c("Dart","jl","R","ipy","pl","Rust","Kotlin","TypeScript","Cs","Go","Scala","rb","java","C","PY","JS");
res = c();
for (la in las){
res=rbind(res, c(t.test(a[,2,la]-a[,3,la])$estimate,t.test(a[,2,la]-a[,3,la])$p.value))
}
dimnames(res)[[1]]=las;
res
Dart 0.41207559 3.120130e-92
jl 0.20955929 8.565540e-05
R 0.14442871 1.455249e-06
ipy 0.19954272 6.677312e-65
pl 0.04645639 2.852958e-13
Rust 0.20947185 2.010680e-151
Kotlin 0.20606213 1.090052e-139
TypeScript 0.23007271 0.000000e+00
Cs 0.24571956 6.162232e-137
Go 0.14883848 0.000000e+00
Scala 0.20382756 8.451967e-89
rb 0.16819598 3.796952e-188
java 0.12770313 0.000000e+00
C 0.13112611 0.000000e+00
PY 0.11885238 0.000000e+00
JS 0.09861961 0.000000e+00
#prepare project prediction
perl prepPredPrj.perl | gzip > eAp.sAPD
python3 measureAPvR.py| gzip > measureAPvR.gz
aa = read.table("eAp.c2a.gz",sep=";",quote="",comment.char="");
amed = as.character(aa[aa[,1]>100&aa[,1]<25000,2]);
f='measureAPvR.gz'
x = read.table(f,sep=";",quote="",comment.char="");
#zz=table(x[,1]);ind = match(x[,1],names(zz)[zz>5],nomatch=0)
ind = match(x[,1], amed,nomatch=0);
a = tapply(x$V4[ind>0], list(x$V1[ind>0],x$V2[ind>0]), mean,na.rm=T);
t.test(a[,2]-a[,3])
data: a[, 2] - a[, 3]
t = 8.8863, df = 8614, p-value < 2.2e-16
alternative hypothesis: true mean is not equal to 0
95 percent confidence interval:
0.01347707 0.02110568
sample estimates:
mean of x
0.01729138
#prepare Author prediction
perl prepPredAuth.perl | gzip > eAp.sPAD
python3 measurePAvR.py|perl -ane 's/\r//g;print'| gzip > measurePAvR.gz
f='measurePAvR.gz'
x = read.table(f,sep=";",quote="",comment.char="");
ind = match(x[,3], amed,nomatch=0);
a = tapply(x$V4[ind>0], list(x$V1[ind>0],x$V2[ind>0]), mean,na.rm=T);
t.test(a[,2]-a[,3])
data: a[, 2] - a[, 3]
t = 18.216, df = 513, p-value < 2.2e-16
alternative hypothesis: true mean is not equal to 0
95 percent confidence interval:
0.1253809 0.1556942
sample estimates:
mean of x
0.1405376
##################################################################################################################
#do PRs
# Try new PR data
perl joinPrs.perl > joinedPrs.csv
cut -d\; -f2 joinedPrs.csv | sort -u -t\; | gzip > au.prs.new
zcat au.prs.new | perl ~/lookup/mp.perl 0 /da0_data/basemaps/gz/a2AQ.s | lsort 1G -t\; -u | gzip > Au.prs.new
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do zcat PtAPkgR$la.s | perl ~/lookup/grepField.perl Au.prs.new 3 | gzip > PtAPkgR$la.prs.s
done
cat joinedPrs.csv | sed 's|https://github.com/||;s|/pull/|;|;s|/|_|;' | perl ~/lookup/mp.perl 0 /da0_data/basemaps/gz/p2PR.s | perl ~/lookup/mp.perl 2 /da0_data/basemaps/gz/a2AQ.s > joinedPrsAP.csv
cut=1518784533
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Go Scala rb Cs C java PY JS
do zcat PtAPkgR$la.prs.s | awk '{print "'$la';"$0}'
done | perl -e 'while(<STDIN>){chop(); ($la,$p,$t,$a,@ms)=split(/;/);if ($t < '$cut'){ for $m (@ms){$k{"$p;$a;$la"}{$m}++}}};while (($p, $v)=each %k){@ms=sort keys %{$v}; print "$p;".(join ";", @ms)."\n";}' | gzip > prs.Rnew.s2.$cut
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Go Scala rb Cs C java PY JS
do zcat PtAPkgR$la.prs.s
done | perl -e 'while(<STDIN>){chop(); ($p,$t,$a,@ms)=split(/;/);if ($t >= '$cut'){ for $m (@ms){$k{"$p;$a"}{$m}++}}};while (($p, $v)=each %k){@ms=sort keys %{$v}; print "$p;".(join ";", @ms)."\n";}' | gzip > prs.Rnew.s4.$cut
perl cmpAprsvRnew.perl prs.Rnew $cut | gzip > prs.Rnew.sAD.$cut
python3 measureAPprsvRnew.py /da4_data/play/api/doc2vecR.200.30.20.5.$cut.JS.trained prs.Rnew.sAD.$cut | perl -ane 's/\r//g;print' > out.prs.JSRnew.$cut
python3 fitXldRprs.py PtAPkgR 200 30 20 5 1518784533 PRs F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS 2> fitPRs.err
python3 measureAPprsvRnew.py doc2vecR.200.30.20.5.1518784533.PRs.trained prs.Rnew.sAD.$cut 2> missPRs | perl -ane 's/\r//g;print' > out.prs.PRsRnew.$cut
x=read.table("out.prs.PRsRnew.1518784533",sep=";",quote="",comment.char="");
if (length(grep('\\bbot\\b', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('\\(bot\\)', x$V1,perl=T,ignore.case=T),]
if (length(grep('Automation', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('Automation', x$V1,perl=T,ignore.case=T),]
sim=x[,dim(x)[2]];
y = x[,3]=='True';
prev = x[,4]>0;
z=x[,-c(1:4,20,23)]
summary(glm(y~sim,family=binomial))$coefficients
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.2851478 0.01129879 25.23701 1.572824e-140
sim 0.5007773 0.02464404 20.32043 8.483674e-92
#JS specific, where most of PRs are
x=read.table("out.prs.JSRnew.1518784533",sep=";",quote="",comment.char="");
if (length(grep('\\bbot\\b', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('\\(bot\\)', x$V1,perl=T,ignore.case=T),]
if (length(grep('Automation', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('Automation', x$V1,perl=T,ignore.case=T),]
#nn = table(as.character(x[,1]));ind = match(x[,1], names(nn[nn<3]),nomatch=0); x=x[ind > 0,];
#ind = match(x[,1], amed,nomatch=0);x=x[ind > 0,];
#x=x[x$V8+x$V7>0,]
#response
#y=cbind(x$V8,x$V7)
sim=x[,dim(x)[2]];
y = x[,3]=='True';
prev = x[,4]>0;
z=x[,-c(1:4,20:23)]
summary(glm(y~sim,family=binomial))$coefficients
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.2584875 0.01106767 23.35519 1.220673e-120
sim 0.7322888 0.02614693 28.00669 1.346974e-172
form=as.formula(paste(c("y~sim",names(z)),collapse="+"));
mod = glm(form,family=binomial,data=z,subs=!prev)
summary(mod);
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.582e+00 5.351e-02 -29.565 < 2e-16 ***
sim 5.044e-01 9.093e-02 5.547 2.90e-08 ***
V5 -1.084e-04 1.946e-05 -5.572 2.51e-08 ***
V6 1.132e+00 3.422e-02 33.076 < 2e-16 ***
V7 -7.296e-06 9.040e-07 -8.071 6.98e-16 ***
V8 3.209e+00 5.957e-02 53.864 < 2e-16 ***
V9 -2.346e-01 2.291e-02 -10.240 < 2e-16 ***
V10 -1.436e-06 1.286e-08 -111.726 < 2e-16 ***
V11 6.754e-03 1.363e-03 4.956 7.18e-07 ***
V12 1.505e-02 1.014e-03 14.841 < 2e-16 ***
V13 -2.105e-02 7.262e-04 -28.993 < 2e-16 ***
V14 6.316e-06 1.569e-06 4.026 5.67e-05 ***
V15 -7.116e-06 1.921e-06 -3.704 0.000212 ***
V16 -1.608e-03 1.918e-04 -8.384 < 2e-16 ***
V17 2.648e-01 2.344e-02 11.299 < 2e-16 ***
V18 -4.830e-01 3.881e-01 -1.244 0.213322
V19 9.170e-01 2.867e-02 31.980 < 2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 86374 on 62419 degrees of freedom
Residual deviance: 50436 on 62403 degrees of freedom
AIC: 50470
library(car)
> vif(mod)
sim V5 V6 V7 V8 V9 V10 V11
1.065648 1.031543 1.414611 1.242080 1.101948 1.033086 1.288278 1.246721
V12 V13 V14 V15 V16 V17 V18 V19
1.276105 1.395016 1.938039 1.824200 1.265469 1.083477 1.001566 1.527913
mod = glm(y~sim+V5+V6+ V7 + V8 + V9 + V10 + V11 + V12 + V17+V18+V19+V21+V22,family=binomial,data=z,subs=!prev)
summary(mod)
Estimate Std. Error z value Pr(>|z|)
(Intercept) -1.648e+00 5.429e-02 -30.363 < 2e-16 ***
sim 6.020e-01 9.332e-02 6.450 1.12e-10 ***
V5 -1.154e-03 1.084e-04 -10.641 < 2e-16 ***
V6 1.204e+00 3.529e-02 34.117 < 2e-16 ***
V7 -4.674e-06 9.073e-07 -5.152 2.58e-07 ***
V8 3.055e+00 5.997e-02 50.944 < 2e-16 ***
V9 -2.546e-01 2.317e-02 -10.988 < 2e-16 ***
V10 -1.426e-06 1.302e-08 -109.481 < 2e-16 ***
V11 2.421e-03 1.351e-03 1.792 0.0732 .
