Jua Python SDK

Access industry-leading weather forecasts with ease

The Jua Python SDK provides a simple and powerful interface to Jua's state-of-the-art weather forecasting capabilities. Easily integrate accurate weather data into your applications, research, or analysis workflows.

Getting Started 🚀

Prerequisites

Python 3.11 or higher
Internet connection for API access

Installation

Install jua with pip:

pip install jua

Alternatively, checkout uv for managing dependencies and Python versions:

uv init && uv add jua

Authentication

Simply run jua auth to authenticate via your web browser. Make sure you are already logged in the developer portal. Alternatively, generate an API key from the Jua dashboard and save it to ~/.jua/default/api-key.json.

Examples

Obtaining the metadata for a model

from jua import JuaClient
from jua.weather import Models

client = JuaClient()
model = client.weather.get_model(Models.EPT1_5)
metadata = model.get_metadata()

# Print the metadata
print(metadata)

Getting the forecast runs available for a model

from jua import JuaClient
from jua.weather import Models

client = JuaClient()

# Getting metadata the latest forecast run
latest = model.get_latest_init_time()
print(latest)

# Fetching model runs
available_forecasts = model.get_available_forecasts()

# Fetching all model runs for January 2025
#   Results are paginated so we might need to iterate through
result = model.get_available_forecasts(
    since=datetime(2025, 1, 1),
    before=datetime(2025, 1, 31, 23, 59),
    limit=100,
)
all_forecasts = list(result.forecasts)
while result.has_more:
    print("Fetching next page")
    result = result.next()
    all_forecasts.extend(result.forecasts)

Access the latest 20-day forecast for a point location

Retrieve temperature forecasts for Zurich and visualize the data:

import matplotlib.pyplot as plt
from jua import JuaClient
from jua.types.geo import LatLon
from jua.weather import Models, Variables

client = JuaClient()
model = client.weather.get_model(Models.EPT1_5)
zurich = LatLon(lat=47.3769, lon=8.5417)

# Check if 10-day forecast is ready for the latest available init_time
is_ten_day_ready = model.is_ready(forecasted_hours=240)

# Get latest forecast
if is_ten_day_ready:
    forecast = model.get_forecasts(points=[zurich], max_lead_time=240)
    temp_data = forecast[Variables.AIR_TEMPERATURE_AT_HEIGHT_LEVEL_2M]
    temp_data.to_celcius().to_absolute_time().plot()
    plt.show()

Show output

Forecast Zurich 20d

Access historical weather data

Historical data can be accessed in the same way. In this case, we get all EPT2 forecasts from January 2024, and plot the first 5 together.

from datetime import datetime

import matplotlib.pyplot as plt
from jua import JuaClient
from jua.weather import Models, Variables

client = JuaClient()
zurich = LatLon(lat=47.3769, lon=8.5417)
model = client.weather.get_model(Models.EPT2)
hindcast = model.get_forecasts(
    init_time=slice(
        datetime(2024, 1, 1, 0),
        datetime(2024, 1, 31, 0),
    ),
    points=[zurich],
    min_lead_time=0,
    max_lead_time=(5 * 24),
    variables=[Variables.AIR_TEMPERATURE_AT_HEIGHT_LEVEL_2M],
    method="nearest",
)
data = hindcast[Variables.AIR_TEMPERATURE_AT_HEIGHT_LEVEL_2M]

# Compare the first 5 runs of January
fig, ax = plt.subplots(figsize=(15, 8))
for i in range(5):
    forecast_data = data.isel(init_time=i, points=0).to_celcius().to_absolute_time()
    forecast_data.plot(ax=ax, label=forecast_data.init_time.values)
plt.legend()
plt.show()

Show output

Europe Hindcast

Accessing Market Aggregates

The AggregateVariables enum provides the following variables:

WIND_SPEED_AT_HEIGHT_LEVEL_10M - Wind speed at 10m height (Weighting.WIND_CAPACITY)
WIND_SPEED_AT_HEIGHT_LEVEL_100M - Wind speed at 100m height (Weighting.WIND_CAPACITY)
SURFACE_DOWNWELLING_SHORTWAVE_FLUX_SUM_1H - Surface downwelling shortwave flux (Weighting.SOLAR_CAPACITY)
AIR_TEMPERATURE_AT_HEIGHT_LEVEL_2M - Air temperature at 2m height (Weighting.POPULATION)

Comparing the latest EPT2 and ECMWF IFS run for the Ireland and Northern Ireland market zones:

from jua import JuaClient
from jua.market_aggregates import AggregateVariables, ModelRuns
from jua.types import Countries, MarketZones
from jua.weather import Models, Variables

client = JuaClient()

# Create energy market using MarketZones enum
ir_nir = client.market_aggregates.get_market([MarketZones.IE, MarketZones.GB_NIR])

# Get the market aggregates for the latest EPT2 and ECMWF IFS runs
model_runs = [ModelRuns(Models.EPT2, 0), ModelRuns(Models.ECMWF_IFS_SINGLE, 0)]
ds = ir_nir.compare_runs(
    agg_variable=AggregateVariables.WIND_SPEED_AT_HEIGHT_LEVEL_10M,
    model_runs=model_runs,
    max_lead_time=24,
)

print("Retrieved dataset:")
print(ds)
print()

Obtaining all market zones for a country:

from jua.types import Countries, MarketZones

norway_zones = MarketZones.filter_by_country(Countries.NORWAY)
print(f"Norwegian zones: {[z.zone_name for z in norway_zones]}")

Documentation

For comprehensive documentation, visit docs.jua.ai.

Contributing

See the contribution guide to get started.

Changes

See the changelog for the latest changes.

Support

If you encounter any issues or have questions, please:

Check the documentation
Open an issue on GitHub
Contact support@jua.ai

License

This project is licensed under the MIT License - see the LICENSE file for details.

Development Status
- 4 - Beta
Intended Audience
- Developers
License
- OSI Approved :: MIT License
Programming Language

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jua-0.36.0.tar.gz (1.1 MB view details)

Uploaded Jul 20, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

jua-0.36.0-py3-none-any.whl (130.3 kB view details)

Uploaded Jul 20, 2026 Python 3

File details

Details for the file jua-0.36.0.tar.gz.

File metadata

Download URL: jua-0.36.0.tar.gz
Upload date: Jul 20, 2026
Size: 1.1 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: uv/0.11.29 {"installer":{"name":"uv","version":"0.11.29","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for jua-0.36.0.tar.gz
Algorithm	Hash digest
SHA256	`a0f7914ee49435dbf043286c1a11ebdf9961b37d8bf1c19c8ba2d21570d0189f`
MD5	`48f77a67ec7e864235c91d19289e0083`
BLAKE2b-256	`409587dd2b8ea244677620351bf4d8723852f1c228151590055d4bbcb2933653`

See more details on using hashes here.

File details

Details for the file jua-0.36.0-py3-none-any.whl.

File metadata

Download URL: jua-0.36.0-py3-none-any.whl
Upload date: Jul 20, 2026
Size: 130.3 kB
Tags: Python 3
Uploaded using Trusted Publishing? Yes
Uploaded via: uv/0.11.29 {"installer":{"name":"uv","version":"0.11.29","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for jua-0.36.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`a2871b5a798bb7f9aadf78ae5caf059be25facc5e181fd7df6507ceb03622c99`
MD5	`472574c39468fad9c79fb7b1d3de86a3`
BLAKE2b-256	`f85308183b714ae2d4991ab211916472448c23ab3182ee51e023e54be439df5e`