In [4]:
border = 80
dfserr = []
for exp in ['elev_bands', 'centerlines']: #
fd = f'CRU/{exp}/qc3/pcp2.5/no_match/RGI62/b_{border:03d}/L5/summary/'
fs = glob.glob(fd+'glacier_statistics*.csv')
assert len(fs) == 18
df = []
for f in fs:
df.append(pd.read_csv(f, index_col=0, low_memory=False))
df = pd.concat(df).sort_index()
plt.figure()
sns.countplot(y="error_task", data=df);
plt.show()
print(df.loc[~df['error_task'].isnull()].rgi_area_km2.sum() / df.rgi_area_km2.sum() * 100)
dfserr.append(df.loc[~df['error_task'].isnull()].sort_values(by='rgi_area_km2', ascending=False)[['rgi_area_km2', 'error_task', 'error_msg']].iloc[:15])
2.438449673256872
3.234742981390701
