geocif 0.1.59__tar.gz → 0.1.61__tar.gz

{geocif-0.1.59/geocif.egg-info → geocif-0.1.61}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.59
+Version: 0.1.61
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.59 → geocif-0.1.61}/geocif/analysis.py

@@ -186,11 +186,6 @@ class Geoanalysis:
         return df_metrics, df_regional_metrics, df_national_yield
 
     def _clean_data(self):
-        # Hack exclude 2012 if country == "illinois"
-        if self.country == "illinois":
-            self.df_analysis = self.df_analysis[
-                self.df_analysis["Harvest Year"] != 2012
-            ]
         # Remove rows with missing values in Observed Yield (tn per ha)
         return self.df_analysis.dropna(subset=["Observed Yield (tn per ha)"])
 

{geocif-0.1.59 → geocif-0.1.61}/geocif/geocif.py

@@ -587,6 +587,16 @@ class Geocif:
             df_region[f"Median {self.target}"].values, 3
         )
 
+        if f"Median {self.target} (2014-2018)" in df_region.columns:
+            df.loc[:, f"Median {self.target} (2014-2018)"] = np.around(
+                df_region[f"Median {self.target} (2014-2018)"].values, 3
+            )
+
+        if f"Median {self.target} (2013-2017)" in df_region.columns:
+            df.loc[:, f"Median {self.target} (2013-2017)"] = np.around(
+                df_region[f"Median {self.target} (2013-2017)"].values, 3
+            )
+
         if self.estimate_ci:
             if self.estimate_ci_for_all or self.forecast_season == self.today_year:
                 # Iterate over each element in y_pred_ci
@@ -730,6 +740,8 @@ class Geocif:
 
         if self.median_yield_as_feature:
             self.feature_names.append(f"Median {self.target}")
+            self.feature_names.append(f"Median {self.target} (2014-2018)")
+            self.feature_names.append(f"Median {self.target} (2013-2017)")
 
         if self.lag_yield_as_feature:
             # For the number of years specified in self.number_lag_years
@@ -988,6 +1000,14 @@ class Geocif:
             df, self.all_seasons_with_yield, self.number_median_years, self.target
         )
 
+        df = fe.compute_user_median_statistics(
+            df, [2014, 2015, 2016, 2017, 2018]
+        )
+
+        df = fe.compute_user_median_statistics(
+            df, [2013, 2014, 2015, 2016, 2017]
+        )
+
         if self.median_area_as_feature:
             df = fe.compute_median_statistics(
                 df, self.all_seasons_with_yield, self.number_median_years, "Area (ha)"

{geocif-0.1.59 → geocif-0.1.61}/geocif/ml/feature_engineering.py

@@ -105,6 +105,49 @@ def compute_median_statistics(
     return df
 
 
+def compute_user_median_statistics(df, user_years, target_col="Yield (tn per ha)"):
+    """
+    Enhances the DataFrame with a new column that contains the median yield computed
+    using only the yields from the user-specified list of years.
+
+    Args:
+        df (DataFrame): The original DataFrame containing yield data.
+        user_years (array-like): List of years to consider for computing the median yield.
+        target_col (str): The column name from which to compute the median yield.
+
+    Returns:
+        DataFrame: The original DataFrame enhanced with a new column for median yield.
+    """
+    # Ensure 'Harvest Year' is treated as integer for accurate comparisons.
+    df["Harvest Year"] = df["Harvest Year"].astype(int)
+
+    # Sort the user_years list to reliably extract the earliest and latest years.
+    user_years_sorted = sorted(user_years)
+    first_year = user_years_sorted[0]
+    last_year = user_years_sorted[-1]
+
+    # Define the new column name to include the range of years.
+    new_col_name = f"Median {target_col} ({first_year}-{last_year})"
+
+    # Initialize the new column with NaN values.
+    df[new_col_name] = np.nan
+
+    # Group by region and compute the median yield for the specified years.
+    for region, group in tqdm(df.groupby("Region"), desc="Median yield", leave=False):
+        # Skip if the target column is completely null for this region.
+        if group[target_col].isnull().all():
+            continue
+
+        # Filter the rows to only include harvest years that are in the user provided list.
+        mask = group["Harvest Year"].isin(user_years)
+        median_yield = group.loc[mask, target_col].median()
+
+        # Assign the computed median yield to all rows in the current region.
+        df.loc[df["Region"] == region, new_col_name] = median_yield
+
+    return df
+
+
 def compute_lag_yield(
     df, all_seasons_with_yield, number_lag_years, target_col="Yield (tn per ha)"
 ):

{geocif-0.1.59 → geocif-0.1.61}/geocif/ml/feature_selection.py

@@ -192,7 +192,6 @@ def select_features(X, y, method="RFE", min_features_to_select=3, threshold_nan=
         from boruta import BorutaPy
 
         selector = BorutaPy(forest, n_estimators="auto", random_state=42)
-        breakpoint()
         selector.fit(X.values, y.values)
         selected_features_mask = selector.support_
         selected_features = X.columns[selected_features_mask].tolist()

{geocif-0.1.59 → geocif-0.1.61/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.59
+Version: 0.1.61
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.59 → geocif-0.1.61}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.59",
+    version="0.1.61",
     zip_safe=False,
 )