############### Getting Started ############### Install ======= Pip --- .. code-block:: bash pip install wxee Conda ----- .. code-block:: bash conda install -c conda-forge wxee From Source ----------- .. code-block:: bash git clone https://github.com/aazuspan/wxee cd wxee make install Setup ===== .. currentmodule:: wxee Once you have access to Google Earth Engine, just import :code:`ee` and :code:`wxee` and initialize. .. code-block:: python import ee import wxee wxee.Initialize() .. note:: The :func:`wxee.Initialize` function works similarly to :code:`ee.Initialize` but automatically connects to the `high-volume Earth Engine endpoint `_ that should be used for all automated requests to Earth Engine, such as those made by :code:`wxee`. Usage ===== Basic Features -------------- Basic :code:`wxee` functionality like downloading image collections to :code:`xarray` and :code:`GeoTiff` are extended through the :code:`wx` accessor, like so: .. code-block:: python collection = ee.ImageCollection("IDAHO_EPSCOR/GRIDMET").filterDate("2020", "2021") collection.wx.to_xarray() See the example notebooks for details on the `xarray interface `_, `downloading images and collections `_, and `visualizing color composites `_. Time Series Features -------------------- More advanced functionality requires turning image collections into :class:`TimeSeries` objects. Check out this example notebook for and `introduction to the TimeSeries class `_ You can also find example notebooks on specific :class:`TimeSeries` methods like `temporal aggregation `_, `temporal interpolation `_, `climatological means `_, and `climatological anomalies `_. Applied Examples ---------------- If you prefer, you can check out the applied example notebooks that use a variety of different methods to solve specific problems like `fire progression mapping `_.