geocif 0.2.37__tar.gz → 0.2.39__tar.gz

{geocif-0.2.37/geocif.egg-info → geocif-0.2.39}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.37
+Version: 0.2.39
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.37 → geocif-0.2.39}/geocif/geocif.py

@@ -786,7 +786,7 @@ class Geocif:
         """ Train, Predict, Explain and Store results for each region """
         pbar = tqdm(self.df_train["Region_ID"].unique(), leave=False)
         for idx, region in enumerate(pbar):
-            if self.model_name in ["linear", "gam"]:
+            if self.model_name in ["linear"]:
                 self.create_feature_names(stages, dict_best_cei[region][0:3].tolist())
             elif self.model_name in ["cumulative_1", "cumulative_2", "cumulative_3"]:
                 self.create_feature_names(stages, {})
@@ -831,16 +831,16 @@ class Geocif:
             df_region_train = df_region_train.dropna(subset=[self.target_column])
 
             self.X_train = df_region_train[self.feature_names]
+
             # Drop any columns with NaNs except the lag yield columns
             lag_prefix = "t -"
-            lag_cols = [
-                col for col in self.X_train.columns
-                if col.startswith(lag_prefix) and self.target in col
-            ]
-
-            cols_with_na = self.X_train.columns[self.X_train.isna().any()]
-            cols_to_check = [col for col in cols_with_na if col not in lag_cols]
-            self.X_train.dropna(axis=1, how="any", subset=cols_to_check, inplace=True)
+            lag_cols = [c for c in self.X_train.columns if c.startswith(lag_prefix)]
+            self.X_train = (
+                self.X_train
+                .drop(columns=lag_cols)  # temporarily remove the lag-yield cols
+                .dropna(axis=1, how="any")  # drop cols with any NA left
+                .join(self.X_train[lag_cols])  # add lag-yield cols back untouched
+            )
             self.y_train = df_region_train[self.target_column]
 
             self.apply_feature_selector(region, dir_output)
@@ -1270,8 +1270,8 @@ class Geocif:
 
                 try:
                     self.loop_ml(stage, dict_selected_features, dict_best_cei)
-                except:
-                    pass
+                except Exception as e:
+                    self.logger.error(e)
         wandb.finish()
 
     def setup(self, forecast_season, model):

{geocif-0.2.37 → geocif-0.2.39}/geocif/ml/trainers.py

@@ -351,9 +351,14 @@ def auto_train(
                 "cumulative_3": s(0) + s(1) + s(2) + te(0, 1) + te(0, 2) + te(1, 2) + f(3),
             }
 
-            formula = gam_formulas.get(model_name, gam_cls(n_splines=25, spline_order=3))
-            model = GAM(formula).gridsearch(X_train.values, y_train.values, lam=np.logspace(-3, 3, 11)) if model_name.startswith("gam") else formula
+            # Fill nans with medians
+            for col in X_train.columns:
+                if X_train[col].isnull().any():
+                    median = X_train[col].median()
+                    X_train[col].fillna(median, inplace=True)
 
+            formula = gam_formulas.get(model_name, gam_cls(n_splines=25, spline_order=3))
+            model = gam_cls(n_splines=25, spline_order=3).gridsearch(X_train, y_train.values, lam=np.logspace(-3, 3, 11)) if model_name.startswith("gam") else formula
         elif model_name == "geospaNN":
             import torch
             import geospaNN

{geocif-0.2.37 → geocif-0.2.39/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.37
+Version: 0.2.39
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.37 → geocif-0.2.39}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.2.37",
+    version="0.2.39",
     zip_safe=False,
 )