Skip to content

Commit 51cf8c8

Browse files
jjmaynardjjmaynard
committed
fix: make format changes
1 parent b273b3d commit 51cf8c8

File tree

3 files changed

+114
-110
lines changed

3 files changed

+114
-110
lines changed

‎soil_id/db.py

Lines changed: 14 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -20,12 +20,11 @@
2020

2121
# Third-party libraries
2222
import psycopg
23+
from dotenv import load_dotenv
2324

2425
# local libraries
2526
import soil_id.config
2627

27-
from dotenv import load_dotenv
28-
2928
# Load .env file
3029
load_dotenv()
3130

@@ -325,11 +324,19 @@ def execute_query(query, params):
325324
if not WRB_Comp_List_mapped:
326325
# If no mapping found, return an empty DataFrame or None
327326
logging.warning("No mapped WRB_1984_Full names found for given WRB_2006_Full values.")
328-
return pd.DataFrame(columns=[
329-
"WRB_tax", "Description_en", "Management_en", "Description_es",
330-
"Management_es", "Description_ks", "Management_ks",
331-
"Description_fr", "Management_fr"
332-
])
327+
return pd.DataFrame(
328+
columns=[
329+
"WRB_tax",
330+
"Description_en",
331+
"Management_en",
332+
"Description_es",
333+
"Management_es",
334+
"Description_ks",
335+
"Management_ks",
336+
"Description_fr",
337+
"Management_fr",
338+
]
339+
)
333340

334341
# 3. Get descriptions from wrb_fao90_desc where WRB_tax IN ...
335342
sql2 = """

‎soil_id/global_soil.py

Lines changed: 93 additions & 94 deletions
Original file line numberDiff line numberDiff line change
@@ -13,21 +13,31 @@
1313
# You should have received a copy of the GNU Affero General Public License
1414
# along with this program. If not, see https://www.gnu.org/licenses/.
1515

16-
# local libraries
17-
import soil_id.config
16+
import collections
17+
import csv
18+
import io
1819

19-
from .db import (
20-
get_WRB_descriptions,
21-
getSG_descriptions,
22-
)
20+
# Standard libraries
21+
import logging
22+
import re
23+
from dataclasses import dataclass
2324

24-
from .color import (
25-
calculate_deltaE2000,
26-
)
25+
# Third-party libraries
26+
import numpy as np
27+
import pandas as pd
2728

28-
from .services import get_soilgrids_classification_data, get_soilgrids_property_data
29+
# Load .env file
30+
from dotenv import load_dotenv
31+
from scipy.stats import norm
32+
33+
# local libraries
34+
import soil_id.config
2935

36+
from .color import calculate_deltaE2000
37+
from .db import get_WRB_descriptions, getSG_descriptions
38+
from .services import get_soilgrids_classification_data, get_soilgrids_property_data
3039
from .utils import (
40+
adjust_depth_interval,
3141
agg_data_layer,
3242
assign_max_distance_scores,
3343
calculate_location_score,
@@ -39,27 +49,11 @@
3949
getSand,
4050
getTexture,
4151
gower_distances,
52+
max_comp_depth,
4253
pedon_color,
4354
silt_calc,
44-
max_comp_depth,
45-
adjust_depth_interval,
4655
)
4756

48-
# Standard libraries
49-
import logging
50-
import collections
51-
import csv
52-
import io
53-
import re
54-
from dataclasses import dataclass
55-
56-
# Third-party libraries
57-
import numpy as np
58-
import pandas as pd
59-
from scipy.stats import norm
60-
61-
# Load .env file
62-
from dotenv import load_dotenv
6357
load_dotenv()
6458

6559

@@ -93,7 +87,7 @@ def list_soils_global(lon, lat):
9387
lon,
9488
lat,
9589
# Temporarily change file path
96-
file_path='/mnt/c/LandPKS_API_SoilID-master/global/wise30sec_poly_simp_soil.gpkg',
90+
file_path="/mnt/c/LandPKS_API_SoilID-master/global/wise30sec_poly_simp_soil.gpkg",
9791
# file_path=config.WISE_PATH,
9892
# layer_name=None,
9993
buffer_dist=10000,
@@ -211,11 +205,13 @@ def list_soils_global(lon, lat):
211205
comp_key = muhorzdata_pd["cokey"].unique().tolist()
212206

