-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathexp2.py
1703 lines (1526 loc) · 66.2 KB
/
exp2.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
__author__ = 's3525116'
__author__ = 's3525116'
from string_manipulation import *
#from reviews import *
#-----------------------------------------------------------------------------------------------------------------------
def parseFileTestData(filename,startFrom):
'''
Parsing Stanford Dataset aggressive_dedup.json
"reviewerID": "A2SUAM1J3GNN3B",
"asin": "0000013714",
"reviewerName": "J. McDonald",
"helpful": [2, 3],
"reviewText": "I bought this for my husband who plays the piano. He is having a wonderful time playing these old hymns. The music is at times hard to read because we think the book was published for singing from more than playing from. Great purchase though!",
"overall": 5.0,
"summary": "Heavenly Highway Hymns",
"unixReviewTime": 1252800000,
"reviewTime": "09 13, 2009"
:param filename:
:param entry:
:return:
'''
'''
:param filename:
:param entry:
:return:
'''
print("Procedure to Parse Product Review Data of Stanford Dataset aggressive_dedup.json")
print("Started")
uniqueReviews = dict()
#fp = open(filename, 'r')
counter = 0
allReviews = []
listReviews = []
shouldIStart = 0
line = ""
finishAt = startFrom + 100000
nlinesReadIgnored = 0
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/allproducts_big_run.txt",'a')
with open(filename, 'r') as fp:
for line in fp:
if counter == finishAt:
break
if counter == startFrom:
print("Starting at index "+str(counter))
print("Num lines Ignored "+str(nlinesReadIgnored))
shouldIStart = 1
else:
#fp.readline() #toIgnore
nlinesReadIgnored = nlinesReadIgnored + 1
# print("NotConsidered")
# print(counter)
# print(line)
if shouldIStart == 1:
#line = fp.readline()
#print("Considered")
#print(counter)
#print(line)
new = line.split('reviewerID')
reviewerID = extractFirstString(new[1])
#if reviewerID == "":
# print("Problem with reviewerID")
new = line.split('asin')
asin = extractFirstString(new[1])
#if asin == "":
# print("Problem with asin")
new = line.split('reviewerName')
if len(new)>1:
reviewerName = extractFirstString(new[1])
#if reviewerName == "":
# print("Problem with reviewerName")
new = line.split('helpful')
helpful = extractHelpful(new[1])
if helpful == "":
# print("Problem with helpful")
for i in range(len(new)):
helpful = extractHelpful(new[i])
if helpful != "":
break
numVotes = extractNumVotes(new[1])
#if numVotes == "":
# print("Problem with numVotes")
new = line.split('reviewText')
reviewText = extractFirstString(new[1])
#if reviewText == "":
# print("Problem with reviewText")
new = line.split('overall')
overall = extractRatingTime(new[1])
if overall == "":
for i in range(len(new)):
overall = extractRatingTime(new[i])
if overall != "":
break
#if overall == "":
#print("Problem with overall")
new = line.split('summary')
summary = extractFirstString(new[len(new)-1])
#if summary == "":
# print("Problem with summary")
new = line.split('unixReviewTime')
if len(new) > 1:
unixReviewTime = extractUnixTime(new[1])
#if unixReviewTime == "":
# print("Problem with unixReviewTime")
new = line.split('reviewTime')
reviewTime = extractFirstString(new[1])
#if reviewTime == "":
# print("Problem with reviewTime")
review = Review(reviewerID,asin,reviewTime,helpful,numVotes,overall,reviewText,summary,unixReviewTime)
filehandle.write(line)
#filehandle.write("\n")
if review.productid in uniqueReviews:
listReviews = uniqueReviews[review.productid]
listReviews.append(review)
uniqueReviews[review.productid] = listReviews
else:
listReviews = []
listReviews.append(review)
uniqueReviews[review.productid] = listReviews
counter = counter + 1
else:
counter = counter + 1
continue
filehandle.close()
fp.close()
print("Num Reviews")
print(counter)
print("Processed "+str(counter)+" Reviews so far")
print("Finished")
return uniqueReviews
#-----------------------------------------------------------------------------------------------------------------------
from datetime import datetime
def readDataStanfordDataSetTechniqueTwo(filename,startFrom):
'''
Parsing Stanford Dataset aggressive_dedup.json and write each product file with name product id
