Auto recipe store example¶

Shows the read-only auto store. It exposes registered fixes as one-step recipes.

In [1]:

import numpy as np

import woodpecker
from woodpecker.stores import AutoRecipeStore
from woodpecker.testing import make_cmip6

import numpy as np import woodpecker from woodpecker.stores import AutoRecipeStore from woodpecker.testing import make_cmip6

Create a CMIP6-like dataset where tas uses Celsius units.

In [2]:

dataset = make_cmip6(overrides={"units": "degC"}, seed=7)
original_values = dataset["tas"].values.copy()

dataset

dataset = make_cmip6(overrides={"units": "degC"}, seed=7) original_values = dataset["tas"].values.copy() dataset

Out[2]:

<xarray.Dataset> Size: 32kB
Dimensions:  (time: 12, lat: 18, lon: 36)
Coordinates:
  * time     (time) datetime64[s] 96B 2000-01-01 2000-02-01 ... 2000-12-01
  * lat      (lat) float64 144B -85.0 -75.0 -65.0 -55.0 ... 55.0 65.0 75.0 85.0
  * lon      (lon) float64 288B 0.0 10.0 20.0 30.0 ... 320.0 330.0 340.0 350.0
Data variables:
    tas      (time, lat, lon) float32 31kB 251.3 251.4 251.5 ... 249.7 249.8
Attributes: (12/15)
    project_id:          CMIP6
    dataset_id:          CMIP6.CMIP.MOHC.HadGEM3-GC31-LL.historical.r1i1p1f3....
    source_file:         CMIP6.CMIP.MOHC.HadGEM3-GC31-LL.historical.r1i1p1f3....
    source_id:           HadGEM3-GC31-LL
    source_name:         HadGEM3-GC31-LL
    mip_era:             CMIP6
    ...                  ...
    variable_id:         tas
    table_id:            Amon
    units:               degC
    frequency:           mon
    grid_label:          gn
    nominal_resolution:  250 km

xarray.Dataset

• Dimensions:
  • time: 12
  • lat: 18
  • lon: 36
• Coordinates: (3)
  • time
    (time)
    datetime64[s]
    2000-01-01 ... 2000-12-01

    axis :

    T

    standard_name :

    time

    array(['2000-01-01T00:00:00', '2000-02-01T00:00:00', '2000-03-01T00:00:00',
           '2000-04-01T00:00:00', '2000-05-01T00:00:00', '2000-06-01T00:00:00',
           '2000-07-01T00:00:00', '2000-08-01T00:00:00', '2000-09-01T00:00:00',
           '2000-10-01T00:00:00', '2000-11-01T00:00:00', '2000-12-01T00:00:00'],
          dtype='datetime64[s]')

  • lat
    (lat)
    float64
    -85.0 -75.0 -65.0 ... 75.0 85.0

    axis :

    Y

    standard_name :

    latitude

    units :

    degrees_north

    array([-85., -75., -65., -55., -45., -35., -25., -15.,  -5.,   5.,  15.,  25.,
            35.,  45.,  55.,  65.,  75.,  85.])

  • lon
    (lon)
    float64
    0.0 10.0 20.0 ... 330.0 340.0 350.0

    axis :

    X

    standard_name :

    longitude

    units :

    degrees_east

    array([  0.,  10.,  20.,  30.,  40.,  50.,  60.,  70.,  80.,  90., 100., 110.,
           120., 130., 140., 150., 160., 170., 180., 190., 200., 210., 220., 230.,
           240., 250., 260., 270., 280., 290., 300., 310., 320., 330., 340., 350.])

• Data variables: (1)
  • tas
    (time, lat, lon)
    float32
    251.3 251.4 251.5 ... 249.7 249.8

    standard_name :

    air_temperature

    units :

    degC

    array([[[251.25006, 251.40385, 251.5099 , ..., 250.80956, 251.02943,
             251.07071],
            [256.74838, 256.93314, 256.99445, ..., 256.31027, 256.50873,
             256.51147],
            [262.22684, 262.38406, 262.58646, ..., 261.81882, 261.98666,
             262.13574],
            ...,
            [262.25458, 262.39645, 262.51572, ..., 261.7234 , 261.99524,
             262.03647],
            [256.68518, 256.85718, 257.08725, ..., 256.33325, 256.52124,
             256.63013],
            [251.21996, 251.38817, 251.56146, ..., 250.8747 , 251.00104,
             251.08731]],
    
           [[249.9617 , 250.03717, 250.2387 , ..., 249.49352, 249.66158,
             249.72684],
            [255.39217, 255.49796, 255.74046, ..., 255.02864, 255.09956,
             255.25482],
            [260.88004, 261.0321 , 261.0684 , ..., 260.51486, 260.61487,
             260.76715],
    ...
            [257.3523 , 257.39072, 257.59402, ..., 256.89362, 256.99808,
             257.13202],
            [251.79507, 251.83777, 252.03273, ..., 251.32108, 251.5068 ,
             251.65724],
            [246.26027, 246.37535, 246.44487, ..., 245.83664, 245.96971,
             246.1535 ]],
    