V12 4.903e-03 9.239e-04 5.306 1.12e-07 ***
V17 2.615e-01 2.365e-02 11.057 < 2e-16 ***
V18 -4.678e-01 3.971e-01 -1.178 0.2388
V19 7.501e-01 2.872e-02 26.119 < 2e-16 ***
V21 -1.510e-06 1.229e-06 -1.228 0.2194
V22 1.375e-05 2.133e-06 6.445 1.15e-10 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 81054 on 58590 degrees of freedom
Residual deviance: 49093 on 58576 degrees of freedom
### old PR data
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do zcat PtaPkgR$la.prs.s
done | perl -e 'while(<STDIN>){chop(); ($p,$t,$a,@ms)=split(/;/);if ($t >= '$cut'){ for $m (@ms){$k{"$p;$a"}{$m}++}}};while (($p, $v)=each %k){@ms=sort keys %{$v}; print "$p;".(join ";", @ms)."\n";}' | gzip > prs.R.s4.$cut
cat PRdata_newA.csv | perl ~/lookup/mp.perl 1 /da0_data/basemaps/gz/p2PR.s > PRdata_newAR.csv
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb java C PY JS
do zcat PtAPkgR$la.s | perl ~/bin/grepField.perl au.prs 3 | gzip > PtaPkgR$la.prs.s
done
cut=1550908281
cut=1518784533
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do zcat PtaPkgR$la.prs.s | awk '{print "'$la';"$0}'
done | perl -e 'while(<STDIN>){chop(); ($la,$p,$t,$a,@ms)=split(/;/);if ($t < '$cut'){ for $m (@ms){$k{"$p;$a;$la"}{$m}++}}};while (($p, $v)=each %k){@ms=sort keys %{$v}; print "$p;".(join ";", @ms)."\n";}' | gzip > prs.R.s2.$cut
for la in F jl R ipy pl Rust Dart Kotlin TypeScript Cs Go Scala rb C java PY JS
do zcat PtaPkgR$la.prs.s
done | perl -e 'while(<STDIN>){chop(); ($p,$t,$a,@ms)=split(/;/);if ($t >= '$cut'){ for $m (@ms){$k{"$p;$a"}{$m}++}}};while (($p, $v)=each %k){@ms=sort keys %{$v}; print "$p;".(join ";", @ms)."\n";}' | gzip > prs.R.s4.$cut
perl cmpAprsvR.perl prs.R $cut | gzip > prs.R.sAD.$cut
x=read.table("out.prs.R100.1518784533",sep=";",quote="",comment.char="");
if (length(grep('\\bbot\\b', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('\\(bot\\)', x$V1,perl=T,ignore.case=T),]
if (length(grep('Automation', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('Automation', x$V1,perl=T,ignore.case=T),]
#nn = table(as.character(x[,1]));ind = match(x[,1], names(nn[nn<3]),nomatch=0); x=x[ind > 0,];
#ind = match(x[,1], amed,nomatch=0);x=x[ind > 0,];
x=x[x$V8+x$V7>0,]
#response
y=cbind(x$V8,x$V7)
sim=x$V9
summary(glm(y~sim,family=binomial))$coefficients
for la in JS
do zcat PtaPkgR$la.prs.s | awk '{print "'$la';"$0}'
done | perl -e 'while(<STDIN>){chop(); ($la,$p,$t,$a,@ms)=split(/;/);if ($t < '$cut'){ for $m (@ms){$k{"$p;$a;$la"}{$m}++}}};while (($p, $v)=each %k){@ms=sort keys %{$v}; print "$p;".(join ";", @ms)."\n";}' | gzip > prs.JSR.s2.$cut
for la in JS
do zcat PtaPkgR$la.prs.s
done | perl -e 'while(<STDIN>){chop(); ($p,$t,$a,@ms)=split(/;/);if ($t >= '$cut'){ for $m (@ms){$k{"$p;$a"}{$m}++}}};while (($p, $v)=each %k){@ms=sort keys %{$v}; print "$p;".(join ";", @ms)."\n";}' | gzip > prs.JSR.s4.$cut
perl cmpAprsvR.perl prs.JSR $cut | gzip > prs.JSR.sAD.$cut
#python3 measureAPprsvR.py /da4_data/play/api/doc2vecR.200.30.20.5.$cut.eAp.trained prs.R.sAD.$cut |perl -ane 's/\r//g;print' > out.prs.R.$cut
#python3 measureAPprsvR.py /da4_data/play/api/doc2vecR.200.30.20.5.1550908281.eAp.trained prs.R.sAD.$cut |perl -ane 's/\r//g;print' > out.prs.R.$cut
python3 measureAPprsvR.py /da4_data/play/api/doc2vecR.200.30.20.5.1550908281.eAp.trained prs.JSR.sAD.$cut |perl -ane 's/\r//g;print' > out.prs.JSR.$cut
python3 measureAPprsvR.py /da4_data/play/api/doc2vecR.200.30.20.5.1550908281.eA.trained prs.JSR.sAD.$cut |perl -ane 's/\r//g;print' > out.prs.JSR1.$cut
python3 measureAPprsvR.py /da4_data/play/api/doc2vecR.200.30.20.5.$cut.eA.trained prs.R.sAD.$cut |perl -ane 's/\r//g;print' > out.prs.R1.$cut
python3 measureAPprsvR.py /da4_data/play/api/doc2vecR.200.30.20.5.$cut.eAp100.trained prs.R.sAD.$cut |perl -ane 's/\r//g;print' > out.prs.R100.$cut
aa = read.table("eAp.c2a.gz",sep=";",quote="",comment.char="");
amed = as.character(aa[aa[,1]>100&aa[,1]<25000,2]);
x=read.table("out.prs.R100.1518784533",sep=";",quote="",comment.char="");
if (length(grep('\\bbot\\b', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('\\(bot\\)', x$V1,perl=T,ignore.case=T),]
if (length(grep('Automation', x$V1,perl=T,ignore.case=T) > 0)) x=x[-grep('Automation', x$V1,perl=T,ignore.case=T),]
#nn = table(as.character(x[,1]));ind = match(x[,1], names(nn[nn<3]),nomatch=0); x=x[ind > 0,];
#ind = match(x[,1], amed,nomatch=0);x=x[ind > 0,];
x=x[x$V8+x$V7>0,]
#response
y=cbind(x$V8,x$V7)
sim=x$V9
summary(glm(y~sim,family=binomial))$coefficients
Estimate Std. Error z value Pr(>|z|)
(Intercept) -0.39494073 0.01360379 -29.031662 2.622661e-185
sim 0.09917047 0.03403742 2.913572 3.573196e-03
#
#nn = table(as.character(x[,1]));ind = match(x[,1], names(nn[nn<3]),nomatch=0); x=x[ind > 0,];
#############################################
#do self-assessment Table 5-6 ICSE
#############################################
python3 m675vR.py > out675.vR
mttp = function (x) t.test(x)$p.value
mtte = function (x) t.test(x)$estimate
z=read.table('out675.vR',sep=";",quote="",comment.char="")
##################################################
# Table 5 ICSE
##################################################
summary(lm(V4~-1+V1+log(V2)+V3,data=z))
Estimate Std. Error t value Pr(>|t|)
V1mongodb 0.2494751 0.0130248 19.154 < 2e-16 ***
V1react 0.3070126 0.0111510 27.532 < 2e-16 ***
V1socketio 0.4220339 0.0118403 35.644 < 2e-16 ***
log(V2) -0.0002471 0.0015631 -0.158 0.874
V3 0.0143766 0.0030008 4.791 1.81e-06 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.1232 on 1602 degrees of freedom
Multiple R-squared: 0.8992, Adjusted R-squared: 0.8988
F-statistic: 2857 on 5 and 1602 DF, p-value: < 2.2e-16
##################################################
# Table 6 ICSE
##################################################
summary(lm(V3~-1+V1+log(V2)+V4,data=z))
Estimate Std. Error t value Pr(>|t|)
V1mongodb 2.54606 0.10101 25.207 < 2e-16 ***
V1react 2.94646 0.08426 34.969 < 2e-16 ***
V1socketio 1.93059 0.12187 15.841 < 2e-16 ***
log(V2) 0.11060 0.01262 8.762 < 2e-16 ***
V4 0.98250 0.20508 4.791 1.81e-06 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.018 on 1602 degrees of freedom
Multiple R-squared: 0.919, Adjusted R-squared: 0.9187
F-statistic: 3633 on 5 and 1602 DF, p-value: < 2.2e-16
######################################################################################
