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

arjvik
/
dvc-demo
mirror of https://github.com/arjvik/dvc-demo

Watch 1
Discussions 0

dvc.lock 3.7 KB
Permalink 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 
  1. split:
    2. 

  2.   cmd: python3 main.py split
    3. 

  3.   deps:
    4. 

  4.   - path: data/CrossValidated-Questions-Nov-2020.csv
    5. 

  5.     md5: 1465d5fe76bf646bca8ee53c8686b745
    6. 

  6.     size: 75856988
    7. 

  7.   - path: main.py
    8. 

  8.     md5: de163b0e187e2be0c1039db0c3bc1060
    9. 

  9.     size: 6753
    10. 

  10.   params:
    11. 

  11.     params.yaml:
    12. 

  12.       paths.dataset: data/CrossValidated-Questions-Nov-2020.csv
    13. 

  13.       paths.test_df: outputs/test.csv.gz
    14. 

  14.       paths.train_df: outputs/train.csv.gz
    15. 

  15.       split.seed: 42
    16. 

  16.   outs:
    17. 

  17.   - path: outputs/test.csv.gz
    18. 

  18.     md5: e1a7c37816b585cc3446b47d49b25832
    19. 

  19.     size: 6161717
    20. 

  20.   - path: outputs/train.csv.gz
    21. 

  21.     md5: 77adfc72aeb6c5dbd63f169f5ab2425b
    22. 

  22.     size: 18668820
    23. 

  23. featurize:
    24. 

  24.   cmd: python3 main.py featurize
    25. 

  25.   deps:
    26. 

  26.   - path: main.py
    27. 

  27.     md5: de163b0e187e2be0c1039db0c3bc1060
    28. 

  28.     size: 6753
    29. 

  29.   - path: outputs/test.csv.gz
    30. 

  30.     md5: e1a7c37816b585cc3446b47d49b25832
    31. 

  31.     size: 6161717
    32. 

  32.   - path: outputs/train.csv.gz
    33. 

  33.     md5: 77adfc72aeb6c5dbd63f169f5ab2425b
    34. 

  34.     size: 18668820
    35. 

  35.   params:
    36. 

  36.     params.yaml:
    37. 

  37.       paths.test_df: outputs/test.csv.gz
    38. 

  38.       paths.test_df_featurized: outputs/test-featurized.csv.gz
    39. 

  39.       paths.train_df: outputs/train.csv.gz
    40. 

  40.       paths.train_df_featurized: outputs/train-featurized.csv.gz
    41. 

  41.   outs:
    42. 

  42.   - path: outputs/test-featurized.csv.gz
    43. 

  43.     md5: 75de8d6a3f8a91a5ddddc0e1ee5ba0a1
    44. 

  44.     size: 6740069
    45. 

  45.   - path: outputs/train-featurized.csv.gz
    46. 

  46.     md5: 0b21899597750e809a6bb20d9b67de25
    47. 

  47.     size: 20416177
    48. 

  48. tfidf:
    49. 

  49.   cmd: python3 main.py tfidf
    50. 

  50.   deps:
    51. 

  51.   - path: main.py
    52. 

  52.     md5: de163b0e187e2be0c1039db0c3bc1060
    53. 

  53.     size: 6753
    54. 

  54.   - path: outputs/test-featurized.csv.gz
    55. 

  55.     md5: 75de8d6a3f8a91a5ddddc0e1ee5ba0a1
    56. 

  56.     size: 6740069
    57. 

  57.   - path: outputs/train-featurized.csv.gz
    58. 

  58.     md5: 0b21899597750e809a6bb20d9b67de25
    59. 

  59.     size: 20416177
    60. 

  60.   params:
    61. 

  61.     params.yaml:
    62. 

  62.       paths.test_df_featurized: outputs/test-featurized.csv.gz
    63. 

  63.       paths.test_tfidf: outputs/test-tfidf.npz
    64. 

  64.       paths.tfidf: outputs/tfidf.pkl
    65. 