           [[249.92268, 250.0612 , 250.1606 , ..., 249.47388, 249.61845,
             249.78221],
            [255.41084, 255.63947, 255.7134 , ..., 254.98636, 255.11833,
             255.21419],
            [260.8588 , 261.064  , 261.09976, ..., 260.50873, 260.6594 ,
             260.6807 ],
            ...,
            [260.8669 , 261.0395 , 261.1738 , ..., 260.49658, 260.5588 ,
             260.8415 ],
            [255.35657, 255.51753, 255.71071, ..., 254.98915, 255.16171,
             255.35387],
            [249.88087, 250.03723, 250.12605, ..., 249.49487, 249.67337,
             249.79913]]], shape=(12, 18, 36), dtype=float32)

• Attributes: (15)

  project_id :

  CMIP6

  dataset_id :

  CMIP6.CMIP.MOHC.HadGEM3-GC31-LL.historical.r1i1p1f3.Amon.tas.gn.v20200101

  source_file :

  CMIP6.CMIP.MOHC.HadGEM3-GC31-LL.historical.r1i1p1f3.Amon.tas.gn.v20200101.nc

  source_id :

  HadGEM3-GC31-LL

  source_name :

  HadGEM3-GC31-LL

  mip_era :

  CMIP6

  activity_id :

  CMIP

  experiment_id :

  historical

  variant_label :

  r1i1p1f3

  variable_id :

  tas

  table_id :

  Amon

  units :

  degC

  frequency :

  mon

  grid_label :

  gn

  nominal_resolution :

  250 km

The auto store lists registered fixes as generated recipe ids.

In [3]:

store = AutoRecipeStore()

[recipe.id for recipe in store.list_recipes() if recipe.id.startswith("woodpecker.")]

store = AutoRecipeStore() [recipe.id for recipe in store.list_recipes() if recipe.id.startswith("woodpecker.")]

Out[3]:

['woodpecker.normalize_tas_units_to_kelvin',
 'woodpecker.merge_equivalent_dimensions',
 'woodpecker.ensure_latitude_is_increasing',
 'woodpecker.rename_variables',
 'woodpecker.promote_missing_dimension_coords',
 'woodpecker.remove_coordinate_fill_value_encodings',
 'woodpecker.set_coordinate_variables',
 'woodpecker.convert_units',
 'woodpecker.normalize_longitude_convention',
 'woodpecker.drop_variables']

Lookup returns generated recipes whose fix matches() method applies to the dataset.

In [4]:

matched_plans = store.lookup(dataset)
[recipe.id for recipe in matched_plans]

matched_plans = store.lookup(dataset) [recipe.id for recipe in matched_plans]

Out[4]:

['woodpecker.normalize_tas_units_to_kelvin',
 'xmip.broadcast_lon_lat',
 'xmip.rename_cmip6_axes']

Use the generated recipe through the public recipe API.

In [5]:

recipe_id = "woodpecker.normalize_tas_units_to_kelvin"

findings = woodpecker.recipe.check(dataset, woodpecker.recipe.auto(recipe_id))
findings.fix_ids

recipe_id = "woodpecker.normalize_tas_units_to_kelvin" findings = woodpecker.recipe.check(dataset, woodpecker.recipe.auto(recipe_id)) findings.fix_ids

Out[5]:

('woodpecker.normalize_tas_units_to_kelvin',)

In [6]:

write = woodpecker.recipe.apply(dataset, woodpecker.recipe.auto(recipe_id), dry_run=False)

(
    write.stats,
    dataset["tas"].attrs["units"],
    np.allclose(dataset["tas"].values, original_values + 273.15),
)

write = woodpecker.recipe.apply(dataset, woodpecker.recipe.auto(recipe_id), dry_run=False) ( write.stats, dataset["tas"].attrs["units"], np.allclose(dataset["tas"].values, original_values + 273.15), )

Out[6]:

({'attempted': 1,
  'changed': 1,
  'persist_attempted': 1,
  'persisted': 1,
  'persist_failed': 0,
  'preview': [{'path': 'HadGEM3-GC31-LL',
    'fix_id': 'woodpecker.normalize_tas_units_to_kelvin',
    'name': 'Normalize tas-like units to Kelvin',
    'labels': ['risk.value_transformation'],
    'label_titles': ['careful: value transformation'],
    'label_metadata': [{'id': 'risk.value_transformation',
      'title': 'careful: value transformation',
      'description': 'Transforms data or coordinate values.',
      'category': 'risk-medium'}],
    'changed': True}]},
 'K',
 True)