geocif 0.1.81__tar.gz → 0.1.83__tar.gz

{geocif-0.1.81/geocif.egg-info → geocif-0.1.83}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.81
+Version: 0.1.83
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.81 → geocif-0.1.83}/geocif/cei/indices.py

@@ -555,7 +555,7 @@ class CEIs:
         if not col:
             raise ValueError(f"Unknown method: {self.method}")
 
-        stages = sorted(df[col].unique())
+        stages = df[col].unique()
         valid_stages = None
 
         if self.method == "phenological_stages":

{geocif-0.1.81 → geocif-0.1.83}/geocif/geocif.py

@@ -945,11 +945,12 @@ class Geocif:
         parts = all_cei_columns[-1].split("_")
         cei = parts[0] if parts[1].isdigit() else "_".join(parts[:2])
 
-        # For each region, find the column with the longest string in cei_column
-        group_by = ["Region"]
-        groups = df.groupby(group_by)
         if self.use_cumulative_features:
             frames = []
+            # For each region, find the column with the longest string in cei_column
+            group_by = ["Region"]
+            groups = df.groupby(group_by)
+
             for name, group in groups:
                 # Drop columns with all NaNs
                 group.dropna(axis=1, how="all", inplace=True)
@@ -1019,26 +1020,45 @@ 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)"
@@ -1053,7 +1073,10 @@ 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":
@@ -1067,7 +1090,7 @@ class Geocif:
 
             # Region_ID should be type category
             df["Region_ID"] = df["Region_ID"].astype("category")
-
+        breakpoint()
         return df
 
     def execute(self):
@@ -1474,7 +1497,8 @@ class Geocif:
             assert all_files, f"No files found in {_dir_country} with {file_name}"
 
             self.df_inputs = pd.concat(
-                (pd.read_csv(f) for f in all_files), ignore_index=True
+                (pd.read_csv(f, engine="pyarrow") for f in tqdm(all_files, desc="Reading CSVs", leave=False)),
+                ignore_index=True
             )
 
             self.df_inputs = stats.add_statistics(
@@ -1486,7 +1510,9 @@ class Geocif:
                 [self.target] + self.statistics_columns,
                 self.method,
             )
+
             """ Add information on starting and ending time period for each stage"""
+            self.logger.info("Adding starting and ending time period for each stage")
             self.df_inputs = stages.add_stage_information(self.df_inputs, self.method)
 
             self.df_inputs.to_csv(file, index=False)

{geocif-0.1.81 → geocif-0.1.83}/geocif/ml/embedding.py

@@ -32,7 +32,10 @@ def _compute_correlations(X, y):
         f_series = X[feature]
 
         # Ignore NaN values in either y or f_series
-        mask = ~(np.isnan(y) | np.isnan(f_series))
+        try:
+            mask = ~(np.isnan(y) | np.isnan(f_series))
+        except:
+            breakpoint()
         y_filtered = y[mask]
         f_series_filtered = f_series[mask]
 

{geocif-0.1.81 → geocif-0.1.83}/geocif/ml/stages.py

@@ -268,6 +268,11 @@ 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-0.1.81 → geocif-0.1.83/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.81
+Version: 0.1.83
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.81 → geocif-0.1.83}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.81",
+    version="0.1.83",
     zip_safe=False,
 )