├── .github
├── ISSUE_TEMPLATE
│ └── issue.md
└── workflows
│ ├── dev.yml
│ └── python-publish.yml
├── .gitignore
├── LICENSE
├── README.md
├── ecmwf
└── opendata
│ ├── __init__.py
│ ├── bufr.py
│ ├── client.py
│ ├── date.py
│ ├── grib.py
│ └── urls.py
├── examples
└── aifs-ens-earthkit.ipynb
├── pytest.ini
├── setup.py
├── tests
├── requirements.txt
├── test_aifs_ens.py
├── test_date.py
├── test_examples.py
├── test_latest.py
├── test_opendata.py
├── test_request.py
├── test_sources.py
└── test_stream.py
├── tools
├── .gitignore
├── README
├── check-index.py
├── crawl.py
├── get-all.py
├── param-units.py
├── parse.py
├── possible.py
├── requirements.txt
├── upload.py
└── upload.sh
└── tox.ini
/.github/ISSUE_TEMPLATE/issue.md:
--------------------------------------------------------------------------------
1 | ---
2 | name: Issue
3 | about: Report an issue with ecmwf-opendata
4 | title: ''
5 | labels: ''
6 | assignees: ''
7 |
8 | ---
9 |
10 | Please note that comments on this platform are not monitored by ECMWF. The open data is provided on a best effort basis, without further support from ECMWF. However, users are free to discuss their experiences and issues related to the software tool, and propose clean merge requests with appropriate testing and documentation. If you do require support or assistance, we encourage you to create a support request in the ECMWF Support Portal. Thank you for your understanding and for your contribution to our community.
11 |
--------------------------------------------------------------------------------
/.github/workflows/dev.yml:
--------------------------------------------------------------------------------
1 | name: Dev test
2 |
3 | on:
4 | workflow_dispatch: {}
5 |
6 | jobs:
7 | checks:
8 | strategy:
9 | fail-fast: false
10 | matrix:
11 | platform: ["ubuntu-latest", "macos-latest"]
12 | python-version: ["3.9", "3.10", "3.11" ]
13 |
14 | name: Python ${{ matrix.python-version }} on ${{ matrix.platform }}
15 | runs-on: ${{ matrix.platform }}
16 |
17 | steps:
18 | - uses: actions/checkout@v2
19 |
20 | - uses: actions/setup-python@v2
21 | with:
22 | python-version: ${{ matrix.python-version }}
23 |
24 | - name: Install
25 | run: |
26 | pip install pytest
27 | pip install -e .
28 | pip install -r tests/requirements.txt
29 | pip freeze
30 |
31 | - name: Tests
32 | run: pytest tests/test_examples.py
33 |
--------------------------------------------------------------------------------
/.github/workflows/python-publish.yml:
--------------------------------------------------------------------------------
1 | # This workflow will upload a Python Package using Twine when a release is created
2 | # For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
3 |
4 | name: Upload Python Package
5 |
6 | on:
7 | push: {}
8 | release:
9 | types: [ created ]
10 |
11 | jobs:
12 | quality:
13 | name: Code QA
14 | runs-on: ubuntu-latest
15 | steps:
16 | - uses: actions/checkout@v2
17 | - run: pip install black flake8 isort
18 | - run: black --version
19 | - run: isort --version
20 | - run: flake8 --version
21 | - run: isort --check .
22 | - run: black --check .
23 | - run: flake8 .
24 |
25 | checks:
26 | if: ${{ github.event_name == 'release' }}
27 |
28 | strategy:
29 | fail-fast: false
30 | matrix:
31 | platform: [ "ubuntu-latest", "macos-latest" ]
32 | python-version: [ "3.9", "3.10", "3.11" ]
33 |
34 | name: Python ${{ matrix.python-version }} on ${{ matrix.platform }}
35 | runs-on: ${{ matrix.platform }}
36 | needs: quality
37 |
38 | steps:
39 | - uses: actions/checkout@v2
40 |
41 | - uses: actions/setup-python@v2
42 | with:
43 | python-version: ${{ matrix.python-version }}
44 |
45 | - name: Install
46 | run: |
47 | pip install pytest
48 | pip install -e .
49 | pip install -r tests/requirements.txt
50 | pip freeze
51 |
52 | - name: Tests
53 | run: env SOURCES_TO_TEST=ecmwf pytest
54 |
55 | deploy:
56 |
57 | if: ${{ github.event_name == 'release' }}
58 | runs-on: ubuntu-latest
59 | needs: checks
60 |
61 | steps:
62 | - uses: actions/checkout@v2
63 |
64 | - name: Set up Python
65 | uses: actions/setup-python@v2
66 | with:
67 | python-version: '3.10'
68 |
69 | - name: Check that tag version matches code version
70 | run: |
71 | tag=${GITHUB_REF#refs/tags/}
72 | version=$(python setup.py --version)
73 | echo 'tag='$tag
74 | echo "version file="$version
75 | test "$tag" == "$version"
76 |
77 | - name: Install dependencies
78 | run: |
79 | python -m pip install --upgrade pip
80 | pip install build twine
81 | - name: Build and publish
82 | env:
83 | TWINE_USERNAME: __token__
84 | TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
85 | run: |
86 | python -m build
87 | twine upload dist/*
88 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | # Byte-compiled / optimized / DLL files
2 | __pycache__/
3 | *.py[cod]
4 | *$py.class
5 |
6 | # C extensions
7 | *.so
8 |
9 | # Distribution / packaging
10 | .Python
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | wheels/
23 | pip-wheel-metadata/
24 | share/python-wheels/
25 | *.egg-info/
26 | .installed.cfg
27 | *.egg
28 | MANIFEST
29 |
30 | # PyInstaller
31 | # Usually these files are written by a python script from a template
32 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
33 | *.manifest
34 | *.spec
35 |
36 | # Installer logs
37 | pip-log.txt
38 | pip-delete-this-directory.txt
39 |
40 | # Unit test / coverage reports
41 | htmlcov/
42 | .tox/
43 | .nox/
44 | .coverage
45 | .coverage.*
46 | .cache
47 | nosetests.xml
48 | coverage.xml
49 | *.cover
50 | *.py,cover
51 | .hypothesis/
52 | .pytest_cache/
53 |
54 | # Translations
55 | *.mo
56 | *.pot
57 |
58 | # Django stuff:
59 | *.log
60 | local_settings.py
61 | db.sqlite3
62 | db.sqlite3-journal
63 |
64 | # Flask stuff:
65 | instance/
66 | .webassets-cache
67 |
68 | # Scrapy stuff:
69 | .scrapy
70 |
71 | # Sphinx documentation
72 | docs/_build/
73 |
74 | # PyBuilder
75 | target/
76 |
77 | # Jupyter Notebook
78 | .ipynb_checkpoints
79 |
80 | # IPython
81 | profile_default/
82 | ipython_config.py
83 |
84 | # pyenv
85 | .python-version
86 |
87 | # pipenv
88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
91 | # install all needed dependencies.
92 | #Pipfile.lock
93 |
94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow
95 | __pypackages__/
96 |
97 | # Celery stuff
98 | celerybeat-schedule
99 | celerybeat.pid
100 |
101 | # SageMath parsed files
102 | *.sage.py
103 |
104 | # Environments
105 | .env
106 | .venv
107 | env/
108 | venv/
109 | ENV/
110 | env.bak/
111 | venv.bak/
112 |
113 | # Spyder project settings
114 | .spyderproject
115 | .spyproject
116 |
117 | # Rope project settings
118 | .ropeproject
119 |
120 | # mkdocs documentation
121 | /site
122 |
123 | # mypy
124 | .mypy_cache/
125 | .dmypy.json
126 | dmypy.json
127 |
128 | # Pyre type checker
129 | .pyre/
130 |
131 | # Other
132 | *.swp
133 | test.py
134 | .vscode/
135 | target
136 | data
137 | *.grib
138 | *.grib2
139 | ?
140 | *.download
141 | *.index
142 | *.out
143 | *.1
144 | test.*
145 | *.bufr
146 | done
147 | *.raw
148 | ?.*
149 | TODO
150 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright [yyyy] [name of copyright owner]
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # ecmwf-opendata
2 |
3 | `ecmwf-opendata` is a package to simplify the download of ECMWF [open data](https://www.ecmwf.int/en/forecasts/datasets/open-data). It implements a request-based interface to the dataset using ECMWF's MARS language to select meteorological fields, similar to the existing [ecmwf-api-client](https://github.com/ecmwf/ecmwf-api-client) Python package.
4 |
5 | A collection of Jupyter Notebooks that make use of that package is available [here](https://github.com/ecmwf/notebook-examples/tree/master/opencharts).
6 |
7 | ## Installation
8 |
9 | The `ecmwf-opendata` Python package can be installed from PyPI with:
10 |
11 | ```$ pip install ecmwf-opendata```
12 |
13 | ## Usage
14 | The example below will download the latest available 10-day forecast for the *mean sea level pressure* (`msl`) into a local file called `data.grib2`:
15 |
16 | ```python
17 | from ecmwf.opendata import Client
18 |
19 | client = Client()
20 |
21 | client.retrieve(
22 | step=240,
23 | type="fc",
24 | param="msl",
25 | target="data.grib2",
26 | )
27 | ```
28 |
29 | > ❗ **NOTE:** This package is designed for users that want to download a subset of the whole dataset. If you plan to download a large percentage of each data file, it may be more efficient to download whole files and filter out the data you want locally. See the documentation on the [file naming convention](https://confluence.ecmwf.int/display/DAC/ECMWF+open+data%3A+real-time+forecasts+from+IFS+and+AIFS) for more information. Alternatively, you can use this tool to download whole files by only specifying `date`, `time`, `step`, `stream` and `type`. Please be aware that all data for a full day is in the order of 726 GiB.
30 |
31 |
32 | ## Options
33 |
34 | The constructor of the client object takes the following options:
35 |
36 | ```python
37 | client = Client(
38 | source="ecmwf",
39 | model="ifs",
40 | resol="0p25",
41 | preserve_request_order=False,
42 | infer_stream_keyword=True,
43 | )
44 | ```
45 |
46 | where:
47 |
48 | - `source` is either the name of server to contact or a fully qualified URL. Possible values are `ecmwf` to access ECMWF's servers, `aws` for data hosted by Amazon Web Services or `azure` to access data hosted on Microsoft's Azure. Default is `ecmwf`.
49 |
50 | - `model` is the name of the model that produced the data. Use `ifs` for the physics-driven model, `aifs-single` for the data-driven model, and `aifs-ens` for the ensemble data-driven model. Default is `ifs`.
51 |
52 | - `resol` specifies the resolution of the data. Default is `0p25` for 0.25 degree resolution, and is the only resolution that is currently available.
53 |
54 | - `preserve_request_order`. If this flag is set to `True`, the library will attempt to write the retrieved data into the target file in the order specified by the request. For example, if the request specifies `param=[2t,msl]` the library will ensure that the field `2t` is first in the target file, while with `param=[msl,2t]`, the field `msl` will be first. This also works across different keywords: `...,levelist=[500,100],param=[z,t],...` will produce different output to `...,param=[z,t],levelist=[500,100],...`
55 | If the flag is set to `False`, the library will sort the request to minimise the number of HTTP requests made to the server, leading to faster download speeds. Default is `False`.
56 |
57 | - `infer_stream_keyword`. The `stream` keyword represents the ECMWF forecasting system that creates the data. Setting it properly requires knowledge of how ECMWF runs its operations. If this boolean is set to `True`, the library will try to infer the correct value for the `stream` keyword based on the rest of the request. Default is `True` if model is `ifs`.
58 |
59 | > ⚠️ **NOTE:** It is recommended **not** to set the `preserve_request_order` flag to `True` when downloading a large number of fields as this will add extra load on the servers.
60 |
61 | ## Methods
62 |
63 | > `Client.retrieve()`
64 |
65 | The `Client.retrieve()` method takes request as input and will retrieve the corresponding data from the server and write them in the user's target file.
66 |
67 | A request is a list of keyword/value pairs used to select the desired data. It is possible to specify a list of values for a given keyword.
