Skip to content

fix: OSD data aggregation and CEC duplicate column issues #360

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.

Sign up for GitHub

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

Open
jjmaynard wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: OSD data aggregation and CEC duplicate column issues #360

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ecf4202
Update CEC infill method and rename column
jjmaynard Jan 20, 2026
bfe86d4
fix/OSD data aggregation
jjmaynard Jan 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 26 additions & 8 deletions soil_id/us_soil.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -766,20 +766,29 @@ def list_soils(lon, lat):
lab_lyrs.append(["", "", ""])
munsell_lyrs.append("")
else:
# Use the horizon bottom depths that match the stored horizon structure
# Convert string values to float, filtering out empty strings
horizon_bottom_depths = [
float(v) if v != "" else np.nan
for v in hzb_lyrs[index].values()
]
# Filter out NaN values
horizon_bottom_depths = [d for d in horizon_bottom_depths if not np.isnan(d)]

# Aggregate data for each color dimension
l_d = aggregate_data(
data=lab_intpl["l"],
bottom_depths=muhorzdata_pd_group["hzdepb_r"].tolist(),
bottom_depths=horizon_bottom_depths,
sd=2,
).fillna("")
a_d = aggregate_data(
data=lab_intpl["a"],
bottom_depths=muhorzdata_pd_group["hzdepb_r"].tolist(),
bottom_depths=horizon_bottom_depths,
sd=2,
).fillna("")
b_d = aggregate_data(
data=lab_intpl["b"],
bottom_depths=muhorzdata_pd_group["hzdepb_r"].tolist(),
bottom_depths=horizon_bottom_depths,
sd=2,
).fillna("")

Expand Down Expand Up @@ -909,16 +918,25 @@ def list_soils(lon, lat):

getProfile_cokey[index] = getProfile_mod

# Use the horizon bottom depths that match the stored horizon structure
# Convert string values to float, filtering out empty strings
horizon_bottom_depths = [
float(v) if v != "" else np.nan
for v in hzb_lyrs[index].values()
]
# Filter out NaN values
horizon_bottom_depths = [d for d in horizon_bottom_depths if not np.isnan(d)]

# Aggregate sand data
snd_d_osd = aggregate_data(
data=OSD_sand_intpl.iloc[:, 0],
bottom_depths=muhorzdata_pd_group["hzdepb_r"].tolist(),
bottom_depths=horizon_bottom_depths,
)

# Aggregate clay data
cly_d_osd = aggregate_data(
data=OSD_clay_intpl.iloc[:, 1],
bottom_depths=muhorzdata_pd_group["hzdepb_r"].tolist(),
bottom_depths=horizon_bottom_depths,
)

# Calculate texture data based on sand and clay data
Expand All @@ -931,7 +949,7 @@ def list_soils(lon, lat):
# Aggregate rock fragment data
rf_d_osd = aggregate_data(
data=OSD_rfv_intpl.c_cfpct_intpl,
bottom_depths=muhorzdata_pd_group["hzdepb_r"].tolist(),
bottom_depths=horizon_bottom_depths,
)

# Fill NaN values
Expand All @@ -952,9 +970,9 @@ def list_soils(lon, lat):
# Update cec, ph, and ec layers if they contain only a single
# empty string
for lyr in [cec_lyrs, ph_lyrs, ec_lyrs]:
if len(lyr[index]) == 1 and lyr[index][0] == "":
if len(lyr[index]) == 1 and list(lyr[index].values())[0] == "":
empty_values = [""] * len(hzb_lyrs[index])
lyr[index] = dict(zip(hzb_lyrs[index], empty_values))
lyr[index] = dict(zip(hzb_lyrs[index].keys(), empty_values))

else:
OSDhorzdata_group_cokey[index] = group_sorted
Expand Down
5 changes: 2 additions & 3 deletions soil_id/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1611,10 +1611,9 @@ def process_horizon_data(muhorzdata_pd):
["cokey", "chkey", "hzname"]
].astype(str)

# Infill missing CEC values with ECEC
muhorzdata_pd["CEC"] = muhorzdata_pd["cec7_r"].fillna(muhorzdata_pd["ecec_r"])
# Infill missing CEC values with ECEC and rename columns for better clarity
muhorzdata_pd["cec7_r"] = muhorzdata_pd["cec7_r"].fillna(muhorzdata_pd["ecec_r"])

# Rename columns for better clarity
muhorzdata_pd = muhorzdata_pd.rename(
columns={"cec7_r": "CEC", "ph1to1h2o_r": "pH", "ec_r": "EC"}
)
Expand Down
Loading