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

jnirschl
/
titanic_dvc
mirror of https://github.com/jnirschl/titanic_dvc.git

Watch 1
Issues   Discussions 0 Invite collaborators

dvc.lock 3.7 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 
  1. make_dataset:
    2. 

  2.   cmd: python3 src/data/make_dataset.py -c titanic -tr train.csv -te test.csv -o ./data/raw
    3. 

  3.   deps:
    4. 

  4.   - path: src/data/make_dataset.py
    5. 

  5.     md5: 6003407559d33e14c4122af507648dfd
    6. 

  6.     size: 2280
    7. 

  7.   params:
    8. 

  8.     params.yaml:
    9. 

  9.       dtypes:
    10. 

  10.         Age: float
    11. 

  11.         Embarked: category
    12. 

  12.         Fare: float
    13. 

  13.         Parch: int
    14. 

  14.         Pclass: category
    15. 

  15.         Sex: category
    16. 

  16.         SibSp: int
    17. 

  17.         Survived: category
    18. 

  18.   outs:
    19. 

  19.   - path: data/raw/test.csv
    20. 

  20.     md5: 029c9cd22461f6dbe8d9ab01def965c6
    21. 

  21.     size: 28629
    22. 

  22.   - path: data/raw/train.csv
    23. 

  23.     md5: 61fdd54abdbf6a85b778e937122e1194
    24. 

  24.     size: 61194
    25. 

  25.   - path: reports/figures/data_dictionary.tex
    26. 

  26.     md5: 10c5361db59b330722bd70b83ce0fcee
    27. 

  27.     size: 1521
    28. 

  28.   - path: reports/figures/table_one.tex
    29. 

  29.     md5: 4581508bdb37e12d9b9b5ff03244390d
    30. 

  30.     size: 844
    31. 

  31. encode_labels:
    32. 

  32.   cmd: python3 src/data/encode_labels.py -tr data/raw/train.csv -te data/raw/test.csv
    33. 

  33.     -o data/interim
    34. 

  34.   deps:
    35. 

  35.   - path: data/raw/test.csv
    36. 

  36.     md5: 029c9cd22461f6dbe8d9ab01def965c6
    37. 

  37.     size: 28629
    38. 

  38.   - path: data/raw/train.csv
    39. 

  39.     md5: 61fdd54abdbf6a85b778e937122e1194
    40. 

  40.     size: 61194
    41. 

  41.   - path: src/data/encode_labels.py
    42. 

  42.     md5: d86af08312c29e68579950e4898c0e6b
    43. 

  43.     size: 3625
    44. 

  44.   params:
    45. 

  45.     params.yaml:
    46. 

  46.       dtypes:
    47. 

  47.         Age: float
    48. 

  48.         Embarked: category
    49. 

  49.         Fare: float
    50. 

  50.         Parch: int
    51. 

  51.         Pclass: category
    52. 

  52.         Sex: category
    53. 

  53.         SibSp: int
    54. 

  54.         Survived: category
    55. 

  55.   outs:
    56. 

  56.   - path: data/interim/label_encoding.yaml
    57. 

  57.     md5: 8e736d94ad872a9a10f2321653990609
    58. 

  58.     size: 115
    59. 

  59.   - path: data/interim/test_categorized.csv
    60. 

  60.     md5: f0fcdcd7bb08c23d382a665ac1436034
    61. 

  61.     size: 10788
    62. 

  62.   - path: data/interim/train_categorized.csv
    63. 

  63.     md5: 5d06666c95fed743140b44190fb67c77
    64. 

  64.     size: 23884
    65. 

  65. impute_nan:
    66. 

  66.   cmd: python3 src/data/replace_nan.py -tr data/interim/train_categorized.csv -te
    67. 

  67.     data/interim/test_categorized.csv -o data/interim
    68. 

  68.   deps:
    69. 

  69.   - path: data/interim/test_categorized.csv
    70. 

  70.     md5: f0fcdcd7bb08c23d382a665ac1436034
    71. 

  71.     size: 10788
    72. 

  72.   - path: data/interim/train_categorized.csv
    73. 

  73.     md5: 5d06666c95fed743140b44190fb67c77
    74. 

  74.     size: 23884
    75. 

  75.   - path: src/data/replace_nan.py
    76. 

  76.     md5: 6834705a17ff8aec05abebfdb220dc77
    77. 

  77.     size: 2600
    78. 

  78.   params:
    79. 

  79.     params.yaml:
    80. 

  80.       imputation:
    81. 

  81.         Age: 29.6991
    82. 

  82.   outs:
    83. 

  83.   - path: data/interim/test_nan_imputed.csv
    84. 

  84.     md5: aa7540d1d3818bc69f943afdf4b57d39
    85. 

  85.     size: 11132
    86. 

  86.   - path: data/interim/train_nan_imputed.csv
    87. 

  87.     md5: 9edd0421f46d2f0786ea6d82fdcf4e12
    88. 

  88.     size: 24592
    89. 

  89. normalize_data:
    90. 

  90.   cmd: python3 src/data/normalize_data.py -tr data/interim/train_nan_imputed.csv -te
    91. 

  91.     data/interim/test_nan_imputed.csv -o data/processed/
    92. 

  92.   deps:
    93. 

  93.   - path: data/interim/test_nan_imputed.csv
    94. 

  94.     md5: aa7540d1d3818bc69f943afdf4b57d39
    95. 

  95.     size: 11132
    96. 

  96.   - path: data/interim/train_nan_imputed.csv
    97. 

  97.     md5: 9edd0421f46d2f0786ea6d82fdcf4e12
    98. 

  98.     size: 24592
    99. 

  99.   - path: src/data/normalize_data.py
    100. 

  100.     md5: b7f1a5e16165928f55495fa6d48ca26e
    101. 

  101.     size: 1925
    102. 

  102.   params:
    103. 

  103.     params.yaml:
    104. 

  104.       normalize: None
    105. 

  105.   outs:
    106. 

  106.   - path: data/processed/test_processed.csv
    107. 

  107.     md5: aa7540d1d3818bc69f943afdf4b57d39
    108. 

  108.     size: 11132
    109. 

  109.   - path: data/processed/train_processed.csv
    110. 

  110.     md5: 9edd0421f46d2f0786ea6d82fdcf4e12
    111. 

  111.     size: 24592
    112. 

  112. split_train_dev:
    113. 

  113.   cmd: python3 src/data/split_train_dev.py -tr data/processed/train_processed.csv
    114. 

  114.     -o data/processed/
    115. 

  115.   deps:
    116. 

  116.   - path: data/processed/train_processed.csv
    117. 

  117.     md5: 9edd0421f46d2f0786ea6d82fdcf4e12
    118. 

  118.     size: 24592
    119. 

  119.   - path: src/data/split_train_dev.py
    120. 

  120.     md5: 5b39923281d4fc59839e236664d5d0ea
    121. 

  121.     size: 2978
    122. 

  122.   params:
    123. 

  123.     params.yaml:
    124. 

  124.       random_seed: 12345
    125. 

  125.       train_test_split:
    126. 

  126.         target_class: Survived
    127. 

  127.         n_split: 10
    128. 

  128.         shuffle: true
    129. 

  129.   outs:
    130. 

  130.   - path: data/processed/split_train_dev.csv
    131. 

  131.     md5: d4d2c3159380a986fc2f04a8bcffda08
    132. 

  132.     size: 56115
    133.
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!

titanic_dvc 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!

titanic_dvc 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!

titanic_dvc 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!

titanic_dvc is now integrated with Azure Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes