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
etl_instacart:
cmd: python src/etl_instacart.py data/raw/order_products__prior.csv data/raw/products.csv
deps:
- path: data/raw/order_products__prior.csv
md5: 8bca7ad1968ee8e07760b94db74461fb
- path: data/raw/products.csv
md5: dfcfded9d4af77d8b747913a4cbe6ffc
- path: src/etl_instacart.py
md5: 22e3b742c1fd6891b8c0ca48a950fbc7
- path: src/tools/etl_tools.py
md5: 8f4d02a9f5f12bc1afb93b24ca9f9482
outs:
- path: data/input/instacart_transformed.csv
md5: bd8ffc219e463a7cc05ac1d1c8d10a1c
etl_online_retail_ii:
cmd: python src/etl_online_retail_ii.py data/raw/online_retail_II.xlsx
deps:
- path: data/raw/online_retail_II.xlsx
md5: ed54ccfc5d358481c399cc11d0a244be
- path: src/etl_online_retail_ii.py
md5: b45477ef56c2f1907a5707e43a7ac431
- path: src/tools/etl_tools.py
md5: 8f4d02a9f5f12bc1afb93b24ca9f9482
outs:
- path: data/input/online_retail_transformed.csv
md5: d816f3e9174cab9e66f849b353195ea1
product_name_normalization:
cmd: python src/names_cleaner.py data/input/
deps:
- path: data/input/
md5: 03c3034ee49009d97c07a806864bf6d1.dir
- path: src/names_cleaner.py
md5: 8d26e21b8114b566f5194dd9b3d2535d
- path: src/tools/preprocess_tools.py
md5: cb3cff250564f34299890fa0fd25a95b
outs:
- path: data/input_names_normalized/
md5: 38158811565ea03ea29516a96347583f.dir
prepare_embeddings_sets:
cmd: python src/prepare_embeddings_sets.py -o data/computed_embeddings_sets -p params.yaml
deps:
- path: src/prepare_embeddings_sets.py
md5: 86b3bae7557d279f38b5a0ade62af219
params:
params.yaml:
eimp.embeddings.dataset_size: 2000, 5000
eimp.embeddings.train_size: 0.9
eimp.embeddings.vector_size: 50,100,200, 300
outs:
- path: data/computed_embeddings_sets/test/
md5: 6e4fe22bde4de43f4087f5833201dade.dir
- path: data/computed_embeddings_sets/train/
md5: 3788f0454bb06f2e2f3cb5a63dd30c53.dir
prepare_eipt_params:
cmd: python src/prepare_eipt_params.py -p params.yaml -o data/eipt/testing_params
deps:
- path: src/prepare_eipt_params.py
md5: 2e6bef09101906509358c14fd8997c04
params:
params.yaml:
eimp.model:
faiss:
venc:
- 8
- 16
- 32
- 64
indexes:
- Flat
- HNSW32,Flat
- IVF65536_HNSW32,Flat
- HNSW32,SQ8
- IVF65536_HNSW32,SQ8
nprobe:
- 1
- 5
- 10
- 20
- 40
- 80
- 100
nlist:
- 1
- 5
- 10
- 20
- 40
- 80
- 100
M:
- 1
- 10
- 100
- 1000
annoy:
n_trees:
- 10
- 50
- 100
- 200
- 500
- 1000
postgre:
indexes:
- gist
- spgist
KDTree:
leaf_size:
- 10
- 50
- 100
- 200
- 500
- 1000
outs:
- path: data/eipt/testing_params
md5: cb41b8d7955e681212ce07e2d6cbbd9e.dir
fullscan_eipt_index_search:
cmd: python src/fullscan_eipt_index_searcher.py
deps:
- path: data/computed_embeddings_sets/
md5: 0f9055632dfcdd3cf10dc9db07a0682b.dir
- path: src/fullscan_eipt_index_searcher.py
md5: d1f1ccb9fcb6f4ffede93373ff28e36d
params:
params.yaml:
eimp.search_params:
k:
- 1
- 10
outs:
- path: data/eipt/metrics/by_model/fullscan/
md5: fa278f48078e42a81fe61d76418d7c5c.dir
- path: data/eipt/recommendations/fullscan/
md5: 6ae0fff71a0405c1e8c2344cb58009d6.dir
annoy_eipt_index_embeddings:
cmd: python src/eipt_annoy_embeddings_indexer.py
deps:
- path: data/computed_embeddings_sets/train
md5: 3788f0454bb06f2e2f3cb5a63dd30c53.dir
- path: data/eipt/testing_params/annoy_grid.csv
md5: 8a6b6372d0e84607a150972e9764fa88
- path: src/eipt_annoy_embeddings_indexer.py
md5: de64a03ae0f18540cc51666d83b1defd
params:
params.yaml:
eimp.model.annoy:
n_trees:
- 10
- 50
- 100
- 200
- 500
- 1000
eimp.search_params:
k:
- 1
- 10