"reviewerID": "A2SUAM1J3GNN3B",
"asin": "0000013714",
"reviewerName": "J. McDonald",
"helpful": [2, 3],
"reviewText": "I bought this for my husband who plays the piano. He is having a wonderful time playing these old hymns. The music is at times hard to read because we think the book was published for singing from more than playing from. Great purchase though!",
"overall": 5.0,
"summary": "Heavenly Highway Hymns",
"unixReviewTime": 1252800000,
"reviewTime": "09 13, 2009"
:param filename:
:param entry:
:return:
'''
'''
:param filename:
:param entry:
:return:
'''
print("Procedure to Parse Product Review Data of Stanford Dataset aggressive_dedup.json")
print("Started at ")
start = datetime.now()
print(start)
uniqueReviews = dict()
#numReviesPerProduct = dict()
fp = open(filename, 'r')
counter = 0
allReviews = []
listReviews = []
shouldIStart = 0
line = ""
finishAt = startFrom + 2000000
while 1:
if counter == finishAt:
break
if counter == startFrom:
print("Starting at index "+str(counter))
shouldIStart = 1
else:
line = fp.readline() #toIgnore
if shouldIStart == 1:
line = fp.readline()
new = line.split('reviewerID')
reviewerID = extractFirstString(new[1])
#if reviewerID == "":
# print("Problem with reviewerID")
new = line.split('asin')
asin = extractFirstString(new[1])
#if asin == "":
# print("Problem with asin")
new = line.split('reviewerName')
if len(new)>1:
reviewerName = extractFirstString(new[1])
#if reviewerName == "":
# print("Problem with reviewerName")
new = line.split('helpful')
helpful = extractHelpful(new[1])
if helpful == "":
# print("Problem with helpful")
for i in range(len(new)):
helpful = extractHelpful(new[i])
if helpful != "":
break
numVotes = extractNumVotes(new[1])
#if numVotes == "":
# print("Problem with numVotes")
new = line.split('reviewText')
reviewText = extractFirstString(new[1])
#if reviewText == "":
# print("Problem with reviewText")
new = line.split('overall')
overall = extractRatingTime(new[1])
if overall == "":
for i in range(len(new)):
overall = extractRatingTime(new[i])
if overall != "":
break
#if overall == "":
#print("Problem with overall")
new = line.split('summary')
summary = extractFirstString(new[len(new)-1])
#if summary == "":
# print("Problem with summary")
new = line.split('unixReviewTime')
if len(new) > 1:
unixReviewTime = extractUnixTime(new[1])
#if unixReviewTime == "":
# print("Problem with unixReviewTime")
new = line.split('reviewTime')
reviewTime = extractFirstString(new[1])
#if reviewTime == "":
# print("Problem with reviewTime")
review = Review(reviewerID,asin,reviewTime,helpful,numVotes,overall,reviewText,summary,unixReviewTime)
filehandle = None
try:
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_two/"+review.productid,'a')
writeReviewToFile(filehandle,review)
except OSError as e:
to = e.errno
finally:
if filehandle is not None:
filehandle.close()
'''
print(counter)
if review.productid in uniqueReviews:
filehandle = uniqueReviews[review.productid]
writeReviewToFile(filehandle,review)
#filehandle.close()
else:
try:
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_two/"+review.productid,'a')
writeReviewToFile(filehandle,review)
uniqueReviews[review.productid] = filehandle
except OSError as e:
to = e.errno
print(counter)
if review.productid in uniqueReviews:
filehandle = uniqueReviews[review.productid]
writeReviewToFile(filehandle,review)
filehandle.close()
#numReviesPerProduct[review.productid] = numReviesPerProduct[review.productid] +1
else:
print(counter)
writeReviewToFile(filehandle,review)
uniqueReviews[review.productid] = filehandle
filehandle.close()
#numReviesPerProduct[review.productid] = 1
'''
counter = counter + 1
print("Processed "+str(counter)+" Reviews so far")
print("Num Reviews processed in this run")
print(counter-startFrom)
print("Num Unique Products")
#print(len(uniqueReviews))
'''
countNumProducts = 0
print("Num Products with 20 reviews or more ")
for key,value in numReviesPerProduct.items():
if value >19:
countNumProducts = countNumProducts + 1
print(countNumProducts)
'''
Finished = datetime.now()
print("Finished at ")
print(Finished)
print("Taking ")
