geocif 0.2.36__tar.gz → 0.2.38__tar.gz

{geocif-0.2.36/geocif.egg-info → geocif-0.2.38}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.36
+Version: 0.2.38
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.36 → geocif-0.2.38}/geocif/geocif.py

@@ -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)
@@ -1270,7 +1270,8 @@ class Geocif:
 
                 try:
                     self.loop_ml(stage, dict_selected_features, dict_best_cei)
-                except:
+                except Exception as e:
+                    breakpoint()
                     pass
         wandb.finish()
 

{geocif-0.2.36 → geocif-0.2.38}/geocif/ml/correlations.py

@@ -199,6 +199,7 @@ def _all_correlated_feature_by_time(df, **kwargs):
 
     # Only select columns that have been observed till the current stage
     pbar = tqdm(stages_features, total=len(stages_features), leave=False)
+
     for stage in pbar:
         pbar.set_description(f"Calculating correlations")
         pbar.update()

{geocif-0.2.36 → geocif-0.2.38/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.36
+Version: 0.2.38
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.36 → geocif-0.2.38}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.2.36",
+    version="0.2.38",
     zip_safe=False,
 )