68 |
69 | The request can either be specified as a dictionary:
70 |
71 | ```python
72 | from ecmwf.opendata import Client
73 |
74 | client = Client(source="ecmwf")
75 |
76 | request = {
77 | "time": 0,
78 | "type": "fc",
79 | "step": 24,
80 | "param": ["2t", "msl"],
81 | }
82 |
83 | client.retrieve(request, "data.grib2")
84 |
85 | # or:
86 |
87 | client.retrieve(
88 | request=request,
89 | target="data.grib2",
90 | )
91 | ```
92 |
93 | or directly as arguments to the `retrieve()` method:
94 |
95 | ```python
96 | from ecmwf.opendata import Client
97 |
98 | client = Client(source="ecmwf")
99 |
100 | client.retrieve(
101 | time=0,
102 | type="fc",
103 | step=24,
104 | param=["2t", "msl"],
105 | target="data.grib2",
106 | )
107 | ```
108 |
109 | The `date` and `time` keyword are used to select the date and time of the forecast run (see [Date and time](#date-and-time) below). If `date` or both `date` and `time` are not specified, the library will query the server for the most recent matching data. The `date` and `time` of the downloaded forecast is returned by the `retrieve()` method.
110 |
111 | ```python
112 | from ecmwf.opendata import Client
113 |
114 | client = Client(source="ecmwf")
115 |
116 | result = client.retrieve(
117 | type="fc",
118 | step=24,
119 | param=["2t", "msl"],
120 | target="data.grib2",
121 | )
122 |
123 | print(result.datetime)
124 | ```
125 |
126 | may print `2022-01-23 00:00:00`.
127 |
128 | > `Client.download()`
129 |
130 | The `Client.download()` method takes the same parameters as the `Client.retrieve()` method, but will download the whole data files from the server, ignoring keywords like `param`, `levelist` or `number`.
131 |
132 | The example below will download all field from the latest time step 24, ignoring the keyword `param`:
133 |
134 | ```python
135 | from ecmwf.opendata import Client
136 |
137 | client = Client(source="ecmwf")
138 |
139 | client.download(
140 | param="msl",
141 | type="fc",
142 | step=24,
143 | target="data.grib2",
144 | )
145 |
146 | ```
147 |
148 | > `Client.latest()`
149 |
150 | The `Client.latest()` method takes the same parameters as the `Client.retrieve()` method, and returns the date of the most recent matching forecast without downloading the data:
151 |
152 | ```python
153 | from ecmwf.opendata import Client
154 |
155 | client = Client(source="ecmwf")
156 |
157 | print(client.latest(
158 | type="fc",
159 | step=24,
160 | param=["2t", "msl"],
161 | target="data.grib2",
162 | ))
163 | ```
164 |
165 | may print `2022-01-23 00:00:00`.
166 |
167 | > ⏰ **NOTE**: The data is available between 7 and 9 hours after the forecast starting date and time, depending on the forecasting system and the time step specified.
168 |
169 | ## Request keywords
170 |
171 | The supported keywords are:
172 |
173 | - `type`: the type of data (compulsory, defaults to `fc`).
174 | - `stream`: the forecast system (optional if unambiguous, compulsory otherwise). See the `infer_stream_keyword` [above](#options).
175 | - `date`: the date at which the forecast starts.
176 | - `time`: the time at which the forecast starts.
177 | - `step`: the forecast time step in hours, or `fcmonth`, the time step in months for the seasonal forecast (compulsory, default to `0` and `1`, respectively).
178 |
179 | and (all optional, with no defaults):
180 |
181 | - `param`: the meteorological parameters, such as wind, pressure or humidity.
182 | - `levtype`: select between single level parameters and parameters on pressure levels.
183 | - `levelist`: the list of pressure levels when relevant.
184 | - `number`: the list of ensemble member numbers when relevant.
185 |
186 | The keywords in the first list are used to identify which file to access, while the second list is used to identify which parts of the files need to be actually downloaded. Some HTTP servers are able to return multiple parts of a file, while other can only return a single part from a file. In the latter case, the library may perform many HTTP requests to the server. If you wish to download whole files, only provide keywords from the first list.
187 |
188 | ### Date and time
189 |
190 | The date and time parameters refer to the starting time of the forecast. All date and time are expressed in UTC.
191 |
192 | There are several ways to specify the date and time in a request.
193 |
194 | Date can be specified using strings, numbers and Python `datetime.datetime` or `datetime.date` objects:
195 |
196 | ```python
197 | ...
198 | date='20220125',
199 | time=12,
200 | ...
201 | date='2022-01-25',
202 | time=12,
203 | ...
204 | date='2022-01-25 12:00:00',
205 | ...
206 | date=20220125,
207 | time=12,
208 | ...
209 | date=datetime.datetime(2022, 1, 25, 12, 0, 0),
210 | ...
211 | date=datetime.date(2022, 1, 25),
212 | time=12,
213 | ...
214 | ```
215 |
216 | Dates can also be given as a number less than or equal to zero. In this case, it is equivalent to the current UTC date minus the given number of days:
217 |
218 | ```python
219 | ...
220 | date=0, # today
221 | date=-1, # yesterday
222 | date=-2, # the day before yesterday
223 | ...
224 | ```
225 |
226 | The keyword `time` can be given as a string or an integer, or a Python `datetime.time` object. All values of time below are equivalent:
227 |
228 | ```python
229 | ...
230 | time=12,
231 | ...
232 | time=1200,
233 | ...
234 | time='12',
235 | ...
236 | time='1200',
237 | ...
238 | time=datetime.time(12),
239 | ...
240 | ```
241 |
242 | | List of valid values for time |
243 | | ----------------------------- |
244 | | 0, 6, 12 and 18 |
245 |
246 | If `time` is not specified, the time is extracted from the date.
247 |
248 | ```python
249 | ...
250 | date='2022-01-25 12:00:00',
251 | ...
252 | ```
253 |
254 | is equivalent to:
255 |
256 | ```python
257 | ...
258 | date='2022-01-25',
259 | time=12,
260 | ...
261 | ```
262 |
263 | If the `time` keyword is specified, it overrides any time given in the request.
264 |
265 | ```python
266 | ...
267 | date='2022-01-25 12:00:00',
268 | time=18,
269 | ...
270 | ```
271 |
272 | is equivalent to:
273 |
274 | ```python
275 | ...
276 | date='2022-01-25',
277 | time=18,
278 | ...
279 | ```
280 |
281 | As stated before, if `date` or both `date` and `time` are not specified, the library will query the server for the most recent matching data. The `date` and `time` of the downloaded forecast is returned by the `retrieve()` method:
282 |
283 | Example without the `date` keyword:
284 |
285 | ```python
286 | from ecmwf.opendata import Client
287 |
288 | client = Client(source="ecmwf")
289 |
290 | result = client.retrieve(
291 | time=12,
292 | type="fc",
293 | param="2t",
294 | step="24",
295 | target="data.grib2",
296 | )
297 |
298 | print(result.datetime)
299 |
300 | ```
301 |
302 | will print `2022-01-22 12:00:00` if run in the morning of 2022-01-23.
303 |
304 | Example without the `date` and `time` keywords:
305 |
306 | ```python
307 | from ecmwf.opendata import Client
308 |
309 | client = Client(source="ecmwf")
310 |
311 | result = client.retrieve(
312 | type="fc",
313 | param="2t",
314 | step="24",
315 | target="data.grib2",
316 | )
317 |
318 | print(result.datetime)
319 |
320 | ```
321 |
322 | will print `2022-01-23 00:00:00` if run in the morning of 2022-01-23.
323 |
324 | ### Stream and type
325 |
326 | ECMWF runs several forecasting systems:
327 |
328 | - [HRES](https://confluence.ecmwf.int/display/FUG/HRES+-+High-Resolution+Forecast): High Resolution Forecast.
329 | - [ENS](https://confluence.ecmwf.int/display/FUG/ENS+-+Ensemble+Forecasts): Ensemble Forecasts.
330 | - [SEAS](https://confluence.ecmwf.int/display/FUG/Long-Range+%28Seasonal%29+Forecast): Long-Range (Seasonal) Forecast.
331 |
332 | Each of these forecasts also produces several types of products, that are referred to using the keywords
333 | `stream` and `type`.
334 |
335 | > Valid values for `type` are:
336 |
337 | HRES:
338 |
339 | - `fc`: Forecast.
340 |
341 | ENS:
342 |
343 | - `cf`: Control forecast.
344 | - `pf`: Perturbed forecast.
345 | - `em`: Ensemble mean.
346 | - `es`: Ensemble standard deviation.
347 | - `ep`: Probabilities.
348 |
349 | > Valid values for `stream` are:
350 |
351 | - `oper`: Atmospheric fields from HRES - 00 UTC and 12 UTC.
352 | - `wave`: Ocean wave fields from HRES - 00 UTC and 12 UTC.
353 | - `enfo`: Atmospheric fields from ENS.
354 | - `waef`: Ocean wave fields from ENS.
355 | - `scda`: Atmospheric fields from HRES - 06 UTC and 18 UTC.
356 | - `scwv`: Ocean wave fields from HRES - 06 UTC and 18 UTC.
357 |
358 | > 📌 **NOTE**: if the client's flag [`infer_stream_keyword`](#options) is set to `True`, the library will infer the stream from the `type` and `time`. In that case, you just need to specify `stream=wave` to access ocean wave products, and don't provide a value for `stream` in other cases.
359 |
360 | ### Time steps
361 |
362 | To select a time step, use the `step` keyword:
363 |
364 | ```python
365 | ...
366 | step=24,
367 | ...
368 | step=[24, 48],
369 | ...
370 | ```
371 |
372 | | Forecasting system | Time | List of time steps |
373 | | -------- | ---- | ------------------ |
374 | | HRES | 00 and 12 | 0 to 144 by 3, 144 to 240 by 6 |
375 | | ENS | 00 and 12 | 0 to 144 by 3, 144 to 360 by 6 |
376 | | HRES | 06 and 18 | 0 to 90 by 3 |
377 | | ENS | 06 and 18 | 0 to 144 by 3 |
378 | | Probabilities - Instantaneous weather events | 00 and 12 | 0 to 360 by 12 |
379 | | Probabilities - Daily weather events | 00 and 12 | 0-24 to 336-360 by 12 |
380 |
381 | > 📌 **NOTE**: Not specifying `step` will return all available time steps.
382 |
383 | ### Parameters and levels
384 |
385 | To select a parameter, use the `param` keyword:
386 |
387 | ```python
388 | ...
389 | param="msl",
390 | ...
391 | param=["2t", "msl"]
392 | ...
393 | ```
394 |
395 | for pressure level parameters, use the `levelist` keyword:
396 |
397 | ```python
398 | ...
399 | param="t",
400 | levelist=850,
401 | ...
402 | param=["u", "v"],
403 | levelist=[1000, 850, 500],
404 | ...
405 | ```
406 |
407 | > 📌 **NOTE**: Not specifying `levelist` will return all available levels, and not specifying `param` will return all available parameters.
