geocif 0.1.94__tar.gz → 0.1.96__tar.gz

{geocif-0.1.94/geocif.egg-info → geocif-0.1.96}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.94
+Version: 0.1.96
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.94 → geocif-0.1.96}/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-0.1.94 → geocif-0.1.96}/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 = []
@@ -1014,11 +1015,10 @@ 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)
 
         # Change column name

{geocif-0.1.94 → geocif-0.1.96}/geocif/ml/feature_selection.py

@@ -133,6 +133,27 @@ def select_features(X, y, method="RFE", min_features_to_select=3, threshold_nan=
         selected_features = (
             shap_importance_df["feature"].head(optimal_N).values.tolist()
         )
+    elif method == "stabl":
+        from stabl.stabl import Stabl
+        from sklearn.linear_model import LogisticRegression
+
+        lasso = LogisticRegression(
+            penalty="l1", class_weight="balanced", max_iter=int(1e6), solver="liblinear", random_state=42
+        )
+        stabl = Stabl(
+            base_estimator=lasso,
+            n_bootstraps=100,
+            artificial_type="knockoff",
+            artificial_proportion=.5,
+            replace=False,
+            fdr_threshold_range=np.arange(0.1, 1, 0.01),
+            sample_fraction=0.5,
+            random_state=42,
+            lambda_grid={"C": np.linspace(0.004, 0.4, 30)},
+            verbose=1
+        )
+        stabl.fit(X, y)
+        selected_features = stabl.get_feature_names_out()
     elif method == "feature_engine":
         from feature_engine.selection import SmartCorrelatedSelection
 
@@ -304,7 +325,8 @@ def select_features(X, y, method="RFE", min_features_to_select=3, threshold_nan=
     else:
         raise ValueError("Method not recognized. Use BorutaPy, Genetic, or RFE")
     # tentative_features = X.columns[selector.support_weak_].tolist()
-
+    print(selected_features)
+    breakpoint()
     non_eo = are_all_features_non_eo(selected_features)
     if non_eo or method == "SelectKBest":
         from sklearn.feature_selection import SelectKBest, f_regression

{geocif-0.1.94 → geocif-0.1.96}/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-0.1.94 → geocif-0.1.96/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.94
+Version: 0.1.96
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.94 → geocif-0.1.96}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.94",
+    version="0.1.96",
     zip_safe=False,
 )