Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel
Resources  
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Explore Pricing
Product  
Data Engine LLMs Platform Enterprise
Connect to Dagshub Discord channel
Register
Login

Simon
/
sentiment-classification
mirror of https://github.com/hsuehkuan-lu/sentiment-classification

Watch 1
Issues   Discussions 0 Invite collaborators

dvc.yaml 8.5 KB
History Raw

You have to be logged in to leave a comment. Sign In
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 
  1. stages:
    2. 

  2.   prepare:
    3. 

  3.     cmd: python -m scripts.prepare
    4. 

  4.     deps:
    5. 

  5.     - scripts/prepare.py
    6. 

  6.     - data/all.csv
    7. 

  7.     params:
    8. 

  8.     - basic
    9. 

  9.     outs:
    10. 

  10.     - outputs/vocab.plk
    11. 

  11.     - outputs/config.json
    12. 

  12.   validate:
    13. 

  13.     foreach: # List of simple values
    14. 

  14.       - mlp
    15. 

  15.       - lstm
    16. 

  16.       - cnn
    17. 

  17.       - selected
    18. 

  18.     do:
    19. 

  19.       cmd: python -m scripts.validate ${item}
    20. 

  20.       deps:
    21. 

  21.         - data/all.csv
    22. 

  22.         - outputs/vocab.plk
    23. 

  23.         - outputs/config.json
    24. 

  24.         - scripts/validate.py
    25. 

  25.       params:
    26. 

  26.         - ${item}
    27. 

  27.         - validate
    28. 

  28.       metrics:
    29. 

  29.         - outputs/${item}_validate_results.json:
    30. 

  30.             cache: false
    31. 

  31.       plots:
    32. 

  32.         - outputs/${item}_validate_plots.csv:
    33. 

  33.             cache: false
    34. 

  34. 

  35.   validate_bert:
    36. 

  36.     foreach: # List of simple values
    37. 

  37.       bert-base-uncased_basic:
    38. 

  38.         pretrained_model: bert-base-uncased
    39. 

  39.         method: basic
    40. 

  40.       bert-base-uncased_lstm:
    41. 

  41.         pretrained_model: bert-base-uncased
    42. 

  42.         method: lstm
    43. 

  43.       bert-large-uncased_basic:
    44. 

  44.         pretrained_model: bert-large-uncased
    45. 

  45.         method: basic
    46. 

  46.       bert-large-uncased_lstm:
    47. 

  47.         pretrained_model: bert-large-uncased
    48. 

  48.         method: lstm
    49. 

  49.     do:
    50. 

  50.       cmd: python -m scripts.validate_bert bert ${item.pretrained_model} ${item.method}
    51. 

  51.       deps:
    52. 

  52.         - data/all.csv
    53. 

  53.         - model/bert/${item.method}.py
    54. 

  54.         - scripts/validate_bert.py
    55. 

  55.       params:
    56. 

  56.         - bert.max_len
    57. 

  57.         - bert.do_lower_case
    58. 

  58.         - bert.${item.method}
    59. 

  59.         - validate
    60. 

  60.       metrics:
    61. 

  61.         - outputs/bert-${item.pretrained_model}-${item.method}_validate_results.json:
    62. 

  62.             cache: false
    63. 

  63.       plots:
    64. 

  64.         - outputs/bert-${item.pretrained_model}-${item.method}_validate_plots.csv:
    65. 

  65.             cache: false
    66. 

  66. 

  67.   validate_xlnet:
    68. 

  68.     foreach: # List of simple values
    69. 

  69.       - basic
    70. 

  70.       - sequence_classification
    71. 

  71.     do:
    72. 

  72.       cmd: python -m scripts.validate_bert xlnet ${item}
    73. 

  73.       deps:
    74. 

  74.         - data/all.csv
    75. 

  75.         - model/xlnet/${item}.py
    76. 

  76.         - scripts/validate_bert.py
    77. 

  77.       params:
    78. 

  78.         - xlnet.max_len
    79. 

  79.         - xlnet.${item}
    80. 

