data-lectures/migration.yml at main · QuantEcon/data-lectures · 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
103
104
105
106
107
108
109
# migration.yml — the migration lifecycle tracker for data-lectures.
#
# One record per dataset moving into this repo, holding the PROCESS facts the
# manifests deliberately do not: which PRs landed the file, which PRs repointed
# each consumer, and where the dataset sits in the lifecycle. Manifests
# (lectures/*.yml) are the permanent record of a dataset; this file documents
# a transition and can be archived once the migration programme completes,
# without touching a single manifest.
#
# The audit dashboard (scripts/build_audit.py) renders this file and VERIFIES
# it against reality on every build: a dataset marked `repointed` whose
# consumers still read an old URL (or vice versa) fails the consistency check.
#
# Lifecycle (status):
#   pending    identified for migration; nothing landed here yet
#   landed     file + manifest merged in data-lectures; consumers unchanged
#   repointed  every consumer reads this repo's interim raw URL
#   final      every consumer reads https://data.quantecon.org/lectures/…
#              (gated on the Phase 4 DNS work — data-lectures#15)

datasets:
  lingcod_msy_recovery.csv:
    pilot: P1
    status: repointed
    prior_pattern: local-path
    landed:
      pr: QuantEcon/data-lectures#12
      date: 2026-07-15
    repoints:
      - repo: QuantEcon/lecture-python-intro
        pr: QuantEcon/lecture-python-intro#792
        date: 2026-07-17
    cutover: null

  realwage.csv:
    pilot: P2
    status: repointed
    prior_pattern: legacy
    landed:
      pr: QuantEcon/data-lectures#17
      date: 2026-07-17
    repoints:
      - repo: QuantEcon/lecture-python-programming
        pr: QuantEcon/lecture-python-programming#578
        date: 2026-07-17
      - repo: QuantEcon/lecture-python.myst
        pr: QuantEcon/lecture-python.myst#973
        date: 2026-07-17
    cutover: null

  countries.csv:
    pilot: P2
    status: repointed
    prior_pattern: legacy
    landed:
      pr: QuantEcon/data-lectures#17
      date: 2026-07-17
    repoints:
      - repo: QuantEcon/lecture-python-programming
        pr: QuantEcon/lecture-python-programming#578
        date: 2026-07-17
      - repo: QuantEcon/lecture-python.myst
        pr: QuantEcon/lecture-python.myst#973
        date: 2026-07-17
    cutover: null

  employ.csv:
    pilot: P2
    status: repointed
    prior_pattern: legacy   # programming read the legacy repo; python.myst its own copy
    landed:
      pr: QuantEcon/data-lectures#17
      date: 2026-07-17
    repoints:
      - repo: QuantEcon/lecture-python-programming
        pr: QuantEcon/lecture-python-programming#578
        date: 2026-07-17
      - repo: QuantEcon/lecture-python.myst
        pr: QuantEcon/lecture-python.myst#973
        date: 2026-07-17
    cutover: null

# Planned waves that have not landed anything here yet. `datasets` names the
# files as the audit sees them today, so the dashboard can join the two views.
# `title` is the reader-facing milestone name (the dashboard is read by people
# who are not doing the migration); `scope` carries the insider detail.
pending:
  - pilot: P3
    title: Large data files, and the external data repository
    scope: the LFS case — heavy_tails Forbes/cities set + SCF extracts (fold in high_dim_data)
    datasets:
      - forbes-global2000.csv
      - forbes-billionaires.csv
      - cities_us.csv
      - cities_brazil.csv
      - SCF_plus_mini.csv
      - SCF_plus_mini_no_weights.csv
    tracking:
      - QuantEcon/data-lectures#2
      - QuantEcon/meta#337
  - pilot: P4
    title: Maintained snapshots for lectures that fetch live API data
    scope: the dynamic-snapshot case — a maintained UNRATE twin for the incidental FRED consumers
    datasets: []          # produces a NEW file here; no existing static file moves
    tracking:
      - QuantEcon/meta#338

# Interim → final URL cutover (status: repointed → final) is tracked as one
# sweep, not per dataset: QuantEcon/data-lectures#15, gated on Phase 4 DNS.