408 |
409 | | List of pressure levels (hPa) |
410 | | ----------------------------- |
411 | | 1000, 925, 850, 700, 500, 300, 250, 200 and 50 |
412 |
413 |
414 | Below is the list of all parameters:
415 |
416 | > Atmospheric fields on pressure levels
417 |
418 | | Parameter | Description | Units |
419 | | --------- | ----------- | ----- |
420 | | d | Divergence | s-1 |
421 | | gh | Geopotential height | gpm |
422 | | q | Specific humidity | kg kg-1 |
423 | | r | Relative humidity | % |
424 | | t | Temperature | K |
425 | | u | U component of wind | m s-1 |
426 | | v | V component of wind | m s-1 |
427 | | vo | Vorticity (relative) | s-1 |
428 |
429 | > Atmospheric fields on a single level
430 |
431 | | Parameter | Description | Units |
432 | | --------- | ----------- | ----- |
433 | | 10u | 10 metre U wind component | m s-1 |
434 | | 10v | 10 metre V wind component | m s-1 |
435 | | 2t | 2 metre temperature | K |
436 | | msl | Mean sea level pressure | Pa |
437 | | ro | Runoff | m |
438 | | skt | Skin temperature | K |
439 | | sp | Surface pressure | Pa |
440 | | st | Soil Temperature | K |
441 | | stl1 | Soil temperature level 1 | K |
442 | | tcwv | Total column vertically-integrated water vapour | kg m-2 |
443 | | tp | Total Precipitation | m |
444 |
445 | > Ocean waves fields
446 |
447 | | Parameter | Description | Units |
448 | | --------- | ----------- | ----- |
449 | | mp2 | Mean zero-crossing wave period | s |
450 | | mwd | Mean wave direction | Degree true |
451 | | mwp | Mean wave period | s |
452 | | pp1d | Peak wave period | s |
453 | | swh | Significant height of combined wind waves and swell | m |
454 |
455 | > Ensemble mean and standard deviation - pressure levels
456 |
457 | | Parameter | Description | Units | Levels |
458 | | --------- | ----------- | ----- | ------ |
459 | | gh | Geopotential height | gpm | 300, 500, 1000 |
460 | | t | Temperature | K | 250, 500, 850 |
461 | | ws | Wind speed | m s-1 | 250, 850 |
462 |
463 | > Ensemble mean and standard deviation - single level
464 |
465 | | Parameter | Description | Units |
466 | | --------- | ----------- | ----- |
467 | | msl | Mean sea level pressure | Pa |
468 |
469 | > Instantaneous weather events - atmospheric fields - 850 hPa
470 |
471 | | Parameter | Description | Units |
472 | | --------- | ----------- | ----- |
473 | | ptsa_gt_1p5stdev | Probability of temperature standardized anomaly greater than 1.5 standard deviation | % |
474 | | ptsa_gt_1stdev | Probability of temperature standardized anomaly greater than 1 standard deviation | % |
475 | | ptsa_gt_2stdev | Probability of temperature standardized anomaly greater than 2 standard deviation | % |
476 | | ptsa_lt_1p5stdev | Probability of temperature standardized anomaly less than -1.5 standard deviation | % |
477 | | ptsa_lt_1stdev | Probability of temperature standardized anomaly less than -1 standard deviation | % |
478 | | ptsa_lt_2stdev | Probability of temperature standardized anomaly less than -2 standard deviation | % |
479 |
480 | > Daily weather events - atmospheric fields - single level
481 |
482 | | Parameter | Description | Units |
483 | | --------- | ----------- | ----- |
484 | | 10fgg10 | 10 metre wind gust of at least 10 m/s | % |
485 | | 10fgg15 | 10 metre wind gust of at least 15 m/s | % |
486 | | 10fgg25 | 10 metre wind gust of at least 25 m/s | % |
487 | | tpg1 | Total precipitation of at least 1 mm | % |
488 | | tpg10 | Total precipitation of at least 10 mm | % |
489 | | tpg100 | Total precipitation of at least 100 mm | % |
490 | | tpg20 | Total precipitation of at least 20 mm | % |
491 | | tpg25 | Total precipitation of at least 25 mm | % |
492 | | tpg5 | Total precipitation of at least 5 mm | % |
493 | | tpg50 | Total precipitation of at least 50 mm | % |
494 |
495 | > Instantaneous weather events - ocean waves fields
496 |
497 | | Parameter | Description | Units |
498 | | --------- | ----------- | ----- |
499 | | swhg2 | Significant wave height of at least 2 m | % |
500 | | swhg4 | Significant wave height of at least 4 m | % |
501 | | swhg6 | Significant wave height of at least 6 m | % |
502 | | swhg8 | Significant wave height of at least 8 m | % |
503 |
504 | ### Ensemble numbers
505 |
506 | You can select individual members of the ensemble forecast use the keyword `number`.
507 |
508 | ```python
509 | ...
510 | stream="enfo",
511 | step=24,
512 | param="msl",
513 | number=1,
514 | ...
515 | stream="enfo",
516 | step=24,
517 | param="msl",
518 | number=[1, 10, 20],
519 | ...
520 | ```
521 |
522 | | List of ensemble numbers |
523 | | ----------------------------- |
524 | | 1 to 50 |
525 |
526 | > 📌 **NOTE**: Not specifying `number` will return all ensemble forecast members.
527 |
528 | ## Examples
529 |
530 | ### Download a single surface parameter at a single forecast step from ECMWF's 00UTC HRES forecast
531 |
532 | ```python
533 | from ecmwf.opendata import Client
534 |
535 | client = Client(source="ecmwf")
536 |
537 | client.retrieve(
538 | time=0,
539 | stream="oper",
540 | type="fc",
541 | step=24,
542 | param="2t",
543 | target="data.grib2",
544 | )
545 | ```
546 |
547 | ### Download the tropical cyclone tracks from ECMWF's 00UTC HRES forecast
548 |
549 | ```python
550 | from ecmwf.opendata import Client
551 |
552 | client = Client(source="ecmwf")
553 |
554 | client.retrieve(
555 | time=0,
556 | stream="oper",
557 | type="tf",
558 | step=240,
559 | target="data.bufr",
560 | )
561 | ```
562 |
563 | - The downloaded data are encoded in BUFR edition 4
564 | - For the HRES Tropical Cyclone tracks at time=06 and time=18 use:
565 |
566 | ```python
567 | ...
568 | step = 90,
569 | ...
570 | ```
571 |
572 | > ❗ **NOTE:** Tropical cyclone tracks products are only available when there are tropical cyclones observed or forecast.
573 |
574 | ### Download a single surface parameter at a single forecast step for all ensemble members from ECMWF's 12UTC 00UTC ENS forecast
575 |
576 | ```python
577 | from ecmwf.opendata import Client
578 |
579 | client = Client(source="ecmwf")
580 |
581 | client.retrieve(
582 | time=0,
583 | stream="enfo",
584 | type="pf",
585 | param="msl",
586 | target="data.grib2",
587 | )
588 | ```
589 |
590 | - To download a single ensemble member, use the `number` keyword: `number=1`.
591 | - All of the odd numbered ensemble members use `number=[num for num in range(1,51,2)]`.
592 | - To download the control member, use `type="cf"`.
593 |
594 |
595 | ### Download a single surface parameter at a single forecast step for all ensemble members from ECMWF's 12UTC 00UTC AIFS-ENS forecast
596 |
597 | ```python
598 | from ecmwf.opendata import Client
599 |
600 | client = Client(source="ecmwf", model="aifs-ens")
601 |
602 | client.retrieve(
603 | time=0,
604 | stream="enfo",
605 | type="pf",
606 | param="msl",
607 | target="data.grib2",
608 | )
609 | ```
610 |
611 | - To download a single ensemble member, use the `number` keyword: `number=1`.
612 | - All of the odd numbered ensemble members use `number=[num for num in range(1,51,2)]`.
613 | - To download the control member, use `type="cf"`.
614 |
615 | ### Download the Tropical Cyclone tracks from ECMWF's 00UTC ENS forecast
616 |
617 | The Tropical Cyclone tracks are identified by the keyword `type="tf"`.
618 |
619 | ```python
620 | from ecmwf.opendata import Client
621 |
622 | client = Client(source="ecmwf")
623 |
624 | client.retrieve(
625 | time=0,
626 | stream="enfo",
627 | type="tf",
628 | step=240,
629 | target="data.bufr",
630 | )
631 | ```
632 |
633 | - The downloaded data are encoded in BUFR edition 4
634 | - For the ENS Tropical Cyclone tracks at time=06 and time=18 replace `step=240` with `step=144`.
635 |
636 | ### Download the ensemble mean and standard deviation for all parameters at a single forecast step from ECMWF's 00UTC ENS forecast
637 |
638 | The ensemble mean and standard deviation are identified by the keywords `type="em"`:
639 |
640 | ```python
641 | from ecmwf.opendata import Client
642 |
643 | client = Client(source="ecmwf")
644 |
645 | client.retrieve(
646 | time=0,
647 | stream="enfo",
648 | type="em",
649 | step=24,
650 | target="data.grib2",
651 | )
652 | ```
653 |
654 | and `type="es"`, respectively:
655 |
656 | ```python
657 | from ecmwf.opendata import Client
658 |
659 | client = Client(source="ecmwf")
660 |
661 | client.retrieve(
662 | time=0,
663 | stream="enfo",
664 | type="es",
665 | step=24,
666 | target="data.grib2",
667 | )
668 |
669 | ```
670 |
671 | ### Download the ensemble probability products
672 |
673 | The ensemble probability products are identified by the keyword `type="ep"`. The probability products are available only for `time=00` and `time=12`.
674 |
675 | Two different products are available.
676 |
677 | #### Probabilities - Instantaneous weather events - Pressure levels
678 |
679 | The probability of temperature standardized anomalies at a constant
680 | pressure level of 850hPa are available at 12 hourly forecast steps.
681 |
682 | ```python
683 | from ecmwf.opendata import Client
684 |
685 | client = Client(source="ecmwf")
686 |
687 | client.retrieve(
688 | time=0,
689 | stream="enfo",
690 | type="ep",
691 | step=[i for i in range(12, 361, 12)],
692 | levelist=850,
693 | param=[
694 | "ptsa_gt_1stdev",
695 | "ptsa_gt_1p5stdev",
696 | "ptsa_gt_2stdev",
697 | "ptsa_lt_1stdev",
698 | "ptsa_lt_1p5stdev",
699 | "ptsa_lt_2stdev",
700 | ],
701 | target="data.grib2",
702 | )
703 | ```
704 |
705 | #### Probabilities - Daily weather events - Single level
706 |
707 | The probabilities of total precipitation and wind gusts exceeding specified thresholds in a 24 hour period are available for step ranges 0-24 to 336-360 by 12. These are specified in the retrieval request using, e.g.: `step=["0-24", "12-36", "24-48"]`.
708 |
709 | ```python
710 | from ecmwf.opendata import Client
711 |
712 | client = Client(source="ecmwf")
713 |
714 | steps = [f"{12 * i}-{ 12 * i + 24}" for i in range(29)]
715 |
716 | client.retrieve(
717 | time=0,
718 | stream="enfo",
719 | type="ep",
720 | step=steps,
721 | param=["tpg1", "tpg5", "10fgg10"],
722 | target="data.grib2",
723 | )
724 | ```
725 |
726 | ### ECMWF open data license
727 |
728 | By downloading data from the ECMWF open data dataset, you agree to the terms: Attribution 4.0 International (CC BY 4.0). If you do not agree with such terms, do not download the data. Visit [this page](https://apps.ecmwf.int/datasets/licences/general/) for more information.
729 |
730 | ### License
731 |
732 | [Apache License 2.0](LICENSE) In applying this licence, ECMWF does not waive the privileges and immunities
733 | granted to it by virtue of its status as an intergovernmental organisation nor does it submit to any jurisdiction.
734 |
--------------------------------------------------------------------------------
/ecmwf/opendata/__init__.py:
--------------------------------------------------------------------------------
1 | # (C) Copyright 2021 ECMWF.
2 | #
3 | # This software is licensed under the terms of the Apache Licence Version 2.0
4 | # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
5 | # In applying this licence, ECMWF does not waive the privileges and immunities
6 | # granted to it by virtue of its status as an intergovernmental organisation
7 | # nor does it submit to any jurisdiction.
8 | #
9 |
10 |
11 | from .client import Client
12 |
13 | __version__ = "0.3.23"
14 |
15 | __all__ = ["Client"]
16 |
--------------------------------------------------------------------------------
/ecmwf/opendata/bufr.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # (C) Copyright 2021 ECMWF.
3 | #
4 | # This software is licensed under the terms of the Apache Licence Version 2.0
5 | # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
6 | # In applying this licence, ECMWF does not waive the privileges and immunities
7 | # granted to it by virtue of its status as an intergovernmental organisation
8 | # nor does it submit to any jurisdiction.
9 | #
10 |
11 | """
12 | For testing
13 | """
14 |
15 | from eccodes import codes_bufr_new_from_file, codes_release
16 |
17 |
18 | def count_bufrs(path):
19 | count = 0
20 | with open(path, "rb") as f:
21 | while True:
22 | handle = codes_bufr_new_from_file(f, headers_only=True)
23 | if handle is None:
24 | return count
25 | count += 1
26 | codes_release(handle)
27 |
--------------------------------------------------------------------------------
/ecmwf/opendata/client.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # (C) Copyright 2021 ECMWF.
3 | #
4 | # This software is licensed under the terms of the Apache Licence Version 2.0
5 | # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
6 | # In applying this licence, ECMWF does not waive the privileges and immunities
7 | # granted to it by virtue of its status as an intergovernmental organisation
8 | # nor does it submit to any jurisdiction.
9 | #
10 |
11 | import datetime
12 | import itertools
13 | import json
14 | import logging
15 | import os
16 | from collections import defaultdict
17 |
18 | import requests
19 | from multiurl import download, robust
20 |
21 | from .date import (
22 | canonical_time,
23 | end_step,
24 | expand_date,
25 | expand_list,
26 | expand_time,
27 | full_date,
28 | )
29 | from .urls import URLS
30 |
31 | LOG = logging.getLogger(__name__)
32 |
33 | HOURLY_PATTERN = (
34 | "{_url}/{_yyyymmdd}/{_H}z/{model}/{resol}/{_stream}/"
35 | "{_yyyymmddHHMMSS}-{step}h-{_stream}-{type}.{_extension}"
36 | )
37 |
38 | MONTHLY_PATTERN = (
39 | "{_url}/{_yyyymmdd}/{_H}z/{model}/{resol}/{_stream}/"
40 | "{_yyyymmddHHMMSS}-{fcmonth}m-{_stream}-{type}.{_extension}"
41 | )
42 |
43 | PATTERNS = {"mmsa": MONTHLY_PATTERN}
44 | EXTENSIONS = {"tf": "bufr"}
45 |
46 | ONCE = set()
47 |
48 | _ATTRIBUTION_SHOWN = False # module-level guard to avoid spamming
49 |
50 |
51 | def _show_attribution_message():
52 | global _ATTRIBUTION_SHOWN
53 | if not _ATTRIBUTION_SHOWN:
54 | print(
55 | "By downloading data from the ECMWF open data dataset, you agree to "
56 | "the terms: Attribution 4.0 International (CC BY 4.0). Please "
57 | "attribute ECMWF when downloading this data."
