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


  
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

	
            prepare_data:
  cmd: python3 src/data/make_dataset.py -o data/interim/ -tr data/raw/train.csv -te
    data/raw/test.csv -r True
  deps:
  - path: data/raw/test.csv
    md5: 029c9cd22461f6dbe8d9ab01def965c6
    size: 28629
  - path: data/raw/train.csv
    md5: 61fdd54abdbf6a85b778e937122e1194
    size: 61194
  - path: src/data/make_dataset.py
    md5: 42647a24ea4f7b7a52e46c53c8809923
    size: 3769
  outs:
  - path: data/interim/label_encoding.yaml
    md5: 6be9b7aa50b322d947ab061b023d30d8
    size: 58
  - path: data/interim/test_categorized.csv
    md5: e2b2f8d01bc9a59b47cbc7af3a30632b
    size: 10527
  - path: data/interim/train_categorized.csv
    md5: 9ccff89e173158915d08684117191ce9
    size: 20716
train_model:
  cmd: python3 src/models/train_model.py -o results/ -tr data/interim/train_categorized.csv
    -te data/interim/test_categorized.csv
  deps:
  - path: data/interim/test_categorized.csv
    md5: e2b2f8d01bc9a59b47cbc7af3a30632b
    size: 10527
  - path: data/interim/train_categorized.csv
    md5: 9ccff89e173158915d08684117191ce9
    size: 20716
  - path: src/models/train_model.py
    md5: a115f8a70b935bd799930296479f17d4
    size: 4306
  params:
    params.yaml:
      random_seed: 12345
      test_size: 0.2
  outs:
  - path: results/metrics.json
    md5: 36d0eec6799a7ab19f2e6022180098d0
    size: 59
  - path: results/test_submission.csv
    md5: 24c71f9277bf187e8e446ab19b89d639
    size: 2839