-
Notifications
You must be signed in to change notification settings - Fork 3
/
log.txt
416 lines (388 loc) · 73.3 KB
/
log.txt
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
SUPERVISED
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender Supervised
--params history_length=1 --last_k -1 --top_n_list 100,10,5 --last_months 2
2017-03-09 19:50:15,603 - INFO - Loading data
2017-03-09 19:50:31,459 - INFO - Splitting train and test:0.8
2017-03-09 19:50:31,483 - INFO - Train size:92466 test size:23117
2017-03-09 19:50:31,529 - INFO - Average sequence length:7.395092703944352
2017-03-09 19:50:31,530 - INFO - Fitting Recommender: <recommenders.Supervised_Recommender.SupervisedRecommender object at 0x000001F6A332F470>
100%|██████████████████████████████████████████████████████████████████████████████| 5000/5000 [48:08<00:00, 1.85it/s]
2017-03-09 20:38:44,750 - INFO - Ranking quality top_n: 100
100%|█████████████████████████████████████████████████████████████████████████| 23117/23117 [14:41:28<00:00, 2.40s/it]
2017-03-10 11:20:13,746 - INFO - Set evaluation - Precision:0.0024514426612449467, Recall:0.04196524890047476
3%|██ | 675/23117 [3:44:31<3063:44:17, 491.47s/it]
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
FPMC
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender FPMC
--params n_factor=92,learn_rate=0.01,regular=0.001,n_epoch=40,n_neg=10 --last_k -1 --top_n_list 100,10,5 --last_months 2
2017-03-09 19:44:02,037 - INFO - Splitting train and test:0.8
2017-03-09 19:44:02,052 - INFO - Train size:92466 test size:23117
2017-03-09 19:44:02,081 - INFO - Average sequence length:7.395092703944352
2017-03-09 19:44:02,082 - INFO - Fitting Recommender: <recommenders.FPMC_Recommender.FPMCRecommender object at 0
2017-03-09 19:49:58,983 - INFO - Ranking quality top_n: 100
100%|██████████████████████████████████████████████████████████████████████████| 23117/23117 [3:22:09<00:00, 1.91it/s]
2017-03-09 23:12:08,165 - INFO - Set evaluation - Precision:0.026544966907466827, Recall:0.46062054202005753
100%|█████████████████████████████████████████████████████████████████████████| 23117/23117 [23:56:42<00:00, 5.08s/it]
2017-03-10 23:08:50,541 - INFO - Sequential evaluation - Precision:0.005344300826688646, Recall:0.5344300826688474
2017-03-10 23:08:50,545 - INFO - Ranking quality top_n: 10
100%|██████████████████████████████████████████████████████████████████████████| 23117/23117 [4:28:41<00:00, 1.46it/s]
2017-03-11 03:37:32,086 - INFO - Set evaluation - Precision:0.1429856815330592, Recall:0.26673393849162785
100%|█████████████████████████████████████████████████████████████████████████| 23117/23117 [15:26:08<00:00, 2.09s/it]
2017-03-11 19:03:40,611 - INFO - Sequential evaluation - Precision:0.031090250336992177, Recall:0.3109025033699143
2017-03-11 19:03:40,611 - INFO - Ranking quality top_n: 5
100%|██████████████████████████████████████████████████████████████████████████| 23117/23117 [2:07:24<00:00, 2.71it/s]
2017-03-11 21:11:05,164 - INFO - Set evaluation - Precision:0.17477181295149855, Recall:0.17991677843336054
100%|█████████████████████████████████████████████████████████████████████████| 23117/23117 [13:21:13<00:00, 2.09s/it]
2017-03-12 10:32:18,811 - INFO - Sequential evaluation - Precision:0.0421397134595222, Recall:0.2106985672975992
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender FPMC
--params n_factor=92,learn_rate=0.01,regular=0.001,n_epoch=40,n_neg=10 --last_k -5 --top_n_list 100,10,5 --last_months 2
2017-03-09 19:52:27,366 - INFO - Loading data
2017-03-09 19:52:44,148 - INFO - Splitting train and test:0.8
2017-03-09 19:52:44,159 - INFO - Train size:44767 test size:11192
2017-03-09 19:52:44,181 - INFO - Average sequence length:11.648760699798066
2017-03-09 19:52:44,181 - INFO - Fitting Recommender: <recommenders.FPMC_Recommender.FPMCRecommender object at 0x00000161F7288358>
2017-03-09 19:59:52,721 - INFO - Ranking quality top_n: 100
100%|██████████████████████████████████████████████████████████████████████████| 11192/11192 [1:31:28<00:00, 2.07it/s]
2017-03-09 21:31:21,028 - INFO - Set evaluation - Precision:0.0284685489635443, Recall:0.5027629117887503