outs:
- path: data/eipt/indexer_models/annoy/
md5: 7d53ac1e5c2303ed594db682e6273a27.dir
- path: data/eipt/metrics/by_model/annoy/train.csv
md5: ed8f00e6452540e03d185798d2247f2d
annoy_eipt_index_search:
cmd: python src/annoy_eipt_index_searcher.py
deps:
- path: data/computed_embeddings_sets/test/
md5: 6e4fe22bde4de43f4087f5833201dade.dir
- path: data/eipt/indexer_models/annoy/
md5: 7d53ac1e5c2303ed594db682e6273a27.dir
- path: src/annoy_eipt_index_searcher.py
md5: f2ce518d413dc9d7936fba646d12b63d
params:
params.yaml:
eimp.model.annoy:
n_trees:
- 10
- 50
- 100
- 200
- 500
- 1000
eimp.search_params:
k:
- 1
- 10
outs:
- path: data/eipt/metrics/by_model/annoy/test.csv
md5: 8b417c14cc877b97357b011be9ecafc7
- path: data/eipt/recommendations/annoy/
md5: 3e82a6335b93b27a0a178433cee241c0.dir
eipt_analysis:
cmd: python src/eipt_analysis.py -p params.yaml -o data/eipt/metrics/ -m data/eipt/metrics/by_model/
-r data/eipt/recommendations -g data/eipt/testing_params/ -t data/eipt/template.md
-d embedding_indexer_performance_testing.md
deps:
- path: data/eipt/metrics/by_model/
md5: f0c9c692650facf7083c8845cc2efdd0.dir
- path: data/eipt/template.md
md5: 08744d5b03ce51cb0213315d8a8a5df5
- path: data/eipt/testing_params/
md5: 7a450cd4c20113f7d25f116c5b70eb54.dir
- path: src/eipt_analysis.py
md5: e3884737e9a1a9e03d6e75807d0d00fa
params:
params.yaml:
eimp:
embeddings:
vector_size: 50,100,200, 300
dataset_size: 2000, 5000
train_size: 0.9
all_models_params:
metric:
- euclidean
- manhattan
- chebyshev
- cosine
- angular
search_params:
k:
- 1
- 10
model:
faiss:
venc:
- 8
- 16
- 32
- 64
indexes:
- Flat
- HNSW32,Flat
- IVF65536_HNSW32,Flat
- HNSW32,SQ8
- IVF65536_HNSW32,SQ8
nprobe:
- 1
- 5
- 10
- 20
- 40
- 80
- 100
nlist:
- 1
- 5
- 10
- 20
- 40
- 80
- 100
M:
- 1
- 10
- 100
- 1000
annoy:
n_trees:
- 10
- 50
- 100
- 200
- 500
- 1000
postgre:
indexes:
- gist
- spgist
KDTree:
leaf_size:
- 10
- 50
- 100
- 200
- 500
- 1000
estimation:
aimed_param_values:
dataset_size: 5000
metric: euclidean
vector_size: 300
k: 10
x:
- k
- dataset_size
- vector_size
y:
train:
- training_time
- saving_time
- model_size
test:
- search_time
- loading_time
lines:
- k
- metric
- model
facet:
- k
- dataset_size
- vector_size
- metric
topn: 3
relative_graphs: false
log10_graphs: true
outs:
- path: data/eipt/metrics/graphs/
md5: 4340b476d009c0be56badba8406dec53.dir
- path: data/eipt/metrics/test_metrics_summary.csv
md5: d61de8d8d93de378b13af2b10820622e
- path: data/eipt/metrics/train_metrics_summary.csv
md5: 7df6f8addfc6cb2aed99077c4aaf044f
- path: embedding_indexer_performance_testing.md
md5: f9cd222fc5f00dffd37ca79f7135bd32
drop_products_by_name:
cmd: python3 src/products_removers.py data/input_names_normalized/
deps:
- path: data/input_names_normalized/
md5: 38158811565ea03ea29516a96347583f.dir
- path: src/products_removers.py
md5: 1415f5df76d7a9caf988362c9258042c
- path: src/tools/preprocess_tools.py
md5: cb3cff250564f34299890fa0fd25a95b
outs:
- path: data/input_preprocessed/
md5: 0cb51a4fdb39730877c0ddb00e3668fa.dir
split_into_subsets_all_data:
cmd: python3 src/train_test_split.py 0.8 data/input_preprocessed/
deps:
- path: data/input_preprocessed/
md5: 0cb51a4fdb39730877c0ddb00e3668fa.dir
- path: src/tools/preprocess_tools.py
md5: cb3cff250564f34299890fa0fd25a95b
- path: src/train_test_split.py
md5: 825cf8cbe9aebb1a6d7b11d54818b64b
outs:
- path: data/test_data/
md5: 19c6886bb90dc9a64a06aa37fe6eab07.dir
- path: data/train_data/