######################################################################################
#prepare data mapping projects/time/author/apis for the following languages
for LA in R Rust
do zcat /da0_data/play/${LA}thruMaps/b2cPtaPkgR${LA}.*.s | cut -d\; -f3- | lsort 100G -t\; -k2 | uniq | gzip > PtaPkgR$LA.s
done
#this is for R and Rust
python3 fitXldR.py /fast/PtaPkgR 200 30 20 5 1618784533 Rust Rust
cut -d\; -f1 ChrisRust.P2p | awk '{print "p2p;"$1}' | grep -v HyeonuPark_srtp | grep -v Isan-Rivkin_rsocket-rs | python3 predXpclF.py 100
for LA in jl F Dart ipy pl Kotlin Scala Go; do zcat /da0_data/play/${LA}thruMaps/b2cPtaPkgR${LA}.*.s | cut -d\; -f3- | perl -ane 'chop();($a,$b,$c,@ms)=split(/;/);%o=();for $m (@ms){$m=~s|^\s+||;$m=~s|\s+$||;$m=~s|^.*/||;$o{$m}++ if $m ne ""}; print "$a;$b;$c;".(join ";", sort keys %o)."\n";' | lsort 100G -t\; -k2,3 | uniq | gzip > PtaPkgR$LA.s; done
for la in rb Go TypesScript JS Cs PY java C; do zcat /da0_data/play/${LA}thruMaps/b2cPtaPkgR${LA}.*.s | cut -d\; -f3- | perl -ane 'chop();($a,$b,$c,@ms)=split(/;/);%o=();for $m (@ms){$m=~s|^\s+||;$m=~s|\s+$||;$m=~s|^.*/||;$o{$m}++ if $m ne ""}; print "$a;$b;$c;".(join ";", sort keys %o)."\n";' | lsort 100G -t\; -k2,3 | uniq | gzip > PtaPkgR$LA.s; done
#just rust
python3 fitXldR.py /fast/PtaPkgR 200 30 20 5 1618784533 RRust R Rust
python3 fitXldR.py /fast/PtaPkgR 200 30 20 5 1618784533 Rust Rust
cut -d\; -f1 ChrisRust.P2p | awk '{print "p2p;"$1}' | grep -v HyeonuPark_srtp| python3 predXpclF.py 1000 .3 > dist
cut -d\; -f2- dist | awk -F\; '{print $3";"$2";"$1}' | perl connectExportVwP2a.perl dist
143751 nodes and 1152000
cp -p dist.versions ~/src/networkit
zcat dist.weights > ~/src/networkit/w
zcat dist.versions | ./clusterw 143751 1152000 | gzip > dist.PLM
modularity=0.611794 nver=143751 clusters=36032 largest=24916
modularity=0.616274 nver=143751 clusters=36032 largest=29823
zcat ~/src/networkit/dist.PLM | perl rank1.perl dist | gzip > dist.crank.map
zcat dist.crank.map | lsort 1G -t\; -k3 -rn | awk -F\; '{if ($1 != $2) print $0}' | head
therealprof_mkw41z-hal;eldruin_hdc20xx-rs;1.486938;1.508500
m9s_xmc1000;eldruin_hdc20xx-rs;1.479339;1.508500
TeXitoi_bme280-rs;eldruin_hdc20xx-rs;1.445716;1.508500
no111u3_serialio;eldruin_hdc20xx-rs;1.433340;1.508500
thenewwazoo_elatec-twn4-simple;eldruin_hdc20xx-rs;1.427218;1.508500
fionawhim_cortex-m-systick-countdown;eldruin_hdc20xx-rs;1.409276;1.508500
smart-leds-rs_apa102-spi-rs;eldruin_hdc20xx-rs;1.392477;1.508500
JoshMcguigan_tsl256x;eldruin_hdc20xx-rs;1.391639;1.508500
therealprof_stm32f767-hal;eldruin_hdc20xx-rs;1.389100;1.508500
lucazulian_l298n;eldruin_hdc20xx-rs;1.387941;1.508500
#if mixed with R
m9s_xmc1000;therealprof_mkw41z-hal;1.438271;1.477410
eldruin_hdc20xx-rs;therealprof_mkw41z-hal;1.421558;1.477410
TeXitoi_bme280-rs;therealprof_mkw41z-hal;1.406271;1.477410
thenewwazoo_elatec-twn4-simple;therealprof_mkw41z-hal;1.405293;1.477410
no111u3_serialio;therealprof_mkw41z-hal;1.396393;1.477410
smart-leds-rs_apa102-spi-rs;therealprof_mkw41z-hal;1.380515;1.477410
fionawhim_cortex-m-systick-countdown;therealprof_mkw41z-hal;1.379802;1.477410
JoshMcguigan_shift-register-driver;therealprof_mkw41z-hal;1.368159;1.477410
mathk_mfxstm32l152;therealprof_mkw41z-hal;1.362509;1.477410
richardeoin_stm32h7-fmc;therealprof_mkw41z-hal;1.362391;1.477410
zcat dist.crank.map | lsort 1G -t\; -k3 -rn | awk -F\; '{if ($1 != $2) print $0}' | grep '<' | head
Henk Dieter Oordt <[email protected]>;eldruin_hdc20xx-rs;0.489912;1.508500
Albert Moravec <[email protected]>;eldruin_hdc20xx-rs;0.487719;1.508500
PinkNoize <[email protected]>;eldruin_hdc20xx-rs;0.465511;1.508500
cmoran <[email protected]>;eldruin_hdc20xx-rs;0.454001;1.508500
Roma Sokolov <[email protected]>;eldruin_hdc20xx-rs;0.449869;1.508500
Trond Hbertz Emaus <[email protected]>;eldruin_hdc20xx-rs;0.423623;1.508500
inazarenko <[email protected]>;eldruin_hdc20xx-rs;0.422698;1.508500
Igor Nazarenko <[email protected]>;eldruin_hdc20xx-rs;0.414672;1.508500
Neil Goldader <[email protected]>;eldruin_hdc20xx-rs;0.408192;1.508500
irwineffect <[email protected]>;eldruin_hdc20xx-rs;0.405343;1.508500
#if mixed with R
inazarenko <[email protected]>;therealprof_mkw41z-hal;0.464728;1.477410
Henk Dieter Oordt <[email protected]>;therealprof_mkw41z-hal;0.452849;1.477410
PinkNoize <[email protected]>;therealprof_mkw41z-hal;0.451155;1.477410
Roma Sokolov <[email protected]>;therealprof_mkw41z-hal;0.430368;1.477410
Igor Nazarenko <[email protected]>;therealprof_mkw41z-hal;0.415571;1.477410
Felipe Lalanne <[email protected]>;therealprof_mkw41z-hal;0.402307;1.477410
Anderson Nascimento <[email protected]>;therealprof_mkw41z-hal;0.394570;1.477410
cjbe <[email protected]>;therealprof_mkw41z-hal;0.390449;1.477410
Neil Goldader <[email protected]>;therealprof_mkw41z-hal;0.389320;1.477410
Garrett Greenwood <[email protected]>;therealprof_mkw41z-hal;0.388886;1.477410
####################
#old ver Q
####################
#Investigate joint frequencies
zcat PtAPkgQR.s0 | cut -d\; -f4- | perl -e 'while(<STDIN>){chop();@m=sort split(/;/);for $i (0..$#m){$a{$m[$i]}++;for $j (($i+1)..$#m){$n{$m[$i]}{$m[$j]}++;$n{$m[$j]}{$m[$i]}++}}};for $i (keys %a){for $j (keys %a){ print "$i;$j;$a{$i};$a{$j};$n{$i}{$j}\n" if ($i cmp $j)<0 && $a{$j}>5000 && $a{$i} > 5000 }}' | gzip > crosstab.gz
x=read.table("crosstab.gz", sep=";",quote="",comment.char="")
names(x)=c("a","b","na","nb","nab")
x$mn = apply(x[,c("na","nb")],1,min)
x$mor = x$mn/(x$nab+1);
x$tot=x$na+x$nb-x$nab;
x$ind=(x$na/x$tot * x$nb/x$tot);
x$pab = x$nab/x$tot;
x$or = x$ind/(1-x$ind)*(1-x$pab)/x$pab
#x=x[x$na>1000&x$nb>1000&x$or>3,]
myftestl = function(y){
y=as.integer(y)
res = fisher.test(matrix(c(y[1]-y[3], y[3], y[3], y[2]-y[3]),ncol=2))
res$conf.int[1];
}
myftestu = function(y){
y=as.integer(y)
res = fisher.test(matrix(c(y[1]-y[3], y[3], y[3], y[2]-y[3]),ncol=2))
res$conf.int[2];
}
x$orl = apply(x[,3:5],1,myftestl)
x$oru = apply(x[,3:5],1,myftestu)
quantile(x$oru)
y = x[x$a=='tidyr'&x$b=='readr',3:5]
fisher.test(matrix(as.integer(c(y[1]-y[3], y[3], y[3], y[2]-y[3])),ncol=2))
Fisher's Exact Test for Count Data
data: matrix(as.integer(c(y[1] - y[3], y[3], y[3], y[2] - y[3])), ncol = 2)
p-value < 2.2e-16
alternative hypothesis: true odds ratio is not equal to 1
95 percent confidence interval:
13.59858 13.99002
sample estimates:
odds ratio
13.7906