100%|██████████████████████████████████████████████████████████████████████████| 11192/11192 [9:33:04<00:00, 1.47s/it]
2017-03-10 07:04:25,441 - INFO - Sequential evaluation - Precision:0.005249572635680222, Recall:0.5249572635680378
2017-03-10 07:04:25,441 - INFO - Ranking quality top_n: 10
100%|██████████████████████████████████████████████████████████████████████████| 11192/11192 [1:27:25<00:00, 2.06it/s]
2017-03-10 08:31:51,317 - INFO - Set evaluation - Precision:0.147525017869904, Recall:0.2902557245971232
100%|█████████████████████████████████████████████████████████████████████████| 11192/11192 [10:56:40<00:00, 2.13s/it]
2017-03-10 19:28:31,835 - INFO - Sequential evaluation - Precision:0.030143963063769385, Recall:0.3014396306376879
2017-03-10 19:28:31,835 - INFO - Ranking quality top_n: 5
100%|██████████████████████████████████████████████████████████████████████████| 11192/11192 [1:51:52<00:00, 1.63it/s]
2017-03-10 21:20:24,258 - INFO - Set evaluation - Precision:0.17914581844175045, Recall:0.18537321256023268
100%|█████████████████████████████████████████████████████████████████████████| 11192/11192 [11:15:42<00:00, 1.17s/it]
2017-03-11 08:36:06,948 - INFO - Sequential evaluation - Precision:0.038556765570083924, Recall:0.1927838278504187
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender FPMC
--params n_factor=92,learn_rate=0.01,regular=0.001,n_epoch=40,n_neg=10 --last_k -10 --top_n_list 100,10,5 --last_months 2
2017-03-10 15:06:56,288 - INFO - Splitting train and test:0.8
2017-03-10 15:06:56,320 - INFO - Train size:17497 test size:4375
2017-03-10 15:06:56,349 - INFO - Average sequence length:17.986786759326993
2017-03-10 15:06:56,384 - INFO - Fitting Recommender: <recommenders.FPMC_Recommender.FPMCRecommender object at 0x00000200736F8400>
2017-03-10 15:15:10,754 - INFO - Ranking quality top_n: 100
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [36:09<00:00, 2.23it/s]
2017-03-10 15:51:20,176 - INFO - Set evaluation - Precision:0.021341714285714634, Recall:0.35489697420631344
100%|████████████████████████████████████████████████████████████████████████████| 4375/4375 [4:26:21<00:00, 2.73s/it]
2017-03-10 20:17:41,470 - INFO - Sequential evaluation - Precision:0.003657341860823396, Recall:0.3657341860823411
2017-03-10 20:17:41,470 - INFO - Ranking quality top_n: 10
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [33:42<00:00, 2.20it/s]
2017-03-10 20:51:23,763 - INFO - Set evaluation - Precision:0.09561142857142947, Recall:0.190181938292845
100%|████████████████████████████████████████████████████████████████████████████| 4375/4375 [4:17:54<00:00, 2.71s/it]
2017-03-11 01:09:18,205 - INFO - Sequential evaluation - Precision:0.019559237875647832, Recall:0.19559237875647867
2017-03-11 01:09:18,205 - INFO - Ranking quality top_n: 5
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [33:19<00:00, 1.95it/s]
2017-03-11 01:42:37,986 - INFO - Set evaluation - Precision:0.1234742857142843, Recall:0.13769889954649142
100%|████████████████████████████████████████████████████████████████████████████| 4375/4375 [4:17:41<00:00, 2.71s/it]
2017-03-11 06:00:19,366 - INFO - Sequential evaluation - Precision:0.02819531252451847, Recall:0.14097656262259153
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
PROD2VEC
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender Prod2Vec
--params min_count=10,size=300,workers=4,window=5 --last_k -1 --top_n_list 100,10,5 --last_months 2
2017-03-11 11:01:37,952 - INFO - Loading data
2017-03-11 11:01:54,317 - INFO - Splitting train and test:0.8
2017-03-11 11:01:54,343 - INFO - Train size:92466 test size:23117
2017-03-11 11:01:54,389 - INFO - Average sequence length:7.395092703944352
2017-03-11 11:01:54,389 - INFO - Fitting Recommender: <recommenders.Prod2Vec_Recommender.Prod2VecRecommender object at 0x000001925A1BD4E0>
2017-03-11 11:02:29,574 - INFO - Ranking quality top_n: 100
0%| | 0/23117 [00:00<?, ?it/s]2017-03-11 11:02:29,578 - INFO - precomputing L2-norms of word weight vectors
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [00:48<00:00, 479.92it/s]
2017-03-11 11:03:17,749 - INFO - Set evaluation - Precision:0.16444175282258933, Recall:0.30106781472298366
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [03:16<00:00, 117.35it/s]
2017-03-11 11:06:34,742 - INFO - Sequential evaluation - Precision:0.035565499318130786, Recall:0.355654993181289
2017-03-11 11:06:34,743 - INFO - Ranking quality top_n: 10
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [00:28<00:00, 817.25it/s]
2017-03-11 11:07:03,048 - INFO - Set evaluation - Precision:0.16444175282258933, Recall:0.30106781472298366
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [02:42<00:00, 142.12it/s]
2017-03-11 11:09:45,712 - INFO - Sequential evaluation - Precision:0.035565499318130786, Recall:0.355654993181289
2017-03-11 11:09:45,713 - INFO - Ranking quality top_n: 5
100%|██████████████████████████████████████████████████████████████████████████| 23117/23117 [00:17<00:00, 1290.04it/s]
2017-03-11 11:10:03,638 - INFO - Set evaluation - Precision:0.21122117921874753, Recall:0.2114398879649963
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [02:01<00:00, 190.79it/s]
2017-03-11 11:12:04,806 - INFO - Sequential evaluation - Precision:0.05767803885490176, Recall:0.2883901942744989
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender Prod2Vec
--params min_count=10,size=300,workers=4,window=5 --last_k -5 --top_n_list 100,10,5 --last_months 2
2017-03-11 11:03:06,735 - INFO - Ranking quality top_n: 100
0%| | 0/11192 [00:00<?, ?it/s]2017-03-11 11:03:06,740 - INFO - precomputing L2-norms of word weight vectors
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [00:14<00:00, 776.56it/s]
2017-03-11 11:03:21,154 - INFO - Set evaluation - Precision:0.1766797712651854, Recall:0.36002058383017377
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [01:40<00:00, 111.27it/s]
2017-03-11 11:05:01,746 - INFO - Sequential evaluation - Precision:0.038660385805378276, Recall:0.38660385805376446
2017-03-11 11:05:01,747 - INFO - Ranking quality top_n: 10
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [00:15<00:00, 700.38it/s]
2017-03-11 11:05:17,735 - INFO - Set evaluation - Precision:0.1766797712651854, Recall:0.36002058383017377
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [01:41<00:00, 110.24it/s]
2017-03-11 11:06:59,270 - INFO - Sequential evaluation - Precision:0.038660385805378276, Recall:0.38660385805376446
2017-03-11 11:06:59,270 - INFO - Ranking quality top_n: 5
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [00:14<00:00, 795.31it/s]
2017-03-11 11:07:13,351 - INFO - Set evaluation - Precision:0.25048248749106394, Recall:0.279204190817003
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [01:36<00:00, 115.66it/s]
2017-03-11 11:08:50,123 - INFO - Sequential evaluation - Precision:0.06602422306639465, Recall:0.3301211153319614
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender Prod2Vec
--params min_count=10,size=300,workers=4,window=5 --last_k -10 --top_n_list 100,10,5 --last_months 2
2017-03-11 11:17:09,046 - INFO - Loading data
2017-03-11 11:17:23,597 - INFO - Splitting train and test:0.8
2017-03-11 11:17:23,601 - INFO - Train size:17497 test size:4375
2017-03-11 11:17:23,614 - INFO - Average sequence length:17.986786759326993
2017-03-11 11:17:23,615 - INFO - Fitting Recommender: <recommenders.Prod2Vec_Recommender.Prod2VecRecommender object at 0x000002A6D30E82E8>
2017-03-11 11:17:41,387 - INFO - Ranking quality top_n: 100
0%| | 0/4375 [00:00<?, ?it/s]2017-03-11 11:17:41,389 - INFO - precomputing L2-norms of word weight vectors
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:04<00:00, 954.37it/s]
2017-03-11 11:17:45,975 - INFO - Set evaluation - Precision:0.12902857142857296, Recall:0.2710728775218497
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:39<00:00, 111.64it/s]
2017-03-11 11:18:25,166 - INFO - Sequential evaluation - Precision:0.029394055991802535, Recall:0.2939405599180288
2017-03-11 11:18:25,166 - INFO - Ranking quality top_n: 10
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:04<00:00, 969.31it/s]
2017-03-11 11:18:29,682 - INFO - Set evaluation - Precision:0.12902857142857296, Recall:0.2710728775218497
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:37<00:00, 115.28it/s]
2017-03-11 11:19:07,637 - INFO - Sequential evaluation - Precision:0.029394055991802535, Recall:0.2939405599180288
