geocif 0.2.54__tar.gz → 0.2.57__tar.gz

{geocif-0.2.54/geocif.egg-info → geocif-0.2.57}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.54
+Version: 0.2.57
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.54 → geocif-0.2.57}/geocif/geocif.py

@@ -296,12 +296,21 @@ class Geocif:
                         cat_features=self.cat_features,
                         verbose=False,
                     )
-                elif self.model_name in ["ngboost", "oblique", "tabpfn"]:
+                elif self.model_name in ["tabpfn"]:
+                    # Identify the column indices for cat_features in X_train
+                    if self.cat_features is None:
+                        cat_feature_indices = []
+                    cat_feature_indices = [X_train.columns.get_loc(col) for col in self.cat_features if
+                        col in X_train.columns]
+
+                    self.model.fit(X_train, self.y_train, categorical_feature_indices=cat_feature_indices)
+                elif self.model_name in ["ngboost", "oblique"]:
                     X_train = X_train.drop(
                         columns=[
                             item for item in self.cat_features if item != "Harvest Year"
                         ]
                     )
+
                     self.model.fit(X_train, self.y_train)
                 elif self.model_name == "ydf":
                     # Combine X_train and y_train
@@ -367,6 +376,8 @@ class Geocif:
                     X_train_scaled = pd.concat([X_scaled_numeric, X_region], axis=1)
 
                     self.model.fit(X_train_scaled, self.y_train)
+                elif self.model_name in ["desreg"]:
+                    self.model.fit(X_train, self.y_train)
             except Exception as e:
                 self.logger.error(
                     f"Error fitting model for {self.country} {self.crop} {e}"
@@ -511,12 +522,7 @@ class Geocif:
             elif self.model_name == "ydf":
                 y_pred = self.model.evaluate(X_test)
                 best_hyperparameters = {}
-            elif self.model_name == "tabpfn":
-                X_test = X_test.drop(
-                    columns=[
-                        item for item in self.cat_features if item != "Harvest Year"
-                    ]
-                )
+            elif self.model_name in ["tabpfn", "desreg"]:
                 y_pred = self.model.predict(X_test)
                 best_hyperparameters = {}
             else:
@@ -1353,7 +1359,7 @@ class Geocif:
                 self.cluster_strategy = "single"
                 self.select_cei_by = "Index"
                 self.use_cumulative_features = True
-            elif self.model_name in ["tabpfn"]:
+            elif self.model_name in ["tabpfn", "desreg"]:
                 self.do_xai = False
                 self.estimate_ci = False
             elif self.model_name in ["oblique", "ydf"]:

{geocif-0.2.54 → geocif-0.2.57}/geocif/ml/trainers.py

@@ -306,11 +306,29 @@ def auto_train(
             # Identify the column indices for cat_features in X_train
             if cat_features is None:
                 cat_feature_indices = []
-            cat_feature_indices = [X_train.columns.get_loc(col) for col in cat_features if
-                col in X_train.columns]
+            else:
+                cat_feature_indices = [X_train.columns.get_loc(col) for col in cat_features if
+                    col in X_train.columns]
+
             model = AutoTabPFNRegressor(max_time=600,
-                                        categorical_feature_indices=cat_feature_indices,
+                                        #categorical_feature_indices=cat_feature_indices,
                                         ignore_pretraining_limits=True)
+        elif model_name == "desreg":
+            from desReg.des.DESRegression import DESRegression
+
+            model_catboost = CatBoostRegressor(**hyperparams, cat_features=cat_features)
+                        from tabpfn_extensions.post_hoc_ensembles.sklearn_interface import AutoTabPFNRegressor
+
+            # Identify the column indices for cat_features in X_train
+            if cat_features is None:
+                cat_feature_indices = []
+            else:
+                cat_feature_indices = [X_train.columns.get_loc(col) for col in cat_features if
+                    col in X_train.columns]
+            model_tabpfn = AutoTabPFNRegressor(max_time=600,
+                                               # categorical_feature_indices=cat_feature_indices,
+                                               ignore_pretraining_limits=True)
+            model = DESRegression(regressors_list=[model_catboost, model_tabpfn])
         elif model_name == "ngboost":
             if model_type == "REGRESSION":
                 from ngboost import NGBRegressor

{geocif-0.2.54 → geocif-0.2.57/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.54
+Version: 0.2.57
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.54 → geocif-0.2.57}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.2.54",
+    version="0.2.57",
     zip_safe=False,
 )