58 | )
59 | _ATTRIBUTION_SHOWN = True
60 |
61 |
62 | def warning_once(*args, did_you_mean=None):
63 | if repr(args) in ONCE:
64 | return
65 |
66 | LOG.warning(*args)
67 |
68 | ONCE.add(repr(args))
69 |
70 | if did_you_mean:
71 | (words, vocabulary) = did_you_mean
72 |
73 | def levenshtein(a, b):
74 | if len(a) == 0:
75 | return len(b)
76 |
77 | if len(b) == 0:
78 | return len(a)
79 |
80 | if a[0].lower() == b[0].lower():
81 | return levenshtein(a[1:], b[1:])
82 |
83 | return 1 + min(
84 | [
85 | levenshtein(a[1:], b[1:]),
86 | levenshtein(a[1:], b),
87 | levenshtein(a, b[1:]),
88 | ]
89 | )
90 |
91 | if not isinstance(words, (list, tuple)):
92 | words = [words]
93 |
94 | for word in words:
95 | distance, best = min((levenshtein(word, w), w) for w in vocabulary)
96 | if distance < min(len(word), len(best)):
97 | LOG.warning(
98 | "Did you mean %r instead of %r?",
99 | best,
100 | word,
101 | )
102 |
103 |
104 | class Result:
105 | def __init__(self, urls, target, dates, for_urls, for_index):
106 | self.urls = urls
107 | self.target = target
108 | if len(dates) == 1:
109 | self.datetime = dates[0]
110 | else:
111 | self.datetime = dates
112 | self.for_urls = for_urls
113 | self.for_index = for_index
114 |
115 |
116 | class Client:
117 | def __init__(
118 | self,
119 | source="ecmwf",
120 | model="ifs",
121 | resol="0p25",
122 | beta=False, # to access experimental data
123 | preserve_request_order=False,
124 | infer_stream_keyword=True,
125 | debug=False,
126 | verify=True,
127 | ):
128 | self._url = None
129 | self.source = source
130 | self.model = model
131 | self.resol = resol
132 | self.beta = beta
133 | self.preserve_request_order = preserve_request_order
134 | self.infer_stream_keyword = infer_stream_keyword
135 | self.session = requests.Session()
136 | self.verify = verify
137 |
138 | if debug:
139 | logging.basicConfig(level=logging.DEBUG)
140 |
141 | @property
142 | def url(self):
143 | if self._url is None:
144 | if self.source.startswith("http://") or self.source.startswith("https://"):
145 | self._url = self.source
146 | else:
147 | if self.source not in URLS:
148 | warning_once(
149 | "Unknown source %r. Known sources are %r",
150 | self.source,
151 | list(URLS.keys()),
152 | did_you_mean=(self.source, list(URLS.keys())),
153 | )
154 | raise ValueError("Unknown source %r" % (self.source,))
155 | self._url = URLS[self.source]
156 |
157 | return self._url
158 |
159 | def retrieve(self, request=None, target=None, **kwargs):
160 | result = self._get_urls(request, target=target, use_index=True, **kwargs)
161 | result.size = download(
162 | result.urls,
163 | target=result.target,
164 | verify=self.verify,
165 | session=self.session,
166 | )
167 | _show_attribution_message()
168 | return result
169 |
170 | def download(self, request=None, target=None, **kwargs):
171 | result = self._get_urls(request, target=target, use_index=False, **kwargs)
172 | result.size = download(
173 | result.urls,
174 | target=result.target,
175 | verify=self.verify,
176 | session=self.session,
177 | )
178 | _show_attribution_message()
179 | return result
180 |
181 | def latest(self, request=None, **kwargs):
182 | if request is None:
183 | params = dict(**kwargs)
184 | else:
185 | params = dict(**request)
186 |
187 | if "time" not in params:
188 | delta = datetime.timedelta(hours=6)
189 | else:
190 | delta = datetime.timedelta(days=1)
191 |
192 | date = full_date(0, params.get("time", 18))
193 |
194 | stop = date - datetime.timedelta(days=2)
195 |
196 | while date > stop:
197 | result = self._get_urls(
198 | request=None,
199 | use_index=False,
200 | date=date,
201 | **params,
202 | )
203 | codes = [
204 | robust(self.session.head)(url, verify=self.verify).status_code
205 | for url in result.urls
206 | ]
207 | if len(codes) > 0 and all(c == 200 for c in codes):
208 | return date
209 | date -= delta
210 |
211 | raise ValueError("Cannot establish latest date for %r" % (result.for_urls,))
212 |
213 | def _get_urls(self, request=None, use_index=None, target=None, **kwargs):
214 | assert use_index in (True, False)
215 | if request is None:
216 | params = dict(**kwargs)
217 | else:
218 | params = dict(**request)
219 |
220 | if "date" not in params:
221 | params["date"] = self.latest(params)
222 |
223 | if target is None:
224 | target = params.pop("target", None)
225 |
226 | for_urls, for_index = self.prepare_request(params)
227 |
228 | for_urls["_url"] = [self.url]
229 |
230 | seen = set()
231 | data_urls = []
232 |
233 | dates = set()
234 |
235 | for args in (
236 | dict(zip(for_urls.keys(), x)) for x in itertools.product(*for_urls.values())
237 | ):
238 | pattern = PATTERNS.get(args["stream"], HOURLY_PATTERN)
239 | date = full_date(args.pop("date", None), args.pop("time", None))
240 | dates.add(date)
241 | args["_yyyymmdd"] = date.strftime("%Y%m%d")
242 | args["_H"] = date.strftime("%H")
243 | args["_yyyymmddHHMMSS"] = date.strftime("%Y%m%d%H%M%S")
244 | args["_extension"] = EXTENSIONS.get(args["type"], "grib2")
245 | args["_stream"] = self.patch_stream(args)
246 |
247 | if self.beta:
248 | # test data is put in an /experimental subdir after resol
249 | # it is not part of a mars request, so we inject it here
250 | args["resol"] += "/experimental"
251 |
252 | url = pattern.format(**args)
253 |
254 | if self.resol == "0p4-beta":
255 | url = url.replace("/ifs/", "/")
256 |
257 | if url not in seen:
258 | data_urls.append(url)
259 | seen.add(url)
260 |
261 | if for_index and use_index:
262 | data_urls = self.get_parts(data_urls, for_index)
263 |
264 | return Result(
265 | urls=data_urls,
266 | target=target,
267 | dates=sorted(dates),
268 | for_urls=for_urls,
269 | for_index=for_index,
270 | )
271 |
272 | def get_parts(self, data_urls, for_index):
273 | count = len(for_index)
274 | result = []
275 | line = None
276 |
277 | possible_values = defaultdict(set)
278 |
279 | for url in data_urls:
280 | base, _ = os.path.splitext(url)
281 | index_url = f"{base}.index"
282 | r = robust(self.session.get)(index_url, verify=self.verify)
283 | r.raise_for_status()
284 |
285 | parts = []
286 | for line in r.iter_lines():
287 | line = json.loads(line)
288 | matches = []
289 | for i, (name, values) in enumerate(for_index.items()):
290 | idx = line.get(name)
291 | if idx is not None:
292 | possible_values[name].add(idx)
293 | if idx in values:
294 | if self.preserve_request_order:
295 | for j, v in enumerate(values):
296 | if v == idx:
297 | matches.append((i, j))
298 | else:
299 | matches.append(line["_offset"])
300 |
301 | if len(matches) == count:
302 | parts.append((tuple(matches), (line["_offset"], line["_length"])))
303 |
304 | if parts:
305 | result.append((url, tuple(p[1] for p in sorted(parts))))
306 |
307 | for name, values in for_index.items():
308 | diff = set(values).difference(possible_values[name])
309 | for d in diff:
310 | warning_once(
311 | "No index entries for %s=%s",
312 | name,
313 | d,
314 | did_you_mean=(d, possible_values[name]),
315 | )
316 |
317 | if not result:
318 | raise ValueError("Cannot find index entries matching %r" % (for_index,))
319 |
320 | return result
321 |
322 | def user_to_index(self, key, value, request, for_index):
323 | FOR_INDEX = {
324 | ("type", "ef"): ["cf", "pf"],
325 | }
326 |
327 | return FOR_INDEX.get((key, value), value)
328 |
329 | def user_to_url(self, key, value, request, for_urls, model):
330 | FOR_URL = {
331 | ("type", "cf"): "ef",
332 | ("type", "pf"): "ef",
333 | ("type", "em"): "ep",
334 | ("type", "es"): "ep",
335 | ("type", "fcmean"): "fc",
336 | ("stream", "mmsa"): "mmsf",
337 | }
338 |
339 | # If the model is aifs-ens, we need to map the type to pf/cf because aifs-ens does not currently use ef
340 | if model == "aifs-ens":
341 | FOR_URL[("type", "pf")] = "pf"
342 | FOR_URL[("type", "cf")] = "cf"
343 |
344 | if key == "step" and for_urls["type"] == ["ep"]:
345 | if end_step(value) <= 240:
346 | return "240"
347 | else:
348 | return "360"
349 |
350 | return FOR_URL.get((key, value), value)
351 |
352 | def prepare_request(self, request=None, **kwargs):
353 | if request is None:
354 | params = dict(**kwargs)
355 | else:
356 | params = dict(**request)
357 |
358 | # If model is in the retireve overwrite the client model
359 | # Warn user if client model does not match the model in retrieve
360 | if "model" in params:
361 | if self.model != params["model"]:
362 | warning_once(
363 | "Model %r does not match the client model %r, using model %r from retrieve",
364 | params["model"],
365 | self.model,
366 | params["model"],
367 | did_you_mean=(params["model"], self.model),
368 | )
369 | model = params["model"]
370 | else:
371 | model = self.model
372 |
373 | if "class" in params:
374 | model = {"od": "ifs", "ai": "aifs-single", "aifs-ens": "aifs-ens"}[
375 | params["class"]
376 | ]
377 |
378 | # Default stream for aifs-ens is enfo as this model only has ensemble forecasts
379 | if model == "aifs-ens":
380 | params["stream"] = "enfo"
381 |
382 | DEFAULTS_FC = dict(
383 | model=model,
384 | resol=self.resol,
385 | type="fc",
386 | stream="oper",
387 | step=0,
388 | fcmonth=1,
389 | )
390 |
391 | DEFAULTS_EF = dict(
392 | model=model,
393 | resol=self.resol,
394 | type=["cf", "pf"],
395 | stream="enfo",
396 | step=0,
397 | fcmonth=1,
398 | )
399 |
400 | DEFAULTS = {
401 | "enfo": DEFAULTS_EF,
402 | "waef": DEFAULTS_EF,
403 | }
404 |
405 | URL_COMPONENTS = (
406 | "date",
407 | "time",
408 | "model",
409 | "resol",
410 | "stream",
411 | "type", # Must be before 'step' in that list
412 | "step",
413 | "fcmonth",
414 | )
415 |
416 | INDEX_COMPONENTS = (
417 | "param",
418 | "type",
419 | "step",
420 | "fcmonth",
421 | "number",
422 | "levelist",
423 | "levtype",
424 | )
425 |
426 | CANONICAL = {
427 | "time": lambda x: str(canonical_time(x)),
428 | # "param": lambda x: str(x).lower(),
429 | # "type": lambda x: str(x).lower(),
430 | # "stream": lambda x: str(x).lower(),
431 | }
432 |
433 | EXPAND_LIST = {
434 | "date": expand_date,
435 | "time": expand_time,
436 | }
437 |
438 | OTHER_STEP = {"mmsa": "step"}
439 |
440 | POSPROCESSING = {
441 | "area",
442 | "grid",
443 | "rotation",
444 | "frame",
445 | "bitmap",
446 | "gaussian",
447 | "accuracy",
448 | "format",
449 | }
450 |
451 | POSSIBLE_VALUES = {
452 | "type": ["tf", "fc", "fcmean", "cf", "pf", "em", "ep", "es"],
453 | "stream": ["oper", "wave", "scda", "scwv", "enfo", "waef", "mmsa"],
454 | }
455 |
456 | defaults = DEFAULTS.get(params.get("stream"), DEFAULTS_FC)
457 | for key, value in defaults.items():
458 | params.setdefault(key, value)
459 |
460 | params.pop("target", None)