2017-03-11 11:19:07,637 - INFO - Ranking quality top_n: 5
100%|████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:04<00:00, 1021.15it/s]
2017-03-11 11:19:11,924 - INFO - Set evaluation - Precision:0.18505142857142978, Recall:0.21846595294605275
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:41<00:00, 105.24it/s]
2017-03-11 11:19:53,496 - INFO - Sequential evaluation - Precision:0.05032560602187711, Recall:0.25162803010938806
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
FPM
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender FPM
--params minsup=0.001,minconf=0.1,max_context=10,min_context=1,spmf_path=spmf/spmf.jar --last_k -1 --top_n_list 100,10,5 --last_months 2
2017-03-11 11:18:57,697 - INFO - Loading data
2017-03-11 11:19:18,361 - INFO - Splitting train and test:0.8
2017-03-11 11:19:18,396 - INFO - Train size:92466 test size:23117
2017-03-11 11:19:18,449 - INFO - Average sequence length:7.395092703944352
2017-03-11 11:19:18,449 - INFO - Creating db for SPMF
2017-03-11 11:19:19,103 - INFO - Fitting Recommender: <recommenders.Freq_Seq_Mining_Recommender.FreqSeqMiningRecommender object at 0x000001AFE6B7B9B0>
2017-03-11 11:19:19,130 - INFO - Using SPMF
java -jar spmf/spmf.jar run PrefixSpan sequences.txt tmp_output.txt 0.1%
2017-03-11 11:19:38,791 - INFO - 300098 frequent sequences found
2017-03-11 11:24:16,942 - INFO - Ranking quality top_n: 100
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [01:11<00:00, 324.21it/s]
2017-03-11 11:25:28,254 - INFO - Set evaluation - Precision:0.08283390086567166, Recall:0.06587118305420953
100%|████████████████████████████████████████████████████████████████████████████| 23117/23117 [39:27<00:00, 9.76it/s]
2017-03-11 12:04:56,016 - INFO - Sequential evaluation - Precision:0.03770344128610938, Recall:0.08923021833573132
2017-03-11 12:04:56,019 - INFO - Ranking quality top_n: 10
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [01:19<00:00, 290.12it/s]
2017-03-11 12:06:15,714 - INFO - Set evaluation - Precision:0.08322173745563469, Recall:0.06220476172261448
100%|████████████████████████████████████████████████████████████████████████████| 23117/23117 [39:42<00:00, 9.70it/s]
2017-03-11 12:45:58,483 - INFO - Sequential evaluation - Precision:0.0377657893820386, Recall:0.08807992888284329
2017-03-11 12:45:58,486 - INFO - Ranking quality top_n: 5
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [01:26<00:00, 266.62it/s]
2017-03-11 12:47:25,217 - INFO - Set evaluation - Precision:0.08445948868797876, Recall:0.04798689263512188
100%|████████████████████████████████████████████████████████████████████████████| 23117/23117 [40:53<00:00, 9.42it/s]
2017-03-11 13:28:19,006 - INFO - Sequential evaluation - Precision:0.038983737742185894, Recall:0.08371583728327564
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender FPM
--params minsup=0.001,minconf=0.1,max_context=10,min_context=1,spmf_path=spmf/spmf.jar --last_k -5 --top_n_list 100,10,5 --last_months 2
2017-03-11 13:52:50,731 - INFO - Loading data
2017-03-11 13:53:08,729 - INFO - Splitting train and test:0.8
2017-03-11 13:53:08,742 - INFO - Train size:44767 test size:11192
2017-03-11 13:53:08,781 - INFO - Average sequence length:11.648760699798066
2017-03-11 13:53:08,781 - INFO - Creating db for SPMF
2017-03-11 13:53:09,087 - INFO - Fitting Recommender: <recommenders.Freq_Seq_Mining_Recommender.FreqSeqMiningRecommender object at 0x0000011CDA8A9630>
2017-03-11 13:53:09,098 - INFO - Using SPMF
java -jar spmf/spmf.jar run PrefixSpan sequences.txt tmp_output.txt 0.1%
2017-03-11 13:53:59,945 - INFO - 1369790 frequent sequences found
2017-03-11 14:34:44,113 - INFO - Ranking quality top_n: 100
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [03:24<00:00, 54.65it/s]
2017-03-11 14:38:08,915 - INFO - Set evaluation - Precision:0.22037550759194297, Recall:0.19116485754625445
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [35:32<00:00, 5.25it/s]
2017-03-11 15:13:40,990 - INFO - Sequential evaluation - Precision:0.10782674123064073, Recall:0.2489736490110922
2017-03-11 15:13:40,990 - INFO - Ranking quality top_n: 10
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [02:57<00:00, 63.15it/s]
2017-03-11 15:16:38,229 - INFO - Set evaluation - Precision:0.22149764003766817, Recall:0.1872671057566829
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [30:45<00:00, 4.91it/s]
2017-03-11 15:47:24,091 - INFO - Sequential evaluation - Precision:0.10800188018946753, Recall:0.24593259771121517
2017-03-11 15:47:24,092 - INFO - Ranking quality top_n: 5
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [02:51<00:00, 67.60it/s]
2017-03-11 15:50:15,473 - INFO - Set evaluation - Precision:0.22339617583988575, Recall:0.16150295457958652
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [36:32<00:00, 3.82it/s]
2017-03-11 16:26:48,041 - INFO - Sequential evaluation - Precision:0.10949543389024737, Recall:0.22813730920560438
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender FPM
--params minsup=0.002,minconf=0.1,max_context=10,min_context=1,spmf_path=spmf/spmf.jar --last_k -10 --top_n_list 100,10,5 --last_months 2
C:\Users\Umberto\Anaconda3\envs\srs\lib\site-packages\gensim\utils.py:855: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")
2017-03-11 15:59:00,783 - INFO - 'pattern' package not found; tag filters are not available for English
2017-03-11 15:59:01,947 - INFO - Loading data
2017-03-11 15:59:17,570 - INFO - Splitting train and test:0.8
2017-03-11 15:59:17,575 - INFO - Train size:17497 test size:4375
2017-03-11 15:59:17,586 - INFO - Average sequence length:17.986786759326993
2017-03-11 15:59:17,586 - INFO - Creating db for SPMF
2017-03-11 15:59:17,684 - INFO - Fitting Recommender: <recommenders.Freq_Seq_Mining_Recommender.FreqSeqMiningRecommender object at 0x000001F3DC932CC0>
2017-03-11 15:59:17,687 - INFO - Using SPMF
java -jar spmf/spmf.jar run PrefixSpan sequences.txt tmp_output.txt 0.2%
2017-03-11 16:00:35,579 - INFO - 2731329 frequent sequences found
2017-03-11 17:04:08,124 - INFO - Ranking quality top_n: 100
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [02:05<00:00, 34.73it/s]
2017-03-11 17:06:14,115 - INFO - Set evaluation - Precision:0.19698168090643103, Recall:0.17015113384721356
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [16:11<00:00, 4.28it/s]
2017-03-11 17:22:25,132 - INFO - Sequential evaluation - Precision:0.10012857470676127, Recall:0.22437934527731093
2017-03-11 17:22:25,133 - INFO - Ranking quality top_n: 10
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [02:04<00:00, 35.25it/s]
2017-03-11 17:24:29,241 - INFO - Set evaluation - Precision:0.1977309750566895, Recall:0.1623725407920552
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [16:07<00:00, 4.19it/s]
2017-03-11 17:40:36,758 - INFO - Sequential evaluation - Precision:0.10024412204537135, Recall:0.2163615837437476
2017-03-11 17:40:36,758 - INFO - Ranking quality top_n: 5
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [02:06<00:00, 34.59it/s]
2017-03-11 17:42:43,252 - INFO - Set evaluation - Precision:0.19987428571428595, Recall:0.1403505097486256
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [17:00<00:00, 4.29it/s]
2017-03-11 17:59:43,620 - INFO - Sequential evaluation - Precision:0.10150696598994259, Recall:0.19679089168865385
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
POP
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender top_pop
--top_n_list 100,10,5 --last_months 2 --last_k -1
2017-03-11 16:46:17,059 - INFO - Loading data
2017-03-11 16:46:36,303 - INFO - Splitting train and test:0.8
2017-03-11 16:46:36,324 - INFO - Train size:92466 test size:23117
2017-03-11 16:46:36,374 - INFO - Average sequence length:7.395092703944352
2017-03-11 16:46:36,374 - INFO - Fitting Recommender: <recommenders.Popularity_Recommender.PopularityRecommender object at 0x000001E64D63E4E0>
2017-03-11 16:46:36,747 - INFO - Ranking quality top_n: 100
100%|██████████████████████████████████████████████████████████████████████████| 23117/23117 [00:08<00:00, 2783.81it/s]
2017-03-11 16:46:45,056 - INFO - Set evaluation - Precision:0.005625297400181958, Recall:0.07864525116421402
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [00:43<00:00, 526.44it/s]
2017-03-11 16:47:28,974 - INFO - Sequential evaluation - Precision:0.0007902738605438175, Recall:0.07902738605438006
