geocif 0.1.39__tar.gz → 0.1.41__tar.gz

{geocif-0.1.39/geocif.egg-info → geocif-0.1.41}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.39
+Version: 0.1.41
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.39 → geocif-0.1.41}/geocif/experiments.py

@@ -15,6 +15,10 @@ warnings.simplefilter(action="ignore", category=FutureWarning)
 
 
 def main(inputs, logger, parser, section, item, type, values):
+    # Set experiment_name
+    experiment_name = f"{section}_{item}"
+    parser.set("DEFAULT", "experiment_name", experiment_name)
+
     if type == "str":
         original_value = parser.get(section, item)
     elif type == "bool":
@@ -49,13 +53,25 @@ def run(path_config_files=[Path("../config/geocif.txt")]):
     logger.info("\tStarting GEOCIF Experiments")
     logger.info("=============================")
 
-    # Experiment 1: include_lat_lon
+    # Experiment: Models
+    logger.info("Experiment 0: Models")
+    parser = main(
+        inputs,
+        logger,
+        parser,
+        "DEFAULT",
+        "model",
+        "str",
+        ["catboost", "merf", "linear"],
+    )
+
+    # Experiment: include_lat_lon
     logger.info("Experiment 1: include_lat_lon")
     parser = main(
         inputs, logger, parser, "ML", "include_lat_lon", "bool", [True, False]
     )
 
-    # Experiment 2: feature_selection
+    # Experiment: feature_selection
     logger.info("Experiment 2: feature_selection")
     parser = main(
         inputs,
@@ -67,13 +83,13 @@ def run(path_config_files=[Path("../config/geocif.txt")]):
         ["SelectKBest", "BorutaPy", "Leshy", "RFECV", "RFE"],
     )
 
-    # Experiment 3: lag_years
+    # Experiment: lag_years
     logger.info("Experiment 3: lag_years")
     parser = main(
         inputs, logger, parser, "ML", "lag_years", "int", [1, 2, 3, 4, 5]
     )
 
-    # Experiment 4: lag_yield_as_feature
+    # Experiment: lag_yield_as_feature
     logger.info("Experiment 4: lag_yield_as_feature")
     parser = main(
         inputs,
@@ -85,13 +101,13 @@ def run(path_config_files=[Path("../config/geocif.txt")]):
         [True, False],
     )
 
-    # Experiment 5: median_years
+    # Experiment: median_years
     logger.info("Experiment 5: median_years")
     parser = main(
         inputs, logger, parser, "ML", "median_years", "int", [2, 3, 4, 5]
     )
 
-    # Experiment 6: median_yield_as_feature
+    # Experiment: median_yield_as_feature
     logger.info("Experiment 6: median_yield_as_feature")
     parser = main(
         inputs,
@@ -103,7 +119,7 @@ def run(path_config_files=[Path("../config/geocif.txt")]):
         [True, False],
     )
 
-    # Experiment 7: analogous_year_yield_as_feature
+    # Experiment: analogous_year_yield_as_feature
     logger.info("Experiment 7: analogous_year_yield_as_feature")
     parser = main(
         inputs,
@@ -115,7 +131,7 @@ def run(path_config_files=[Path("../config/geocif.txt")]):
         [True, False],
     )
 
-    # Experiment 8: optimize
+    # Experiment: optimize
     logger.info("Experiment 8: optimize")
     parser = main(
         inputs, logger, parser, "DEFAULT", "optimize", "bool", [True, False]

{geocif-0.1.39 → geocif-0.1.41}/geocif/geocif.py

@@ -132,6 +132,9 @@ class Geocif:
         self.median_yield_as_feature = self.parser.getboolean(
             "ML", "median_yield_as_feature"
         )
+        self.median_area_as_feature = self.parser.getboolean(
+            "ML", "median_area_as_feature"
+        )
         self.number_lag_years = self.parser.getint("ML", "lag_years")
         self.cluster_strategy = self.parser.get("ML", "cluster_strategy")
         self.feature_selection = self.parser.get("ML", "feature_selection")
@@ -644,6 +647,7 @@ class Geocif:
                 kwargs = {
                     "cluster_strategy": self.cluster_strategy,
                     "model": self.model,
+                    "model_name": self.model_name,
                     "forecast_season": self.forecast_season,
                     "crop": self.crop,
                     "country": self.country,
@@ -659,6 +663,7 @@ class Geocif:
                 model = self.model.estimator_
             else:
                 model = self.model
+
             output.store(self.db_path, experiment_id, df, model, self.model_name)
 
     def get_cei_column_names(self, df):
@@ -734,10 +739,15 @@ class Geocif:
             df = fe.compute_last_year_yield(df)
 
         if self.median_yield_as_feature:
-            df = fe.compute_median_yield(
+            df = fe.compute_median_statistics(
                 df, self.all_seasons_with_yield, self.number_median_years
             )
 