461 | params.pop("class", None)
462 |
463 | params.pop(OTHER_STEP.get(params["stream"], "fcmonth"), None)
464 |
465 | postproc = POSPROCESSING.intersection(set(params.keys()))
466 | if postproc:
467 | warning_once("MARS post-processing keywords %r not supported", postproc)
468 |
469 | for_urls = defaultdict(list)
470 | for_index = defaultdict(list)
471 | ignored = set()
472 |
473 | def sorter(kv):
474 | a = kv[0]
475 | if a in URL_COMPONENTS:
476 | return URL_COMPONENTS.index(a)
477 | if a in INDEX_COMPONENTS:
478 | return INDEX_COMPONENTS.index(a) + len(URL_COMPONENTS)
479 | return len(URL_COMPONENTS) + len(INDEX_COMPONENTS)
480 |
481 | for k, v in sorted(params.items(), key=sorter):
482 | if isinstance(v, str):
483 | v = v.split("/")
484 |
485 | if not isinstance(v, (list, tuple)):
486 | v = [v]
487 |
488 | v = EXPAND_LIST.get(k, expand_list)(v)
489 |
490 | # Return canonical forms
491 | v = [CANONICAL.get(k, str)(x) for x in v]
492 |
493 | if k.startswith("_"):
494 | continue
495 |
496 | if k in POSSIBLE_VALUES:
497 | possible_values = POSSIBLE_VALUES[k]
498 | for value in v:
499 | if value not in possible_values:
500 | warning_once(
501 | "Unknown value %r for keyword %r",
502 | value,
503 | k,
504 | did_you_mean=(value, possible_values),
505 | )
506 |
507 | if k in INDEX_COMPONENTS:
508 | for values in [self.user_to_index(k, x, params, for_index) for x in v]:
509 | if not isinstance(values, (list, tuple)):
510 | values = [values]
511 | for value in values:
512 | if value not in for_index[k]:
513 | for_index[k].append(value)
514 |
515 | if k in URL_COMPONENTS:
516 | for values in [
517 | self.user_to_url(k, x, params, for_urls, model) for x in v
518 | ]:
519 | if not isinstance(values, (list, tuple)):
520 | values = [values]
521 | for value in values:
522 | if value not in for_urls[k]:
523 | for_urls[k].append(value)
524 |
525 | if (
526 | k not in URL_COMPONENTS
527 | and k not in INDEX_COMPONENTS
528 | and k not in POSPROCESSING
529 | ):
530 | ignored.add(k)
531 |
532 | if ignored:
533 | warning_once(
534 | "The following keywords %r are ignored",
535 | ignored,
536 | did_you_mean=(list(ignored), URL_COMPONENTS + INDEX_COMPONENTS),
537 | )
538 |
539 | if params.get("type") == "tf":
540 | for_index.clear()
541 |
542 | return (dict(**for_urls), dict(**for_index))
543 |
544 | def patch_stream(self, args):
545 | URL_STREAM_MAPPING = {
546 | ("oper", "06"): "scda",
547 | ("oper", "18"): "scda",
548 | ("wave", "06"): "scwv",
549 | ("wave", "18"): "scwv",
550 | #
551 | ("oper", "ef"): "enfo",
552 | ("wave", "ef"): "waef",
553 | ("oper", "ep"): "enfo",
554 | ("wave", "ep"): "waef",
555 | ("scda", "ef"): "enfo",
556 | ("scwv", "ef"): "waef",
557 | ("scda", "ep"): "enfo",
558 | ("scwv", "ep"): "waef",
559 | }
560 | stream, time, type = args["stream"], args["_H"], args["type"]
561 |
562 | if not self.infer_stream_keyword or args["model"] == "aifs-single":
563 | return stream
564 |
565 | stream = URL_STREAM_MAPPING.get((stream, time), stream)
566 | stream = URL_STREAM_MAPPING.get((stream, type), stream)
567 |
568 | return stream
569 |
--------------------------------------------------------------------------------
/ecmwf/opendata/date.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # (C) Copyright 2021 ECMWF.
3 | #
4 | # This software is licensed under the terms of the Apache Licence Version 2.0
5 | # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
6 | # In applying this licence, ECMWF does not waive the privileges and immunities
7 | # granted to it by virtue of its status as an intergovernmental organisation
8 | # nor does it submit to any jurisdiction.
9 | #
10 | import datetime
11 | import re
12 |
13 | VALID_DATE = re.compile(r"\d\d\d\d-\d\d-\d\d([T\s]\d\d:\d\d(:\d\d)?)?Z?")
14 |
15 |
16 | def end_step(p):
17 | if isinstance(p, str):
18 | return int(p.split("-")[-1])
19 | return int(p)
20 |
21 |
22 | def canonical_time(time):
23 | if isinstance(time, datetime.time):
24 | assert datetime.time(time.hour) == time, time
25 | return time.hour
26 | time = int(time)
27 | if time >= 100:
28 | assert time % 100 == 0, time
29 | time //= 100
30 | return time
31 |
32 |
33 | def full_date(date, time=None):
34 | if isinstance(date, datetime.date) and not isinstance(date, datetime.datetime):
35 | date = datetime.datetime(date.year, date.month, date.day)
36 |
37 | if isinstance(date, int):
38 | if date <= 0:
39 | date = datetime.datetime.utcnow() + datetime.timedelta(days=date)
40 | date = datetime.datetime(date.year, date.month, date.day)
41 | else:
42 | date = datetime.datetime(date // 10000, date % 10000 // 100, date % 100)
43 |
44 | if isinstance(date, str):
45 | try:
46 | return full_date(int(date), time)
47 | except ValueError:
48 | pass
49 |
50 | if VALID_DATE.match(date):
51 | date = datetime.datetime.fromisoformat(date)
52 |
53 | if not isinstance(date, datetime.datetime):
54 | raise ValueError("Invalid date: {} ({})".format(date, type(date)))
55 |
56 | if time is not None:
57 | time = canonical_time(time)
58 | date = datetime.datetime(date.year, date.month, date.day, time, 0, 0)
59 |
60 | return date
61 |
62 |
63 | def _expandable(lst):
64 | if len(lst) not in (3, 5):
65 | return False
66 |
67 | if not isinstance(lst[1], str) or lst[1].lower() != "to":
68 | return False
69 |
70 | if len(lst) == 5 and (not isinstance(lst[3], str) or lst[3].lower() != "by"):
71 | return False
72 |
73 | return True
74 |
75 |
76 | def expand_list(lst):
77 | if not _expandable(lst):
78 | return lst
79 |
80 | start = int(lst[0])
81 | end = int(lst[2])
82 | by = 1
83 |
84 | if len(lst) == 5:
85 | by = int(lst[4])
86 |
87 | assert start <= end and by > 0, (start, end, by)
88 |
89 | return list(range(start, end + by, by))
90 |
91 |
92 | def expand_date(lst):
93 | if not _expandable(lst):
94 | return lst
95 |
96 | start = full_date(lst[0])
97 | end = full_date(lst[2])
98 | by = 1
99 |
100 | if len(lst) == 5:
101 | by = int(lst[4])
102 |
103 | assert start <= end and by > 0, (start, end, by)
104 |
105 | result = []
106 | by = datetime.timedelta(days=by)
107 |
108 | while start <= end:
109 | result.append(start.strftime("%Y%m%d"))
110 | start += by
111 |
112 | return result
113 |
114 |
115 | def expand_time(lst):
116 | if not _expandable(lst):
117 | return lst
118 |
119 | start = canonical_time(lst[0])
120 | end = canonical_time(lst[2])
121 | by = 6
122 |
123 | if len(lst) == 5:
124 | by = int(lst[4])
125 |
126 | assert start <= end and by > 0, (start, end, by)
127 |
128 | return list(range(start, end + by, by))
129 |
--------------------------------------------------------------------------------
/ecmwf/opendata/grib.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # (C) Copyright 2021 ECMWF.
3 | #
4 | # This software is licensed under the terms of the Apache Licence Version 2.0
5 | # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
6 | # In applying this licence, ECMWF does not waive the privileges and immunities
7 | # granted to it by virtue of its status as an intergovernmental organisation
8 | # nor does it submit to any jurisdiction.
9 | #
10 |
11 | """
12 | For testing
13 | """
14 |
15 | from eccodes import (
16 | codes_get_long,
17 | codes_get_string,
18 | codes_grib_new_from_file,
19 | codes_keys_iterator_delete,
20 | codes_keys_iterator_get_name,
21 | codes_keys_iterator_new,
22 | codes_keys_iterator_next,
23 | codes_release,
24 | )
25 |
26 |
27 | def grib_index(path):
28 | index = []
29 | with open(path, "rb") as f:
30 | while True:
31 | handle = codes_grib_new_from_file(f, headers_only=True)
32 | if handle is None:
33 | return index
34 | try:
35 | keys = {}
36 | iter = codes_keys_iterator_new(handle, "mars")
37 | try:
38 | while codes_keys_iterator_next(iter):
39 | name = codes_keys_iterator_get_name(iter)
40 | if name.startswith("_"):
41 | continue
42 | value = codes_get_string(handle, name)
43 | keys[name] = value
44 |
45 | if "step" not in keys and "fcmonth" not in keys:
46 | if keys["stream"] in ("mmsa",):
47 | keys["fcmonth"] = str(
48 | (codes_get_long(handle, "endStep") + 48) // (24 * 30)
49 | )
50 |
51 | finally:
52 | codes_keys_iterator_delete(iter)
53 |
54 | keys["param"] = codes_get_string(handle, "shortName")
55 | keys["_offset"] = codes_get_long(handle, "offset")
56 | keys["_length"] = codes_get_long(handle, "totalLength")
57 |
58 | index.append(keys)
59 | finally:
60 | codes_release(handle)
61 |
62 |
63 | def count_gribs(path):
64 | count = 0
65 | with open(path, "rb") as f:
66 | while True:
67 | handle = codes_grib_new_from_file(f, headers_only=True)
68 | if handle is None:
69 | return count
70 | count += 1
71 | codes_release(handle)
72 |
--------------------------------------------------------------------------------
/ecmwf/opendata/urls.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # (C) Copyright 2021 ECMWF.
3 | #
4 | # This software is licensed under the terms of the Apache Licence Version 2.0
5 | # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
6 | # In applying this licence, ECMWF does not waive the privileges and immunities
7 | # granted to it by virtue of its status as an intergovernmental organisation
8 | # nor does it submit to any jurisdiction.
9 | #
10 |
11 | import json
12 | import os
13 |
14 | DOT_ECMWF_OPENDATA = os.path.expanduser("~/.ecmwf-opendata")
15 |
16 | URLS = {
17 | "ecmwf": "https://data.ecmwf.int/forecasts",
18 | "azure": "https://ai4edataeuwest.blob.core.windows.net/ecmwf",
19 | "aws": "https://ecmwf-forecasts.s3.eu-central-1.amazonaws.com",
20 | "ecmwf-esuites": "https://xdiss.ecmwf.int/ecpds/home/opendata",
21 | }
22 |
23 | if os.path.exists(DOT_ECMWF_OPENDATA):
24 | with open(DOT_ECMWF_OPENDATA) as f:
25 | URLS.update(json.load(f))
26 |
27 | if "ECMWF_OPENDATA_URLS" in os.environ:
28 | URLS.update(json.loads(os.environ["ECMWF_OPENDATA_URLS"]))
29 |
--------------------------------------------------------------------------------
/pytest.ini:
--------------------------------------------------------------------------------
1 | [pytest]
2 | addopts=-s --verbose
3 | testpaths = tests
4 |
--------------------------------------------------------------------------------
/setup.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # (C) Copyright 2021 ECMWF.
3 | #
4 | # This software is licensed under the terms of the Apache Licence Version 2.0
5 | # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
6 | # In applying this licence, ECMWF does not waive the privileges and immunities
7 | # granted to it by virtue of its status as an intergovernmental organisation
8 | # nor does it submit to any jurisdiction.
