geocif 0.1.53__tar.gz → 0.1.55__tar.gz

{geocif-0.1.53/geocif.egg-info → geocif-0.1.55}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.53
+Version: 0.1.55
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.53 → geocif-0.1.55}/geocif/analysis.py

@@ -93,6 +93,9 @@ class Geoanalysis:
                 & (self.df_analysis["Crop"] == self.crop)
                 & (self.df_analysis["Model"] == self.model)
             ]
+
+            # Drop columns that are empty
+            # self.df_analysis = self.df_analysis.dropna(axis=1, how="all")
         except Exception as e:
             pass
 
@@ -384,7 +387,7 @@ class Geoanalysis:
         from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_percentage_error
 
         # Ensure 'Harvest Year' is numeric
-        df["Harvest Year"] = pd.to_numeric(df["Harvest Year"], errors="coerce")
+        df.loc[:, "Harvest Year"] = pd.to_numeric(df["Harvest Year"], errors="coerce")
 
         # Extract data
         y_observed = df["Observed Yield (tn per ha)"]
@@ -414,8 +417,15 @@ class Geoanalysis:
             rmse = np.sqrt(mean_squared_error(y_observed, y_predicted))
             mape = mean_absolute_percentage_error(y_observed, y_predicted)
             r2 = r2_score(y_observed, y_predicted)
+            n_points = len(y_observed)  # Number of data points
+
+            textstr = (
+                f"RMSE: {rmse:.2f} tn/ha\n"
+                f"MAPE: {mape:.2%}\n"
+                f"$r^2$: {r2:.2f}\n"
+                f"N: {n_points}"
+            )
 
-            textstr = f"RMSE: {rmse:.2f} tn/ha\nMAPE: {mape:.2%}\n$r^2$: {r2:.2f}"
             ax.annotate(
                 textstr,
                 xy=(0.05, 0.95),
@@ -485,7 +495,15 @@ class Geoanalysis:
             mape = mean_absolute_percentage_error(y_observed, y_predicted)
             r2 = r2_score(y_observed, y_predicted)
 
-            textstr = f"RMSE: {rmse:.2f} tn/ha\nMAPE: {mape:.2%}\nr²: {r2:.2f}"
+            n_points = len(y_observed)  # Number of data points
+
+            textstr = (
+                f"RMSE: {rmse:.2f} tn/ha\n"
+                f"MAPE: {mape:.2%}\n"
+                f"$r^2$: {r2:.2f}\n"
+                f"N: {n_points}"
+            )
+
             ax.annotate(
                 textstr,
                 xy=(0.05, 0.95),
@@ -636,7 +654,7 @@ class Geoanalysis:
                     #
                     #                 """ % of total area """
                     if idx == 0:
-                        fname = f"{self.country}_{self.crop}_perc_area.png"
+                        fname = f"map_{self.country}_{self.crop}_perc_area.png"
                         col = "% of total Area (ha)"
                         plot.plot_df_shpfile(
                             self.dg,  # dataframe containing adm1 name and polygon
@@ -652,13 +670,13 @@ class Geoanalysis:
                             cmap=pal.scientific.sequential.Bamako_20_r,
                             series="sequential",
                             show_bg=False,
-                            annotate_regions=True,
+                            annotate_regions=self.annotate_regions,
                             annotate_region_column=annotate_region_column,
                             loc_legend="lower left",
                         )
                     #
                     """ Unique regions """
-                    fname = f"{self.country}_{self.crop}_region_ID.png"
+                    fname = f"map_{self.country}_{self.crop}_region_ID.png"
                     col = "Region_ID"
                     df_model[col] = df_model[col].astype(int) + 1
                     if len(df_model["Region_ID"].unique() > 1):
@@ -668,27 +686,27 @@ class Geoanalysis:
                             for key in df_time_period["Region_ID"].unique()
                         }
 