+        if self.median_area_as_feature:
+            df = fe.compute_median_statistics(
+                df, self.all_seasons_with_area, self.number_median_years, "Area (ha)"
+            )
+
         if self.lag_yield_as_feature:
             df = fe.compute_lag_yield(
                 df, self.all_seasons_with_yield, self.number_lag_years
@@ -1105,6 +1115,10 @@ def loop_execute(inputs):
     with PyCallGraph(output=graphviz, config=config):
         country, crop, season, model, logger, parser = inputs
 
+        logger.info("=====================================================")
+        logger.info(f"\tStarting GEOCIF: {country} {crop} {season} {model}")
+        logger.info("=====================================================")
+
         obj = Geocif(logger=logger, parser=parser)
         obj.read_data(country, crop, season)
 
@@ -1176,10 +1190,6 @@ def main(logger, parser):
     Returns:
 
     """
-    logger.info("===========================")
-    logger.info("\tStarting GEOCIF")
-    logger.info("===========================")
-
     inputs = gather_inputs(parser)
     execute_models(inputs, logger, parser)
 

{geocif-0.1.39 → geocif-0.1.41}/geocif/indices_runner_v2.py

@@ -157,7 +157,7 @@ class cei_runner(base.BaseGeo):
                 "ndvi",
                 False,  # redo
             )
-            for year in range(2024, ar.utcnow().year + 1)
+            for year in range(2001, ar.utcnow().year + 1)
             for status, path, filename, admin_zone, category in combinations
         ]
 

{geocif-0.1.39 → geocif-0.1.41}/geocif/ml/feature_engineering.py

@@ -62,7 +62,7 @@ def compute_closest_years(all_years, harvest_year, number_lag_years):
     return closest_years.tolist()
 
 
-def compute_median_yield(
+def compute_median_statistics(
     df, all_seasons_with_yield, number_median_years, target_col="Yield (tn per ha)"
 ):
     """

{geocif-0.1.39 → geocif-0.1.41}/geocif/ml/output.py

@@ -107,6 +107,7 @@ def store(db_path, experiment_id, df, model, model_name):
     try:
         utils.to_db(db_path, experiment_id, df)
     except Exception as e:
+        breakpoint()
         print(f"Error: {e}")
 
     index_columns = ["Country", "Region", "Crop", "Harvest Year", "Stages"]
@@ -127,6 +128,7 @@ def store(db_path, experiment_id, df, model, model_name):
         df_model.index.set_names(["Index"], inplace=True)
         utils.to_db(db_path, "models", df_model)
     except Exception as e:
+        breakpoint()
         print(f"Error: {e}")
 
     con.commit()

{geocif-0.1.39 → geocif-0.1.41}/geocif/ml/xai.py

@@ -8,6 +8,7 @@ from tqdm import tqdm
 def explain(df_train, df_test, **kwargs):
     cluster_strategy = kwargs.get("cluster_strategy", "auto_detect")
     model = kwargs.get("model")
+    model_name = kwargs.get("model_name")
     forecast_season = kwargs.get("forecast_season")
     crop = kwargs.get("crop")
     country = kwargs.get("country")
@@ -48,7 +49,7 @@ def explain(df_train, df_test, **kwargs):
     plt.tight_layout()
 
     fname = f"beeswarm_{region_name}_{forecast_season}.png"
-    out_dir = analysis_dir / country / crop / str(forecast_season)
+    out_dir = analysis_dir / country / crop / model_name / str(forecast_season)
     os.makedirs(out_dir, exist_ok=True)
     plt.savefig(out_dir / fname, dpi=250)
     plt.close()

{geocif-0.1.39 → geocif-0.1.41}/geocif/utils.py

@@ -332,7 +332,7 @@ def create_output_directory(method, admin_zone, country, crop, path_output):
 
     :return:
     """
-    dir_output = path_output / "fao" / "indices" / method / admin_zone / country / crop
+    dir_output = path_output / "cei" / "indices" / method / admin_zone / country / crop
     os.makedirs(dir_output, exist_ok=True)
 
     return dir_output

{geocif-0.1.39 → geocif-0.1.41/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.39
+Version: 0.1.41
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.39 → geocif-0.1.41}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.39",
+    version="0.1.41",
     zip_safe=False,
 )