-
Notifications
You must be signed in to change notification settings - Fork 126
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add ensemble tide modelling functionality to model_tides
#1231
Conversation
model_tides
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please add the test data to the PR: ../Supplementary_data/Interpolation/interpolation_points.geojson
lambda x: pd.Series({"start": start_point, "end": x}) | ||
if x.type == "Point" | ||
else pd.Series({"start": None, "end": None}) | ||
lambda x: ( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just Black formatting stuff, can ignore this
lambda x: pd.Series({"start": x.geoms[0], "end": x.geoms[-1]}) | ||
if x.type == "MultiPoint" | ||
else pd.Series({"start": None, "end": None}) | ||
lambda x: ( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Just Black formatting stuff, can ignore this
@@ -542,25 +717,26 @@ def model_tides( | |||
results stacked vertically along "tide_model" and "tide_m" | |||
columns), or wide format (with a column for each tide model). | |||
Defaults to "long". | |||
epsg : int, DEPRECATED |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Removed this deprecated param
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks great Robbi! It's very thoroughly documented and easy to read. Nice job!
* Add updated `xr_regression` function for multi-dimensional linear regression (#1226) * Add updated xr_regression function * Add dask support for lazy computation * Set dtypes * Update docstring * Update docstring * Add MAD outliers * Update docstring * Remove lag functionality * Update docstrings * Add better error handling * Update stream gauge corr notebook to use new func * Adding DEAfrica Wetland Turbidity notebook for Australian study site (#1175) * Adding DEAfrica Wetland Turbidity notebook for Australian study site * change all instances of NDTI to NDTI2 to reflect usage at top of notebook * update notebook to use Collection 3 WO Statistics * rerun notebook --------- Co-authored-by: BexDunn <bex.dunn@ga.gov.au> * Add spatial interpolation with `xr_interpolate` notebook (#1233) * Add ensemble tide modelling functionality to model_tides * Update test_coastal.py * Remove test * Updates to IDW, xr_interpolate and ensemble tide modelling code" * Doco updates * Switch ensemble rankings from high to low = good * Update docstring * Fix doco * Add interpolation notebook * Remove coastal files from branch * Add points data * Review feedback; * Add p param to IDW * Fix test * Updates to product notebook Knowledge Hub links and DEA notebook content (#1221) * Move KH links into consistent alert box format * Update DEA notebook * Minor wording updates * Minor wording * Temporarily remove STAC notebook from tests * Add ensemble tide modelling functionality to `model_tides` (#1231) * Add ensemble tide modelling functionality to model_tides * Update test_coastal.py * Remove test * Updates to IDW, xr_interpolate and ensemble tide modelling code" * Doco updates * Switch ensemble rankings from high to low = good * Update docstring * Fix doco * Add interpolation notebook --------- Co-authored-by: Matt-dea <129345253+Matt-dea@users.noreply.github.com> Co-authored-by: BexDunn <bex.dunn@ga.gov.au>
Proposed changes
This PR implements some major changes to our coastal tide modelling functions, to support new "ensemble" tide modelling functionality that combines multiple input tide models into a single higher quality output.
Key changes include:
dea_tools.coastal.model_tides
function, that combines multiple tide models using external model ranking data to identify the best performing models locally (the "ensemble" model generation can be customised by providing custom functions via theensemble_func
param). By implementing "ensemble" functionality inmodel_tides
, it automatically becomes available inpixel_tides
and other downstream functions we use for generating coastal datasets.model_tides
andpixel_tides