geocif 0.1.62__tar.gz → 0.1.63__tar.gz

{geocif-0.1.62/geocif.egg-info → geocif-0.1.63}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.62
+Version: 0.1.63
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.62 → geocif-0.1.63}/geocif/geocif.py

@@ -308,9 +308,12 @@ class Geocif:
                         cat_features=self.cat_features,
                         verbose=False,
                     )
-                elif self.model_name == "ngboost":
-                    self.model.fit(X_train, y_train)
-                elif self.model_name in ["oblique"]:
+                elif self.model_name in ["ngboost", "oblique", "tabpfn"]:
+                    X_train = X_train.drop(
+                        columns=[
+                            item for item in self.cat_features if item != "Harvest Year"
+                        ]
+                    )
                     self.model.fit(X_train, y_train)
                 elif self.model_name == "ydf":
                     # Combine X_train and y_train
@@ -517,6 +520,14 @@ 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"
+                    ]
+                )
+                y_pred = self.model.predict(X_test)
+                best_hyperparameters = {}
             else:
                 y_pred = self.model.predict(X_test)
                 best_hyperparameters = self.model.get_params().copy()
@@ -1280,6 +1291,9 @@ class Geocif:
                 self.cluster_strategy = "single"
                 self.select_cei_by = "Index"
                 self.use_cumulative_features = True
+            elif self.model_name in ["tabpfn"]:
+                self.do_xai = False
+                self.estimate_ci = False
             elif self.model_name in ["oblique", "ydf"]:
                 self.do_xai = False
                 self.estimate_ci = False
@@ -1360,6 +1374,9 @@ class Geocif:
         if self.country == "nepal":
             self.dg["ADM0_NAME"] = "nepal"
             self.dg["Country Region"] = self.dg["ADM0_NAME"] + " " + self.dg["PR_NAME"]
+        elif self.country == "wolayita":
+            self.dg["ADM0_NAME"] = "ethiopia"
+            self.dg["Country Region"] = self.dg["ADM0_NAME"] + " " + self.dg["W_NAME"]
         elif self.admin_zone == "admin_1":
             self.dg["Country Region"] = (
                 self.dg["ADM0_NAME"] + " " + self.dg["ADM1_NAME"]

{geocif-0.1.62 → geocif-0.1.63}/geocif/geocif_runner.py

@@ -26,40 +26,41 @@ def loop_execute(inputs):
     Returns:
 
     """
-    from pycallgraph2 import Config, PyCallGraph, GlobbingFilter
-    from pycallgraph2.output import GraphvizOutput
-
-    graphviz = GraphvizOutput()
-    graphviz.output_file = "geocif_visualization.png"
-    plt.rcParams["figure.dpi"] = 600
-    config = Config(max_depth=5)
-    config.trace_filter = GlobbingFilter(
-        exclude=[
-            "pycallgraph.*",
-        ]
-    )
-
-    with PyCallGraph(output=graphviz, config=config):
-        project_name, country, crop, season, model, logger, parser, index = inputs
-
-        logger.info("=====================================================")
-        logger.info(f"\tStarting GEOCIF: {country} {crop} {season} {model}")
-        logger.info("=====================================================")
-
-        obj = geocif.Geocif(logger=logger,
-                            parser=parser,
-                            project_name=project_name)
-        obj.read_data(country, crop, season)
-
-        # Store config file in database, only execute this for
-        # the first iteration of the loop
-        if index == 0:
-            output.config_to_db(obj.db_path, obj.parser, obj.today)
-
-        # Setup metadata and run ML code
-        obj.setup(season, model)
-        if obj.simulation_stages:
-            obj.execute()
+    # from pycallgraph2 import Config, PyCallGraph, GlobbingFilter
+    # from pycallgraph2.output import GraphvizOutput
+    #
+    # graphviz = GraphvizOutput()
+    # graphviz.output_file = "geocif_visualization.png"
+    # plt.rcParams["figure.dpi"] = 600
+    # config = Config(max_depth=5)
+    # config.trace_filter = GlobbingFilter(
+    #     exclude=[
+    #         "pycallgraph.*",
+    #         "torch*",
+    #     ]
+    # )
+    #
+    # with PyCallGraph(output=graphviz, config=config):
+    project_name, country, crop, season, model, logger, parser, index = inputs
+
+    logger.info("=====================================================")
+    logger.info(f"\tStarting GEOCIF: {country} {crop} {season} {model}")
+    logger.info("=====================================================")
+
+    obj = geocif.Geocif(logger=logger,
+                        parser=parser,
+                        project_name=project_name)
+    obj.read_data(country, crop, season)
+
+    # Store config file in database, only execute this for
+    # the first iteration of the loop
+    if index == 0:
+        output.config_to_db(obj.db_path, obj.parser, obj.today)
+
+    # Setup metadata and run ML code
+    obj.setup(season, model)
+    if obj.simulation_stages:
+        obj.execute()
 
 
 def gather_inputs(parser):

{geocif-0.1.62 → geocif-0.1.63}/geocif/indices_runner_angola.py

@@ -12,7 +12,7 @@ warnings.filterwarnings("ignore")
 from .cei import indices
 from geoprepare import base
 
-country = "wolayita"
+country = "ethiopia"
 
 def remove_duplicates(lst):
     """
@@ -171,10 +171,10 @@ class cei_runner(base.BaseGeo):
         # Only keep those entries in combinations where the third elemt is
         # mozambique, south_africa, angola or dem_people's_rep_of_korea
         # This is done to test the code for these countries
-        combinations = [i for i in combinations if f"{country}_maize_s1" in i[3]]
+        combinations = [i for i in combinations if f"{country}_wheat_s1" in i[3]]
 
         if True:
-            num_cpu = int(cpu_count() * 0.5)
+            num_cpu = int(cpu_count() * 0.9)
             with Pool(num_cpu) as p:
                 for i, _ in enumerate(p.imap_unordered(indices.process, combinations)):
                     pass

{geocif-0.1.62 → geocif-0.1.63}/geocif/ml/trainers.py

@@ -300,6 +300,10 @@ def auto_train(
                 n_estimators=1500, max_depth=20, max_features=n_features**2,
                 feature_combinations=n_features, n_jobs=-1, random_state=42
             )
+        elif model_name == "tabpfn":
+            from tabpfn_extensions.post_hoc_ensembles.sklearn_interface import AutoTabPFNRegressor
+
+            model = AutoTabPFNRegressor()
         elif model_name == "ngboost":
             if model_type == "REGRESSION":
                 from ngboost import NGBRegressor

{geocif-0.1.62 → geocif-0.1.63/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.62
+Version: 0.1.63
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.62 → geocif-0.1.63}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.62",
+    version="0.1.63",
     zip_safe=False,
 )