2017-03-11 16:47:28,975 - INFO - Ranking quality top_n: 10
100%|█████████████████████████████████████████████████████████████████████████| 23117/23117 [00:01<00:00, 13073.73it/s]
2017-03-11 16:47:30,749 - INFO - Set evaluation - Precision:0.010503092961889282, Recall:0.014805590317465646
100%|██████████████████████████████████████████████████████████████████████████| 23117/23117 [00:07<00:00, 3013.40it/s]
2017-03-11 16:47:38,426 - INFO - Sequential evaluation - Precision:0.001492807303274353, Recall:0.01492807303274341
2017-03-11 16:47:38,426 - INFO - Ranking quality top_n: 5
100%|█████████████████████████████████████████████████████████████████████████| 23117/23117 [00:01<00:00, 18298.03it/s]
2017-03-11 16:47:39,696 - INFO - Set evaluation - Precision:0.01154128995976969, Recall:0.008313483816321424
100%|██████████████████████████████████████████████████████████████████████████| 23117/23117 [00:05<00:00, 4043.05it/s]
2017-03-11 16:47:45,418 - INFO - Sequential evaluation - Precision:0.0016753539804200783, Recall:0.008376769902100374
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender top_pop
--top_n_list 100,10,5 --last_months 2 --last_k -5
2017-03-11 16:48:52,461 - INFO - Loading data
2017-03-11 16:49:11,355 - INFO - Splitting train and test:0.8
2017-03-11 16:49:11,372 - INFO - Train size:44767 test size:11192
2017-03-11 16:49:11,409 - INFO - Average sequence length:11.648760699798066
2017-03-11 16:49:11,409 - INFO - Fitting Recommender: <recommenders.Popularity_Recommender.PopularityRecommender object at 0x0000017161F782B0>
2017-03-11 16:49:11,709 - INFO - Ranking quality top_n: 100
100%|██████████████████████████████████████████████████████████████████████████| 11192/11192 [00:04<00:00, 2672.63it/s]
2017-03-11 16:49:15,905 - INFO - Set evaluation - Precision:0.006460864903502559, Recall:0.09227595770251441
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [00:21<00:00, 510.36it/s]
2017-03-11 16:49:37,840 - INFO - Sequential evaluation - Precision:0.0009246277419032747, Recall:0.09246277419032735
2017-03-11 16:49:37,840 - INFO - Ranking quality top_n: 10
100%|█████████████████████████████████████████████████████████████████████████| 11192/11192 [00:00<00:00, 14853.29it/s]
2017-03-11 16:49:38,598 - INFO - Set evaluation - Precision:0.011454610436025615, Recall:0.0168583753750332
100%|██████████████████████████████████████████████████████████████████████████| 11192/11192 [00:03<00:00, 2928.57it/s]
2017-03-11 16:49:42,423 - INFO - Sequential evaluation - Precision:0.0016963941109947606, Recall:0.016963941109947537
2017-03-11 16:49:42,424 - INFO - Ranking quality top_n: 5
100%|█████████████████████████████████████████████████████████████████████████| 11192/11192 [00:00<00:00, 17537.22it/s]
2017-03-11 16:49:43,067 - INFO - Set evaluation - Precision:0.011919228020014357, Recall:0.009208846539507773
100%|██████████████████████████████████████████████████████████████████████████| 11192/11192 [00:02<00:00, 3847.06it/s]
2017-03-11 16:49:45,980 - INFO - Sequential evaluation - Precision:0.001853589815524784, Recall:0.009267949077623946
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender top_pop
--top_n_list 100,10,5 --last_months 2 --last_k -10
2017-03-11 16:51:22,630 - INFO - Loading data
2017-03-11 16:51:40,333 - INFO - Splitting train and test:0.8
2017-03-11 16:51:40,340 - INFO - Train size:17497 test size:4375
2017-03-11 16:51:40,353 - INFO - Average sequence length:17.986786759326993
2017-03-11 16:51:40,353 - INFO - Fitting Recommender: <recommenders.Popularity_Recommender.PopularityRecommender object at 0x0000017735BFC320>
2017-03-11 16:51:40,510 - INFO - Ranking quality top_n: 100
100%|████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:01<00:00, 2597.24it/s]
2017-03-11 16:51:42,201 - INFO - Set evaluation - Precision:0.007264000000000067, Recall:0.09151592876811442
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:10<00:00, 432.02it/s]
2017-03-11 16:51:52,331 - INFO - Sequential evaluation - Precision:0.000920646056226837, Recall:0.09206460562268425
2017-03-11 16:51:52,332 - INFO - Ranking quality top_n: 10