213207
# Subset mucompdata_pd by new compname_key and add suffix to name if there are duplicates
214-
mucompdata_pd = mucompdata_pd.loc[mucompdata_pd['cokey'].isin(comp_key)].reset_index(drop=True)
208+
mucompdata_pd = mucompdata_pd.loc[mucompdata_pd["cokey"].isin(comp_key)].reset_index(drop=True)
215209
mucompdata_pd["compname_grp"] = mucompdata_pd["compname"]
216210

217211
# Sort by 'distance_score' (descending) and 'distance' (ascending), then reset the index
218-
mucompdata_pd = mucompdata_pd.sort_values(['distance_score', 'distance'], ascending=[False, True]).reset_index(drop=True)
212+
mucompdata_pd = mucompdata_pd.sort_values(
213+
["distance_score", "distance"], ascending=[False, True]
214+
).reset_index(drop=True)
219215

220216
# Add suffix to duplicate names
221217
name_counts = collections.Counter(mucompdata_pd["compname"])
@@ -250,9 +246,7 @@ def list_soils_global(lon, lat):
250246

251247
for group_key, group in muhorzdata_group_cokey:
252248
profile = (
253-
group.sort_values(by="hzdept_r")
254-
.drop_duplicates(keep="first")
255-
.reset_index(drop=True)
249+
group.sort_values(by="hzdept_r").drop_duplicates(keep="first").reset_index(drop=True)
256250
)
257251

258252
# profile depth
@@ -276,10 +270,14 @@ def list_soils_global(lon, lat):
276270
[
277271
sand_pct_intpl[["c_sandpct_intpl_grp"]], # DataFrame
278272
clay_pct_intpl[["c_claypct_intpl_grp"]], # DataFrame
279-
cf_pct_intpl[["c_cfpct_intpl_grp"]], # DataFrame
280-
pd.DataFrame(profile.compname.unique(), columns=["compname"]), # Convert to DataFrame
281-
pd.DataFrame(profile.cokey.unique(), columns=["cokey"]), # Convert to DataFrame
282-
pd.DataFrame(profile.comppct_r.unique(), columns=["comppct"]), # Convert to DataFrame
273+
cf_pct_intpl[["c_cfpct_intpl_grp"]], # DataFrame
274+
pd.DataFrame(
275+
profile.compname.unique(), columns=["compname"]
276+
), # Convert to DataFrame
277+
pd.DataFrame(profile.cokey.unique(), columns=["cokey"]), # Convert to DataFrame
278+
pd.DataFrame(
279+
profile.comppct_r.unique(), columns=["comppct"]
280+
), # Convert to DataFrame
283281
],
284282
axis=1,
285283
)
@@ -301,17 +299,33 @@ def list_soils_global(lon, lat):
301299
}
302300
)
303301

304-
snd_d, hz_depb = agg_data_layer(sand_pct_intpl.c_sandpct_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=True)
305-
cly_d = agg_data_layer(clay_pct_intpl.c_claypct_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False)
302+
snd_d, hz_depb = agg_data_layer(
303+
sand_pct_intpl.c_sandpct_intpl,
304+
bottom=c_bottom_temp["c_very_bottom"].iloc[0],
305+
depth=True,
306+
)
307+
cly_d = agg_data_layer(
308+
clay_pct_intpl.c_claypct_intpl,
309+
bottom=c_bottom_temp["c_very_bottom"].iloc[0],
310+
depth=False,
311+
)
306312
txt_d = [
307313
getTexture(row=None, sand=s, silt=(100 - (s + c)), clay=c) for s, c in zip(snd_d, cly_d)
308314
]
309315
txt_d = pd.Series(txt_d, index=snd_d.index)
310316

311-
rf_d = agg_data_layer(cf_pct_intpl.c_cfpct_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False)
312-
cec_d = agg_data_layer(cec_intpl.c_cec_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False)
313-
ph_d = agg_data_layer(ph_intpl.c_ph_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False)
314-
ec_d = agg_data_layer(ec_intpl.c_ec_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False)
317+
rf_d = agg_data_layer(
318+
cf_pct_intpl.c_cfpct_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False
319+
)
320+
cec_d = agg_data_layer(
321+
cec_intpl.c_cec_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False
322+
)
323+
ph_d = agg_data_layer(
324+
ph_intpl.c_ph_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False
325+
)
326+
ec_d = agg_data_layer(
327+
ec_intpl.c_ec_intpl, bottom=c_bottom_temp["c_very_bottom"].iloc[0], depth=False
328+
)
315329

316330
# Fill NaN values and append to lists
317331
for data_list, data in zip(
@@ -370,9 +384,9 @@ def list_soils_global(lon, lat):
370384
]
371385
soilIDRank_output_pd = pd.concat(soilIDRank_output, axis=0).reset_index(drop=True)
372386

373-
mucompdata_cond_prob = mucompdata_pd.sort_values(
374-
"distance_score", ascending=False
375-
).reset_index(drop=True)
387+
mucompdata_cond_prob = mucompdata_pd.sort_values("distance_score", ascending=False).reset_index(
388+
drop=True
389+
)
376390

377391
# Generate the Rank_Loc column values
378392
rank_id = 1
@@ -500,16 +514,7 @@ def list_soils_global(lon, lat):
500514
)
501515
)
502516
for row in zip(
503-
ID,
504-
Site,
505-
hz_lyrs,
506-
snd_lyrs,
507-
cly_lyrs,
508-
txt_lyrs,
509-
rf_lyrs,
510-
cec_lyrs,
511-
ph_lyrs,
512-
ec_lyrs
517+
ID, Site, hz_lyrs, snd_lyrs, cly_lyrs, txt_lyrs, rf_lyrs, cec_lyrs, ph_lyrs, ec_lyrs
513518
)
514519
]
515520

@@ -567,7 +572,7 @@ def rank_soils_global(
567572
rfvDepth,
568573
lab_Color,
569574
bedrock,
570-
cracks
575+
cracks,
571576
):
572577
# ------------------------------------------------------------------------------------------------
573578
# ------ Load in user data --------#
@@ -687,9 +692,7 @@ def rank_soils_global(
687692

688693
# Construct final dataframe with adjusted data
689694
p_compname = pd.Series("sample_pedon", index=np.arange(len(p_sandpct_intpl)))
690-
p_hz_data = pd.concat(
691-
[p_compname, p_sandpct_intpl, p_claypct_intpl, p_cfg_intpl], axis=1
692-
)
695+
p_hz_data = pd.concat([p_compname, p_sandpct_intpl, p_claypct_intpl, p_cfg_intpl], axis=1)
693696
p_hz_data.columns = [
694697
"compname",
695698
"sandpct_intpl",
@@ -1169,12 +1172,9 @@ def rank_soils_global(
11691172
and "leptosols" in row["compname"].lower()
11701173
):
11711174
D_final_loc.at[i, "Score_Data_Loc"] = 1.001
1172-
elif (
1173-
(bedrock is None or bedrock > 50)
1174-
and any(
1175-
term in row["compname"].lower()
1176-
for term in ["lithosols", "leptosols", "rendzinas", "rankers"]
1177-
)
1175+
elif (bedrock is None or bedrock > 50) and any(
1176+
term in row["compname"].lower()
1177+
for term in ["lithosols", "leptosols", "rendzinas", "rankers"]
11781178
):
11791179
D_final_loc.at[i, "Score_Data_Loc"] = 0.001
11801180

@@ -1243,9 +1243,7 @@ def rank_soils_global(
12431243
"Score_Data_Loc",
12441244
"distance_score",
12451245
]
1246-
].fillna(
1247-
0.0
1248-
)
1246+
].fillna(0.0)
12491247

12501248
# Construct the output format
12511249
Rank = [
@@ -1280,6 +1278,7 @@ def rank_soils_global(
12801278