#prepare data mapping projects/time/author/apis for the following languages
for LA in jl pl R F Go Scala Rust Cs PY ipy JS C java rb
do zcat PtaPkgQ$LA.*.gz | lsort 500G -t\| | uniq | gzip > PtaPkgQ$LA.s
zcat PtaPkgQ$LA.s | perl -ane 'chop();($p,$t,$a,@ms) = split(/;/); for $m (@ms){print "$p;$m\n"}' | lsort 500G -t\; -k1,2 -u | gzip > P2Pkg$LA.s
zcat PtaPkgQ$LA.s | perl -ane 'chop();($p,$t,$a,@ms) = split(/;/); for $m (@ms){print "$a;$m\n"}' | lsort 500G -t\; -k1,2 -u | gzip > a2Pkg$LA.s
done
#Select ML/AI
zcat PtaPkgQPY.s | grep -iE 'systemml|cntk|opennn|pandas|numpy|tensorflow|random|sklearn|gensim|nltk|scipy|skimage|datacube|matplotlib|face_recognition|fastai|keras|torch|basicnn|DecisionTree|baseline_cnn|pyaicnn|mtcnn_detector|nnclf|cnn|clustering|svm|caffe|scikit|mlib|torch|theano|veles|h2o' | cut -d\; -f1 | uniq | gzip > b.gz
zcat PtaPkgQPY.s | perl ~/lookup/grepField.perl b.gz 1 | gzip > PtaPkgQPYml.s
#try on several small languages 'F', 'R', 'jl', 'pl', 'ipy'
(time python3 fit.py F R jl pl ipy) &
#one iteration takes 5 hr on da4 (see /da4_data/play/api)
# lets look at the second iteration
import gzip,collections,gensim.models.doc2vec,math
from gensim.models import Doc2Vec
mod = Doc2Vec.load ("doc2vec.QFRjlplipy.2")
mod = Doc2Vec.load ("doc2vec.QFipy.7")
#get most similar packages to language, project, author
mod.wv.similar_by_vector(mod.docvecs['R'])
it1-7: [('extrafont', 0.9955250024795532), ('csnorm', 0.9952453374862671), ('knitr', 0.9948492050170898), ('stringr', 0.9943090081214905), ('matrixStats', 0.9934355020523071), ('building.h', 0.9933176636695862), ('scam', 0.9915322065353394), ('gridExtra', 0.9907146096229553), ('shinystan', 0.9894420504570007), ('esprdbfile.h', 0.9891785979270935)]
mod.wv.similar_by_vector(mod.docvecs['cran_tidyquery'])
it7: [('HuffmanDecoder.jl', 0.46050825715065), ('general.fh', 0.4211460053920746), ('OPN', 0.4155998229980469), ('qubarqu_nInJququbar_465_Sq1_specs.h', 0.41047632694244385), ('arcgis.geocode', 0.4010382294654846), ('dataset_export.jl', 0.39810460805892944), ('NQS_Header', 0.3891255855560303), ('mapStats', 0.3890906870365143), ('curlib', 0.38832515478134155), ('cctk_Faces.h', 0.38744601607322693)]
ii1-3: [('HuffmanDecoder.jl', 0.46050825715065), ('general.fh', 0.4211460053920746), ('bokeh.palettes.all_palettes', 0.4210362434387207), ('OPN', 0.4131404757499695), ('qubarqu_nInJququbar_465_Sq1_specs.h', 0.41047632694244385), ('flask_pymongo.PyMongo', 0.39284461736679077), ('mapStats', 0.3890906870365143), ('curlib', 0.38832515478134155), ('cctk_Faces.h', 0.38744601607322693), ('PhageR', 0.38713282346725464)]
mod.wv.similar_by_vector(mod.docvecs['Yannick Spill <[email protected]>']);
it1-7: [('csnorm', 0.9973132610321045), ('extrafont', 0.9968918561935425), ('stringr', 0.9961603283882141), ('matrixStats', 0.9951667785644531), ('jiebaRD', 0.9946102499961853), ('knitr', 0.9934378862380981), ('flowCore', 0.9919644594192505), ('rhdf5', 0.9909929037094116), ('mgcv', 0.9899401664733887), ('scam', 0.9892599582672119)]
#get most similar languages, projects,authors to language, project, author
mod.docvecs.most_similar('R');
it7: [('F', 0.9947392344474792), ('Yannick Spill <[email protected]>', 0.9929205179214478), ('AsaEE_ESP-rSource', 0.992476224899292), ('jhand <jhand@7d53e970-de11-0410-8a54-3d01b9da36cf>', 0.9924437999725342), ('2DegreesInvesting_PortCheck', 0.990721583366394), ('Clare2D <[email protected]>', 0.9905468225479126), ('Taylor Posey <[email protected]>', 0.9884799718856812), ('tinaGNAW <[email protected]>', 0.9880185127258301), ('Paul Fischer <[email protected]>', 0.987598180770874), ('12379Monty_scRNASeq', 0.9872961044311523)]
it:1-3: ('F', 0.9947392344474792), ('Yannick Spill <[email protected]>', 0.9929205179214478), ('AsaEE_ESP-rSource', 0.992476224899292), ('jhand <jhand@7d53e970-de11-0410-8a54-3d01b9da36cf>', 0.9924437999725342), ('2DegreesInvesting_PortCheck', 0.990721583366394), ('Clare2D <[email protected]>', 0.9905468225479126), ('Taylor Posey <[email protected]>', 0.9884799718856812), ('tinaGNAW <[email protected]>', 0.9880185127258301), ('Paul Fischer <[email protected]>', 0.987598180770874), ('12379Monty_scRNASeq', 0.9872961044311523)]
mod.docvecs.most_similar('cran_tidyquery')
it2:[('kungeinus_Prediction_Assignment_Writeup', 0.49396124482154846), ('parserpro_db_update', 0.48060914874076843), ('adisarid <[email protected]>', 0.47186779975891113), ('danthemango <[email protected]>', 0.4652522802352905), ('arnarg_plex_exporter', 0.46454471349716187), ('colin-combe_CLMS-UI', 0.4438340663909912), ('alanaw1_CulturalHitchhiking', 0.4377615451812744), ('lavanyaj09_BE223A', 0.4339529275894165), ('jnarhan_Kaggle-Pneumonia', 0.43245214223861694), ('gxe778_Trajectory-Inference-Methods-applied-on-early-cell-lines-from-human-embryo', 0.42638999223709106)]
it1:[('parserpro_db_update', 0.4985978603363037), ('kungeinus_Prediction_Assignment_Writeup', 0.49396124482154846), ('adisarid <[email protected]>', 0.47186779975891113), ('danthemango <[email protected]>', 0.4674111604690552), ('arnarg_plex_exporter', 0.46454471349716187), ('PeterHenell_goora', 0.4478600025177002), ('colin-combe_CLMS-UI', 0.44383400678634644), ('danthemango_ClientRG', 0.4412115514278412), ('alanaw1_CulturalHitchhiking', 0.4377615451812744), ('jnarhan_Kaggle-Pneumonia', 0.43245214223861694)]
mod.docvecs.most_similar('Yannick Spill <[email protected]>')
it2:[('R', 0.992920458316803), ('3schwartz_SpecialeScrAndFun', 0.9900994300842285), ('Francois <[email protected]>', 0.9879549145698547), ('215ALab4_lab4', 0.9871786832809448), ('12379Monty_scRNASeq', 0.986408531665802), ('12379Monty <[email protected]>', 0.9862282872200012), ('3wen_elus', 0.9861852526664734), ('52North_tamis', 0.9858419299125671), ('tinaGNAW <[email protected]>', 0.9855629205703735), ('2DegreesInvesting_PortCheck', 0.984999418258667)]
it1:[('3DGenomes_binless', 0.9939588904380798), ('R', 0.9929205179214478), ('3schwartz_SpecialeScrAndFun', 0.9900994300842285), ('Francois <[email protected]>', 0.9879549145698547), ('215ALab4_lab4', 0.9871785640716553), ('12379Monty_scRNASeq', 0.986408531665802), ('12379Monty <[email protected]>', 0.986228346824646), ('3wen_elus', 0.9861852526664734), ('52North_tamis', 0.9858419299125671), ('tinaGNAW <[email protected]>', 0.9855630397796631)]
#get most similar packages to a package
mod.wv.most_similar('pandas')
