# xarray Extensions

## Jua xarray Extensions

The Jua Python SDK extends the popular [xarray](https://docs.xarray.dev/) library with weather-specific functionality to make working with meteorological data more intuitive and convenient.

### Overview

Jua's xarray extensions provide:

1. Weather-specific data selection capabilities
2. Unit conversion utilities
3. Time handling enhancements
4. Point-based geographic selection
5. Enhanced type hints for better IDE support

These extensions are automatically applied when you use the SDK - no extra steps required.

### Extended Functionality at a Glance

The SDK adds several powerful extensions to xarray:

* **Enhanced `sel()` method** with additional parameters:
  * `prediction_timedelta` - Select by forecast lead time
  * `points` - Select by geographic points
  * Support for proper North-to-South latitude slicing
* **New accessor methods** via `.jua` accessor or direct methods:
  * `.to_celcius()` - Convert temperature from Kelvin to Celsius
  * `.to_absolute_time()` - Convert from lead times to absolute dates
  * `.select_point()` - Select data at specific geographic locations
* **Variable access** with Jua's `Variables` enum for type safety

### Key Features

#### Extended Data Selection

```python
# Select data using prediction lead times
forecast_data.sel(prediction_timedelta=24)  # 24-hour forecast
forecast_data.sel(prediction_timedelta=slice(24, 72))  # 1-3 day forecast
forecast_data.sel(prediction_timedelta=slice(0, 120, 6))  # Every 6 hours up to 5 days

# Select geographic regions with natural ordering
# Note: latitude goes from North to South (higher to lower values)
europe_data = forecast_data.sel(
    latitude=slice(72, 36),    # North to South
    longitude=slice(-15, 35)   # West to East
)
```

#### Point-Based Selection

```python
from jua.types.geo import LatLon

# Select data for specific locations
cities = [
    LatLon(lat=51.5074, lon=-0.1278, name="London"),
    LatLon(lat=40.7128, lon=-74.0060, name="New York")
]

# Using direct selection
city_data = forecast_data.sel(points=cities)

# Or using the accessor
city_data = forecast_data.jua.select_point(cities)

# Access data for a specific city
london_data = city_data.sel(points="London")
```

#### Unit Conversions

```python
# Get temperature data
temperature = forecast_data["air_temperature_at_height_level_2m"]

# Convert from Kelvin to Celsius
celsius = temperature.to_celcius()
# or
celsius = temperature.jua.to_celcius()
```

#### Time Handling

```python
# Convert from prediction lead times to absolute times
absolute_times = forecast_data.to_absolute_time()
# or
absolute_times = forecast_data.jua.to_absolute_time()
```

#### Type-Safe Variable Access

```python
from jua.weather import Variables

# Access variables using enum members (with autocompletion and type checking)
temperature = forecast_data[Variables.AIR_TEMPERATURE_AT_HEIGHT_LEVEL_2M]
wind_speed = forecast_data[Variables.WIND_SPEED_AT_HEIGHT_LEVEL_10M]
```

Best Practices

1. **Use Variables enum** for type-safe variable access
2. **Use xarray's powerful data analysis capabilities** - these extensions preserve all standard xarray functionality


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.jua.ai/python-sdk/weather/xarray-extensions.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.