Fraud-Detection-MLOps/dvc.yaml at dev · Mark007-R/Fraud-Detection-MLOps · 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
stages:
  load_fdb:
    cmd: python src/load_fdb.py
    deps:
      - src/load_fdb.py
    params:
      - fdb
    outs:
      - data/raw/sparkov.csv

  combine:
    cmd: python src/combine_datasets.py
    deps:
      - src/combine_datasets.py
      - data/raw/paysim.csv
      - data/raw/sparkov.csv
    params:
      - combine
    outs:
      - data/processed/combined_transactions.csv

  preprocess:
    cmd: python src/preprocess.py
    deps:
      - src/preprocess.py
      - data/processed/combined_transactions.csv
    params:
      - preprocess
    outs:
      - data/processed/features.csv
      - data/processed/feature_thresholds.json

  train:
    cmd: python src/train.py
    deps:
      - src/train.py
      - data/processed/features.csv
      - data/processed/feature_thresholds.json
    params:
      - train
      - data
    outs:
      - models/fraud_model.pkl
      - data/processed/X_test.csv
      - data/processed/y_test.csv

  evaluate:
    cmd: python src/evaluate.py
    deps:
      - src/evaluate.py
      - models/fraud_model.pkl
      - data/processed/X_test.csv
      - data/processed/y_test.csv
    params:
      - evaluate
      - data
    metrics:
      - metrics/scores.json:
          cache: false
    plots:
      - reports/confusion_matrix.svg
      - reports/roc_curve.svg

  benchmark_fdb:
    cmd: python -m src.benchmark_fdb
    deps:
      - src/benchmark_fdb.py
      - models/fraud_model.pkl
    params:
      - fdb
      - benchmark
    metrics:
      - metrics/fdb_benchmark.json:
          cache: false