nasaharvest / crop-mask

End-to-end workflow for generating high resolution cropland maps
Apache License 2.0
94 stars 26 forks source link

Intercomparison results table generation update #388

Closed ivanzvonkov closed 2 months ago

ivanzvonkov commented 2 months ago

Key Change: For mean metrics, take mean of the standard errors not standard deviation

Before

mean = country_df[country_df['dataset'].isin(map_order)][metric].mean()
std = country_df[country_df['dataset'].isin(map_order)][err].std()
latex_table += "& ${:.2f}\pm{:.2f}$ ".format(mean, std)

After

mean = country_df[country_df['dataset'].isin(map_order)][metric].mean()
std = country_df[country_df['dataset'].isin(map_order)][err].mean() # Changed from std to mean
latex_table += "& ${:.2f}\pm{:.2f}$ ".format(mean, std)

Updated the table in overleaf

review-notebook-app[bot] commented 2 months ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB