geocif 0.2.60__tar.gz → 0.2.61__tar.gz

{geocif-0.2.60/geocif.egg-info → geocif-0.2.61}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.60
+Version: 0.2.61
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.60 → geocif-0.2.61}/geocif/geocif.py

@@ -250,7 +250,7 @@ class Geocif:
 
         """
         X_train = df_region[self.selected_features + self.cat_features]
-
+        print("dsdsdsds")
         # Drop columns in X_train that have any NaNs, log the number of columns dropped
         initial_columns = X_train.shape[1]
         X_train = X_train.dropna(axis=1, how="any")
@@ -325,7 +325,7 @@ class Geocif:
             elif self.model_name == "ydf":
                 # Combine X_train and y_train
                 df_train = pd.concat([X_train, self.y_train], axis=1)
-
+                breakpoint()
                 self.model = self.model.train(df_train)
             elif self.model_name == "geospaNN":
                 self.model.fit(
@@ -535,6 +535,7 @@ class Geocif:
                 ]
                 w_train = data_train.y - self.estimate(data_train.x)
             elif self.model_name == "ydf":
+                breakpoint()
                 y_pred = self.model.evaluate(X_test)
                 best_hyperparameters = {}
             elif self.model_name in ["tabpfn", "desreg"]:
@@ -871,7 +872,7 @@ class Geocif:
             self.y_train = df_region_train[self.target_column]
 
             self.apply_feature_selector(region, dir_output)
-
+            print("dsdsdsdswqqwqwq")
             if self.cluster_strategy == "individual":
                 region_name = self.df_train["Region"].unique()[idx]
                 pbar.set_description(f"Fit/Predict for {region_name}")
@@ -1562,4 +1563,5 @@ class Geocif:
             self.df_inputs.rename(
                 columns={self.target: self.new_name_target}, inplace=True
             )
-            self.target = "Yield"
+            self.target = self.new_name_target
+            self.target_column = self.new_name_target

{geocif-0.2.60 → geocif-0.2.61}/geocif/ml/trainers.py

@@ -369,7 +369,8 @@ def auto_train(
                 categorical_algorithm='RANDOM',
                 split_axis='SPARSE_OBLIQUE',
                 sparse_oblique_normalization='MIN_MAX',
-                sparse_oblique_num_projections_exponent=2.0
+                sparse_oblique_num_projections_exponent=2.0,
+                validation_ratio=0.0,
             )
             hyperparams = templates["benchmark_rank1v1"]
 

{geocif-0.2.60 → geocif-0.2.61/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.60
+Version: 0.2.61
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.60 → geocif-0.2.61}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.2.60",
+    version="0.2.61",
     zip_safe=False,
 )