done = Finished - start
print(str(round(done.total_seconds()/60,3))+" minutes")
return #numReviesPerProduct
#-----------------------------------------------------------------------------------------------------------------------
def readDataStanfordDataSetTechniqueOne():
print("Started at ")
start = datetime.now()
print(start)
uniqueReviews= parseFileTestData("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/aggressive_dedup.json/aggressive_dedup.json.gz2",0)
print("Num Unique Products")
print(len(uniqueReviews))
countNumProducts = 0
totalNumReviews = 0
for key,value in uniqueReviews.items():
numReviews = len(value)
if numReviews > 19:
valid = writeEachProductReviewsToFile(key,value,"C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_one-p2/")
if valid == 1:
countNumProducts = countNumProducts + 1
totalNumReviews = totalNumReviews + numReviews
print("Num Products with 20 reviews or more ")
print(countNumProducts)
print("With Total Num Reviews")
print(totalNumReviews)
Finished = datetime.now()
print("Finished at ")
print(Finished)
print("Taking ")
done = Finished - start
print(str(round(done.total_seconds()/60,3))+" minutes")
return
#-----------------------------------------------------------------------------------------------------------------------
def readDataStanfordDataSetTechniqueThree(filename):
print("Procedure to Parse Product Review Data of Stanford Dataset aggressive_dedup.json")
print("Started")
uniqueReviews = dict()
#fp = open(filename, 'r')
counter = 0
allReviews = []
listReviews = []
shouldIStart = 0
start = datetime.now()
print("Started Searching for Products with reviews >= 20 at")
print(start)
line = ""
startFrom = 0
#finishAt = 10000
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/products_with_big_reviews.txt",'a')
with open(filename, 'r') as fp:
for line in fp:
#if counter == finishAt:
# break
if counter == startFrom:
shouldIStart = 1
if shouldIStart == 1:
new = line.split('asin')
asin = extractFirstString(new[1])
if asin in uniqueReviews:
numReviews = uniqueReviews[asin]
numReviews = numReviews + 1
uniqueReviews[asin] = numReviews
else:
uniqueReviews[asin] = 0
counter = counter + 1
else:
counter = counter + 1
continue
Finished = datetime.now()
done = Finished - start
print("Finished Searching in "+str(round(done.total_seconds()/60,3))+" minutes")
print("Now Writing values to file")
for key,value in uniqueReviews.items():
if value > 19:
filehandle.write(key)
filehandle.write("\t")
filehandle.write(str(value))
filehandle.write("\n")
FinishedWriting = datetime.now()
done = FinishedWriting - done
#print("Finished Writing in "+str(round(done.total_seconds()/60,3))+" minutes")
filehandle.close()
fp.close()
print("Num Reviews")
print(counter)
print("Processed "+str(counter)+" Reviews so far")
FinishedAll = datetime.now()
done = FinishedAll - start
print("Finished the process in "+str(round(done.total_seconds()/60,3))+" minutes")
return
#-----------------------------------------------------------------------------------------------------------------------
def parseReviewLineStanfordDataset(line):
new = line.split('reviewerID')
reviewerID = extractFirstString(new[1])
new = line.split('asin')
asin = extractFirstString(new[1])
reviewerName = ""
new = line.split('reviewerName')
if len(new)>1 :
reviewerName = extractFirstString(new[1])
new = line.split('helpful')
helpful = extractHelpful(new[1])
if helpful == "":
for i in range(len(new)):
helpful = extractHelpful(new[i])
if helpful != "":
break
numVotes = extractNumVotes(new[1])
new = line.split('reviewText')
reviewText = extractFirstString(new[1])
new = line.split('overall')
overall = extractRatingTime(new[1])
if overall == "":
for i in range(len(new)):
overall = extractRatingTime(new[i])
if overall != "":
break
new = line.split('summary')
summary = extractFirstString(new[len(new)-1])
unixReviewTime = 0
new = line.split('unixReviewTime')
if len(new) > 1:
unixReviewTime = extractUnixTime(new[1])
new = line.split('reviewTime')
reviewTime = extractFirstString(new[1])
review = Review(reviewerID,asin,reviewTime,helpful,numVotes,overall,reviewText,summary,unixReviewTime)
return review
