geocif 0.2.67__tar.gz → 0.2.69__tar.gz

{geocif-0.2.67/geocif.egg-info → geocif-0.2.69}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: geocif
-Version: 0.2.67
+Version: 0.2.69
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal
@@ -16,6 +16,17 @@ Classifier: Programming Language :: Python :: 3.9
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-python
+Dynamic: summary
 
 # geocif
 

{geocif-0.2.67 → geocif-0.2.69}/geocif/geocif.py

@@ -836,12 +836,13 @@ class Geocif:
 
             """ Feature selection and then Train """
             # Filter dataframe based on region and self.feature_names
+            breakpoint()
             df_region_train = self.df_train[mask_train]
             df_region_train = df_region_train[self.fixed_columns + common_columns]
             df_region_train.reset_index(drop=True, inplace=True)
             df_region_train = df_region_train.dropna(subset=[self.target_column])
 
-            self.X_train = df_region_train[self.feature_names]
+            self.X_train = df_region_train[self.feature_names + ["Region"]]
 
             # Drop any columns with NaNs except the lag yield columns
             lag_prefix = "t -"
@@ -1543,6 +1544,7 @@ class Geocif:
             self.logger.info("Adding starting and ending time period for each stage")
             self.df_inputs = stages.add_stage_information(self.df_inputs, self.method)
 
+            self.logger.info("Writing input file to disk")
             self.df_inputs.to_csv(file, index=False)
         else:
             self.df_inputs = pd.read_csv(file)

{geocif-0.2.67 → geocif-0.2.69}/geocif/ml/feature_selection.py

@@ -65,7 +65,6 @@ def select_features(
     X_filtered : pd.DataFrame of selected features
     selected_features : list[str]
     """
-
     # copy original for multi-mode recursion
     X_clean = X.copy()
 
@@ -250,10 +249,30 @@ def select_features(
 
     elif method == "BorutaPy":
         from boruta import BorutaPy
-        sel = BorutaPy(forest, n_estimators="auto", random_state=42, verbose=0)
-        sel.fit(X_clean.values, y)
-        mask = sel.support_ | sel.support_weak_
-        selected = X_clean.columns[mask].tolist()
+        from collections import Counter
+        import itertools as it
+
+        region_selected = {}                         # {region: [features …]}
+        for region in tqdm(X_clean["Region"].unique(), desc="BorutaPy", leave=False):
+            idx = X_clean["Region"] == region
+            X_region = X_clean.loc[idx].drop(columns=["Region"])
+            y_region = y.loc[idx] if hasattr(y, "loc") else y[idx]
+
+            sel = BorutaPy(
+                estimator=forest,
+                n_estimators="auto",
+                random_state=42,
+                verbose=0          
+            )
+            sel.fit(X_region.values, y_region.values)
+
+            region_selected[region] = (
+                X_region.columns[sel.support_ | sel.support_weak_].tolist()
+            )
+
+        # ─── 3. keep features chosen in ≥ 2 regions ------------------------------
+        counts   = Counter(it.chain.from_iterable(region_selected.values()))
+        selected = [feat for feat, n in counts.items() if n >= 2]
 
     elif method == "Leshy":
         import arfs.feature_selection.allrelevant as arfsgroot

{geocif-0.2.67 → geocif-0.2.69}/geocif/ml/stages.py

@@ -1,5 +1,6 @@
 import numpy as np
 from typing import Union
+from tqdm import tqdm
 
 from geocif import utils
 
@@ -46,14 +47,16 @@ def add_stage_information(df, method):
         df["Starting Stage"].map(dict) + " - " + df["Ending Stage"].map(dict)
     )
 
-    # Group by Region, Harvest Year
-    # For each group, add a column called Percentage Season
-    # that is the percentage of the season that has passed based on the number of rows
-    # in the group
+    df["Percentage Season"] = float("nan")
+
+    # Group by Region and Harvest Year
     grouped = df.groupby(["Region", "Harvest Year"])
-    df["Percentage Season"] = (
-        grouped.cumcount() * 100.0 / grouped["CEI"].transform("size")
-    )
+
+    # Loop through groups with tqdm
+    for (region, year), group in tqdm(grouped, desc="Computing Percentage Season"):
+        idx = group.index
+        n = len(group)
+        df.loc[idx, "Percentage Season"] = [i * 100.0 / n for i in range(n)]
 
     return df
 

{geocif-0.2.67 → geocif-0.2.69}/geocif/ml/stats.py

@@ -18,7 +18,7 @@ def get_yld_prd(df, name_crop, cntr, region, calendar_year, region_column="ADM1_
 
     """
     # Get yield and production for country for specific year
-    val = np.NaN
+    val = np.nan
 
     # df.columns.values: [u'ADM0_NAME', u'ADM1_NAME', u'ADM2_NAME', u'str_ID', u'num_ID', 1990 ... 2015]
     if calendar_year in df.columns:
@@ -88,7 +88,7 @@ def get_yld_prd(df, name_crop, cntr, region, calendar_year, region_column="ADM1_
 
             try:
                 if val.isnull().all():
-                    val = np.NaN
+                    val = np.nan
                 else:
                     val = val.values[0]
             except:
@@ -97,10 +97,10 @@ def get_yld_prd(df, name_crop, cntr, region, calendar_year, region_column="ADM1_
         else:
             # The values[-1] is a hack to accommodate multiple types of green maize
             vals = df[calendar_year]
-            val = vals.values[-1] if not vals.empty else np.NaN
+            val = vals.values[-1] if not vals.empty else np.nan
 
     # Replace yield/production value of 0 with NaN
-    val = np.NaN if val == 0.0 else val
+    val = np.nan if val == 0.0 else val
 
     return val
 
@@ -120,7 +120,7 @@ def add_GEOGLAM_statistics(dir_stats, df, stats, method, admin_zone):
     """
     # Create empty columns for all the ag statistics
     for stat in stats:
-        df.loc[:, stat] = np.NaN
+        df.loc[:, stat] = np.nan
 
     # Fill in the ag statistics columns with data when available
     # Compute national scale statistics

{geocif-0.2.67 → geocif-0.2.69}/geocif/playground/aa.py

@@ -1,3 +1,4 @@
+
 from graphviz import Source
 
 # Read your dot file

{geocif-0.2.67 → geocif-0.2.69/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: geocif
-Version: 0.2.67
+Version: 0.2.69
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal
@@ -16,6 +16,17 @@ Classifier: Programming Language :: Python :: 3.9
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-python
+Dynamic: summary
 
 # geocif
 

{geocif-0.2.67 → geocif-0.2.69}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.2.67",
+    version="0.2.69",
     zip_safe=False,
 )