  65.       paths.train_df_featurized: outputs/train-featurized.csv.gz
    66. 

  66.       paths.train_tfidf: outputs/train-tfidf.npz
    67. 

  67.       tfidf.max_features: 25000
    68. 

  68.   outs:
    69. 

  69.   - path: outputs/test-tfidf.npz
    70. 

  70.     md5: bf4d56b5fe415833b0a52c36f06e8483
    71. 

  71.     size: 10338250
    72. 

  72.   - path: outputs/tfidf.pkl
    73. 

  73.     md5: ee1310e14c5dea8619e13ba92f55c749
    74. 

  74.     size: 2981751
    75. 

  75.   - path: outputs/train-tfidf.npz
    76. 

  76.     md5: 52c2b75f42dea3eb50cf6cd94f4af44d
    77. 

  77.     size: 31280925
    78. 

  78. train:
    79. 

  79.   cmd: python3 main.py train
    80. 

  80.   deps:
    81. 

  81.   - path: main.py
    82. 

  82.     md5: de163b0e187e2be0c1039db0c3bc1060
    83. 

  83.     size: 6753
    84. 

  84.   - path: outputs/train-featurized.csv.gz
    85. 

  85.     md5: 0b21899597750e809a6bb20d9b67de25
    86. 

  86.     size: 20416177
    87. 

  87.   - path: outputs/train-tfidf.npz
    88. 

  88.     md5: 52c2b75f42dea3eb50cf6cd94f4af44d
    89. 

  89.     size: 31280925
    90. 

  90.   params:
    91. 

  91.     params.yaml:
    92. 

  92.       paths.model: outputs/model.pkl
    93. 

  93.       paths.train_df_featurized: outputs/train-featurized.csv.gz
    94. 

  94.       paths.train_metrics: metrics-train.yaml
    95. 

  95.       paths.train_tfidf: outputs/train-tfidf.npz
    96. 

  96.       train.loss: modified_huber
    97. 

  97.       train.seed: 42
    98. 

  98.   outs:
    99. 

  99.   - path: metrics-train.yaml
    100. 

  100.     md5: fd190bc237bcceb426e2029d35c5b29d
    101. 

  101.     size: 174
    102. 

  102.   - path: outputs/model.pkl
    103. 

  103.     md5: 079208a940d11ec5249a95198ef5cfdd
    104. 

  104.     size: 200962
    105. 

  105. test:
    106. 

  106.   cmd: python3 main.py test
    107. 

  107.   deps:
    108. 

  108.   - path: main.py
    109. 

  109.     md5: de163b0e187e2be0c1039db0c3bc1060
    110. 

  110.     size: 6753
    111. 

  111.   - path: outputs/model.pkl
    112. 

  112.     md5: 079208a940d11ec5249a95198ef5cfdd
    113. 

  113.     size: 200962
    114. 

  114.   - path: outputs/test-featurized.csv.gz
    115. 

  115.     md5: 75de8d6a3f8a91a5ddddc0e1ee5ba0a1
    116. 

  116.     size: 6740069
    117. 

  117.   - path: outputs/test-tfidf.npz
    118. 

  118.     md5: bf4d56b5fe415833b0a52c36f06e8483
    119. 

  119.     size: 10338250
    120. 

  120.   params:
    121. 

  121.     params.yaml:
    122. 

  122.       paths.model: outputs/model.pkl
    123. 

  123.       paths.test_df_featurized: outputs/test-featurized.csv.gz
    124. 

  124.       paths.test_metrics: metrics-test.yaml
    125. 

  125.       paths.test_tfidf: outputs/test-tfidf.npz
    126. 

  126.   outs:
    127. 

  127.   - path: metrics-test.yaml
    128. 

  128.     md5: 4a89b0048cc302e5999fffca39599b9c
    129. 

  129.     size: 166
    130.
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!

dvc-demo 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!

dvc-demo 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!

dvc-demo 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!

dvc-demo is now integrated with Azure Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes