geocif 0.1.34__tar.gz → 0.1.35__tar.gz

{geocif-0.1.34/geocif.egg-info → geocif-0.1.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.34
+Version: 0.1.35
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.34 → geocif-0.1.35}/geocif/cei/indices.py

@@ -393,6 +393,7 @@ class CEIs:
             / self.admin_zone
             / self.country
         )
+
         os.makedirs(self.dir_output, exist_ok=True)
         os.makedirs(self.dir_intermediate, exist_ok=True)
 

{geocif-0.1.34 → geocif-0.1.35}/geocif/geocif.py

@@ -487,10 +487,9 @@ class Geocif:
             "Harvest Year",
             "Stage Name",
         ]
-        try:
-            df.index = df.apply(lambda row: "_".join([str(row[col]) for col in index_columns]), axis=1)
-        except Exception as e:
-            breakpoint()
+        df.index = df.apply(
+            lambda row: "_".join([str(row[col]) for col in index_columns]), axis=1
+        )
 
         # name the index level
         df.index.set_names(["Index"], inplace=True)

{geocif-0.1.34 → geocif-0.1.35}/geocif/indices_runner_v2.py

@@ -155,22 +155,21 @@ class cei_runner(base.BaseGeo):
                 "ndvi",
                 False,  # redo
             )
-            for year in range(2001, ar.utcnow().year + 1)
+            for year in range(2024, ar.utcnow().year + 1)
             for status, path, filename, admin_zone, category in combinations
         ]
 
         # 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 "ethiopia_maize_s1" in i[3]
-        #]
-        #                 "malawi" in i[2]]
-
-        if True:
-            num_cpu = int(cpu_count() * 0.8)
+        combinations = [
+           i
+           for i in combinations
+           if "malawi_maize_s1" in i[3]
+        ]
+
+        if False:
+            num_cpu = int(cpu_count() * 0.3)
             with Pool(num_cpu) as p:
                 for i, _ in enumerate(p.imap_unordered(indices.process, combinations)):
                     pass
@@ -198,7 +197,7 @@ def run(path_config_files=[]):
     indices.validate_index_definitions()
 
     for method in [
-        "phenological_stages",  # "dekad_r"  # "dekad_r"
+        "biweekly_r",  # "dekad_r"  # "dekad_r"
     ]:  # , "full_season", "phenological_stages", "fraction_season"]:
         obj = cei_runner(path_config_files)
         obj.main(method)

{geocif-0.1.34 → geocif-0.1.35}/geocif/ml/correlations.py

@@ -246,6 +246,7 @@ def all_correlated_feature_by_time(df, **kwargs):
     Returns:
 
     """
+    THRESHOLD = 0.1
     national_correlation = kwargs.get("national_correlation")
     group_by = kwargs.get("groupby")
     combined_dict = kwargs.get("combined_dict")
@@ -264,8 +265,16 @@ def all_correlated_feature_by_time(df, **kwargs):
             df_corr = df_corr.dropna(thresh=len(df_corr) / 2, axis=1)
 
             if not df_corr.empty:
-                df_tmp = df_corr[df_corr.columns[(df_corr.mean() > 0.1)]]
-                dict_selected_features[region_id] = df_tmp.columns
+                df_tmp = df_corr[df_corr.columns[(abs(df_corr.mean()) > THRESHOLD)]]
+                # Add the columns to dict_selected_features along with the absolute mean value
+                absolute_medians = df_tmp.abs().median()
+
+                # Create a DataFrame to display the column names and their absolute median values
+                absolute_median_df = absolute_medians.reset_index()
+                absolute_median_df.columns = ['CEI', 'Median']
+
+                # Add the CEI and Median value to dict_selected_features
+                dict_selected_features[region_id] = absolute_median_df
 
                 df_tmp2 = (
                     df_tmp.median(axis=0)
@@ -293,24 +302,31 @@ def all_correlated_feature_by_time(df, **kwargs):
             else:
                 # HACK
                 df_corr = _all_correlated_feature_by_time(df, **kwargs)
-                dict_selected_features[region_id] = df_corr.columns
-                dict_best_cei[region_id] = {}
 
-                # dict_selected_features[region_id] = dict_selected_features[0]
-                # dict_best_cei[region_id] = dict_best_cei[0]
-                # Combine all unique values from the existing dictionary elements
-                # combined_metrics = set()
-                # for key in dict_selected_features:
-                #     breakpoint()
-                #     combined_metrics.update(dict_selected_features[key])
-                #
-                # # Add the combined set as a new element with key 3
-                # dict_selected_features[region_id] = sorted(list(combined_metrics))
+                df_tmp = df_corr[df_corr.columns[(abs(df_corr.mean()) > THRESHOLD)]]
+                # Add the columns to dict_selected_features along with the absolute mean value
+                absolute_medians = df_tmp.abs().median()
+
+                # Create a DataFrame to display the column names and their absolute median values
+                absolute_median_df = absolute_medians.reset_index()
+                absolute_median_df.columns = ['CEI', 'Median']
+
+                # Add the CEI and Median value to dict_selected_features
+                dict_selected_features[region_id] = absolute_median_df
+                dict_best_cei[region_id] = {}
     else:
         df_corr = _all_correlated_feature_by_time(df, **kwargs)
-        dict_selected_features[0] = df_corr.columns
+        df_tmp = df_corr[df_corr.columns[(abs(df_corr.mean()) > THRESHOLD)]]
+        # Add the columns to dict_selected_features along with the absolute mean value
+        absolute_medians = df_tmp.abs().median()
+
+        # Create a DataFrame to display the column names and their absolute median values
+        absolute_median_df = absolute_medians.reset_index()
+        absolute_median_df.columns = ['CEI', 'Median']
+
+        # Add the CEI and Median value to dict_selected_features
+        dict_selected_features[0] = absolute_median_df
 
-        df_corr = df_corr[df_corr.columns[(df_corr.mean() > 0.1)]]
         plot_feature_corr_by_time(df_corr, **kwargs)
 
     return dict_selected_features, dict_best_cei

{geocif-0.1.34 → geocif-0.1.35/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.34
+Version: 0.1.35
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.34 → geocif-0.1.35}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.34",
+    version="0.1.35",
     zip_safe=False,
 )