def parseReviewLineStanfordDatasetMinimized(line):
new = line.split('\t')
reviewerID = new[0]
asin = new[1]
reviewerName = ""
reviewTime = new[2]
numVotes = new[3]
helpful = new[4]
overall = new[5]
reviewText = new[6]
summary = new[7]
unixReviewTime = new[8]
review = Review(reviewerID,asin,reviewTime,helpful,numVotes,overall,reviewText,summary,unixReviewTime)
return review
def writeListofReviews(listOfReviews):
for review in listOfReviews:
filehandle = None
try:
filehandle = open("/research/remote/petabyte/users/yassien/Unique_Products_Stanford_three/Product_Reviews/"+review.productid+".txt",'a')
writeReviewToFile(filehandle,review)
except OSError as e:
to = e.errno
return
def writeListofReviewsNew(listOfReviews,AllFiles):
numFilesWritten = 0
for key,value in listOfReviews.items():
filehandle = None
if value != "":
try:
filehandle = AllFiles[key]
try:
filehandle.write(value)
numFilesWritten = numFilesWritten +1
except IOError as e:
pass
except KeyError as e:
if len(AllFiles) >= 500:
#filehandle = AllFiles[0]
#del AllFiles[0]
#filehandle.close()
AllFiles.clear()
try:
filehandle = open("/research/remote/petabyte/users/yassien/Unique_Products_Stanford_three/Product_Reviews/"+key+".txt",'a')
filehandle.write(value)
AllFiles[key] = filehandle
numFilesWritten = numFilesWritten +1
except IOError as e:
pass
else:
try:
filehandle = open("/research/remote/petabyte/users/yassien/Unique_Products_Stanford_three/Product_Reviews/"+key+".txt",'a')
filehandle.write(value)
AllFiles[key] = filehandle
numFilesWritten = numFilesWritten +1
except IOError as e:
pass
print("Num Files written in this round " +str(numFilesWritten))
return
def writeListofReviewsNewNew(listOfReviews):
numFilesWritten = 0
counter = 0
numLen = len(listOfReviews)
for key,value in listOfReviews.items():
filehandle = None
if value != "":
try:
fileName = "/research/remote/petabyte/users/yassien/Unique_Products_Stanford_three/Product_Reviews/"+key+".txt"
try:
filehandle = open(fileName,'a')#open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/Product_Reviews/"+key+".txt",'a')
filehandle.write(value)
numFilesWritten = numFilesWritten +1
except IOError as e:
pass
except KeyError as e:
pass
counter = counter + 1
if counter%10000 == 0:
print(str(counter) +" is done out of "+str(numLen))
print("Num Files written in this round " +str(numFilesWritten))
return
def writeOneFileToImportantProducts(listOfReviews,filehandle):
numFilesWritten = 0
for key,value in listOfReviews.items():
#filehandle = None
if value != "":
try:
filehandle.write(value)
numFilesWritten = numFilesWritten +1
except IOError as e:
pass
print("Num Files written in this round " +str(numFilesWritten))
return
def convertReviewtoText(review):
'''
reviewString = review.memberid
reviewString = reviewString + "\t"+review.productid
reviewString = reviewString + "\t"+review.date
reviewString = reviewString + "\t"+str(review.numfeedback)
reviewString = reviewString + "\t"+str(review.numhelpful)
reviewString = reviewString + "\t"+str(review.rating)
reviewString = reviewString + "\t"+review.body
reviewString = reviewString + "\t"+review.summary
reviewString = reviewString + "\t"+str(review.unixtime) + "\n"
'''
reviewString = ''.join([review.memberid, "\t",review.productid,"\t",review.date,"\t",str(review.numfeedback),"\t",str(review.numhelpful),"\t",str(review.rating),"\t",review.body,"\t",review.summary,"\t",str(review.unixtime),"\n"])
#print("reviewString")
#print(reviewString)
return reviewString
#-----------------------------------------------------------------------------------------------------------------------
#import sys
def retrieveProductReviewsPerProduct(filename):
print("Procedure to retrieve all reviews for product from Stanford Dataset aggressive_dedup.json")
print("Started")
counter = 0
shouldIStart = 0
start = datetime.now()
print(start)
line = ""
print("Reading all available products with the criteria")
productList = retrieveAllProductsFromProductReviewFile("/research/remote/petabyte/users/yassien/Unique_Products_Stanford_three/products_with_big_reviews.txt")
#allFileHandles = createfileHandlesForAllProducts(productList)
step1Finished = datetime.now()
done = step1Finished - start
