geocif 0.1.77__tar.gz → 0.1.78__tar.gz

{geocif-0.1.77/geocif.egg-info → geocif-0.1.78}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.77
+Version: 0.1.78
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.77 → geocif-0.1.78}/geocif/analysis.py

@@ -347,7 +347,9 @@ class Geoanalysis:
         df_tmp = df_region.copy()
 
         # Fill
-        df_tmp[area_ha] = df_tmp.groupby("Country")[area_ha].transform(lambda x: x.fillna(x.median()))
+        df_tmp[area_ha] = df_tmp.groupby("Country")[area_ha].transform(
+            lambda x: x.fillna(x.median())
+        )
 
         # Log that we are filling missing values with the median
         self.logger.info(
@@ -379,7 +381,11 @@ class Geoanalysis:
         """
         Plot observed vs predicted yield for all regions and all years.
         """
-        from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_percentage_error
+        from sklearn.metrics import (
+            mean_squared_error,
+            r2_score,
+            mean_absolute_percentage_error,
+        )
 
         # Ensure 'Harvest Year' is numeric
         df.loc[:, "Harvest Year"] = pd.to_numeric(df["Harvest Year"], errors="coerce")
@@ -391,7 +397,9 @@ class Geoanalysis:
 
         # Generate colors for years
         cmap = plt.cm.viridis  # Colormap for years
-        norm = plt.Normalize(vmin=years.min(), vmax=years.max())  # Normalize years to colormap
+        norm = plt.Normalize(
+            vmin=years.min(), vmax=years.max()
+        )  # Normalize years to colormap
         colors = [cmap(norm(year)) for year in years]
 
         # Create the plot
@@ -442,7 +450,9 @@ class Geoanalysis:
             cbar.set_label("Harvest Year")
 
             # Set equispaced ticks for exactly 5 points
-            ticks = np.linspace(years.min(), years.max(), 5, dtype=int)  # 5 equispaced ticks
+            ticks = np.linspace(
+                years.min(), years.max(), 5, dtype=int
+            )  # 5 equispaced ticks
             cbar.set_ticks(ticks)
             cbar.ax.set_yticklabels([str(tick) for tick in ticks])
 
@@ -454,10 +464,16 @@ class Geoanalysis:
             plt.close()
 
     def _plot_national_yield(self, df_national_yield):
-        from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_percentage_error
+        from sklearn.metrics import (
+            mean_squared_error,
+            r2_score,
+            mean_absolute_percentage_error,
+        )
 
         # Ensure 'Harvest Year' is numeric
-        df_national_yield["Harvest Year"] = pd.to_numeric(df_national_yield["Harvest Year"], errors="coerce")
+        df_national_yield["Harvest Year"] = pd.to_numeric(
+            df_national_yield["Harvest Year"], errors="coerce"
+        )
 
         # Extract data
         x = df_national_yield["Harvest Year"]
@@ -516,7 +532,9 @@ class Geoanalysis:
             # Add legend for years
             sm = plt.cm.ScalarMappable(cmap=cmap, norm=norm)
             sm.set_array([])
-            cbar = fig.colorbar(sm, ax=ax, aspect=50, pad=0.02)  # Specify the axis explicitly
+            cbar = fig.colorbar(
+                sm, ax=ax, aspect=50, pad=0.02
+            )  # Specify the axis explicitly
             cbar.set_label("Harvest Year")
 
             # Set equispaced ticks for exactly 5 points
@@ -579,10 +597,8 @@ class Geoanalysis:
         )
 
         # Merge the median yield columns with the % of total production dataframe
-        df_historic = (
-            df_pct
-            .merge(df_median_2018_2022, on="Region", how="left")
-            .merge(df_median_2013_2017, on="Region", how="left")
+        df_historic = df_pct.merge(df_median_2018_2022, on="Region", how="left").merge(
+            df_median_2013_2017, on="Region", how="left"
         )
 
         return df_historic
@@ -1081,7 +1097,7 @@ class RegionalMapper(Geoanalysis):
             df_tmp = df_model[
                 (df_model["% of total Area (ha)"] < 0.5)
                 & (df_model["Mean Absolute Percentage Error"] > 100)
-                ]
+            ]
 
             df_model = df_model.drop(df_tmp.index)
 
@@ -1113,7 +1129,9 @@ class RegionalMapper(Geoanalysis):
                 # )
 
                 plt.tight_layout()
-                plt.savefig(self.dir_analysis / f"histogram_region_{model}_mape.png", dpi=250)
+                plt.savefig(
+                    self.dir_analysis / f"histogram_region_{model}_mape.png", dpi=250
+                )
                 plt.close()
 
     def plot_mape_map(self):
@@ -1140,7 +1158,7 @@ class RegionalMapper(Geoanalysis):
             col = "Mean Absolute Percentage Error"
             countries = df_model["Country"].unique().tolist()
             countries = [country.title().replace("_", " ") for country in countries]
-            crop = df_model["Crop"].unique()[0].title().replace('_', ' ')
+            crop = df_model["Crop"].unique()[0].title().replace("_", " ")
             df = df_model[df_model["Country"].isin(countries)]
             self.dg = self.dg[self.dg["ADM0_NAME"].isin(countries)]