MLOps-course/dvc.lock at main · CyberLympha/MLOps-course · GitHub

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
schema: '2.0'
stages:
  get-features:
    cmd: python3 scripts/data_processing/get_features.py datasets/raw/train.csv
    deps:
    - path: datasets/raw/train.csv
      md5: 61fdd54abdbf6a85b778e937122e1194
      size: 60302
    - path: scripts/data_processing/get_features.py
      md5: 0f75cb5037194d41f2b27406a0bbaf22
      size: 890
    outs:
    - path: datasets/stage1
      md5: c0881bca7abe13d308e7996ec518d6c1.dir
      size: 10961
      nfiles: 1
  fill-na:
    cmd: python3 scripts/data_processing/fill_na.py datasets/stage1/train.csv
    deps:
    - path: datasets/stage1/train.csv
      md5: ce04b7010e5b8c96d78c7f501f4f298a
      size: 10961
    - path: scripts/data_processing/fill_na.py
      md5: 7dda9bd6c0a23cea3155f334aba62b34
      size: 1174
    outs:
    - path: datasets/stage2
      md5: 45e5bd682374b0307769db2eeb1d2497.dir
      size: 13401
      nfiles: 1
  text_to_numeric:
    cmd: python3 scripts/data_processing/change_text_to_numeric.py datasets/stage2/train.csv
    deps:
    - path: datasets/stage2/train.csv
      md5: f1e1712206e6880fdf26ef70f6a71b70
      size: 13401
    - path: scripts/data_processing/change_text_to_numeric.py
      md5: a4f0a506c57cdce4cc9c37fd05fa410f
      size: 1120
    outs:
    - path: datasets/stage3
      md5: 4b1b7469529e9efbee8b1d415691d041.dir
      size: 10100
      nfiles: 1
  split:
    cmd: python3 scripts/data_processing/train_test_split.py datasets/stage3/train.csv
    deps:
    - path: datasets/stage3/train.csv
      md5: 3ea11bacb3a629eb2727a78c2986201a
      size: 10100
    - path: scripts/data_processing/train_test_split.py
      md5: 989cb306bc05d3bf7cacfa20d13a2b17
      size: 966
    params:
      params.yaml:
        split.split_ratio: 0.3
    outs:
    - path: datasets/stage4
      md5: 132b452e905cf4475d71c06fed4ebd45.dir
      size: 10089
      nfiles: 2
  train:
    cmd: python3 scripts/model_learning/dt.py datasets/stage4/train.csv model.pkl
    deps:
    - path: datasets/stage4/train.csv
      md5: bb43a71ba4e78db226376a4faa807cd3
      size: 7040
    - path: scripts/model_learning/dt.py
      md5: ed0636ab93ca732843eb06285591f5ed
      size: 713
    params:
      params.yaml:
        train.max_depth: 10
        train.seed: 42
    outs:
    - path: models/model.pkl
      md5: 446468ae6cd97418f7fadd8d2ee8757b
      size: 12326
  evaluate:
    cmd: python3 scripts/model_learning/evaluate.py datasets/stage4/test.csv models/model.pkl
    deps:
    - path: datasets/stage4/test.csv
      md5: 545b0aa35dd577a81416bfc09b5ea5a1
      size: 3049
    - path: models/model.pkl
      md5: 446468ae6cd97418f7fadd8d2ee8757b
      size: 12326
    - path: scripts/model_learning/evaluate.py
      md5: 679e5f6ba9bd28d22f3df7f146e50c2f
      size: 553
    outs:
    - path: evaluate/score.json
      md5: 02f3f5537c77f621cf091d9464699d30
      size: 29