100%|███████████████████████████████████████████████████████████████████████████| 4375/4375 [00:00<00:00, 13614.19it/s]
2017-03-11 16:51:52,657 - INFO - Set evaluation - Precision:0.013120000000000074, Recall:0.016848318581844938
100%|████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:01<00:00, 2357.94it/s]
2017-03-11 16:51:54,517 - INFO - Sequential evaluation - Precision:0.0017063782792663602, Recall:0.017063782792663663
2017-03-11 16:51:54,518 - INFO - Ranking quality top_n: 5
100%|███████████████████████████████████████████████████████████████████████████| 4375/4375 [00:00<00:00, 16654.12it/s]
2017-03-11 16:51:54,785 - INFO - Set evaluation - Precision:0.014262857142857192, Recall:0.008950800620023389
100%|████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:01<00:00, 3248.97it/s]
2017-03-11 16:51:56,134 - INFO - Sequential evaluation - Precision:0.0018167817462930755, Recall:0.009083908731465395
%%%%%%%%%%%%%%%%%%%%%%%
MARKOV
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender Markov
--params from_k=1,to_k=1 --last_k -1 --top_n_list 100,10,5 --last_months 2
2017-03-11 11:22:14,410 - INFO - Loading data
2017-03-11 11:22:32,466 - INFO - Splitting train and test:0.8
2017-03-11 11:22:32,483 - INFO - Train size:92466 test size:23117
2017-03-11 11:22:32,528 - INFO - Average sequence length:7.395092703944352
2017-03-11 11:22:32,528 - INFO - Fitting Recommender: <recommenders.Mixed_Markov_Recommender.MixedMarkovChainRecommender object at 0x000002288B27C550>
2017-03-11 11:22:32,554 - INFO - Building Markov Chain model with k = 1
2017-03-11 11:22:32,554 - INFO - Adding nodes
2017-03-11 11:22:56,109 - INFO - Adding edges
2017-03-11 15:05:09,364 - INFO - Applying skipping
2017-03-11 16:01:31,147 - INFO - Applying clustering
2017-03-11 16:01:31,149 - INFO - 5000 states in the graph
2017-03-11 22:57:20,644 - INFO - Ranking quality top_n: 100
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [01:38<00:00, 233.60it/s]
2017-03-11 22:58:59,620 - INFO - Set evaluation - Precision:0.025309733829436493, Recall:0.4312724542590487
100%|████████████████████████████████████████████████████████████████████████████| 23117/23117 [10:41<00:00, 36.02it/s]
2017-03-11 23:09:41,431 - INFO - Sequential evaluation - Precision:0.0051606653227302055, Recall:0.500339869602559
2017-03-11 23:09:41,431 - INFO - Ranking quality top_n: 10
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [01:36<00:00, 239.25it/s]
2017-03-11 23:11:18,060 - INFO - Set evaluation - Precision:0.07626854695678115, Recall:0.1573223120327867
100%|████████████████████████████████████████████████████████████████████████████| 23117/23117 [10:00<00:00, 38.50it/s]
2017-03-11 23:21:18,437 - INFO - Sequential evaluation - Precision:0.02636122994333113, Recall:0.2636122994333036
2017-03-11 23:21:18,437 - INFO - Ranking quality top_n: 5
100%|███████████████████████████████████████████████████████████████████████████| 23117/23117 [01:40<00:00, 230.90it/s]
2017-03-11 23:22:58,559 - INFO - Set evaluation - Precision:0.0751395077215964, Recall:0.08295400107776907
100%|████████████████████████████████████████████████████████████████████████████| 23117/23117 [10:05<00:00, 38.20it/s]
2017-03-11 23:33:03,753 - INFO - Sequential evaluation - Precision:0.03287978119360246, Recall:0.16439890596800702
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender Markov
--params from_k=1,to_k=1 --last_k -5 --top_n_list 100,10,5 --last_months 2
C:\Users\Umberto\Anaconda3\envs\srs\lib\site-packages\gensim\utils.py:855: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")
2017-03-12 11:08:57,207 - INFO - 'pattern' package not found; tag filters are not available for English
2017-03-12 11:08:58,027 - INFO - Loading data
2017-03-12 11:09:08,118 - INFO - Splitting train and test:0.8
2017-03-12 11:09:08,125 - INFO - Train size:44767 test size:11192
2017-03-12 11:09:08,143 - INFO - Average sequence length:11.648760699798066
2017-03-12 11:09:08,143 - INFO - Fitting Recommender: <recommenders.Mixed_Markov_Recommender.MixedMarkovChainRecommender object at 0x000001EFBA1F82E8>
2017-03-12 11:09:08,151 - INFO - Building Markov Chain model with k = 1
2017-03-12 11:09:08,151 - INFO - Adding nodes