  80.         - xlnet.pretrained_model
    81. 

  81.         - validate
    82. 

  82.       metrics:
    83. 

  83.         - outputs/xlnet-${item}_validate_results.json:
    84. 

  84.             cache: false
    85. 

  85.       plots:
    86. 

  86.         - outputs/xlnet-${item}_validate_plots.csv:
    87. 

  87.             cache: false
    88. 

  88. 

  89.   validate_roberta:
    90. 

  90.     foreach: # List of simple values
    91. 

  91.       siebert/sentiment-roberta-large-english_sentiment:
    92. 

  92.         pretrained_model: siebert/sentiment-roberta-large-english
    93. 

  93.         method: sentiment
    94. 

  94.     do:
    95. 

  95.       cmd: python -m scripts.validate_bert roberta ${item.pretrained_model} ${item.method}
    96. 

  96.       deps:
    97. 

  97.         - data/train.csv
    98. 

  98.         - model/roberta/${item.method}.py
    99. 

  99.         - scripts/validate_bert.py
    100. 

  100.       params:
    101. 

  101.         - roberta.max_len
    102. 

  102.         - roberta.do_lower_case
    103. 

  103.         - roberta.${item.method}
    104. 

  104.         - validate
    105. 

  105.       metrics:
    106. 

  106.         - outputs/roberta-${item.pretrained_model}-${item.method}_validate_results.json:
    107. 

  107.             cache: false
    108. 

  108.       plots:
    109. 

  109.         - outputs/roberta-${item.pretrained_model}-${item.method}_validate_plots.csv:
    110. 

  110.             cache: false
    111. 

  111. 

  112.   train:
    113. 

  113.     foreach: # List of simple values
    114. 

  114.     - mlp
    115. 

  115.     - lstm
    116. 

  116.     - cnn
    117. 

  117.     - selected
    118. 

  118.     do:
    119. 

  119.       cmd: python -m scripts.train ${item}
    120. 

  120.       deps:
    121. 

  121.       - data/all.csv
    122. 

  122.       - outputs/vocab.plk
    123. 

  123.       - outputs/config.json
    124. 

  124.       - scripts/train.py
    125. 

  125.       params:
    126. 

  126.       - ${item}
    127. 

  127.       - train
    128. 

  128.       metrics:
    129. 

  129.       - outputs/${item}_results.json:
    130. 

  130.           cache: false
    131. 

  131.       plots:
    132. 

  132.       - outputs/${item}_plots.csv:
    133. 

  133.           cache: false
    134. 

  134.       outs:
    135. 

  135.       - outputs/${item}_checkpoint.pth
    136. 

  136. 

  137.   train_bert:
    138. 

  138.     foreach: # List of simple values
    139. 

  139.       bert-base-uncased_basic:
    140. 

  140.         pretrained_model: bert-base-uncased
    141. 

  141.         method: basic
    142. 

  142.       bert-base-uncased_lstm:
    143. 

  143.         pretrained_model: bert-base-uncased
    144. 

  144.         method: lstm
    145. 

  145.       bert-large-uncased_basic:
    146. 

  146.         pretrained_model: bert-large-uncased
    147. 

  147.         method: basic
    148. 

  148.       bert-large-uncased_lstm:
    149. 

  149.         pretrained_model: bert-large-uncased
    150. 

  150.         method: lstm
    151. 

  151.     do:
    152. 

  152.       cmd: python -m scripts.train_bert bert ${item.pretrained_model} ${item.method}
    153. 

  153.       deps:
    154. 

  154.         - data/all.csv
    155. 

  155.         - model/bert/${item.method}.py
    156. 

  156.         - scripts/train_bert.py
    157. 

  157.       params:
    158. 

  158.         - bert.max_len
    159. 

  159.         - bert.do_lower_case
    160. 

  160.         - bert.${item.method}
    161. 

  161.         - train
    162. 

  162.       metrics:
    163. 

  163.         - outputs/bert-${item.pretrained_model}-${item.method}_results.json:
    164. 