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
'''
print("Creating dicrionary with opened files to write reviews")
productFileHandle = dict([(product, open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/Product_Reviews/"+product+".txt",'a')) for product in productList])
step2Finished = datetime.now()
done = step2Finished - step1Finished
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
'''
AllFiles = dict()
counter = 0
numRightReviews = 0
print("Retrieving all reviews for all product files")
listofReviews = dict()
listRev = []
currentIndex = 0
previous = step1Finished
with open(filename, 'r') as fp:
for line in fp:
new = line.split('\t')
if len(new) > 1:
asin = new[1]
if asin != "":
try:
productId = productList[asin]
if asin == productId:
numRightReviews = numRightReviews + 1
'''
try:
fileName = "C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/Product_Reviews/"+asin+".txt"
filehandle = open(fileName,'a')
filehandle.write(line)
except IOError as e:
pass
'''
if currentIndex == 10000000:
beforeWriting = datetime.now()
print("Will start writing")
writeListofReviewsNewNew(listofReviews)
afterWriting = datetime.now()
done = afterWriting - beforeWriting
print(" Writing took "+str(round(done.total_seconds()/60,3)))
listofReviews = dict()
currentIndex = 0
listofReviews[asin] = line
else:
try:
availableString = listofReviews[asin]
availableString = ''.join([availableString, line])
listofReviews[asin] = availableString
except KeyError as e:
listofReviews[asin] = line
currentIndex = currentIndex + 1
except KeyError as e:
pass
counter = counter + 1
if counter%100000 == 0:
now = datetime.now()
done = now - previous
previous = now
done2 = now - step1Finished
print(str(counter)+" all Processed "+str(numRightReviews)+" good this step took "+str(round(done.total_seconds()/60,3))+" minutes" + " out of "+str(round(done2.total_seconds()/60,3))+" minutes")
if len(listofReviews) > 0 :
print("Writing what's leftover")
writeListofReviewsNewNew(listofReviews)
step3Finished = datetime.now()
done = step3Finished - step1Finished
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
Finished = datetime.now()
done = Finished - start
print("Finished retrieving all reviwes for this product in "+str(round(done.total_seconds()/60,3))+" minutes")
fp.close()
return
#-----------------------------------------------------------------------------------------------------------------------
def retrieveAllProductsFromProductReviewFile(filename):
data_initial = open(filename, "rU")
productList = []
reader = csv.reader((line.replace('\0','') for line in data_initial), delimiter='\n')
for row in reader:
temp = [i.split('\t') for i in row]
temp = list(temp[0])
productList.append(temp[0])
productsFound = dict([(product, product) for product in productList])
return productsFound
def createfileHandlesForAllProducts(productList):
print("Creating All empty files first")
allFileHandles = dict()
start = datetime.now()
counter = 0
print(start)
for key,value in productList.items():
fileName = "C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/Product_Reviews/"+key+".txt"
try:
filehandle = open(fileName,'a')
filehandle.close()
allFileHandles[key] = fileName
except IOError as e:
pass
counter = counter + 1
if counter%100000 == 0:
print(str(counter)+" done so far")
finished = datetime.now()
done = finished - start
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
return allFileHandles
def createSmallerDatasSetFile(filename):
print("Procedure to create Smaller DataSet from Stanford Dataset aggressive_dedup.json")
print("Started")
counter = 0
shouldIStart = 0
start = datetime.now()
print(start)
line = ""
print("Reading all available products with the criteria")
productList = retrieveAllProductsFromProductReviewFile("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/products_with_big_reviews.txt")
step1Finished = datetime.now()
done = step1Finished - start
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/aggressive_dedup_smaller.txt",'a')
filehandle.write(line)
counter = 0
numRightReviews = 0
previous = step1Finished
print("Retrieving all reviews for all product files")
with open(filename, 'r') as fp:
