mlops-credit-card-fraud-detection-end-to-end/dvc.yaml at main · DataForgeOpenAIHub/mlops-credit-card-fraud-detection-end-to-end · 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
95
96
97
98
99
100
101
102
stages:
  extract_data:
    cmd: python3 src/data/data_collection.py
    deps:
    - data/raw/zipped/transactions.zip
    - src/data/data_collection.py
    outs:
    - data/raw/extracted/

  data_processing:
    cmd: python3 src/data/data_processing.py
    deps:
    - data/raw/extracted/transactions.txt
    - src/data/data_processing.py
    outs:
    - data/inprogress/interim_transactions.csv
    - data/inprogress/interim_transactions.h5
    metrics:
    - reports/data_processing_metrics.json:
        cache: false
    - reports/processing_summary.json:
        cache: false
    plots:
    - reports/data_exploration.txt:
        cache: false
    - reports/preprocess_n_analysis.txt:
        cache: false

  advanced_wrangling:
    cmd: python3 src/data-wrangling-advance/adv_data_processing.py
    deps:
    - data/inprogress/interim_transactions.h5
    - src/data-wrangling-advance/adv_data_processing.py
    outs:
    - data/processed/processed_transactions.csv
    - data/processed/processed_transactions.h5
    - reports/figures/transaction_distributions.png
    metrics:
    - reports/advanced_wrangling_metrics.json:
        cache: false
    - reports/advanced_wrangling_summary.json:
        cache: false
    plots:
    - reports/advanced_data_exploration.txt:
        cache: false
    - reports/advanced_feature_analysis.txt:
        cache: false

  train_model:
    cmd: python3 src/models/train_model.py
    deps:
    - data/processed/processed_transactions.h5
    - src/models/train_model.py
    outs:
    - models/best_rf_model.pkl
    - models/best_gb_model.pkl
    - models/best_xgb_model.pkl
    - data/evaluation/balanced_test_set.csv
    - reports/figures/precision_recall_curve_RandomForest.png
    - reports/figures/precision_recall_curve_GradientBoosting.png
    - reports/figures/precision_recall_curve_XGBoost.png
    - reports/figures/roc_curve_RandomForest.png
    - reports/figures/roc_curve_GradientBoosting.png
    - reports/figures/roc_curve_XGBoost.png
    - reports/figures/confusion_matrix_RandomForest.png
    - reports/figures/confusion_matrix_GradientBoosting.png
    - reports/figures/confusion_matrix_XGBoost.png
    metrics:
    - reports/model_metrics.json:
        cache: false
    - reports/model_summary.json:
        cache: false

  predict:
    cmd: python3 src/models/predict_model.py
    deps:
    - models/best_rf_model.pkl
    - models/best_gb_model.pkl
    - models/best_xgb_model.pkl
    - src/models/predict_model.py
    - reports/model_summary.json
    - data/evaluation/balanced_test_set.csv
    outs:
    - data/predictions/fraud_predictions.csv:
        cache: false
    - reports/figures/balanced_prediction/prediction_confusion_matrix.png:
        cache: false
    - reports/figures/balanced_prediction/prediction_roc_curve.png:
        cache: false
    - reports/figures/balanced_prediction/prediction_pr_curve.png:
        cache: false
    - reports/figures/prediction/prediction_confusion_matrix.png:
        cache: false
    - reports/figures/prediction/prediction_roc_curve.png:
        cache: false
    - reports/figures/prediction/prediction_pr_curve.png:
        cache: false
    metrics:
    - reports/prediction_metrics.json:
        cache: false
    - reports/balanced_prediction_metrics.json:
        cache: false