  164.             cache: false
    165. 

  165.       plots:
    166. 

  166.         - outputs/bert-${item.pretrained_model}-${item.method}_plots.csv:
    167. 

  167.             cache: false
    168. 

  168.       outs:
    169. 

  169.         - outputs/bert-${item.pretrained_model}-${item.method}_checkpoint.pth
    170. 

  170. 

  171.   train_xlnet:
    172. 

  172.     foreach: # List of simple values
    173. 

  173.       xlnet-base-cased_basic:
    174. 

  174.         pretrained_model: xlnet-base-cased
    175. 

  175.         method: basic
    176. 

  176.       xlnet-large-cased_basic:
    177. 

  177.         pretrained_model: xlnet-large-cased
    178. 

  178.         method: basic
    179. 

  179.     do:
    180. 

  180.       cmd: python -m scripts.train_bert xlnet ${item.pretrained_model} ${item.method}
    181. 

  181.       deps:
    182. 

  182.         - data/all.csv
    183. 

  183.         - model/xlnet/${item.method}.py
    184. 

  184.         - scripts/train_bert.py
    185. 

  185.       params:
    186. 

  186.         - xlnet.max_len
    187. 

  187.         - xlnet.do_lower_case
    188. 

  188.         - xlnet.${item.method}
    189. 

  189.         - train
    190. 

  190.       metrics:
    191. 

  191.         - outputs/xlnet-${item.pretrained_model}-${item.method}_results.json:
    192. 

  192.             cache: false
    193. 

  193.       plots:
    194. 

  194.         - outputs/xlnet-${item.pretrained_model}-${item.method}_plots.csv:
    195. 

  195.             cache: false
    196. 

  196.       outs:
    197. 

  197.         - outputs/xlnet-${item.pretrained_model}-${item.method}_checkpoint.pth
    198. 

  198. 

  199.   train_roberta:
    200. 

  200.     foreach: # List of simple values
    201. 

  201.       roberta-base_basic:
    202. 

  202.         pretrained_model: roberta-base
    203. 

  203.         method: basic
    204. 

  204.       roberta-large_basic:
    205. 

  205.         pretrained_model: roberta-large
    206. 

  206.         method: basic
    207. 

  207.     do:
    208. 

  208.       cmd: python -m scripts.train_bert roberta ${item.pretrained_model} ${item.method}
    209. 

  209.       deps:
    210. 

  210.         - data/all.csv
    211. 

  211.         - model/roberta/${item.method}.py
    212. 

  212.         - scripts/train_bert.py
    213. 

  213.       params:
    214. 

  214.         - roberta.max_len
    215. 

  215.         - roberta.do_lower_case
    216. 

  216.         - roberta.${item.method}
    217. 

  217.         - train
    218. 

  218.       metrics:
    219. 

  219.         - outputs/roberta-${item.pretrained_model}-${item.method}_results.json:
    220. 

  220.             cache: false
    221. 

  221.       plots:
    222. 

  222.         - outputs/roberta-${item.pretrained_model}-${item.method}_plots.csv:
    223. 

  223.             cache: false
    224. 

  224.       outs:
    225. 

  225.         - outputs/roberta-${item.pretrained_model}-${item.method}_checkpoint.pth
    226. 

  226. 

  227.   inference:
    228. 

  228.     foreach: # List of simple values
    229. 

  229.     - mlp
    230. 

  230.     - lstm
    231. 

  231.     - cnn
    232. 

  232.     - selected
    233. 

  233.     do:
    234. 

  234.       cmd: python -m scripts.inference ${item}
    235. 

  235.       deps:
    236. 

  236.       - data/test.csv
    237. 

  237.       - scripts/inference.py
    238. 

  238.       - outputs/${item}_checkpoint.pth
    239. 

  239.       - outputs/config.json
    240. 

  240.       outs:
    241. 

  241.       - outputs/${item}_submission.csv
    242. 

  242. 

  243.   inference_bert:
    244. 

  244.     foreach: # List of simple values
    245. 