for line in fp:
new = line.split('asin')
if len(new) > 1:
asin = extractFirstString(new[1])
if asin != "":
try:
var1 = productList[asin]
if asin == var1:
numRightReviews = numRightReviews + 1
review = parseReviewLineStanfordDataset(line)
reviewString = convertReviewtoText(review)
filehandle.write(reviewString)
filehandle.write("\n")
except KeyError as e:
pass
counter = counter + 1
if counter%100000 == 0:
now = datetime.now()
done = now - previous
previous = now
done2 = now - step1Finished
print(str(counter)+" all Processed "+str(numRightReviews)+" good this step took "+str(round(done.total_seconds()/60,3))+" minutes" + " out of "+str(round(done2.total_seconds()/60,3))+" minutes")
step3Finished = datetime.now()
done = step3Finished - step1Finished
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
filehandle.close()
Finished = datetime.now()
done = Finished - start
print("Finished retrieving all reviwes for this product in "+str(round(done.total_seconds()/60,3))+" minutes")
fp.close()
return
#-----------------------------------------------------------------------------------------------------------------------
def readMetaDataFileAndWriteOnlyNeeded(filePath):
print("Procedure to retrieve all metaData for product from Stanford Dataset metadata.json")
print("Started")
counter = 0
shouldIStart = 0
start = datetime.now()
print(start)
line = ""
print("Reading all available products with the criteria")
productList = retrieveAllProductsFromProductReviewFile("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/products_with_big_reviews.txt")
step1Finished = datetime.now()
done = step1Finished - start
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/metadata.json/MetaDataSet.txt",'a')
counter = 0
numRightReviews = 0
print("Retrieving all MetaData for all product files")
listofReviews = ""
currentIndex = 0
previous = step1Finished
with open(filePath, 'r') as fp:
for line in fp:
new = line.split('asin')
asin = extractAsin(new[1])
if asin != "":
try:
var1 = productList[asin]
if asin == var1:
filehandle.write(line)
numRightReviews = numRightReviews + 1
except KeyError as e:
pass
counter = counter + 1
if counter%100000 == 0:
now = datetime.now()
done = now - previous
previous = now
done2 = now - step1Finished
print(str(counter)+" all Processed "+str(numRightReviews)+" good this step took "+str(round(done.total_seconds()/60,3))+" minutes" + " out of "+str(round(done2.total_seconds()/60,3))+" minutes")
step3Finished = datetime.now()
done = step3Finished - step1Finished
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
filehandle.close()
Finished = datetime.now()
done = Finished - start
print("Finished retrieving all reviwes for this product in "+str(round(done.total_seconds()/60,3))+" minutes")
fp.close()
return
def createNewMetaDataWithOnlySalesRank(filePath):
print("Procedure to write MetaData File with only Product Id and Sales Rank")
print("Started")
counter = 0
start = datetime.now()
previous = start
print(start)
line = ""
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/metadata.json/Metadata_Sales_Rank.txt",'a')
counter = 0
with open(filePath, 'r') as fp:
for line in fp:
new = line.split('asin')
asin = extractAsin(new[1])
new = line.split('salesRank')
if len(new)>1:
salesRank = extractSalesRank(new[1])
else:
salesRank = ("None", -1)
filehandle.write(str(asin))
filehandle.write("\t")
filehandle.write(salesRank[0])
filehandle.write("\t")
filehandle.write(str(salesRank[1]))
filehandle.write("\n")
if counter%100000 == 0:
now = datetime.now()
done = now - previous
previous = now
print(str(counter)+" all Processed "+str(round(done.total_seconds()/60,3))+" minutes")
counter = counter + 1
filehandle.close()
Finished = datetime.now()
done = Finished - start
print("Finished retrieving all reviwes for this product in "+str(round(done.total_seconds()/60,3))+" minutes")
fp.close()
return
def readSalesRankMetaDataFile(filePath):
print("Procedure to read MetaData File with only Product Id and Sales Rank")
print("Started")
counter = 0
start = datetime.now()
previous = start
print(start)
line = ""
categories = dict()
with open(filePath, 'r') as fp:
for line in fp:
row = line.split('\t')
