geocif 0.2.26__tar.gz → 0.2.28__tar.gz

{geocif-0.2.26/geocif.egg-info → geocif-0.2.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.26
+Version: 0.2.28
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.26 → geocif-0.2.28}/geocif/geocif.py

@@ -211,7 +211,7 @@ class Geocif:
         # obj_pickle = outlook.Outlook(self.pickle_file)
         # self.df_outlook = obj_pickle.read_outlook_file()
 
-    def apply_feature_selector(self, dir_output):
+    def apply_feature_selector(self, region, dir_output):
         if self.model_name in ["cumulative_1", "cumulative_2", "cumulative_3"]:
             all_features = self.X_train.columns
 
@@ -224,7 +224,11 @@ class Geocif:
         else:
             self.logger.info(f"Selecting features for {self.country} {self.crop}")
             selector, _, self.selected_features = fs.select_features(
-                self.X_train, self.y_train, method=self.feature_selection, dir_output=dir_output
+                self.X_train,
+                self.y_train,
+                method=self.feature_selection,
+                dir_output=dir_output,
+                region=region
             )
             self.logger.info(f"Selected features: {self.selected_features}")
 
@@ -837,8 +841,8 @@ class Geocif:
             # Drop any columns with NaNs
             self.X_train.dropna(axis=1, how="any", inplace=True)
             self.y_train = df_region_train[self.target_column]
-            breakpoint()
-            self.apply_feature_selector(dir_output)
+
+            self.apply_feature_selector(region, dir_output)
             self.train_model(df_region_train, scaler, dir_output)
 
             """ Predict """

{geocif-0.2.26 → geocif-0.2.28}/geocif/ml/feature_selection.py

@@ -1,3 +1,5 @@
+import os
+
 import numpy as np
 from tqdm import tqdm
 from sklearn.ensemble import RandomForestRegressor
@@ -38,7 +40,8 @@ def select_features(
     min_features_to_select=3,
     threshold_nan=0.2,
     threshold_unique=0.6,
-    dir_output="."
+    dir_output=".",
+    region=None
 ):
     """
     Feature-selection wrapper supporting many methods plus a new 'multi' option.
@@ -102,7 +105,8 @@ def select_features(
         plt.tight_layout()
 
         dir_output = dir_output / Path("feature_selection")
-        fig.savefig(dir_output / "feature_selection_frequency.png", dpi=300)
+        os.makedirs(dir_output, exist_ok=True)
+        fig.savefig(dir_output / f"feature_selection_frequency_{region}.png", dpi=300)
         plt.close(fig)
 
         return None, X_out, combined

{geocif-0.2.26 → geocif-0.2.28/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.2.26
+Version: 0.2.28
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.2.26 → geocif-0.2.28}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.2.26",
+    version="0.2.28",
     zip_safe=False,
 )