9 | #
10 |
11 |
12 | import io
13 | import os
14 |
15 | import setuptools
16 |
17 |
18 | def read(fname):
19 | file_path = os.path.join(os.path.dirname(__file__), fname)
20 | return io.open(file_path, encoding="utf-8").read()
21 |
22 |
23 | version = None
24 | for line in read("ecmwf/opendata/__init__.py").split("\n"):
25 | if line.startswith("__version__"):
26 | version = line.split("=")[-1].strip()[1:-1]
27 |
28 |
29 | assert version
30 |
31 |
32 | setuptools.setup(
33 | name="ecmwf-opendata",
34 | version=version,
35 | description="A package to download ECMWF open data",
36 | long_description=read("README.md"),
37 | long_description_content_type="text/markdown",
38 | author="European Centre for Medium-Range Weather Forecasts (ECMWF)",
39 | author_email="software.support@ecmwf.int",
40 | license="Apache License Version 2.0",
41 | url="https://github.com/ecmwf/ecmwf-opendata",
42 | packages=setuptools.find_namespace_packages(include=["ecmwf.*"]),
43 | include_package_data=True,
44 | install_requires=["multiurl>=0.2.1"],
45 | zip_safe=True,
46 | keywords="tool",
47 | classifiers=[
48 | "Development Status :: 3 - Alpha",
49 | "Intended Audience :: Developers",
50 | "License :: OSI Approved :: Apache Software License",
51 | "Programming Language :: Python :: 3",
52 | "Programming Language :: Python :: 3.7",
53 | "Programming Language :: Python :: 3.8",
54 | "Programming Language :: Python :: 3.9",
55 | "Programming Language :: Python :: 3.10",
56 | "Programming Language :: Python :: Implementation :: CPython",
57 | "Programming Language :: Python :: Implementation :: PyPy",
58 | "Operating System :: OS Independent",
59 | ],
60 | )
61 |
--------------------------------------------------------------------------------
/tests/requirements.txt:
--------------------------------------------------------------------------------
1 | freezegun
2 | ecmwflibs
3 | eccodes
4 |
--------------------------------------------------------------------------------
/tests/test_aifs_ens.py:
--------------------------------------------------------------------------------
1 | from ecmwf.opendata import Client
2 | from ecmwf.opendata.grib import count_gribs
3 |
4 |
5 | def test_aifs_ens_1():
6 | client = Client(source="ecmwf", model="aifs-ens")
7 | client.retrieve(
8 | date=-1,
9 | time=0,
10 | step=12,
11 | param="10u",
12 | target="data.grib",
13 | )
14 |
15 | assert count_gribs("data.grib") == 51
16 |
17 |
18 | def test_aifs_ens_2():
19 | client = Client(source="ecmwf", model="aifs-ens")
20 | client.retrieve(
21 | date=-1,
22 | time=0,
23 | step=12,
24 | type="cf",
25 | param="10u",
26 | target="data.grib",
27 | )
28 |
29 | assert count_gribs("data.grib") == 1
30 |
31 |
32 | def test_aifs_ens_3():
33 | client = Client(source="ecmwf", model="aifs-ens")
34 | client.retrieve(
35 | date=-1,
36 | time=0,
37 | step=12,
38 | type="pf",
39 | param="10u",
40 | target="data.grib",
41 | )
42 |
43 | assert count_gribs("data.grib") == 50
44 |
--------------------------------------------------------------------------------
/tests/test_date.py:
--------------------------------------------------------------------------------
1 | import datetime
2 |
3 | from freezegun import freeze_time
4 |
5 | from ecmwf.opendata.date import canonical_time, end_step, full_date
6 |
7 |
8 | @freeze_time("2022-01-21T13:21:34Z")
9 | def test_date_1():
10 | assert full_date("20010101") == datetime.datetime(2001, 1, 1)
11 | assert full_date(20010101) == datetime.datetime(2001, 1, 1)
12 | assert full_date("2001-01-01") == datetime.datetime(2001, 1, 1)
13 |
14 | assert full_date(0) == datetime.datetime(2022, 1, 21)
15 | assert full_date(-10) == datetime.datetime(2022, 1, 11)
16 |
17 | assert full_date("20010101", 0) == datetime.datetime(2001, 1, 1)
18 | assert full_date(20010101, 0) == datetime.datetime(2001, 1, 1)
19 | assert full_date("2001-01-01", 0) == datetime.datetime(2001, 1, 1)
20 |
21 | assert full_date(0, 0) == datetime.datetime(2022, 1, 21)
22 | assert full_date(-10, 0) == datetime.datetime(2022, 1, 11)
23 |
24 | assert full_date("20010101", 12) == datetime.datetime(2001, 1, 1, 12)
25 | assert full_date(20010101, 12) == datetime.datetime(2001, 1, 1, 12)
26 | assert full_date("2001-01-01", 12) == datetime.datetime(2001, 1, 1, 12)
27 |
28 | assert full_date(0, 12) == datetime.datetime(2022, 1, 21, 12)
29 | assert full_date(-10, 12) == datetime.datetime(2022, 1, 11, 12)
30 |
31 | assert full_date("20010101", "18") == datetime.datetime(2001, 1, 1, 18)
32 | assert full_date(20010101, "18") == datetime.datetime(2001, 1, 1, 18)
33 | assert full_date("2001-01-01", "18") == datetime.datetime(2001, 1, 1, 18)
34 |
35 | assert full_date(0, "18") == datetime.datetime(2022, 1, 21, 18)
36 | assert full_date(-10, "18") == datetime.datetime(2022, 1, 11, 18)
37 |
38 | assert full_date("20010101", "06") == datetime.datetime(2001, 1, 1, 6)
39 | assert full_date(20010101, "06") == datetime.datetime(2001, 1, 1, 6)
40 | assert full_date("2001-01-01", "06") == datetime.datetime(2001, 1, 1, 6)
41 |
42 | assert full_date(0, "06") == datetime.datetime(2022, 1, 21, 6)
43 | assert full_date(-10, "06") == datetime.datetime(2022, 1, 11, 6)
44 |
45 | assert full_date("20010101", "0600") == datetime.datetime(2001, 1, 1, 6)
46 | assert full_date(20010101, "0600") == datetime.datetime(2001, 1, 1, 6)
47 | assert full_date("2001-01-01", "0600") == datetime.datetime(2001, 1, 1, 6)
48 |
49 | assert full_date(0, "0600") == datetime.datetime(2022, 1, 21, 6)
50 | assert full_date(-10, "0600") == datetime.datetime(2022, 1, 11, 6)
51 |
52 | assert full_date("20010101", "1200") == datetime.datetime(2001, 1, 1, 12)
53 | assert full_date(20010101, "1200") == datetime.datetime(2001, 1, 1, 12)
54 | assert full_date("2001-01-01", "1200") == datetime.datetime(2001, 1, 1, 12)
55 |
56 | assert full_date(0, "1200") == datetime.datetime(2022, 1, 21, 12)
57 | assert full_date(-10, "1200") == datetime.datetime(2022, 1, 11, 12)
58 |
59 | assert full_date("20010101", "18") == datetime.datetime(2001, 1, 1, 18)
60 | assert full_date(20010101, "18") == datetime.datetime(2001, 1, 1, 18)
61 | assert full_date("2001-01-01", "18") == datetime.datetime(2001, 1, 1, 18)
62 |
63 | assert full_date(0, "18") == datetime.datetime(2022, 1, 21, 18)
64 | assert full_date(-10, "18") == datetime.datetime(2022, 1, 11, 18)
65 |
66 | assert full_date("2022-01-25 12:00:00") == datetime.datetime(2022, 1, 25, 12)
67 | assert full_date("2022-01-25 12:00:00", "18") == datetime.datetime(2022, 1, 25, 18)
68 | assert full_date("2022-01-25T12:00:00") == datetime.datetime(2022, 1, 25, 12)
69 |
70 |
71 | def test_date_2():
72 | assert full_date(datetime.datetime(2000, 1, 1, 6)) == datetime.datetime(
73 | 2000, 1, 1, 6
74 | )
75 | assert full_date(datetime.datetime(2000, 1, 1, 6), 12) == datetime.datetime(
76 | 2000, 1, 1, 12
77 | )
78 | assert full_date(datetime.date(2000, 1, 1)) == datetime.datetime(2000, 1, 1)
79 | assert full_date(datetime.date(2000, 1, 1), 12) == datetime.datetime(2000, 1, 1, 12)
80 |
81 |
82 | def test_time():
83 | assert canonical_time(0) == 0
84 | assert canonical_time(6) == 6
85 | assert canonical_time(12) == 12
86 | assert canonical_time(18) == 18
87 |
88 | assert canonical_time("0") == 0
89 | assert canonical_time("6") == 6
90 | assert canonical_time("12") == 12
91 | assert canonical_time("18") == 18
92 |
93 | assert canonical_time("00") == 0
94 | assert canonical_time("06") == 6
95 | assert canonical_time("12") == 12
96 | assert canonical_time("18") == 18
97 |
98 | assert canonical_time(1200) == 12
99 | assert canonical_time(1800) == 18
100 |
101 | assert canonical_time("0000") == 0
102 | assert canonical_time("0600") == 6
103 | assert canonical_time("1200") == 12
104 | assert canonical_time("1800") == 18
105 |
106 | assert canonical_time(datetime.time(12)) == 12
107 |
108 |
109 | def test_step():
110 | assert end_step(24) == 24
111 | assert end_step("24") == 24
112 | assert end_step("12-24") == 24
113 |
--------------------------------------------------------------------------------
/tests/test_examples.py:
--------------------------------------------------------------------------------
1 | import os
2 | import sys
3 |
4 | import pytest
5 |
6 | README = os.path.realpath(
7 | os.path.join(os.path.dirname(os.path.dirname(__file__)), "README.md")
8 | )
9 |
10 |
11 | def example_list():
12 | examples = []
13 | code = []
14 | python = False
15 |
16 | with open(README, "rt", encoding="utf-8") as f:
17 | for line in f:
18 | if line.startswith("```python"):
19 | python = True
20 | continue
21 | if python and line.startswith("```"):
22 | if any("from ecmwf.opendata import Client" in c for c in code):
23 | examples.append(code)
24 | python = False
25 | code = []
26 | continue
27 | if python:
28 | code.append(line)
29 |
30 | return sorted(examples)
31 |
32 |
33 | @pytest.mark.parametrize("example", example_list())
34 | def xxx_test_example(example):
35 | code = "".join(example)
36 | try:
37 | exec(code, dict(__file__=README), {})
38 | except Exception as e:
39 | print("===========", file=sys.stderr)
40 | print(code, file=sys.stderr)
41 | print("===========", file=sys.stderr)
42 | raise ValueError("Exception: %s\n%s" % (e, code))
43 |
44 |
45 | if __name__ == "__main__":
46 | for e in example_list():
47 | try:
48 | xxx_test_example(e)
49 | except Exception:
50 | pass
51 |
--------------------------------------------------------------------------------
/tests/test_latest.py:
--------------------------------------------------------------------------------
1 | import datetime
2 |
3 | from freezegun import freeze_time
4 |
5 | from ecmwf.opendata import Client
6 |
7 | TEST_URL = "https://get.ecmwf.int/repository/ecmwf-opendata/testing"
8 |
9 |
10 | @freeze_time("2022-01-21t13:21:34Z")
11 | def test_utc():
12 | assert datetime.datetime.utcnow() == datetime.datetime(2022, 1, 21, 13, 21, 34)
13 |
14 |
15 | @freeze_time("2022-01-21T13:21:34Z")
16 | def test_latest_00():
17 | client = Client(TEST_URL)
18 | date = client.latest(
19 | time=0,
20 | step=48,
21 | stream="oper",
22 | type="fc",
23 | levtype="sfc",
24 | param="2t",
25 | target="data.grib",
26 | )
27 |
28 | assert date == datetime.datetime(2022, 1, 20)
29 |
30 |
31 | @freeze_time("2022-01-21T13:21:34Z")
32 | def test_latest_06():
33 | client = Client(TEST_URL)
34 | date = client.latest(
35 | time=6,
36 | step=48,
37 | type="fc",
38 | levtype="sfc",
39 | param="2t",
40 | target="data.grib",
41 | )
42 |
43 | assert date == datetime.datetime(2022, 1, 20, 6)
44 |
45 |
46 | @freeze_time("2022-01-21T13:21:34Z")
47 | def test_latest_12():
48 | client = Client(TEST_URL)
49 | date = client.latest(
50 | time=12,
51 | step=48,
52 | type="fc",
53 | levtype="sfc",
54 | param="2t",
55 | target="data.grib",
56 | )
57 |
58 | assert date == datetime.datetime(2022, 1, 20, 12)
59 |
60 |
61 | @freeze_time("2022-01-20T13:21:34Z")
62 | def test_latest_18():
63 | client = Client(TEST_URL)