[('song_data.songs', 0.6327548623085022), ('context.plot.plot.plot_points.plot_points', 0.6035584211349487), ('ax.storage.sqa_store.save.save_experiment', 0.585919976234436), ('emperor', 0.5831856727600098), ('geograph.term_profile.get_term_profile', 0.5705782175064087), ('negmas.apps.scml.utils.anac2019_world', 0.5701258778572083), ('pymove.conversions', 0.5696786642074585), ('learning_curve.learning_curve', 0.5638871192932129), ('ax.Data', 0.5624120831489563), ('starutils.populations.Raghavan_BinaryPopulation', 0.5612468123435974)]
mod.wv.most_similar('numpy')
[('tigre.utilities.plotimg.plotimg', 0.6538034677505493), ('cs231n.classifiers.linear_classifier.LinearSVM', 0.6469931602478027), ('Test_data.data_loader.load_head_phantom', 0.6307787895202637), ('PsyNeuLink.Components.Projections.TransmissiveProjections.MappingProjection.MappingProjection', 0.6261978149414062), ('section3_1_heatingday', 0.6204843521118164), ('tigre.Utilities.plotproj.ppslice', 0.617354154586792), ('tigre.demos.Test_data.data_loader.load_head_phantom', 0.6111389994621277), ('hmtk.hazard.HMTKHazardCurve', 0.6096319556236267), ('pyshtools.spectralanalysis.SHBias', 0.6086275577545166), ('agentnet.learning.n_step', 0.6063860058784485)]
mod.wv.most_similar('ggplot2')
it7: [('bsearchtools', 0.8243459463119507), ('cp_common_uses.h', 0.8239778876304626), ('PTRACERS_FIELDS.h', 0.8211128115653992), ('filnames.h', 0.8199384212493896), ('jelira.h', 0.8191816210746765), ('soilsnow.h', 0.8181809186935425), ('parmhor.h', 0.8178006410598755), ('da_transform_xtoy_pilot_adj.inc', 0.8176625967025757), ('ebbyeb.blk', 0.8171699047088623), ('SCHROD', 0.8164928555488586)]
it2: [('nortest', 0.9667873382568359), ('reshape2', 0.9574425220489502), ('tidyr', 0.9566653966903687), ('partykit', 0.9542033076286316), ('purrr', 0.9534142017364502), ('knitr', 0.9527696371078491), ('aim2_parameters.h', 0.9526889324188232), ('matrixStats', 0.9519108533859253), ('FlowSOM', 0.9512166976928711), ('Obspars.com', 0.9505057334899902)]
it1: ('tidyr', 0.9896135330200195), ('reshape2', 0.9894652366638184), ('nortest', 0.9879751205444336), ('dplyr', 0.9831089973449707), ('knitr', 0.9812949895858765), ('partykit', 0.9795119762420654), ('RColorBrewer', 0.9769814610481262), ('purrr', 0.9767657518386841), ('lubridate', 0.9766140580177307), ('data.table', 0.9752072095870972)]
mod.wv.most_similar('keras_learn')
it2:[('tensorbayes.nputils.log_sum_exp', 0.7950129508972168), ('neural_network_decision_tree.nn_decision_tree', 0.774245023727417), ('TechnicalAnalysis.TechnicalAnalysis', 0.768464207649231), ('models.naive_convnet.NaiveConvColoringModel', 0.762176513671875), ('model_VAE.VAE_mnist', 0.761232316493988), ('batch_generator.dir.DirIterator', 0.7570154070854187), ('optimizer.learing_rate_scheduling', 0.7539881467819214), ('models.yolov3_gpu_head.inference.restore_model', 0.7510530948638916), ('flickr8k_parse', 0.7491798400878906), ('ppo.NNValueFunction', 0.7474846839904785)]
it1:[('tensorbayes.nputils.log_sum_exp', 0.8044129610061646), ('models.yolov3_gpu_head.inference.restore_model', 0.7988119125366211), ('model_VAE.VAE_mnist', 0.7955332398414612), ('antTrainEnv_class.antTrainEnv_class', 0.784370481967926), ('models.naive_convnet.NaiveConvColoringModel', 0.7827848196029663), ('batch_generator.dir.DirIterator', 0.7793075442314148), ('neural_network_decision_tree.nn_decision_tree', 0.7765824198722839), ('TechnicalAnalysis.TechnicalAnalysis', 0.7733845710754395), ('envs.economy.jesusfv', 0.773059606552124), ('model.audio_u_net_dnn', 0.7707473039627075)]
#no most similar language,project.author from package, need to write a function
# get a doc vector based on the set of words and find most closely related terms
mod.wv.similar_by_vector(mod.infer_vector(['ggplot2','data.table']))
[('analyticlab.LaTeX', 0.9497971534729004), ('knitr', 0.9475012421607971), ('lubridate', 0.9463158845901489), ('mafdecls.fh', 0.9458824992179871), ('tidyr', 0.9457533359527588), ('ggthemes', 0.9443897008895874), ('demos.sampling_freq_demo1', 0.9438977837562561), ('meyer.basic_constructs.MRest', 0.9436166286468506), ('errquit.fh', 0.9411042332649231), ('scam', 0.9407658576965332)]
mod.wv.most_similar('data.table')
[('tidyr', 0.9825125336647034), ('scam', 0.9800063967704773), ('knitr', 0.9797146320343018), ('lubridate', 0.9793548583984375), ('purrr', 0.976327657699585), ('espriou.h', 0.9762163758277893), ('plant.h', 0.9760875105857849), ('gksenu.h', 0.9760852456092834), ('ggthemes', 0.9758648872375488), ('g01wsl.h', 0.9758262634277344)]
#similarities among languages
for la in ('F', 'R', 'jl', 'pl', 'ipy'):
for lb in ('F', 'R', 'jl', 'pl', 'ipy'):
print (la+":"+lb+" "+str(mod.docvecs.distance(la,lb))
it7:
F:R 0.005260765552520752
F:jl 0.5538360178470612
F:pl 0.26047611236572266
F:ipy 0.2711484432220459
R:jl 0.5432112514972687
R:pl 0.25471168756484985
R:ipy 0.2826273441314697
jl:pl 0.4799261689186096
jl:ipy 0.7023965418338776
pl:ipy 0.3867550492286682
it2:
F:R 0.005260765552520752
F:jl 0.5120232105255127
F:pl 0.18782222270965576
F:ipy 0.24761343002319336
R:jl 0.5035586059093475
R:pl 0.1807081699371338
R:ipy 0.2535156011581421
jl:pl 0.429531455039978
jl:ipy 0.8230383545160294
pl:ipy 0.4515225887298584
it1:
F:R 0.005260765552520752
F:jl 0.518935889005661
F:pl 0.160944402217865
F:ipy 0.2259724736213684
R:jl 0.5141101777553558
R:pl 0.14899468421936035
R:ipy 0.23450106382369995
jl:pl 0.46918046474456787
jl:ipy 0.8400852829217911
pl:ipy 0.41011691093444824
#measure distance between package and project/author/language
def dist (a, b):
av = mod.wv.get_vector(a)
bv = mod.docvecs[b]
return (sum(av*bv)/math.sqrt(sum(av*av)*sum(bv*bv)))
# save document and word vectors
f = open('outDocs','w')
for t in mod.docvecs.doctags.keys():
f.write(t)
for v in mod.docvecs[t]:
f.write(';'+"{:1.12e}".format(v))
f.write('\n')
f.close()
f = open('outWords','w')
for t in mod.wv.vocab.keys():
f.write(t)
for v in mod.wv[t]:
f.write(';'+"{:1.12e}".format(v))
f.write('\n')
f.close()
for la in F R jl ipy pl Cs Go PYml Rust Scala PY JS java rb; do zcat PtaPkgQ$la.s | perl -e 'while(<STDIN>){chop();($p,$t,$a)=split(/;/);$pre=0; $pre=1 if $t>= 1518784533+3600*24*365.25; $pn{$p}{$pre}++; $an{$a}{$pre}++;}; for my $p (keys %pn){print "p;$p;$pn{$p}{1};$pn{$p}{0}\n";} for my $a (keys %an){print "a;$a;$an{$a}{1};$an{$a}{0}\n";}' | gzip > PtaPkgQ$la.cnt; done &