try:
numProducts = categories[row[1]]
categories[row[1]] = numProducts + 1
except KeyError as e:
categories[row[1]] = 1
pass
counter = 0
for key,value in categories.items():
print(key+" = "+str(value))
counter = counter + value
print("Total Number of all Products = "+str(counter))
return
#-----------------------------------------------------------------------------------------------------------------------
def readSalesRankMetaAndCreateFilesWithCategories(filePath):
print("Procedure to read MetaData File and create files for each category")
print("This file willl contain each product_ID Sales_Rank")
#product_Id Category sales_rank
print("Started")
start = datetime.now()
previous = start
print(start)
counter = 0
line = ""
products = []
categories = dict()
with open(filePath, 'r') as fp:
for line in fp:
row = line.split('\t')
try:
products = categories[row[1]]
products.append((row[0],int(row[2])))
categories[row[1]] = products
except KeyError as e:
products = []
products.append((row[0],int(row[2])))
categories[row[1]] = products
pass
for key,value in categories.items():
print("key")
print(key)
if key !="":
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/categories/"+key+".txt",'a')
for i in range(len(value)):
filehandle.write(str(value[i][0]))
filehandle.write("\t")
filehandle.write(str(value[i][1]))
filehandle.write("\n")
Finished = datetime.now()
done = Finished - start
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
return
def computeMajorityVoteForProductCategories(filePath,category):
print("Procedure to read category File, get a product from it and read its file and compute the average and write to a file for a cetegory file")
print("This file willl contain each product_ID Sales_Rank")
print("Considering "+category)
#product_Id Category sales_rank
print("Started")
start = datetime.now()
print(start)
line = ""
filehandle = open("C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/categories_rating/"+category+".txt",'a')
with open(filePath, 'r') as fp:
for line in fp:
row = line.split('\t')
productId = row[0]
fileName = "C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/Product_Reviews/"+productId+".txt"
overallRate = 0
counter = 0
try:
with open(fileName, 'r') as filep:
for item in filep:
review = item.split('\t')
overallRate = overallRate + float(review[5])
counter = counter + 1
except IOError as e:
pass
filehandle.write(productId)
filehandle.write("\t")
overallRate = overallRate/counter
overallRate = round(overallRate,4)
filehandle.write(str(overallRate))
filehandle.write("\n")
filehandle.close()
Finished = datetime.now()
done = Finished - start
print("Finished in "+str(round(done.total_seconds()/60,3))+" minutes")
return
def computeMajorityVoteForProductCategoriesWithUserExpert(filePath,category,destDirectory):
print("Procedure to read category File, get a product from it and read its file and compute the average and write to a file for a cetegory file")
print("This file willl contain each product_ID Sales_Rank")
print("Considering "+category)
#product_Id Category sales_rank
print("Started")
start = datetime.now()
print(start)
line = ""
#Load User Expertiese per category
filePathExpertiese = "/research/remote/petabyte/users/yassien/Unique_Products_Stanford_three\UserHelpfulVotesPerCategory/"+category+".txt"
userExpert = dict()
with open(filePathExpertiese, 'r') as fp:
for line in fp:
row = line.split('\t')
userExpert[row[0]] = int(row[1])
filehandle = open(destDirectory+category+".txt",'a')
with open(filePath, 'r') as fp:
for line in fp:
row = line.split('\t')
productId = row[0]
fileName = "C:\Yassien_RMIT PhD\Datasets\TruthDiscovery_Datasets\Web data Amazon reviews/Unique_Products_Stanford_three/Product_Reviews/"+productId+".txt"
overallRate = 0
counter = 0
try:
with open(fileName, 'r') as filep:
for item in filep:
review = item.split('\t')
maxVotes = 0
try:
maxVotes = userExpert[review[0]]
except KeyError as e:
maxVotes = 0
numHelpful = int(review[4])
weight = 0
if maxVotes > 0:
weight = float(numHelpful/maxVotes)
overallRate = overallRate + weight*float(review[5])
counter = counter + 1
except IOError as e:
pass
filehandle.write(productId)