geocif 0.1.93__tar.gz → 0.1.94__tar.gz

{geocif-0.1.93/geocif.egg-info → geocif-0.1.94}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.93
+Version: 0.1.94
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.93 → geocif-0.1.94}/geocif/geocif.py

@@ -1020,45 +1020,25 @@ class Geocif:
             # Drop those columns
 
             df = df.drop(columns=cols_to_drop)
-        from collections import Counter
-        esi_cols = df.filter(like="AUC_ESI4WK").columns.tolist()
-        dupes = {k: v for k, v in Counter(esi_cols).items() if v > 1}
-        print("<0>", dupes)
-        # Hack: If
+
         # Change column name
         # e.g. 'vDTR_7_6_5_4_3_2_1_37_36_35_34_33_32_31' to 'vDTR Mar 1-Oct 27'
         df = stages.update_feature_names(df, self.method)
-        from collections import Counter
-        esi_cols = df.filter(like="AUC_ESI4WK").columns.tolist()
-        dupes = {k: v for k, v in Counter(esi_cols).items() if v > 1}
-        print("<111>", dupes)
+
         all_cei_columns = self.get_cei_column_names(df)
         # Fill in any missing values with 0
         df.loc[:, all_cei_columns].fillna(0, inplace=True)
-        from collections import Counter
-        esi_cols = df.filter(like="AUC_ESI4WK").columns.tolist()
-        dupes = {k: v for k, v in Counter(esi_cols).items() if v > 1}
-        print("<1>", dupes)
 
         df = fe.compute_last_year_yield(df, self.target)
-        from collections import Counter
-        esi_cols = df.filter(like="AUC_ESI4WK").columns.tolist()
-        dupes = {k: v for k, v in Counter(esi_cols).items() if v > 1}
-        print("<2>", dupes)
+
         df = fe.compute_median_statistics(
             df, self.all_seasons_with_yield, self.number_median_years, self.target
         )
-        from collections import Counter
-        esi_cols = df.filter(like="AUC_ESI4WK").columns.tolist()
-        dupes = {k: v for k, v in Counter(esi_cols).items() if v > 1}
-        print("<3>", dupes)
+
         df = fe.compute_user_median_statistics(df, range(2018, 2023))
 
         df = fe.compute_user_median_statistics(df, range(2013, 2018))
-        from collections import Counter
-        esi_cols = df.filter(like="AUC_ESI4WK").columns.tolist()
-        dupes = {k: v for k, v in Counter(esi_cols).items() if v > 1}
-        print("<4>", dupes)
+
         if self.median_area_as_feature:
             df = fe.compute_median_statistics(
                 df, self.all_seasons_with_yield, self.number_median_years, "Area (ha)"
@@ -1073,10 +1053,7 @@ class Geocif:
             df = fe.compute_analogous_yield(
                 df, self.all_seasons_with_yield, self.number_median_years, self.target
             )
-        from collections import Counter
-        esi_cols = df.filter(like="AUC_ESI4WK").columns.tolist()
-        dupes = {k: v for k, v in Counter(esi_cols).items() if v > 1}
-        print("5", dupes)
+
         # Create Region_ID column based on Region column category code
         df["Region"] = df["Region"].astype("category")
         if self.cluster_strategy == "single":
@@ -1090,7 +1067,7 @@ class Geocif:
 
             # Region_ID should be type category
             df["Region_ID"] = df["Region_ID"].astype("category")
-        breakpoint()
+
         return df
 
     def execute(self):
@@ -1147,7 +1124,14 @@ class Geocif:
 
         # Join with dg based on Country Region column, only keeping rows that are in df
         # Only use geometry column from self.dg
-        self.dg_country = self.dg_country[["Country Region", "geometry"]].merge(
+        if self.admin_zone == "admin_1":
+            cols = ["Country Region", "geometry", "ADM1_NAME"]
+        elif self.admin_zone == "admin_2":
+            cols = ["Country Region", "geometry", "ADM2_NAME"]
+        else:
+            raise ValueError(f"Unsopported {self.admin_zone}")
+
+        self.dg_country = self.dg_country[cols].merge(
             df[["Country Region", self.correlation_plot_groupby]],
             on="Country Region",
             how="outer",

{geocif-0.1.93 → geocif-0.1.94}/geocif/ml/embedding.py

@@ -47,7 +47,7 @@ def _compute_correlations(X, y):
                 r = pearsonr(y_filtered, f_series_filtered)[0]
                 feature_correlations[feature] = round(r, 3)
             except Exception as e:
-                print(f"Error computing correlation for {feature}: {e}")
+                # print(f"Error computing correlation for {feature}: {e}")
                 feature_correlations[feature] = np.nan
 
     return feature_correlations

{geocif-0.1.93 → geocif-0.1.94}/geocif/ml/stages.py

@@ -268,11 +268,6 @@ def update_feature_names(df, method):
         # Saving the result in the dictionary
         stages_info[element] = (cei, start_stage, end_stage, new_column_name)
 
-        # Check if any duplicates exist in the dictionary
-        if len(stages_info) != len(set(stages_info.values())):
-            breakpoint()
-            raise ValueError(f"Duplicate stage information found for {element}")
-    breakpoint()
     # For each column in df, check if it exists in stages_info, and
     # replace it with the new column name
     # Precompute the rename mapping outside the loop

{geocif-0.1.93 → geocif-0.1.94/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.93
+Version: 0.1.94
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.93 → geocif-0.1.94}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.93",
+    version="0.1.94",
     zip_safe=False,
 )