-                        # plot.plot_df_shpfile(
-                        #     self.dg,  # dataframe containing adm1 name and polygon
-                        #     df_model,  # dataframe containing information that will be mapped
-                        #     dict_lup=dict_region,
-                        #     merge_col="Country Region",  # Column on which to merge
-                        #     name_country=countries,  # Plot global map
-                        #     name_col=col,  # Which column to plot
-                        #     dir_out=self.dir_plot / str(year),  # Output directory
-                        #     fname=fname,  # Output file name
-                        #     label=f"Region Cluster\n{self.crop.title()}",
-                        #     vmin=df_model[col].min(),
-                        #     vmax=df_model[col].max(),
-                        #     cmap=pal.tableau.Tableau_20.mpl_colors,
-                        #     series="qualitative",
-                        #     show_bg=False,
-                        #     alpha_feature=1,
-                        #     use_key=True,
-                        #     annotate_regions=True,
-                        #     annotate_region_column=annotate_region_column,
-                        #     loc_legend="lower left",
-                        # )
+                        plot.plot_df_shpfile(
+                            self.dg,  # dataframe containing adm1 name and polygon
+                            df_model,  # dataframe containing information that will be mapped
+                            dict_lup=dict_region,
+                            merge_col="Country Region",  # Column on which to merge
+                            name_country=countries,  # Plot global map
+                            name_col=col,  # Which column to plot
+                            dir_out=self.dir_plot / str(year),  # Output directory
+                            fname=fname,  # Output file name
+                            label=f"Region Cluster\n{self.crop.title()}",
+                            vmin=df_model[col].min(),
+                            vmax=df_model[col].max(),
+                            cmap=pal.tableau.Tableau_20.mpl_colors,
+                            series="qualitative",
+                            show_bg=False,
+                            alpha_feature=1,
+                            use_key=True,
+                            annotate_regions=self.annotate_regions,
+                            annotate_region_column=annotate_region_column,
+                            loc_legend="lower left",
+                        )
                     #                     breakpoint()
 
                     # """ Anomaly """
@@ -715,7 +733,7 @@ class Geoanalysis:
                     # )
 
                     """ Predicted Yield """
-                    fname = f"{fname_prefix}_{self.crop}_{time_period}_{year}_predicted_yield.png"
+                    fname = f"map_{fname_prefix}_{self.crop}_{time_period}_{year}_predicted_yield.png"
                     plot.plot_df_shpfile(
                         self.dg,  # dataframe containing adm1 name and polygon
                         df_harvest_year,  # dataframe containing information that will be mapped
@@ -730,7 +748,7 @@ class Geoanalysis:
                         cmap=pal.scientific.sequential.Bamako_20_r,
                         series="sequential",
                         show_bg=False,
-                        annotate_regions=True,
+                        annotate_regions=self.annotate_regions,
                         annotate_region_column=annotate_region_column,
                         loc_legend="lower left",
                     )
@@ -759,7 +777,7 @@ class Geoanalysis:
                     # Area
                     # breakpoint()
                     if df_time_period["Area (ha)"].notna().all():
-                        fname = f"{self.country}_{self.crop}_{year}_area.png"
+                        fname = f"map_{self.country}_{self.crop}_{year}_area.png"
                         plot.plot_df_shpfile(
                             self.dg,  # dataframe containing adm1 name and polygon
                             df_time_period,  # dataframe containing information that will be mapped
@@ -774,7 +792,7 @@ class Geoanalysis:
                             cmap=pal.scientific.sequential.Bamako_20_r,
                             series="sequential",
                             show_bg=False,
-                            annotate_regions=True,
+                            annotate_regions=self.annotate_regions,
                             loc_legend="lower left",
                         )
 
@@ -884,6 +902,7 @@ class Geoanalysis:
             engine="pyogrio",
         )
         self.admin_col_name = self.parser.get(country, "admin_col_name")
+        self.annotate_regions = self.parser.getboolean(country, "annotate_regions")
 
         # If ADMIN0 or ADM0_NAME is not in the shapefile, then add ADM0_NAME
         if "ADMIN0" or "ADM0_NAME" not in self.dg.columns:
@@ -950,18 +969,28 @@ class RegionalMapper(Geoanalysis):
         con = sqlite3.connect(self.db_path)
 
         query = "SELECT * FROM regional_metrics"
-        self.df_regional = pd.read_sql_query(query, con)
+        try:
+            self.df_regional = pd.read_sql_query(query, con)
+        except:
+            self.logger.error("Failed to read data from regional_metrics")
+            self.df_regional = pd.DataFrame()
+
         query = "SELECT * FROM regional_metrics_by_year"
-        self.df_regional_by_year = pd.read_sql_query(query, con)
+        try:
+            self.df_regional_by_year = pd.read_sql_query(query, con)
+        except:
+            self.logger.error("Failed to read data from regional_metrics_by_year")
+            self.df_regional_by_year = pd.DataFrame()
 
         con.close()
 
     def clean_data(self):
         """Clean and format the data."""
-        self.df_regional["Country"] = (
-            self.df_regional["Country"].str.replace("_", " ").str.title()
-        )
-        self.df_regional["Model"] = self.df_regional["Model"].str.title()
+        if not self.df_regional.empty:
+            self.df_regional["Country"] = (
+                self.df_regional["Country"].str.replace("_", " ").str.title()
+            )
+            self.df_regional["Model"] = self.df_regional["Model"].str.title()
 
     def plot_heatmap(self):
         """Generate heatmaps of MAPE bins vs. % total area bins."""
@@ -1056,21 +1085,21 @@ class RegionalMapper(Geoanalysis):
                 plt.minorticks_on()
                 plt.xlabel("Mean Absolute Percentage Error (%)")
                 plt.ylabel("Frequency")
-                plt.legend(title="Country", title_fontsize="13")
+                plt.legend(title="Country", title_fontsize="16")
 