64 | date = client.latest(
65 | time=18,
66 | step=48,
67 | type="fc",
68 | levtype="sfc",
69 | param="2t",
70 | target="data.grib",
71 | )
72 |
73 | assert date == datetime.datetime(2022, 1, 19, 18)
74 |
--------------------------------------------------------------------------------
/tests/test_opendata.py:
--------------------------------------------------------------------------------
1 | from freezegun import freeze_time
2 |
3 | from ecmwf.opendata import Client
4 | from ecmwf.opendata.bufr import count_bufrs
5 | from ecmwf.opendata.grib import count_gribs
6 |
7 | TEST_URL = "https://get.ecmwf.int/repository/ecmwf-opendata/testing"
8 |
9 | """
10 | format=bufr, type=tf
11 | HH=00/12
12 | stream=enfo/oper, step=240h
13 | HH=06/18
14 | stream=enfo, step=144h
15 | stream=scda, step=90h
16 |
17 | format=grib2
18 | HH=00/12
19 | stream=enfo/waef
20 | type=ef, step=0h to 144h by 3h, 144h to 360h by 6h
21 | type=ep, step=240h/360h
22 | stream=oper, wave
23 | type=fc, step=0h to 144h by 3h, 144h to 360h by 6h
24 | HH=06/18
25 | stream=enfo/waef
26 | type=ef, step=0h to 144h by 3h
27 | stream= scda /scwv
28 | type=fc, step=0h to 90h by 3h
29 | HH=00
30 | stream=mmsf, type=fc, u=m, step=1m to 7m
31 | """
32 |
33 |
34 | @freeze_time("2022-01-21t13:21:34z")
35 | def xxx_test_opendata_1():
36 | client = Client(TEST_URL)
37 | client.retrieve(
38 | time=0,
39 | step=240,
40 | stream="oper",
41 | type="tf",
42 | levtype="sfc",
43 | param="tpg100",
44 | target="data.bufr",
45 | )
46 |
47 | assert count_bufrs("data.bufr") > 0
48 |
49 |
50 | @freeze_time("2022-01-21t13:21:34z")
51 | def test_opendata_2():
52 | client = Client(TEST_URL)
53 | client.retrieve(
54 | date=-1,
55 | time=0,
56 | step=12,
57 | stream="enfo",
58 | type="ef",
59 | levtype="sfc",
60 | param="10u",
61 | target="data.grib",
62 | )
63 |
64 | assert count_gribs("data.grib") == 51
65 |
66 |
67 | @freeze_time("2022-01-21t13:21:34z")
68 | def test_opendata_3():
69 | client = Client(TEST_URL)
70 | client.retrieve(
71 | date=-1,
72 | time=0,
73 | step=12,
74 | stream="enfo",
75 | type="cf",
76 | levtype="sfc",
77 | param="10u",
78 | target="data.grib",
79 | )
80 |
81 | assert count_gribs("data.grib") == 1
82 |
83 |
84 | @freeze_time("2022-01-21t13:21:34z")
85 | def test_opendata_4():
86 | client = Client(TEST_URL)
87 | client.retrieve(
88 | date=-1,
89 | time=0,
90 | step=12,
91 | stream="enfo",
92 | type="pf",
93 | levtype="sfc",
94 | param="10u",
95 | target="data.grib",
96 | )
97 |
98 | assert count_gribs("data.grib") == 50
99 |
100 |
101 | @freeze_time("2022-01-21t13:21:34z")
102 | def xx_test_opendata_6():
103 | client = Client(TEST_URL)
104 | client.retrieve(
105 | date=-1,
106 | time=0,
107 | type="tf",
108 | stream="enfo",
109 | step=240,
110 | target="data.bufr",
111 | )
112 |
113 | with open("data.bufr", "rb") as f:
114 | assert f.read(4) == b"BUFR"
115 |
--------------------------------------------------------------------------------
/tests/test_request.py:
--------------------------------------------------------------------------------
1 | from ecmwf.opendata import Client
2 |
3 |
4 | def test_request():
5 | client = Client(preserve_request_order=True)
6 |
7 | for_urls, _ = client.prepare_request(step="0/to/120")
8 |
9 | assert for_urls["step"] == [str(s) for s in range(0, 121)]
10 |
11 | for_urls, _ = client.prepare_request(step="0/to/120/by/6")
12 |
13 | assert for_urls["step"] == [str(s) for s in range(0, 121, 6)]
14 |
15 | for_urls, _ = client.prepare_request(time="0/to/18")
16 |
17 | assert for_urls["time"] == [str(s) for s in range(0, 24, 6)]
18 |
19 | for_urls, _ = client.prepare_request(date="20000101/to/20000131")
20 |
21 | assert for_urls["date"] == [str(s) for s in range(20000101, 20000132)]
22 |
23 | for_urls, _ = client.prepare_request(date="20000101/to/20000131/by/7")
24 |
25 | assert for_urls["date"] == [str(s) for s in range(20000101, 20000132, 7)]
26 |
27 |
28 | if __name__ == "__main__":
29 | test_request()
30 |
--------------------------------------------------------------------------------
/tests/test_sources.py:
--------------------------------------------------------------------------------
1 | import os
2 |
3 | import pytest
4 |
5 | from ecmwf.opendata import Client
6 | from ecmwf.opendata.bufr import count_bufrs
7 | from ecmwf.opendata.grib import count_gribs
8 |
9 | SOURCES = os.getenv("SOURCES_TO_TEST", "ecmwf,azure,aws").split(",")
10 |
11 |
12 | @pytest.mark.parametrize("source", SOURCES)
13 | def test_sources_1(source):
14 | client = Client(source)
15 |
16 | client.retrieve(
17 | time=0,
18 | stream="oper",
19 | type="fc",
20 | step=24,
21 | param="2t",
22 | target="data.grib",
23 | )
24 |
25 | assert count_gribs("data.grib") == 1
26 |
27 |
28 | @pytest.mark.parametrize("source", SOURCES)
29 | def xxx_test_sources_2(source):
30 | client = Client(source)
31 | client.retrieve(
32 | time=0,
33 | stream="oper",
34 | type="tf",
35 | step=240,
36 | target="data.bufr",
37 | )
38 |
39 | assert count_gribs("data.grib") == 51
40 |
41 |
42 | @pytest.mark.parametrize("source", SOURCES)
43 | def test_sources_3(source):
44 | client = Client(source)
45 | client.retrieve(
46 | time=0,
47 | stream="enfo",
48 | type="pf",
49 | param="msl",
50 | target="data.grib",
51 | )
52 |
53 | assert count_gribs("data.grib") == 50
54 |
55 |
56 | @pytest.mark.parametrize("source", SOURCES)
57 | def xxx_test_sources_4(source):
58 | client = Client(source)
59 | client.retrieve(
60 | time=0,
61 | stream="enfo",
62 | type="tf",
63 | step=240,
64 | target="data.bufr",
65 | )
66 |
67 | assert count_bufrs("data.bufr") > 0
68 |
69 |
70 | @pytest.mark.parametrize("source", SOURCES)
71 | def test_sources_6(source):
72 | client = Client(source)
73 | client.retrieve(
74 | time=0,
75 | stream="enfo",
76 | type=["es", "em"],
77 | step=24,
78 | target="data.grib",
79 | )
80 | assert count_gribs("data.grib") == 18
81 |
--------------------------------------------------------------------------------
/tests/test_stream.py:
--------------------------------------------------------------------------------
1 | from ecmwf.opendata import Client
2 |
3 |
4 | def patch_stream(stream, time, type):
5 | client = Client(infer_stream_keyword=True)
6 | args = {"stream": stream, "_H": "%02d" % (time,), "type": type, "model": "ifs"}
7 | return client.patch_stream(args)
8 |
9 |
10 | def test_stream():
11 | assert patch_stream("oper", 0, "fc") == "oper"
12 | assert patch_stream("oper", 6, "fc") == "scda"
13 | assert patch_stream("oper", 12, "fc") == "oper"
14 | assert patch_stream("oper", 18, "fc") == "scda"
15 |
16 | assert patch_stream("wave", 0, "fc") == "wave"
17 | assert patch_stream("wave", 6, "fc") == "scwv"
18 | assert patch_stream("wave", 12, "fc") == "wave"
19 | assert patch_stream("wave", 18, "fc") == "scwv"
20 |
21 | assert patch_stream("oper", 0, "ef") == "enfo"
22 | assert patch_stream("oper", 6, "ef") == "enfo"
23 | assert patch_stream("oper", 12, "ef") == "enfo"
24 | assert patch_stream("oper", 18, "ef") == "enfo"
25 |
26 | assert patch_stream("wave", 0, "ef") == "waef"
27 | assert patch_stream("wave", 6, "ef") == "waef"
28 | assert patch_stream("wave", 12, "ef") == "waef"
29 | assert patch_stream("wave", 18, "ef") == "waef"
30 |
31 | assert patch_stream("oper", 0, "ep") == "enfo"
32 | assert patch_stream("oper", 6, "ep") == "enfo"
33 | assert patch_stream("oper", 12, "ep") == "enfo"
34 | assert patch_stream("oper", 18, "ep") == "enfo"
35 |
36 | assert patch_stream("wave", 0, "ep") == "waef"
37 | assert patch_stream("wave", 6, "ep") == "waef"
38 | assert patch_stream("wave", 12, "ep") == "waef"
39 | assert patch_stream("wave", 18, "ep") == "waef"
40 |
41 |
42 | if __name__ == "__main__":
43 | test_stream()
44 |
--------------------------------------------------------------------------------
/tools/.gitignore:
--------------------------------------------------------------------------------
1 | index.txt
2 | done.txt
3 | index.txt
4 |
--------------------------------------------------------------------------------
/tools/README:
--------------------------------------------------------------------------------
1 | ./crawl.py > index.txt
2 |
--------------------------------------------------------------------------------
/tools/check-index.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | import json
3 |
4 | import requests
5 |
6 | seen = {}
7 | x = {}
8 | c = []
9 | OK = {
10 | ("enfo", "cf"): "ef",
11 | ("enfo", "pf"): "ef",
12 | ("waef", "cf"): "ef",
13 | ("waef", "pf"): "ef",
14 | ("enfo", "es"): "ep",
15 | ("enfo", "em"): "ep",
16 | ("enfo", "es", True): "240",
17 | ("waef", "es", True): "240",
18 | ("enfo", "em", True): "240",
19 | ("waef", "em", True): "240",
20 | ("enfo", "ep", True): "240",
21 | ("waef", "ep", True): "240",
22 | ("enfo", "es", False): "360",
23 | ("waef", "es", False): "360",
24 | ("enfo", "em", False): "360",
25 | ("waef", "em", False): "360",
26 | ("enfo", "ep", False): "360",
27 | ("waef", "ep", False): "360",
28 | "mmsa": "mmsf",
29 | ("mmsa", "fcmean"): "fc",
30 | }
31 | with open("index.txt") as f:
32 | for url in f:
33 | if "mmsf" in url:
34 | continue
35 | r = requests.get(url.strip())
36 | r.raise_for_status()
37 |
38 | line = url.strip().split("/")
39 |
40 | line = line[7:]
41 | date = line[0]
42 | time = line[1][:-1] + "00"
43 |
44 | stream = line[3]
45 | line = line[4].split("-")
46 | assert line[0] == f"{date}{time}00"
47 | if line[1][-1] == "m":
48 | fcmonth = line[1][:-1]
49 | step = None
50 | else:
51 | step = line[1][:-1]
52 | fcmonth = None
53 | assert line[2] == stream
54 | type = line[-1].split(".")[0]
55 |
56 | print(url.strip())
57 | for p in r.text.splitlines():
58 | r = json.loads(p)
59 | ok = True
60 | ok = ok and r.get("date") == date
61 | ok = ok and r.get("time") == time
62 |
63 | rstep = r.get("step", "0").split("-")[-1]
64 | rstep = OK.get(
65 | (r.get("stream"), r.get("type"), int(rstep) <= 240),
66 | r.get("step"),
67 | )
68 |
69 | ok = ok and rstep == step
70 | ok = ok and r.get("fcmonth") == fcmonth
71 |
72 | rstream = OK.get(r.get("stream"), r.get("stream"))
73 | ok = ok and rstream == stream
74 |
75 | rtype = OK.get((r.get("stream"), r.get("type")), r.get("type"))
76 | ok = ok and rtype == type
77 |
78 | if not ok:
79 | print(url.strip())
80 | print("Mismatch:", r)
81 |
82 | for a, b, c in (
83 | ("date", r.get("date"), date),
84 | ("time", r.get("time"), time),
85 | ("step", rstep, step),
86 | ("fcmonth", r.get("fcmonth"), fcmonth),
87 | ("stream", rstream, stream),
88 | ("type", rtype, type),
89 | ):
90 | if b != c:
91 | print("Mismatch: %r %r %r" % (a, b, c))
92 | # assert False
93 |
--------------------------------------------------------------------------------
/tools/crawl.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | from urllib.parse import urlparse
3 |
4 | import requests
5 | from bs4 import BeautifulSoup
6 |
7 | from ecmwf.opendata import Client
8 |
9 | url = urlparse(Client().url)