2017-03-12 11:09:19,205 - INFO - Adding edges
2017-03-12 12:27:59,918 - INFO - Applying skipping
2017-03-12 12:28:13,950 - INFO - Applying clustering
2017-03-12 12:28:13,950 - INFO - 5000 states in the graph
2017-03-12 15:56:01,569 - INFO - Ranking quality top_n: 100
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [00:22<00:00, 488.77it/s]
2017-03-12 15:56:24,475 - INFO - Set evaluation - Precision:0.0288809899398137, Recall:0.5211514925965427
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [02:41<00:00, 69.10it/s]
2017-03-12 15:59:06,453 - INFO - Sequential evaluation - Precision:0.005837486313392335, Recall:0.5674916815979182
2017-03-12 15:59:06,454 - INFO - Ranking quality top_n: 10
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [00:21<00:00, 530.76it/s]
2017-03-12 15:59:27,542 - INFO - Set evaluation - Precision:0.12375804145818334, Recall:0.274231995189019
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [02:31<00:00, 73.90it/s]
2017-03-12 16:01:58,993 - INFO - Sequential evaluation - Precision:0.03703047865559294, Recall:0.37030478655591575
2017-03-12 16:01:58,993 - INFO - Ranking quality top_n: 5
100%|███████████████████████████████████████████████████████████████████████████| 11192/11192 [00:21<00:00, 524.11it/s]
2017-03-12 16:02:20,350 - INFO - Set evaluation - Precision:0.14106504646176535, Recall:0.17378764466837907
100%|████████████████████████████████████████████████████████████████████████████| 11192/11192 [02:31<00:00, 73.81it/s]
2017-03-12 16:04:51,982 - INFO - Sequential evaluation - Precision:0.05719117231055061, Recall:0.2859558615527493
(srs) C:\Users\Umberto\Desktop\seq_rec_evaluation>python main.py --dataset datasets/sessions.csv --only_top_k 5000 --recommender Markov
--params from_k=1,to_k=1 --last_k -10 --top_n_list 100,10,5 --last_months 2
C:\Users\Umberto\Anaconda3\envs\srs\lib\site-packages\gensim\utils.py:855: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")
2017-03-12 11:09:33,985 - INFO - 'pattern' package not found; tag filters are not available for English
2017-03-12 11:09:34,652 - INFO - Loading data
2017-03-12 11:09:44,391 - INFO - Splitting train and test:0.8
2017-03-12 11:09:44,394 - INFO - Train size:17497 test size:4375
2017-03-12 11:09:44,401 - INFO - Average sequence length:17.986786759326993
2017-03-12 11:09:44,401 - INFO - Fitting Recommender: <recommenders.Mixed_Markov_Recommender.MixedMarkovChainRecommender object at 0x0000023A47BD82E8>
2017-03-12 11:09:44,403 - INFO - Building Markov Chain model with k = 1
2017-03-12 11:09:44,410 - INFO - Adding nodes
2017-03-12 11:09:52,834 - INFO - Adding edges
2017-03-12 12:03:18,240 - INFO - Applying skipping
2017-03-12 12:03:30,287 - INFO - Applying clustering
2017-03-12 12:03:30,287 - INFO - 5000 states in the graph
2017-03-12 15:04:15,733 - INFO - Ranking quality top_n: 100
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:08<00:00, 515.68it/s]
2017-03-12 15:04:24,225 - INFO - Set evaluation - Precision:0.031598736382497904, Recall:0.5171196860705128
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [01:10<00:00, 62.38it/s]
2017-03-12 15:05:34,361 - INFO - Sequential evaluation - Precision:0.005904105079305731, Recall:0.5563540177457285
2017-03-12 15:05:34,362 - INFO - Ranking quality top_n: 10
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:07<00:00, 549.46it/s]
2017-03-12 15:05:42,327 - INFO - Set evaluation - Precision:0.12164571428571598, Recall:0.26022871827470057
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [01:05<00:00, 66.60it/s]
2017-03-12 15:06:48,019 - INFO - Sequential evaluation - Precision:0.03269973762229419, Recall:0.3269973762229448
2017-03-12 15:06:48,020 - INFO - Ranking quality top_n: 5
100%|█████████████████████████████████████████████████████████████████████████████| 4375/4375 [00:07<00:00, 549.36it/s]
2017-03-12 15:06:55,986 - INFO - Set evaluation - Precision:0.15309714285714343, Recall:0.18920456893047213
100%|██████████████████████████████████████████████████████████████████████████████| 4375/4375 [01:05<00:00, 67.16it/s]
2017-03-12 15:08:01,133 - INFO - Sequential evaluation - Precision:0.055528192985016406, Recall:0.2776409649250848