for la in F jl R ipy pl Cs Go PYml Rust Scala PY PYml JS java rb; do
zcat PtaPkgQ$la.cnt| grep ^a | awk -F\; '{if($4>10 && $3>10)print $0}' > PtaPkgQ$la.cnt10
done
for la in F jl R ipy pl Cs Go PYml Rust Scala PY PYml JS java rb; do
zcat PtaPkgQ$la.cnt| grep ^p | awk -F\; '{if($4>100 && $3>100)print $0}' > PtaPkgQ$la.cnt100
done
for la in F jl R ipy pl Cs Go PYml Rust Scala PY PYml JS java rb; do zcat PtaPkgQ$la.s | perl ~/lookup/mp.perl 2 /da0_data/basemaps/gz/a2AQ.s | gzip > PtAPkgQ$la.s ; done &
for la in F R jl ipy pl Cs Go PYml Rust Scala PY JS java rb; do zcat PtAPkgQ$la.s | perl -e 'while(<STDIN>){chop();($p,$t,$a)=split(/;/);$pre=0; $pre=1 if $t>= 1518784533+3600*24*365.25; $pn{$p}{$pre}++; $an{$a}{$pre}++;}; for my $p (keys %pn){print "p;$p;$pn{$p}{1};$pn{$p}{0}\n";} for my $a (keys %an){print "a;$a;$an{$a}{1};$an{$a}{0}\n";}' | gzip > PtAPkgQ$la.cnt; done
for la in F jl R ipy pl Cs Go Rust Scala PY PYml JS java rb; do
zcat PtAPkgQ$la.cnt| grep ^a | awk -F\; '{if($4>10 && $3>10)print $0}' > PtAPkgQ$la.cnt10
done
for la in F jl R ipy pl Cs Go PYml Rust Scala PY JS java rb; do
zcat PtAPkgQ$la.cnt| grep ^p | awk -F\; '{if($4>100 && $3>100)print $0}' > PtAPkgQ$la.cntp100
done
#Figure out commit counts for authors
for la in F jl R ipy pl Cs Go PYml Rust Scala PY JS java rb
do cut -d\; -f2 PtAPkgQ$la.cnt10
done | lsort 1G -u | gzip > au10.gz
for la in F jl R ipy pl Cs Go Rust Scala PY JS java rb
do zcat PtAPkgQ$la.s | perl ~/bin/grepField.perl au10.gz 3
done | gzip > all.a10.gz
for la in F jl R ipy pl Cs Go Rust Scala PY PYml JS java rb; do
zcat PtAPkgQ$la.cnt| grep ^a | awk -F\; '{if($4>100 && $3>100)print $0}' > PtAPkgQ$la.cnt100
done
for la in F jl R ipy pl Cs Go PYml Rust Scala PY JS java rb
do cut -d\; -f2 PtAPkgQ$la.cnt100
done | lsort 1G -u | gzip > au100.gz
for la in C F jl R ipy pl Cs Go Rust Scala PY JS java rb
do zcat PtAPkgQ$la.s | perl ~/bin/grepField.perl au100.gz 3
done | gzip > all.a100.gz
####################################
#Prepare PR data for FSE submission: Table 4
####################################
cat PRdata_new.csv | perl ~/lookup/mp.perl 0 /da0_data/basemaps/gz/a2AQ.s > PRdata_newA.csv
cut -d\; -f1 PRdata_newA.csv | lsort 1G -u | gzip > au.prs
for la in JS C F jl R ipy pl Cs Go Rust Scala PY java rb
do zcat /da4_data/play/api/PtAPkgQ$la.s | perl ~/bin/grepField.perl au.prs 3 | gzip > PtaPkgQ$la.prs.s
done
####################################
zcat *A*.cnt | grep ^a | awk -F\; '{print $4+$3";"$2}' | lsort 30G -t\; -rn |gzip > topA
zcat topA|awk -F\; '{if ($1>50000){print $2}}' | gzip | lsort 10G -u > topA.50K
zcat au100.gz | lsort 10G -t\; -k1,1 -u | join -t\; -v1 - <(cat topA.50K | lsort 1G -t\; -k1,1)| gzip > au100-50k.gz
zcat au10.gz | lsort 10G -t\; -k1,1 -u | join -t\; -v1 - <(cat topA.50K | lsort 1G -t\; -k1,1)| gzip > au10-50k.gz
for la in F jl R ipy pl Cs Go PYml Rust Scala PY JS java rb; do
zcat PtAPkgQ$la.s | perl ~/bin/grepField.perl au100-50K.gz 3 | gzip > PtAPkgQ$la.a100.s
done
#reproduce import2vec
import gzip,collections,gensim.models.doc2vec,math
from gensim.models import Doc2Vec, Word2Vec
mod = Doc2Vec.load ("doc2vec.QAJS.a100.1558784533.1")
#get most similar packages to language, project, author
mod.wv.most_similar('http')
import gzip,collections,gensim.models.doc2vec,math
from gensim.models import Doc2Vec
mod = Doc2Vec.load ("doc2vec.QAJS.a100.1558784533.5")
mod.wv.most_similar('http')
[('firebase-admin', 0.7661893367767334), ('koa-bodyparser', 0.733301043510437), ('mysql2', 0.7215847969055176), ('react-loadable', 0.6763203144073486), ('vuelidate', 0.665387749671936), ('vue-style-loader', 0.6605743765830994), ('marklar', 0.6552571654319763), ('ipfs-mdns', 0.6538937091827393), ('diap', 0.6523748636245728), ('jQuery', 0.6493134498596191)]
for f in ('doc2vec.QML.2', 'doc2vec.QFRjlipyml.1518784533.9', 'doc2vec.Qipy.9', 'doc2vec.QR.1518784533.9'):
mod = Doc2Vec.load (f)
mod.wv.most_similar('data.table')
mod.wv.similar_by_vector(mod.docvecs['R'])
mod.wv.similar_by_vector(mod.docvecs['R'])
zcat PtAPkgQJS.a100.s | grep ';http;' | wc -l
15375
zcat PtAPkgQJS.a100.s | grep ';http;' | grep -v ';https;' | wc -l
12852
zcat PtAPkgQJS.a100.s | grep ';https\b' > s &
zcat PtAPkgQJS.a100.s | grep ';http\b' > p &
wc -l p s
1239802 3189600 15785383911 s
1899811 4873782 18410486749 p
grep -v ';http\b' s | wc -l
56677
grep -v ';https\b' p | wc -l
716686
#doc2vec (binary, author+project)
f='doc2vec.PAPkgQR.a100b.9'
mod = Doc2Vec.load (f)
mod.wv.most_similar('data.table')
[('ggtree', 0.45562177896499634), ('datastorr', 0.45432671904563904), ('koRpus', 0.45120853185653687), ('emmeans', 0.45097100734710693), ('fansi', 0.44699180126190186), ('datasets', 0.442926287651062), ('ellipse', 0.4332200288772583), ('mlmRev', 0.43092772364616394), ('ddalpha', 0.4287028908729553), ('extrafont', 0.42746877670288086)]
mod.wv.most_similar('readr')
[('reshape2', 0.5896936655044556), ('rgdal', 0.5330021381378174), ('rlist', 0.5308029651641846), ('scales', 0.5262876749038696), ('slam', 0.5214910507202148), ('rstanarm', 0.5202317833900452), ('readstata13', 0.517525315284729), ('reshape', 0.5141236186027527), ('tidyverse', 0.511005163192749), ('pracma', 0.5025790929794312)]
#doc2vec (binary, author only)
f='doc2vecA01.20.1.20.3.PAPkgQR.a100b.10'
mod = Doc2Vec.load (f)
mod.wv.most_similar('data.table')
[('dplyr', 0.9619144797325134), ('devtools', 0.9410998821258545), ('stringr', 0.938940703868866), ('gridExtra', 0.9301508069038391), ('tidyverse', 0.9286336302757263), ('tidyr', 0.9281747341156006), ('ggplot2', 0.924401581287384), ('RColorBrewer', 0.9191794395446777), ('Hmisc', 0.9127570986747742), ('foreach', 0.9072998762130737)]
mod.wv.most_similar('readr')
[('tidyr', 0.9521045684814453), ('tidyverse', 0.9518229961395264), ('lubridate', 0.9460780024528503), ('ggthemes', 0.9348131418228149), ('rvest', 0.9196170568466187), ('scales', 0.912832498550415), ('RColorBrewer', 0.8977759480476379), ('gridExtra', 0.8954176902770996), ('corrplot', 0.8899544477462769), ('stringr', 0.8898525238037109)]
f='doc2vecA01.20.1.20.3.PAPkgQR.a100b.17'
mod = Doc2Vec.load (f)
mod.wv.most_similar('data.table')
[('dplyr', 0.9987048506736755), ('devtools', 0.9978946447372437), ('ggplot2', 0.9974669814109802), ('tidyr', 0.9973721504211426), ('knitr', 0.9970445036888123), ('reshape2', 0.996809720993042), ('tidyverse', 0.996529221534729), ('gridExtra', 0.9961731433868408), ('scales', 0.9960485696792603), ('plyr', 0.9955645203590393)]
