geocif 0.1.93__tar.gz → 0.1.95__tar.gz

{geocif-0.1.93/geocif.egg-info → geocif-0.1.95}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.93
+Version: 0.1.95
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.93 → geocif-0.1.95}/geocif/analysis.py

@@ -627,7 +627,7 @@ class Geoanalysis:
         self.df_analysis["Anomaly"] = (
             self.df_analysis[self.predicted]
             * 100.0
-            / self.df_analysis["Median Yield (tn per ha)"]
+            / self.df_analysis["Median Yield (tn per ha) (2018-2022)_y"]
         )
 
         # Compute the yield from the last year
@@ -782,6 +782,73 @@ class Geoanalysis:
                         loc_legend="lower left",
                     )
 
+                    # Make map of predicted yield by country
+                    for country in countries:
+                        df_country = df_model[df_model["Country"] == country.lower().replace(" ", "_")]
+                        fname = f"map_perc_area_{self.country}_{self.crop}.png"
+                        col = "% of total Area (ha)"
+                        plot.plot_df_shpfile(
+                            self.dg,  # dataframe containing adm1 name and polygon
+                            df_country,  # dataframe containing information that will be mapped
+                            merge_col="Country Region",  # Column on which to merge
+                            name_country=[country],  # 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"% of Total Area (ha)\n{self.crop.title()}",
+                            vmin=df_country[col].min(),
+                            vmax=df_country[col].max(),
+                            cmap=pal.scientific.sequential.Bamako_20_r,
+                            series="sequential",
+                            show_bg=False,
+                            annotate_regions=self.annotate_regions,
+                            annotate_region_column=annotate_region_column,
+                            loc_legend="lower left",
+                        )
+
+                        df_country = df_harvest_year[df_harvest_year["Country"] == country.lower().replace(" ", "_")]
+                        fname = f"map_predicted_yield_{country}_{self.crop}_{time_period}_{year}.png"
+                        plot.plot_df_shpfile(
+                            self.dg,  # dataframe containing adm1 name and polygon
+                            df_country,  # dataframe containing information that will be mapped
+                            merge_col="Country Region",  # Column on which to merge
+                            name_country=[country],  # Plot global map
+                            name_col="Predicted Yield (tn per ha)",  # Which column to plot
+                            dir_out=self.dir_plot / str(year),  # Output directory
+                            fname=fname,  # Output file name
+                            label=f"Predicted Yield (Mg/ha)\n{self.crop.title()}, {year}",
+                            vmin=df_country[self.predicted].min(),
+                            vmax=df_country[self.predicted].max(),
+                            cmap=pal.scientific.sequential.Bamako_20_r,
+                            series="sequential",
+                            show_bg=False,
+                            annotate_regions=self.annotate_regions,
+                            annotate_region_column=annotate_region_column,
+                            loc_legend="lower left",
+                        )
+
+                        fname = (
+                            f"map_anomaly_{country}_{self.crop}_{time_period}_{year}.png"
+                        )
+                        plot.plot_df_shpfile(
+                            self.dg,  # dataframe containing adm1 name and polygon
+                            df_country,  # dataframe containing information that will be mapped
+                            merge_col="Country Region",  # Column on which to merge
+                            name_country=[country],  # Plot global map
+                            name_col="Anomaly",  # Which column to plot
+                            dir_out=self.dir_plot / str(year),  # Output directory
+                            fname=fname,  # Output file name
+                            label=f"% of {self.number_lag_years}-year Median Yield\n{self.crop.title()}, {year}",
+                            vmin=df_country["Anomaly"].min(),
+                            vmax=110,  # df_harvest_year["Anomaly"].max(),
+                            cmap=pal.cartocolors.diverging.Geyser_5_r,
+                            series="sequential",
+                            show_bg=False,
+                            annotate_regions=self.annotate_regions,
+                            annotate_region_column=annotate_region_column,
+                            loc_legend="lower left",
+                        )
+
                     """ Ratio of Predicted to last Year Yield """
                     # fname = f"{self.country}_{self.crop}_{time_period}_{year}_ratio_last_year_yield.png"
                     # plot.plot_df_shpfile(
@@ -934,18 +1001,14 @@ class Geoanalysis:
         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:
+        if "ADMIN0" not in self.dg.columns and "ADM0_NAME" not in self.dg.columns:
             self.dg.loc[:, "ADMIN0"] = country.title().replace("_", " ")
-        # if ADMIN1 or ADM1_NAME is not in the shapefile, then rename admin_col_name to ADM1_NAME
-        if "ADMIN1" or "ADM1_NAME" not in self.dg.columns:
+
+        # If ADMIN1 or ADM1_NAME is not in the shapefile, then rename admin_col_name to ADMIN1
+        if "ADMIN1" not in self.dg.columns and "ADM1_NAME" not in self.dg.columns:
             if admin_zone == "admin_1":
                 self.dg.rename(columns={self.admin_col_name: "ADMIN1"}, inplace=True)
 