  245.       bert-base-uncased_basic:
    246. 

  246.         pretrained_model: bert-base-uncased
    247. 

  247.         method: basic
    248. 

  248.       bert-base-uncased_lstm:
    249. 

  249.         pretrained_model: bert-base-uncased
    250. 

  250.         method: lstm
    251. 

  251.       bert-large-uncased_basic:
    252. 

  252.         pretrained_model: bert-large-uncased
    253. 

  253.         method: basic
    254. 

  254.       bert-large-uncased_lstm:
    255. 

  255.         pretrained_model: bert-large-uncased
    256. 

  256.         method: lstm
    257. 

  257.     do:
    258. 

  258.       cmd: python -m scripts.inference_bert bert ${item.pretrained_model} ${item.method}
    259. 

  259.       deps:
    260. 

  260.         - data/test.csv
    261. 

  261.         - scripts/inference_bert.py
    262. 

  262.         - outputs/bert-${item.pretrained_model}-${item.method}_checkpoint.pth
    263. 

  263.       outs:
    264. 

  264.         - outputs/bert-${item.pretrained_model}-${item.method}_submission.csv
    265. 

  265. 

  266.   inference_xlnet:
    267. 

  267.     foreach: # List of simple values
    268. 

  268.       xlnet-base-cased_basic:
    269. 

  269.         pretrained_model: xlnet-base-cased
    270. 

  270.         method: basic
    271. 

  271.       xlnet-large-cased_basic:
    272. 

  272.         pretrained_model: xlnet-large-cased
    273. 

  273.         method: basic
    274. 

  274.     do:
    275. 

  275.       cmd: python -m scripts.inference_bert xlnet ${item.pretrained_model} ${item.method}
    276. 

  276.       deps:
    277. 

  277.         - data/test.csv
    278. 

  278.         - scripts/inference_bert.py
    279. 

  279.         - outputs/xlnet-${item.pretrained_model}-${item.method}_checkpoint.pth
    280. 

  280.       outs:
    281. 

  281.         - outputs/xlnet-${item.pretrained_model}-${item.method}_submission.csv
    282. 

  282. 

  283.   inference_roberta:
    284. 

  284.     foreach: # List of simple values
    285. 

  285.       roberta-base_basic:
    286. 

  286.         pretrained_model: roberta-base
    287. 

  287.         method: basic
    288. 

  288.       roberta-large_basic:
    289. 

  289.         pretrained_model: roberta-large
    290. 

  290.         method: basic
    291. 

  291.     do:
    292. 

  292.       cmd: python -m scripts.inference_bert roberta ${item.pretrained_model} ${item.method}
    293. 

  293.       deps:
    294. 

  294.         - data/test.csv
    295. 

  295.         - scripts/inference_bert.py
    296. 

  296.         - outputs/roberta-${item.pretrained_model}-${item.method}_checkpoint.pth
    297. 

  297.       outs:
    298. 

  298.         - outputs/roberta-${item.pretrained_model}-${item.method}_submission.csv
    299.
Prev
Next
Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Write Preview
Loading...
Integrate Google Cloud Storage
Use Google Storage
Select bucket
Upload key
Finish

Use Google Cloud Storage!

Browsing data directories saved to Google Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Google Storage bucket

Service Account Key

Congratulations!

sentiment-classification is now integrated with Google Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate AWS S3
Use S3 remote
Select bucket
Access key
Finish

Use AWS S3 as storage!

Browsing data directories saved to S3 is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

sentiment-classification is now integrated with AWS S3!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate S3 compatible storage
Use S3 like remote
Select bucket
Access key
Finish

Use any S3 compatible storage!

Browsing data directories saved to S3 compatible storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

sentiment-classification is now integrated with your S3 compatible storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate Azure Cloud Storage
Use Azure Storage
Select bucket
Set key
Finish

Use Azure Cloud Storage!

Browsing data directories saved to Azure Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Azure Storage bucket

Access key (If needed)

Congratulations!

sentiment-classification is now integrated with Azure Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes