Skip to content

Commit

Permalink
feat: Improve flights.* dataset reproducibility (#645)
Browse files Browse the repository at this point in the history
  • Loading branch information
dangotbanned authored Dec 20, 2024
1 parent 14cc146 commit a88ff4c
Show file tree
Hide file tree
Showing 14 changed files with 1,024 additions and 751 deletions.
49 changes: 49 additions & 0 deletions _data/flights.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,49 @@
[[specs]]
start = 2001-01-01
end = 2001-03-31
n_rows = 2_000
suffix = ".json"
dt_format = "%Y/%m/%d %H:%M"

[[specs]]
start = 2001-01-01
end = 2001-03-31
n_rows = 5_000
suffix = ".json"
dt_format = "%Y/%m/%d %H:%M"

[[specs]]
start = 2001-01-01
end = 2001-03-31
n_rows = 10_000
suffix = ".json"
dt_format = "%Y/%m/%d %H:%M"

[[specs]]
start = 2001-01-01
end = 2001-03-31
n_rows = 20_000
suffix = ".json"
dt_format = "%Y/%m/%d %H:%M"

[[specs]]
start = 2001-01-01
end = 2001-03-31
n_rows = 200_000
suffix = ".json"
dt_format = "decimal"
columns = ["delay", "distance", "time"]

[[specs]]
start = 2001-01-01
end = 2001-03-31
n_rows = 200_000
suffix = ".arrow"
dt_format = "decimal"
columns = ["delay", "distance", "time"]

[[specs]]
start = 2001-01-01
end = 2001-06-30
n_rows = 3_000_000
suffix = ".parquet"
2 changes: 1 addition & 1 deletion data/flights-10k.json

Large diffs are not rendered by default.

Binary file modified data/flights-200k.arrow
Binary file not shown.
2 changes: 1 addition & 1 deletion data/flights-200k.json

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion data/flights-20k.json

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion data/flights-2k.json

Large diffs are not rendered by default.

Binary file modified data/flights-3m.parquet
Binary file not shown.
2 changes: 1 addition & 1 deletion data/flights-5k.json

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion datapackage.json
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
}
],
"version": "2.11.0",
"created": "2024-12-14T19:35:54.935236+00:00",
"created": "2024-12-19T18:26:48.655674+00:00",
"resources": [
{
"name": "7zip.png",
Expand Down
2 changes: 1 addition & 1 deletion datapackage.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# vega-datasets
`2.11.0` | [GitHub](http://github.com/vega/vega-datasets.git) | 2024-12-14 19:35:54 [UTC]
`2.11.0` | [GitHub](http://github.com/vega/vega-datasets.git) | 2024-12-19 18:26:48 [UTC]

Common repository for example datasets used by Vega related projects.
BSD-3-Clause license applies only to package code and infrastructure. Users should verify their use of datasets
Expand Down
1 change: 0 additions & 1 deletion package.json
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,6 @@
"scripts": {
"prebuild": "./scripts/make-url-index.sh > src/urls.ts && ./scripts/build_datapackage.py",
"build": "rollup -c",
"flights": "node scripts/flights.js",
"github": "python scripts/github.py",
"release": "release-it"
}
Expand Down
3 changes: 1 addition & 2 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ dev = ["ipython[kernel]>=8.30.0", "ruff>=0.8.2", "taplo>=0.9.3"]
extend-exclude = [
".venv",
"scripts/budget.py",
"scripts/flights.py",
"scripts/github.py",
"scripts/make-unemployment-across-industries.py",
"scripts/update_countries_json.py",
Expand Down Expand Up @@ -111,7 +110,7 @@ select = [
[tool.pyright]
enableExperimentalFeatures = true
ignore = ["../../../**/Lib", ".venv"]
include = ["./scripts/build_datapackage.py", "./scripts/flights2.py"]
include = ["./scripts/build_datapackage.py", "./scripts/flights.py"]
pythonPlatform = "All"
pythonVersion = "3.12"
reportUnusedExpression = "none"
Expand Down
33 changes: 0 additions & 33 deletions scripts/flights.js

This file was deleted.

Loading

0 comments on commit a88ff4c

Please sign in to comment.