geocif 0.1.69__tar.gz → 0.1.71__tar.gz

{geocif-0.1.69/geocif.egg-info → geocif-0.1.71}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.69
+Version: 0.1.71
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.69 → geocif-0.1.71}/geocif/analysis.py

@@ -560,12 +560,12 @@ class Geoanalysis:
         )
 
         # --- For computing median yields ---
-        # Compute median yield for 2014 - 2018
-        df_median_2014_2018 = (
-            df_all[df_all["Harvest Year"].between(2014, 2018)]
+        # Compute median yield for 2018 - 2022
+        df_median_2018_2022 = (
+            df_all[df_all["Harvest Year"].between(2018, 2022)]
             .groupby("Region")["Yield (tn per ha)"]
-            .median()
-            .rename(f"Median Yield (tn per ha) (2014-2018)")
+            .mean()
+            .rename(f"Median Yield (tn per ha) (2018-2022)")
             .reset_index()
         )
 
@@ -573,7 +573,7 @@ class Geoanalysis:
         df_median_2013_2017 = (
             df_all[df_all["Harvest Year"].between(2013, 2017)]
             .groupby("Region")["Yield (tn per ha)"]
-            .median()
+            .mean()
             .rename("Median Yield (tn per ha) (2013-2017)")
             .reset_index()
         )
@@ -581,7 +581,7 @@ class Geoanalysis:
         # Merge the median yield columns with the % of total production dataframe
         df_historic = (
             df_pct
-            .merge(df_median_2014_2018, on="Region", how="left")
+            .merge(df_median_2018_2022, on="Region", how="left")
             .merge(df_median_2013_2017, on="Region", how="left")
         )
 

{geocif-0.1.69 → geocif-0.1.71}/geocif/cei/indices.py

@@ -675,7 +675,7 @@ class CEIs:
                 elif "STD" in iname:
                     val = np.nanstd(eo_vals)
                 elif "AUC" in iname:
-                    val = np.trapz(eo_vals, dx=len(eo_vals))
+                    val = np.trapz(eo_vals)
                 elif "H-INDEX" in iname:
                     # Multiply by 10 for h-index to work
                     val = utils.compute_h_index(eo_vals * 10)

{geocif-0.1.69 → geocif-0.1.71}/geocif/geocif.py

@@ -997,6 +997,25 @@ class Geocif:
         if self.use_single_time_period_as_feature:
             df = stages.select_single_time_period_features(df)
 
+        # If forecasting for current season, then exclude the latest month data as it will be partial
+        # and will confuse the model
+        if self.forecast_season == self.today_year:
+            current_month = ar.utcnow().month
+
+            # Identify columns where the second chunk equals the current month index
+            cols_to_drop = []
+            for col in df.columns:
+                if "_" in col:
+                    mon = stages.get_stage_information_dict(col, self.method)['Starting Stage']
+
+                    if mon == current_month:
+                        cols_to_drop.append(col)
+
+            # Drop those columns
+
+            df = df.drop(columns=cols_to_drop)
+
+        # 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)
@@ -1343,7 +1362,11 @@ class Geocif:
         # e.g. _stages = ['13_12_11', '13_12_11_10', '13_12_11_10_9']
         # then self.simulation_stages = [array([13, 12, 11]), array([13, 12, 11, 10]), array([13, 12, 11, 10, 9])]
         # Drop stages in self.all_stages that do not have _ in them
-        self.all_stages = [element for element in self.all_stages if "_" in element]
+        # self.all_stages = [element for element in self.all_stages if "_" in element]
+
+        if self.forecast_season == self.today_year:
+            current_month = ar.utcnow().month
+            self.all_stages = [elem for elem in self.all_stages if not elem.startswith(str(current_month))]
 
         self.simulation_stages = [
             np.array([int(stage) for stage in s.split("_")]) for s in self.all_stages

{geocif-0.1.69 → geocif-0.1.71}/geocif/indices_runner_south_africa.py

@@ -162,7 +162,7 @@ class cei_runner(base.BaseGeo):
                 category,
                 year,
                 "ndvi",
-                False,  # redo
+                True,  # redo
             )
             for year in range(2001, ar.utcnow().year + 1)
             for status, path, filename, admin_zone, category in combinations
@@ -174,7 +174,7 @@ class cei_runner(base.BaseGeo):
         combinations = [i for i in combinations if f"{country}_maize_s1" in i[3]]
 
         if True:
-            num_cpu = int(cpu_count() * 0.1)
+            num_cpu = int(cpu_count() * 0.8)
             with Pool(num_cpu) as p:
                 for i, _ in enumerate(p.imap_unordered(indices.process, combinations)):
                     pass

{geocif-0.1.69 → geocif-0.1.71/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.69
+Version: 0.1.71
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.69 → geocif-0.1.71}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.69",
+    version="0.1.71",
     zip_safe=False,
 )