md5: 6a3a0bf946e6208c00ab0d71f26bcb31.dir
preprocess_test_add_dummy_orders:
cmd: python src/prepare_dummy_orders.py data/test_data data/test_final
deps:
- path: data/test_data
md5: 19c6886bb90dc9a64a06aa37fe6eab07.dir
- path: src/prepare_dummy_orders.py
md5: 42bcb5d8efc555f39ab2904ee26c1c9e
- path: src/tools/preprocess_tools.py
md5: cb3cff250564f34299890fa0fd25a95b
outs:
- path: data/test_final
md5: ecd8c089e4fcbba2f96355ff78987f74.dir
preprocess_train_drop_by_size:
cmd: python src/drop_by_order_size.py data/train_data/ data/train_final/
deps:
- path: data/train_data/
md5: 6a3a0bf946e6208c00ab0d71f26bcb31.dir
- path: src/tools/preprocess_tools.py
md5: cb3cff250564f34299890fa0fd25a95b
params:
params.yaml:
order_size_train.max: 10
order_size_train.min: 2
outs:
- path: data/train_final/
md5: 0e1b6c7dfb48399bbf49d17bcd55b469.dir
input_data_for_random_model:
cmd: python src/prepare_train_for_random_model.py data/input_preprocessed/ data/train_for_random/
deps:
- path: data/input_preprocessed/
md5: 0cb51a4fdb39730877c0ddb00e3668fa.dir
- path: src/prepare_train_for_random_model.py
md5: daec1265a186a396254b13aa43a628f7
- path: src/tools/preprocess_tools.py
md5: cb3cff250564f34299890fa0fd25a95b
outs:
- path: data/train_for_random/
md5: d034fc57afd69ef66a7302749a5ed032.dir
input_data_for_embedding_model:
cmd: python src/prepare_train_for_embedding_model.py data/train_final/ data/train_for_embeddings/
deps:
- path: data/train_final/
md5: 0e1b6c7dfb48399bbf49d17bcd55b469.dir
- path: src/prepare_train_for_embedding_model.py
md5: e3c408f0f144c4e1803289c8f2fef84c
- path: src/tools/preprocess_tools.py
md5: cb3cff250564f34299890fa0fd25a95b
outs:
- path: data/train_for_embeddings/
md5: b1016c20e6f47671fb74da7de646e1aa.dir
train_basket_tfidf_perceptron:
cmd: python src/models/trainer_basket_tfidf_perceptron_embedding.py data/train_for_embeddings/
data/embedding_models/basket_tfidf_perceptron/
deps:
- path: data/train_for_embeddings/
md5: b1016c20e6f47671fb74da7de646e1aa.dir
- path: src/models/dataset_iterators.py
md5: 6d64fead780b23af1dcefc0ee0d6f588
- path: src/models/neural_network_embedding.py
md5: ef0d898dd8dc943413ef7ad1ed29fd9b
- path: src/models/trainer_basket_tfidf_perceptron_embedding.py
md5: cc8859f7aad1f6854a1f22395db2b831
params:
params.yaml:
basket_tfidf_perceptron_model.params_grid:
batch_size: 512
epoch_count: 20
lr: 0.001
momentum: 0.8
basket_tfidf_perceptron_model.random_seed: 10027
outs:
- path: data/embedding_models/basket_tfidf_perceptron/
md5: b8da71ff2a147db74c0d10ad59496519.dir
train_random_model:
cmd: python src/trainer_random_model.py data/train_for_random/ data/random_models/
deps:
- path: data/train_for_random/
md5: d034fc57afd69ef66a7302749a5ed032.dir
- path: src/models/trainer_random_model.py
md5: b9b85136088582dc23d43542a4334098
- path: src/trainer_random_model.py
md5: 1ef638f544fb7b82f71d8bd6932eb259
params:
params.yaml:
random_model.random_seed: 2019
outs:
- path: data/random_models/
md5: dbb04670a0e829621d9d485538049f71.dir
build_products_registry:
cmd: python src/generate_products_registry.py data/input_preprocessed/ data/products_registry/
deps:
- path: data/input_preprocessed/
md5: 0cb51a4fdb39730877c0ddb00e3668fa.dir
- path: src/generate_products_registry.py
md5: 6ebe92490a602ba8c749e97cc5fed9fb
outs:
- path: data/products_registry/
md5: c06a85e1a802bd1b02a185e9f2bbd07b.dir
Tip!
Press p or to see the previous file or,
n or to see the next file