mod.wv.most_similar('readr')
[('scales', 0.9980828166007996), ('tidyr', 0.9975719451904297), ('ggthemes', 0.9971051812171936), ('magrittr', 0.9970694780349731), ('lubridate', 0.9966671466827393), ('RColorBrewer', 0.9965049028396606), ('gridExtra', 0.9964038133621216), ('tidyverse', 0.9963114261627197), ('rpart', 0.9957792162895203), ('ggplot2', 0.9957766532897949)]
for f in ('doc2vec.20.30.3.PAPkgQR.a100b.19','doc2vec.20.3.3.PAPkgQR.a100b.19','doc2vec.40.30.3.PAPkgQR.a100b.19', 'doc2vec.40.3.3.PAPkgQR.a100b.19', 'doc2vec.80.30.3.PAPkgQR.a100b.19', 'doc2vec.80.3.3.PAPkgQR.a100b.19', 'doc2vec.120.30.3.PAPkgQR.a100b.19', 'doc2vec.120.3.3.PAPkgQR.a100b.19'):
mod = Doc2Vec.load (f)
#mod.wv.most_similar('data.table')
mod.wv.most_similar('readr')
[('RColorBrewer', 0.9983182549476624), ('scales', 0.998315155506134), ('tidyverse', 0.9982290267944336), ('magrittr', 0.9981428980827332), ('gridExtra', 0.9980251789093018), ('reshape2', 0.9979166388511658), ('knitr', 0.9977608919143677), ('lubridate', 0.997739315032959), ('tidyr', 0.9972754120826721), ('e1071', 0.9971935749053955)]
[('knitr', 0.9893307685852051), ('parallel', 0.9887491464614868), ('data.table', 0.9852929711341858), ('DESeq2', 0.9849643707275391), ('ggplot2', 0.9848182201385498), ('devtools', 0.9846794605255127), ('tidyr', 0.9845887422561646), ('rmarkdown', 0.9837965965270996), ('readxl', 0.9831156134605408), ('tools', 0.9823206663131714)]
[('lubridate', 0.9961996078491211), ('scales', 0.9947738647460938), ('knitr', 0.9944191575050354), ('RColorBrewer', 0.994251012802124), ('magrittr', 0.9941045045852661), ('reshape2', 0.9939345121383667), ('gridExtra', 0.9935609102249146), ('tidyr', 0.9930714964866638), ('ggthemes', 0.9929649233818054), ('readxl', 0.9924424886703491)]
[('tidyr', 0.9897856116294861), ('magrittr', 0.9842157959938049), ('lubridate', 0.9824410676956177), ('tidyverse', 0.9819707870483398), ('scales', 0.9788222908973694), ('RColorBrewer', 0.976738452911377), ('knitr', 0.9757811427116394), ('dplyr', 0.973181426525116), ('reshape2', 0.9710521697998047), ('gridExtra', 0.9706953763961792)]
[('tidyverse', 0.9914058446884155), ('lubridate', 0.9820787906646729), ('ggplot2', 0.981021523475647), ('reshape2', 0.9763184189796448), ('dplyr', 0.96944260597229), ('stringr', 0.9606151580810547), ('scales', 0.9509478807449341), ('ggthemes', 0.9472478032112122), ('rmarkdown', 0.9466075897216797), ('gridExtra', 0.946486234664917)]
[('tidyr', 0.979855477809906), ('tidyverse', 0.9716714024543762), ('dplyr', 0.9697237014770508), ('lubridate', 0.9694627523422241), ('magrittr', 0.9675484895706177), ('ggplot2', 0.9638528823852539), ('knitr', 0.9620657563209534), ('scales', 0.959942638874054), ('data.table', 0.9549976587295532), ('gridExtra', 0.9542347192764282)]
[('magrittr', 0.9877380132675171), ('lubridate', 0.983036994934082), ('tidyverse', 0.9830121994018555), ('scales', 0.9816074967384338), ('knitr', 0.9798682928085327), ('devtools', 0.9794678688049316), ('RColorBrewer', 0.9773341417312622), ('jsonlite', 0.9698127508163452), ('readxl', 0.9695264101028442), ('ggthemes', 0.9690042734146118)]
[('tidyr', 0.9725443720817566), ('dplyr', 0.9542319774627686), ('data.table', 0.9513483047485352), ('magrittr', 0.9475299119949341), ('ggplot2', 0.9475277662277222), ('jsonlite', 0.9473656415939331), ('lubridate', 0.9440580606460571), ('tidyverse', 0.9436643123626709), ('stringr', 0.9377952814102173), ('devtools', 0.9372730255126953)]
for f in ('doc2vecA.20.30.3.PAPkgQR.a100b.19','doc2vecA.20.3.3.PAPkgQR.a100b.19','doc2vecA.40.30.3.PAPkgQR.a100b.19', 'doc2vecA.40.3.3.PAPkgQR.a100b.19', 'doc2vecA.80.30.3.PAPkgQR.a100b.19', 'doc2vecA.80.3.3.PAPkgQR.a100b.19', 'doc2vecA.120.30.3.PAPkgQR.a100b.19', 'doc2vecA.120.3.3.PAPkgQR.a100b.19'):
mod = Doc2Vec.load (f)
#mod.wv.most_similar('data.table')
mod.wv.most_similar('readr')
[('magrittr', 0.9991831183433533), ('tidyverse', 0.9989697933197021), ('gridExtra', 0.9982430934906006), ('tidyr', 0.9982177019119263), ('scales', 0.9980565309524536), ('jsonlite', 0.9979439973831177), ('data.table', 0.9979092478752136), ('reshape2', 0.9978592395782471), ('knitr', 0.9976184368133545), ('stringi', 0.9969038367271423)]
[('tidyverse', 0.9947269558906555), ('tidyr', 0.9942873120307922), ('magrittr', 0.9933727979660034), ('lubridate', 0.9930378794670105), ('knitr', 0.9925771951675415), ('gridExtra', 0.9892634749412537), ('scales', 0.9878233671188354), ('RColorBrewer', 0.9874245524406433), ('devtools', 0.9865281581878662), ('dplyr', 0.9864441752433777)]
[('tidyr', 0.9988787174224854), ('magrittr', 0.9987964630126953), ('knitr', 0.9982733726501465), ('scales', 0.9981702566146851), ('lubridate', 0.9979217648506165), ('gridExtra', 0.9973997473716736), ('ggthemes', 0.9967532157897949), ('reshape2', 0.9961109161376953), ('rpart.plot', 0.995823860168457), ('tidyverse', 0.9956599473953247)]
[('tidyr', 0.9956086277961731), ('tidyverse', 0.9895380735397339), ('magrittr', 0.9875149726867676), ('dplyr', 0.9868128299713135), ('jsonlite', 0.9848260879516602), ('lubridate', 0.9833686947822571), ('devtools', 0.9828656315803528), ('data.table', 0.9797936677932739), ('gridExtra', 0.9791477918624878), ('ggplot2', 0.979009747505188)]
[('scales', 0.997490644454956), ('tidyverse', 0.9954097270965576), ('e1071', 0.9951643943786621), ('knitr', 0.9948922991752625), ('cluster', 0.9930667877197266), ('devtools', 0.9929601550102234), ('rpart.plot', 0.9902037382125854), ('RColorBrewer', 0.9877432584762573), ('ggfortify', 0.9876832365989685), ('DBI', 0.9824402928352356)]
[('tidyr', 0.9836821556091309), ('dplyr', 0.9753010272979736), ('magrittr', 0.9750666618347168), ('lubridate', 0.9709521532058716), ('tidyverse', 0.9692929983139038), ('ggplot2', 0.9688870906829834), ('knitr', 0.9656769037246704), ('jsonlite', 0.965003490447998), ('devtools', 0.9634120464324951), ('RColorBrewer', 0.960491955280304)]
[('magrittr', 0.991066038608551), ('dplyr', 0.9904848337173462), ('ggplot2', 0.9897637963294983), ('lubridate', 0.9878308773040771), ('knitr', 0.9876624941825867), ('data.table', 0.9873613119125366), ('reshape2', 0.9868736267089844), ('tidyverse', 0.9868265390396118), ('gridExtra', 0.9866074919700623), ('stringr', 0.9863458871841431)]
