nirbarazida
/
N2P


  
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

	
            schema: '2.0'
stages:
  data_preprocessing:
    cmd: python src/data_preprocessing.py
    deps:
    - path: data/enron.csv
      md5: 994e368ae5a22a6db1943a397e7c4308
      size: 60219370
    - path: src/const.py
      md5: a1a78570f6c857331d50efd35e4a5945
      size: 1080
    - path: src/data_preprocessing.py
      md5: 7cfaed9a7b23de020f21c691e7f2b134
      size: 1248
    outs:
    - path: data/X_test.csv
      md5: 40fb21a7dee0a0b5656b45dae7d87edb
      size: 7785845
    - path: data/X_train.csv
      md5: 641bc30a53698b79cdc45ebb230bdbed
      size: 31129310
    - path: data/y_test.csv
      md5: b2cf9cd99a5eb2e30a8823031303af67
      size: 15564
    - path: data/y_train.csv
      md5: ab67e66fcba59cf8b6f5089fea82f94e
      size: 62230
  modeling:
    cmd: python src/modeling.py
    deps:
    - path: data/X_test.csv
      md5: 40fb21a7dee0a0b5656b45dae7d87edb
      size: 7785845
    - path: data/X_train.csv
      md5: 641bc30a53698b79cdc45ebb230bdbed
      size: 31129310
    - path: data/y_test.csv
      md5: b2cf9cd99a5eb2e30a8823031303af67
      size: 15564
    - path: data/y_train.csv
      md5: ab67e66fcba59cf8b6f5089fea82f94e
      size: 62230
    - path: src/const.py
      md5: a1a78570f6c857331d50efd35e4a5945
      size: 1080
    - path: src/modeling.py
      md5: 2f91dc6546f3bf1c3402b8725d375d05
      size: 522