capitalbikeshare-mlops/prefect.yaml at main · aaalexlit/capitalbikeshare-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
# Welcome to your prefect.yaml file! You can you this file for storing and managing
# configuration for deploying your flows. We recommend committing this file to source
# control along with your flow code.

# Generic metadata about this project
name: capitalbikeshare-mlops
prefect-version: 2.11.1

# build section allows you to manage and build docker images
build: null

# push section allows you to manage if and how this project is uploaded to remote locations
push: null

# pull section allows you to provide instructions for cloning this project in remote locations
pull:
  - prefect.deployments.steps.git_clone:
      repository: [email protected]:aaalexlit/capitalbikeshare-mlops.git
      branch: main
      access_token: null

definitions:
  work_pools:
    capitalbikeshare_workpool: &capitalbikeshare_workpool
      name: capitalbikeshare-mlops
      work_queue_name: default

# the deployments section allows you to provide configuration for deploying flows
deployments:
  - name: capitalbikeshare-mlops-download-raw
    tags: ["dataflow", "capitalbikeshare-mlops"]
    description: "Download raw data and create its wandb artifact"
    entrypoint: src/data/download_raw.py:download_raw_data
    work_pool: *capitalbikeshare_workpool
  - name: capitalbikeshare-mlops-combine-raw
    tags: ["dataflow", "capitalbikeshare-mlops"]
    description: "Combine monthly raw data into one file that can be later splitted by date"
    entrypoint: src/data/combine_raw.py:combine_raw_data
    work_pool: *capitalbikeshare_workpool
  - name: capitalbikeshare-mlops-prepare
    tags: ["dataflow", "capitalbikeshare-mlops"]
    description: "Add features and split into train-val-test"
    entrypoint: src/data/prepare.py:prepare_data
    work_pool: *capitalbikeshare_workpool
  - name: capitalbikeshare-mlops-xgb-baseline
    tags: ["training", "capitalbikeshare-mlops"]
    description: "Train an XGBooster with default params"
    entrypoint: src/models/xgb_baseline.py:train_xgboost
    work_pool: *capitalbikeshare_workpool
  - name: capitalbikeshare-mlops-xgb-sweep
    tags: ["training", "capitalbikeshare-mlops"]
    description: "XGBoost hyperparameter tuning with wandb sweeps"
    entrypoint: src/models/xgb_sweep.py:train_sweep
    work_pool: *capitalbikeshare_workpool
  - name: capitalbikeshare-mlops-register-best-model
    tags: ["training", "capitalbikeshare-mlops"]
    description: "XGBoost hyperparameter tuning with wandb sweeps"
    entrypoint: src/models/register_best_model.py:register_best_model
    work_pool: *capitalbikeshare_workpool