12811279
return output_data
12821280

1281+
12831282
##################################################################################################
12841283
# getSoilGridsGlobal #
12851284
##################################################################################################
@@ -1355,7 +1354,9 @@ def sg_list(lon, lat):
13551354
# The code assumes each property repeats over the same set of depths.
13561355
n_depths = len(df_top_depth)
13571356
if len(names) % n_depths != 0:
1358-
logging.warning("Number of property names isn't a multiple of the number of depths. Check data.")
1357+
logging.warning(
1358+
"Number of property names isn't a multiple of the number of depths. Check data."
1359+
)
13591360
df_names = pd.DataFrame(names, columns=["prop"])
13601361

13611362
# 5. Combine everything into a single DataFrame.
@@ -1374,7 +1375,7 @@ def sg_list(lon, lat):
13741375
index="bottom_depth",
13751376
columns="prop",
13761377
values="value",
1377-
aggfunc="first" # Change the aggregator if needed
1378+
aggfunc="first", # Change the aggregator if needed
13781379
)
13791380
except Exception as e:
13801381
logging.error(f"Error pivoting the data: {e}")
@@ -1427,7 +1428,23 @@ def sg_list(lon, lat):
14271428
TAXNWRB_pd.index = [f"Rank{i+1}" for i in range(ranks_needed)]
14281429
except Exception as e:
14291430
logging.error(f"Error processing WRB classification: {e}")
1430-
TAXNWRB_pd = pd.DataFrame({
1431+
TAXNWRB_pd = pd.DataFrame(
1432+
{
1433+
"WRB_tax": [""],
1434+
"Prob": [""],
1435+
"Description_en": [""],
1436+
"Management_en": [""],
1437+
"Description_es": [""],
1438+
"Management_es": [""],
1439+
"Description_ks": [""],
1440+
"Management_ks": [""],
1441+
"Description_fr": [""],
1442+
"Management_fr": [""],
1443+
}
1444+
)
1445+
else:
1446+
TAXNWRB_pd = pd.DataFrame(
1447+
{
14311448
"WRB_tax": [""],
14321449
"Prob": [""],
14331450
"Description_en": [""],
@@ -1438,20 +1455,8 @@ def sg_list(lon, lat):
14381455
"Management_ks": [""],
14391456
"Description_fr": [""],
14401457
"Management_fr": [""],
1441-
})
1442-
else:
1443-
TAXNWRB_pd = pd.DataFrame({
1444-
"WRB_tax": [""],
1445-
"Prob": [""],
1446-
"Description_en": [""],
1447-
"Management_en": [""],
1448-
"Description_es": [""],
1449-
"Management_es": [""],
1450-
"Description_ks": [""],
1451-
"Management_ks": [""],
1452-
"Description_fr": [""],
1453-
"Management_fr": [""],
1454-
})
1458+
}
1459+
)
14551460

14561461
# 12. Gather aggregated values for each property
14571462
depths = sg_data_w["hzdepb_r"]
@@ -1461,10 +1466,7 @@ def sg_list(lon, lat):
14611466
pH_pd = sg_data_w["phh2o"]
14621467
cec_pd = sg_data_w["cec"]
14631468
# 13. Additional texture calculations from aggregated values
1464-
texture_pd = pd.DataFrame({
1465-
"sand": sand_pd,
1466-
"clay": clay_pd
1467-
})
1469+
texture_pd = pd.DataFrame({"sand": sand_pd, "clay": clay_pd})
14681470
texture_pd["sand"] = pd.to_numeric(texture_pd["sand"], errors="coerce")
14691471
texture_pd["clay"] = pd.to_numeric(texture_pd["clay"], errors="coerce")
14701472
texture_pd["silt"] = texture_pd.apply(silt_calc, axis=1)
@@ -1530,7 +1532,4 @@ def sg_list(lon, lat):
15301532
},
15311533
}
15321534

1533-
return {
1534-
"metadata": metadata,
1535-
"soilGrids": SoilGrids
1536-
}
1535+
return {"metadata": metadata, "soilGrids": SoilGrids}

0 commit comments

Comments
 (0)