-        # Hack rename Tanzania to United Republic of Tanzania
-        self.dg["ADMIN0"] = self.dg["ADMIN0"].replace(
-            "Tanzania", "United Republic of Tanzania"
-        )
-
         # Rename ADMIN0 to ADM0_NAME and ADMIN1 to ADM1_NAME and ADMIN2 to ADM2_NAME
         self.dg = self.dg.rename(
             columns={

{geocif-0.1.93 → geocif-0.1.95}/geocif/geocif.py

@@ -1005,6 +1005,7 @@ class Geocif:
         # and will confuse the model
         if self.forecast_season == self.today_year:
             current_month = ar.utcnow().month
+            current_day = ar.utcnow().day
 
             # Identify columns where the second chunk equals the current month index
             cols_to_drop = []
@@ -1014,51 +1015,30 @@ class Geocif:
                         "Starting Stage"
                     ]
 
-                    if mon == current_month:
+                    if mon == current_month and current_day > 25:
                         cols_to_drop.append(col)
 
             # 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)"
@@ -1073,10 +1053,7 @@ 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":
@@ -1090,7 +1067,7 @@ class Geocif:
 
             # Region_ID should be type category
             df["Region_ID"] = df["Region_ID"].astype("category")
-        breakpoint()
+
         return df
 
     def execute(self):
@@ -1147,7 +1124,14 @@ class Geocif:
 
         # Join with dg based on Country Region column, only keeping rows that are in df
         # Only use geometry column from self.dg
-        self.dg_country = self.dg_country[["Country Region", "geometry"]].merge(
+        if self.admin_zone == "admin_1":
+            cols = ["Country Region", "geometry", "ADM1_NAME"]
+        elif self.admin_zone == "admin_2":
+            cols = ["Country Region", "geometry", "ADM2_NAME"]
+        else:
+            raise ValueError(f"Unsopported {self.admin_zone}")
+
+        self.dg_country = self.dg_country[cols].merge(
             df[["Country Region", self.correlation_plot_groupby]],
             on="Country Region",
             how="outer",

{geocif-0.1.93 → geocif-0.1.95}/geocif/ml/embedding.py

@@ -47,7 +47,7 @@ def _compute_correlations(X, y):
                 r = pearsonr(y_filtered, f_series_filtered)[0]
                 feature_correlations[feature] = round(r, 3)
             except Exception as e:
-                print(f"Error computing correlation for {feature}: {e}")
+                # print(f"Error computing correlation for {feature}: {e}")
                 feature_correlations[feature] = np.nan
 
     return feature_correlations

{geocif-0.1.93 → geocif-0.1.95}/geocif/ml/stages.py

@@ -268,11 +268,6 @@ 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-0.1.93 → geocif-0.1.95}/geocif/viz/plot.py

@@ -375,6 +375,11 @@ def plot_df_shpfile(
             )
 
             df_country = gpd.read_file(shpfilename, engine="pyogrio")
+            # Hack
+            # Rename Russia to Russian Federation, in the ADMIN column
+            df_country.loc[
+                df_country["ADMIN"].str.lower() == "russia", "ADMIN"
+            ] = "Russian Federation"
             # read the country borders
             _name_country = []
             for cntr in name_country:
@@ -390,14 +395,23 @@ def plot_df_shpfile(
                 )
                 _name_country.append(cntr.replace(" ", "_").lower())
 
-            extent = rgeo.get_country_lat_lon_extent(
-                _name_country, buffer=1.0
-            )  # left, right, bottom, top
-            # Hack: Add space to the top for adding title
-            extent[3] = extent[3] + 2
-            # Add some space to the bottom for adding legend and colorbar
-            extent[2] = extent[2] - 3
-            ax.set_extent(extent)
+            # Hack
+            if _name_country[0] == "russian_federation":
+                extent = [20, 80, 40, 80]
+            else:
+                extent = rgeo.get_country_lat_lon_extent(
+                    _name_country, buffer=1.0
+                )  # left, right, bottom, top
+
+                # Hack: Add space to the top for adding title
+                extent[3] = extent[3] + 2
+                # Add some space to the bottom for adding legend and colorbar
+                extent[2] = extent[2] - 3
+
+            try:
+                ax.set_extent(extent)
+            except:
+                breakpoint()
         elif name_country == "world":
             ax.add_feature(
                 cartopy.feature.LAND.with_scale("50m"), color="white"

{geocif-0.1.93 → geocif-0.1.95/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.93
+Version: 0.1.95
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.93 → geocif-0.1.95}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.93",
+    version="0.1.95",
     zip_safe=False,
 )