10 | top = url.scheme + "://" + url.netloc
11 |
12 |
13 | def crawl(url):
14 | print(f"{top}{url}")
15 | r = requests.get(f"{top}{url}")
16 | r.raise_for_status()
17 | soup = BeautifulSoup(r.text, "html.parser")
18 | for link in soup.find_all("a"):
19 | href = link.get("href")
20 | if href is not None and not url.startswith(href):
21 | if href.startswith("javascript:"):
22 | continue
23 | if href.endswith("/"):
24 | crawl(href)
25 | else:
26 | if href.endswith(".index"):
27 | print(f"{top}{href}")
28 |
29 |
30 | crawl(url.path + ("" if url.path.endswith("/") else "/"))
31 |
--------------------------------------------------------------------------------
/tools/get-all.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import json
3 | import random
4 | import traceback
5 |
6 | import eccodes
7 | import requests
8 |
9 | from ecmwf.opendata import Client
10 |
11 | client = Client()
12 |
13 | done = set()
14 |
15 | with open("done.txt") as f:
16 | for url in f:
17 | url = url.rstrip()
18 | done.add(url)
19 |
20 | ok = open("done.txt", "a")
21 | fail = open("fail.txt", "a")
22 |
23 | with open("index.txt") as f:
24 | for url in f:
25 | url = url.rstrip()
26 | if url in done:
27 | print(url, "DONE")
28 | continue
29 | print(url)
30 | # if "mmsf" in url:
31 | # continue
32 | r = requests.get(url)
33 | r.raise_for_status()
34 |
35 | try:
36 | lines = []
37 | for line in r.text.splitlines():
38 | line = json.loads(line)
39 | lines.append(line)
40 |
41 | random.shuffle(lines)
42 |
43 | for i, line in enumerate(lines):
44 | if i > 20:
45 | break
46 | line["target"] = "data"
47 | client.retrieve(line)
48 | with open("data", "rb") as g:
49 | h = eccodes.codes_new_from_file(g, eccodes.CODES_PRODUCT_GRIB)
50 | try:
51 | for k, v in line.items():
52 | if k in ["target", "_length", "_offset"]:
53 | continue
54 |
55 | if k == "param":
56 | k = "shortName"
57 | w = eccodes.codes_get_string(h, k)
58 | assert v == w, (v, w)
59 | finally:
60 | eccodes.codes_release(h)
61 |
62 | print(url, file=ok)
63 | except Exception as e:
64 | print(traceback.format_exc())
65 | print(url, e, file=fail)
66 |
--------------------------------------------------------------------------------
/tools/param-units.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import json
3 | import sys
4 | from collections import defaultdict
5 |
6 | import eccodes
7 | import requests
8 |
9 | from ecmwf.opendata import Client
10 |
11 | client = Client()
12 |
13 | GROUPS = {
14 | ("oper", "fc", "pl"): "01 Atmospheric fields on pressure levels",
15 | ("scda", "fc", "pl"): "01 Atmospheric fields on pressure levels",
16 | ("enfo", "cf", "pl"): "01 Atmospheric fields on pressure levels",
17 | ("enfo", "pf", "pl"): "01 Atmospheric fields on pressure levels",
18 | ("oper", "fc", "sfc"): "02 Atmospheric fields on a single level",
19 | ("scda", "fc", "sfc"): "02 Atmospheric fields on a single level",
20 | ("enfo", "cf", "sfc"): "02 Atmospheric fields on a single level",
21 | ("enfo", "pf", "sfc"): "02 Atmospheric fields on a single level",
22 | ("wave", "fc", "sfc"): "03 Ocean waves fields",
23 | ("waef", "cf", "sfc"): "03 Ocean waves fields",
24 | ("waef", "pf", "sfc"): "03 Ocean waves fields",
25 | ("scwv", "fc", "sfc"): "03 Ocean waves fields",
26 | ("enfo", "em", "pl"): "04 Ensemble mean and standard deviation - pressure levels",
27 | ("enfo", "es", "pl"): "04 Ensemble mean and standard deviation - pressure levels",
28 | ("enfo", "em", "sfc"): "05 Ensemble mean and standard deviation - single level",
29 | ("enfo", "es", "sfc"): "05 Ensemble mean and standard deviation - single level",
30 | (
31 | "enfo",
32 | "ep",
33 | "pl",
34 | ): "07 Instantaneous weather events - atmospheric fields - 850 hPa",
35 | (
36 | "enfo",
37 | "ep",
38 | "sfc",
39 | ): "08 Daily weather events - atmospheric fields - single level",
40 | ("waef", "ep", "sfc"): "10 Instantaneous weather events - ocean waves fields",
41 | }
42 |
43 | groups = defaultdict(set)
44 | seen = set()
45 |
46 | with open("index.txt") as f:
47 | for j, url in enumerate(f):
48 | url = url.rstrip()
49 |
50 | if (
51 | "240h" not in url
52 | and "360h" not in url
53 | and "90h" not in url
54 | and "1m" not in url
55 | ):
56 | continue
57 |
58 | print(url, file=sys.stderr)
59 |
60 | r = requests.get(url)
61 | r.raise_for_status()
62 |
63 | lines = []
64 | for line in r.text.splitlines():
65 | line = json.loads(line)
66 | lines.append(line)
67 |
68 | for i, line in enumerate(lines):
69 | key = tuple(line.get(x) for x in ("type", "stream", "levtype", "param"))
70 | if key in seen:
71 | continue
72 |
73 | seen.add(key)
74 |
75 | line["target"] = "data"
76 | print(line, file=sys.stderr)
77 | client.retrieve(line)
78 | with open("data", "rb") as g:
79 | h = eccodes.codes_new_from_file(g, eccodes.CODES_PRODUCT_GRIB)
80 | try:
81 | key = (
82 | eccodes.codes_get_string(h, "stream"),
83 | eccodes.codes_get_string(h, "type"),
84 | eccodes.codes_get_string(h, "levtype"),
85 | )
86 | groups[GROUPS[key]].add(
87 | (
88 | eccodes.codes_get_string(h, "shortName"),
89 | eccodes.codes_get_string(h, "nameECMF").replace(
90 | "Geopotential Height", "Geopotential height"
91 | ),
92 | eccodes.codes_get_string(h, "units")
93 | .replace("**-1", "-1")
94 | .replace("**-2", "-2"),
95 | )
96 | )
97 | finally:
98 | eccodes.codes_release(h)
99 |
100 |
101 | x = {}
102 |
103 | for k, v in sorted(groups.items()):
104 | print()
105 | print(">", k[3:])
106 | print()
107 | x = " | ".join(["Parameter", "Description", "Units"])
108 | print("|", x, "|")
109 | x = " | ".join(["---------", "-----------", "-----"])
110 | print("|", x, "|")
111 | for r in sorted(v):
112 | print("|", " | ".join(r), "|")
113 |
114 | with open("param.json", "w") as f:
115 | print(json.dumps(x, indent=4), file=f)
116 |
--------------------------------------------------------------------------------
/tools/parse.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | from climetlab.utils.factorise import factorise
3 |
4 | seen = {}
5 | x = {}
6 | c = []
7 | with open("list.txt") as f:
8 | for line in f:
9 | line = line.strip().split("/")
10 | if line[-1].endswith(".index"):
11 | continue
12 | line = line[6:]
13 | line.pop(1)
14 | line = [line[0]] + line[2].split("-")[1:]
15 | if tuple(line) in seen:
16 | continue
17 | seen[tuple(line)] = True
18 | c.append(
19 | dict(
20 | time=line[0],
21 | step=line[1][:-1],
22 | u=line[1][-1],
23 | stream=line[2],
24 | type=line[3].split(".")[0],
25 | format=line[3].split(".")[1],
26 | )
27 | )
28 |
29 |
30 | def compress(steps):
31 | if len(steps) < 3:
32 | return [str(s) for s in sorted(steps)]
33 |
34 | r = []
35 | d = steps[1] - steps[0]
36 | start = steps[0]
37 | prev = steps[0]
38 | for s in steps[1:]:
39 | nd = s - prev
40 | if nd != d:
41 | r.append("%s-%s-%s" % (start, prev, d))
42 | start = prev
43 | d = nd
44 | prev = s
45 | r.append("%s-%s-%s" % (start, prev, d))
46 | return r
47 |
48 |
49 | p = []
50 | for n in factorise(c).to_list():
51 | n["step"] = compress(sorted(int(x) for x in n["step"]))
52 | p.append(n)
53 |
54 | print(factorise(p).tree())
55 |
--------------------------------------------------------------------------------
/tools/possible.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import json
3 | import traceback
4 | from collections import defaultdict
5 |
6 | import requests
7 |
8 | from ecmwf.opendata import Client
9 |
10 | client = Client()
11 |
12 | done = set()
13 |
14 | possible_values = defaultdict(set)
15 |
16 | with open("index.txt") as f:
17 | for url in f:
18 | try:
19 | url = url.rstrip()
20 | print(url)
21 | r = requests.get(url)
22 | r.raise_for_status()
23 |
24 | lines = []
25 | for line in r.text.splitlines():
26 | line = json.loads(line)
27 | for k, v in line.items():
28 | if not k.startswith("_"):
29 | possible_values[k].add(v)
30 |
31 | except Exception:
32 | print(traceback.format_exc())
33 |
34 | # print(possible_values)
35 |
36 | x = {}
37 |
38 | for k, v in possible_values.items():
39 | x[k] = sorted(v)
40 |
41 | print(json.dumps(x, indent=4))
42 |
--------------------------------------------------------------------------------
/tools/requirements.txt:
--------------------------------------------------------------------------------
1 | beautifulsoup4
2 |
--------------------------------------------------------------------------------
/tools/upload.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python3
2 | import json
3 | import os
4 | import sys
5 |
6 | from nexus.toolkit import Authenticator, DownloadInstance, FileManager
7 |
8 | with open(os.path.expanduser("~/.nexus")) as f:
9 | config = json.load(f)
10 |
11 | authenticator = Authenticator.from_credentials(
12 | username=config["username"],
13 | password=config["password"],
14 | )
15 |
16 | nexus = DownloadInstance(
17 | authenticator=authenticator,
18 | repository="ecmwf-opendata",
19 | )
20 |
21 | file_manager = FileManager(nexus=nexus)
22 |
23 | file_manager.upload(
24 | local_path=sys.argv[1],
25 | remote_path=sys.argv[2],
26 | )
27 |
--------------------------------------------------------------------------------
/tools/upload.sh:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env bash
2 | # https://get.ecmwf.int/#browse/browse:ecmwf-opendata
3 | set -eau
4 |
5 | DATE1=20220119
6 | DATE2=20220120
7 | touch done
8 |
9 | for time in 00 06 12 18
10 | do
11 | DATE=$DATE2
12 | if [[ $time -gt 12 ]]
13 | then
14 | DATE=$DATE1
15 | fi
16 | for stream in oper wave scda scwv enfo waef
17 | do
18 | for type in fc ef ep # tf
19 | do
20 | ext=grib2
21 | if [[ $type == "tf" ]]
22 | then
23 | ext=bufr
24 | fi
25 | for step in $(seq 0 3 144) $(seq 150 6 360)
26 | do
27 |
28 | grep url done && continue
29 |
30 | url=$URL/$DATE/${time}z/0p4-beta/${stream}/${DATE}${time}0000-${step}h-$stream-$type.$ext
31 | code=$(curl --silent --head $url | head -1 | awk '{print $2;}')
32 | if [[ $code -eq 404 ]]
33 | then
34 | continue
35 | fi
36 | if [[ $code -ne 200 ]]
37 | then
38 | echo "Code $code"
39 | exit 1
40 | fi
41 | echo $url
42 | base=$(basename $url .grib2)
43 | data=$base.grib2
44 | index=$base.index
45 | curl --fail $url -o $data.raw
46 | ~/build/mir/bin/mir --grid=20/20 $data.raw $data
47 | ~/build/pgen/bin/pgen-create-index-file -i $data -o $index
48 | yes | ./upload.py $data /testing/$DATE/${time}z/0p4-beta/${stream}/
49 | yes | ./upload.py $index /testing/$DATE/${time}z/0p4-beta/${stream}/
50 | rm -f $data $index $data.raw
51 | echo $url >> done
52 | done
53 | done
54 | done
55 | done
56 |
--------------------------------------------------------------------------------
/tox.ini:
--------------------------------------------------------------------------------
1 | [flake8]
2 | max-line-length = 120
3 | ; See https://black.readthedocs.io/en/stable/the_black_code_style/current_style.html#slices
4 | extend-ignore = E203
5 | [isort]
6 | profile=black
7 |
--------------------------------------------------------------------------------