[('tidyr', 0.982008695602417), ('dplyr', 0.9632465243339539), ('magrittr', 0.9609993696212769), ('ggplot2', 0.9522542953491211), ('lubridate', 0.9505354762077332), ('tidyverse', 0.9469977021217346), ('data.table', 0.9440603256225586), ('devtools', 0.9428290128707886), ('stringr', 0.9426917433738708), ('jsonlite', 0.9396312832832
#W2V
f='word2vec.20.1.3.PAPkgQR.a100b'
mod = Word2Vec.load (f)
mod.most_similar('data.table')
[('devtools', 0.9298685789108276), ('ggplot2', 0.9192495346069336), ('dplyr', 0.9015513062477112), ('reshape2', 0.8996330499649048), ('RColorBrewer', 0.8813983201980591), ('gridExtra', 0.876798689365387), ('knitr', 0.8706860542297363), ('scales', 0.8666546940803528), ('readr', 0.86326003074646), ('magrittr', 0.8588861227035522)]
mod.most_similar('readr')
[('tidyr', 0.9588572978973389), ('magrittr', 0.9268977642059326), ('dplyr', 0.9099311828613281), ('tidyverse', 0.875988781452179), ('patchwork', 0.8729138374328613), ('data.table', 0.86326003074646), ('knitr', 0.8573061227798462), ('forcats', 0.8519827723503113), ('stringi', 0.8486554622650146), ('jsonlite', 0.8443582057952881)]
####################################
# LSI for FSE submission
####################################
python3 fitXtl.py PAPkgQR.a100.s3
records:20700
data.table;1.0
hierinf;0.96815044
MixtureInf;0.9635873
data.cube;0.9635765
macrobenchmark;0.9634209
RcppAPT;0.96161354
sykdomspulscompartmentalinfluenza;0.9587247
JFuncs;0.9568475
antaresWeeklyMargin;0.95673203
readr;0.99999994
stuko;0.9718676
imrParsers;0.97154045
ctsmr;0.9688772
targetscan.Hs.eg.db;0.9636713
wyntonquery;0.9597609
scdhlm;0.9505869
farms;0.9332409
sde;0.9197796
python3 fitXl.py PAPkgQR.a100.s3
records:20700
data.table;0.9999999
macrobenchmark;0.9698489
data.cube;0.96984845
MixtureInf;0.96984583
RcppAPT;0.9698335
hierinf;0.96799344
antaresWeeklyMargin;0.96222705
antaresRead;0.9620175
spatialdatatable;0.9574404
readr;1.0
ctsmr;0.9638993
imrParsers;0.96388185
stuko;0.9625468
wyntonquery;0.9605134
targetscan.Hs.eg.db;0.95924646
scdhlm;0.92792475
stlcsb;0.9269278
NameNeedle;0.92489654
####################################
#JS
f='doc2vecA.30.100.3.PAPkgQJS.0.b.1'
mod = Doc2Vec.load (f)
mod.wv.most_similar('http')
import gzip,collections,gensim.models.doc2vec,math
from gensim.models import Doc2Vec, Word2Vec
python3 fitXw.py PAPkgQR.s1 1 100 50 20 100 200
mod = Word2Vec(docs,sg=dm,size=vs, window=ws, negative=ns, min_count=mc, workers=cores,iter=iter)
mod.save("word2vec."+str(dm)+"."+str(vs)+"."+str(ws)+"."+str(ns)+"."+str(mc)+"."+str(iter)+"."+lst)
f='word2vec.100.50.20.100.200.0.PAPkgQR.s1' #garbage sg=0
f='word2vec.100.50.20.100.200.1.PAPkgQR.s1' #decent sg=1
>>> mod.most_similar('data.table')
[('dplyr', 0.8867905139923096), ('stringr', 0.8839394450187683), ('plyr', 0.8830145001411438), ('magrittr', 0.8689486384391785), ('magclass', 0.8649991154670715), ('readr', 0.8637726902961731), ('tidyr', 0.8611730337142944), ('lubridate', 0.8585350513458252), ('gWidgetsWWW2', 0.8545087575912476), ('lucode', 0.852830171585083)]
>>> mod.most_similar('readr')
[('magrittr', 0.9195265769958496), ('tidyr', 0.8952105641365051), ('dplyr', 0.8914402723312378), ('ggplot2', 0.8837970495223999), ('stringr', 0.8687031865119934), ('data.table', 0.8637727499008179), ('plotly', 0.8532767295837402), ('magclass', 0.852198600769043), ('lucode', 0.8505121469497681), ('plyr', 0.841021716594696)]
f='word2vec.1.100.50.20.100.200.PAPkgQR.s1' # OK
mod = Word2Vec.load (f)
mod.most_similar('data.table')
mod.most_similar('readr')
[('dplyr', 0.838019609451294), ('stringr', 0.7983173131942749), ('plyr', 0.7869787216186523), ('ggplot2', 0.7796253561973572), ('magrittr', 0.7705162167549133), ('reshape2', 0.7650773525238037), ('tidyr', 0.7562291622161865), ('readr', 0.7183531522750854), ('scales', 0.7113677263259888), ('tidyverse', 0.7113019227981567)]
>>> mod.most_similar('readr')
[('dplyr', 0.8551141023635864), ('magrittr', 0.8088136911392212), ('tidyr', 0.8009055852890015), ('stringr', 0.7933487892150879), ('ggplot2', 0.7563961148262024), ('data.table', 0.7183531522750854), ('tidyverse', 0.7072793841362), ('readxl', 0.6874278783798218), ('plotly', 0.6379566192626953), ('scales', 0.6288162469863892)]
f='word2vec.0.100.50.20.100.200.PAPkgQR.s1'
mod = Word2Vec.load (f)
mod.most_similar('data.table') # OK
mod.most_similar('readr')
[('dplyr', 0.6934608221054077), ('stringr', 0.6257824301719666), ('plyr', 0.6186755895614624), ('readr', 0.5545837879180908), ('tidyr', 0.5514156818389893), ('ggplot2', 0.5356006622314453), ('reshape2', 0.5290185809135437), ('lubridate', 0.5161994695663452), ('scales', 0.5158300399780273), ('magrittr', 0.4615442454814911)]
>>> mod.most_similar('readr')
[('dplyr', 0.6838119626045227), ('stringr', 0.6082045435905457), ('tidyverse', 0.5811571478843689), ('tidyr', 0.5662992596626282), ('data.table', 0.5545837879180908), ('lubridate', 0.531836748123169), ('magrittr', 0.5190625190734863), ('ggplot2', 0.4508250951766968), ('readxl', 0.42567265033721924), ('forcats', 0.3814961314201355)]
f='word2vec.20.1.3.PAPkgQJS.0.b'
mod.most_similar('http')
[('color-namer', 0.8891410827636719), ('easyyoutubedownload', 0.8820397257804871), ('socketio', 0.8606370091438293), ('https', 0.858386754989624), ('ffmetadata', 0.8539266586303711), ('tress', 0.8495419025421143), ('lwip', 0.8478525280952454), ('data-utils', 0.847440242767334), ('render', 0.8417345285415649), ('sharedb-mingo-memory', 0.836542546749115)]
mod.most_similar('https')
[('http', 0.858386754989624), ('google-search-scraper', 0.8478592038154602), ('restc', 0.8463708758354187), ('lwip', 0.8457597494125366), ('sanitize', 0.8455460071563721), ('skipper', 0.842998206615448), ('dom-parser', 0.842816948890686), ('mongoose-auto-increment', 0.8401623368263245), ('guid', 0.8306612968444824), ('easyyoutubedownload', 0.8301177024841309)]
#### Compare various LSI methods
#all tl - tfidf + lsi
python3 fitXtl.py PAPkgQ.all1.a100.0.s2
data.table;1.0
lubridate;0.9246081
magrittr;0.92408097
glmnet;0.90353286
dplyr;0.8974145
reshape;0.86968565
tibble;0.8680916
shinydashboard;0.8583525
shinythemes;0.85728675
readr;1.0
synapser;0.915734
RJSONIO;0.9078114
stringr;0.9041679
dplyr;0.8992814
tidyr;0.8970244
gridGraphics;0.8929982
tibble;0.8897572
magrittr;0.8888842
https;1.0000001
facebook-chat-api;0.9842278
shrink-ray;0.9786956
@sanity/mutator;0.9766238
groq;0.9766238
mead;0.9766238