                 # Adding the title at the top-right corner
-                plt.text(
-                    0.95, 0.95,  # Coordinates in axes fraction
-                    f"Model: {model}",
-                    transform=plt.gca().transAxes,
-                    fontsize=14,
-                    verticalalignment="top",
-                    horizontalalignment="right",
-                    bbox=dict(facecolor="white", alpha=0.6, edgecolor="none")
-                )
+                # plt.text(
+                #     0.95, 0.95,  # Coordinates in axes fraction
+                #     f"Model: {model}",
+                #     transform=plt.gca().transAxes,
+                #     fontsize=14,
+                #     verticalalignment="top",
+                #     horizontalalignment="right",
+                #     bbox=dict(facecolor="white", alpha=0.6, edgecolor="none")
+                # )
 
                 plt.tight_layout()
-                plt.savefig(self.dir_analysis / f"mape_histogram_{model}.png", dpi=250)
+                plt.savefig(self.dir_analysis / f"histogram_region_{model}_mape.png", dpi=250)
                 plt.close()
 
     def plot_mape_map(self):
@@ -1101,7 +1130,7 @@ class RegionalMapper(Geoanalysis):
             df = df_model[df_model["Country"].isin(countries)]
             self.dg = self.dg[self.dg["ADM0_NAME"].isin(countries)]
 
-            fname = f"mape_{crop}_{df_model['Model'].iloc[0]}.png"
+            fname = f"map_{crop}_{df_model['Model'].iloc[0]}_mape.png"
             plot.plot_df_shpfile(
                 self.dg,
                 df,
@@ -1116,7 +1145,7 @@ class RegionalMapper(Geoanalysis):
                 cmap=pal.scientific.sequential.Bamako_20_r,
                 series="sequential",
                 show_bg=False,
-                annotate_regions=True,
+                annotate_regions=self.annotate_regions,
                 loc_legend="lower left",
             )
 
@@ -1145,7 +1174,7 @@ class RegionalMapper(Geoanalysis):
             plt.xticks(rotation=0)
 
             plt.tight_layout()
-            plt.savefig(self.dir_analysis / "mape_by_year.png", dpi=250)
+            plt.savefig(self.dir_analysis / "bar_mape_by_year.png", dpi=250)
             plt.close()
 
 

{geocif-0.1.53 → geocif-0.1.55}/geocif/geocif.py

@@ -582,11 +582,10 @@ class Geocif:
             }
         )
 
-        if self.median_yield_as_feature:
-            # Add median yield to dataframe
-            df.loc[:, f"Median {self.target}"] = np.around(
-                df_region[f"Median {self.target}"].values, 3
-            )
+        # Add median yield to dataframe
+        df.loc[:, f"Median {self.target}"] = np.around(
+            df_region[f"Median {self.target}"].values, 3
+        )
 
         if self.estimate_ci:
             if self.estimate_ci_for_all or self.forecast_season == self.today_year:
@@ -1142,6 +1141,9 @@ class Geocif:
         group_by = ["Region"]
         groups = self.df_train.groupby(group_by)
         for key, group in groups:
+            if group.empty:
+                continue
+
             if self.check_yield_trend:
                 if group[self.target].any():
                     detrended_data = trend.detrend_dataframe(

{geocif-0.1.53 → geocif-0.1.55}/geocif/ml/feature_engineering.py

@@ -361,10 +361,11 @@ def classify_target(df, target_col, number_classes):
     new_target_col = f"{target_col}_class"
 
     # Change the target column to categorical with the specified number of classes
-    try:
-        df[new_target_col], bins = pd.qcut(df[target_col], q=number_classes, labels=False, retbins=True, duplicates='drop')
-    except:
-        breakpoint()
+    df[new_target_col], bins = pd.qcut(df[target_col],
+                                       q=number_classes,
+                                       labels=False,
+                                       retbins=True,
+                                       duplicates='drop')
 
     return df, new_target_col, bins
 

{geocif-0.1.53 → geocif-0.1.55/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.53
+Version: 0.1.55
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.53 → geocif-0.1.55}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.53",
+    version="0.1.55",
     zip_safe=False,
 )