geocif 0.1.30__tar.gz → 0.1.31__tar.gz

{geocif-0.1.30/geocif.egg-info → geocif-0.1.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.30
+Version: 0.1.31
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.30 → geocif-0.1.31}/geocif/geocif.py

@@ -355,6 +355,8 @@ class Geocif:
         experiment_id = f"{self.country}_{self.crop}"
         now = ar.utcnow().to("America/New_York").format("MMMM-DD-YYYY HH:mm:ss")
         selected_features = self.selected_features + self.cat_features
+        # Compute percentage difference between y_pred and y_test
+        ape = np.abs((y_pred - y_test) / y_test) * 100
         df = pd.DataFrame(
             {
                 "Experiment_ID": np.full(shp, experiment_id),
@@ -378,6 +380,7 @@ class Geocif:
                 "Area (ha)": df_region["Area (ha)"].values,
                 f"Observed {self.target}": np.around(y_test, 3).ravel(),
                 f"Predicted {self.target}": np.around(y_pred, 3).ravel(),
+                f"APE": np.around(ape, 3).ravel(),
             }
         )
 
@@ -720,7 +723,7 @@ class Geocif:
         """ Convert this dataframe into an ML ready format and save to disk """
         df = self.create_ml_dataframe(df)
         dir_output = (
-            self.dir_analysis / self.country / self.crop / str(self.forecast_season)
+            self.dir_analysis / self.country / self.crop / self.model_name / str(self.forecast_season)
         )
         os.makedirs(dir_output, exist_ok=True)
         df.to_csv(
@@ -768,6 +771,9 @@ class Geocif:
         dict_kwargs["dg_country"] = self.dg_country
         dict_kwargs["combined_dict"] = self.combined_dict
 
+        if self.spatial_autocorrelation:
+           sa.compute_spatial_autocorrelation(self.df_results, **dict_kwargs)
+
         if self.correlation_plots:
             self.logger.info(f"Correlation plot for {self.country} {self.crop}")
             (
@@ -775,9 +781,6 @@ class Geocif:
                 dict_best_cei,
             ) = correlations.all_correlated_feature_by_time(df, **dict_kwargs)
 
-        if self.spatial_autocorrelation:
-           sa.compute_spatial_autocorrelation(self.df_results, **dict_kwargs)
-
         """ Separate into train and test datasets based on forecast_season """
         mask = df["Harvest Year"] == self.forecast_season
         self.df_train = df[~mask]

{geocif-0.1.30 → geocif-0.1.31}/geocif/ml/spatial_autocorrelation.py

@@ -1,7 +1,11 @@
+import warnings
+
+from tqdm import tqdm
+import matplotlib.pyplot as plt
 import pandas as pd
 from pysal.lib import weights
-from pysal.explore import esda
-import matplotlib.pyplot as plt
+
+warnings.filterwarnings("ignore")
 
 
 def validate_inputs(df_results, required_columns):
@@ -40,24 +44,26 @@ def preprocess_data(df_results, dg_country):
     dg_country["Country Region"] = dg_country["Country Region"].str.lower()
     dg_country = dg_country[dg_country["Country Region"].isin(df["Country Region"])]
 
+    dg_country.reset_index(drop=True, inplace=True)
+
     merged_df = dg_country.merge(df, on="Country Region", how="inner")
 
-    return merged_df, dg_country
+    return merged_df
 
 
-def create_base_weights(dg_country):
+def create_base_weights(merged_df):
     """
 
     Args:
-        dg_country:
+        merged_df:
 
     Returns:
 
     """
-    dg_subset = dg_country[["Country Region", "geometry"]].drop_duplicates()
+    dg = merged_df[["Country Region", "geometry"]].drop_duplicates()
 
     try:
-        w_base = weights.Queen.from_dataframe(dg_subset)
+        w_base = weights.Queen.from_dataframe(dg)
     except Exception as e:
         raise RuntimeError(f"Failed to create spatial weights: {e}")
 
@@ -65,13 +71,10 @@ def create_base_weights(dg_country):
         index for index, neighbors in w_base.neighbors.items() if len(neighbors) == 0
     ]
     if no_neighbors:
-        print(f"Removing {len(no_neighbors)} polygons with 0 neighbors")
-        dg_country = dg_country.drop(index=no_neighbors).reset_index(drop=True)
-        w_base = weights.Queen.from_dataframe(
-            dg_country[["Country Region", "geometry"]]
-        )
+        dg = dg.drop(index=no_neighbors[0]).reset_index(drop=True)
+        w_base = weights.Queen.from_dataframe(dg[["Country Region", "geometry"]])
 
-    return w_base, dg_country
+    return w_base, dg
 
 
 def create_weights_for_year(dg_country, regions_with_data):
@@ -84,14 +87,22 @@ def create_weights_for_year(dg_country, regions_with_data):
     Returns:
 
     """
-    dg_subset = dg_country[dg_country["Country Region"].isin(regions_with_data)]
+    dg = dg_country[dg_country["Country Region"].isin(regions_with_data)]
+    dg = dg.reset_index(drop=True)
+
+    wt = weights.Queen.from_dataframe(dg)
 
-    wt = weights.Queen.from_dataframe(dg_subset)
+    no_neighbors = [
+        index for index, neighbors in wt.neighbors.items() if len(neighbors) == 0
+    ]
+    if no_neighbors:
+        dg = dg.drop(index=no_neighbors[0]).reset_index(drop=True)
+        wt = weights.Queen.from_dataframe(dg[["Country Region", "geometry"]])
 
-    return wt
+    return wt, dg
 
 
-def compute_morans_i(merged_df, dg_country):
+def compute_morans_i(merged_df):
     """
 
     Args:
@@ -101,25 +112,35 @@ def compute_morans_i(merged_df, dg_country):
     Returns:
 
     """
+    from pysal.explore import esda
+
+    # Drop any regions with missing data
+    merged_df = merged_df.dropna(subset=["Yield (tn per ha)"])
+
     years = merged_df["Harvest Year"].unique()
     results = {"Harvest Year": [], "Moran's I": [], "p-value": [], "Significant": []}
 
-    for year in years:
+    for year in tqdm(years, desc="Compute Moran's I"):
         year_data = merged_df[merged_df["Harvest Year"] == year]
         regions_with_data = year_data["Country Region"].unique()
         year_data = year_data[year_data["Country Region"].isin(regions_with_data)]
 
-        y = year_data[["Region", "Yield (tn per ha)"]].drop_duplicates()
+        y = year_data[["Country Region", "Region", "Yield (tn per ha)"]].drop_duplicates()
+        dg_country = year_data[["Country Region", "geometry"]].drop_duplicates()
 
         if len(y) > 1:
-            w = create_weights_for_year(dg_country, regions_with_data)
+            w, x = create_weights_for_year(dg_country, regions_with_data)
+            y = y[y["Country Region"].isin(x["Country Region"])]
 
             try:
                 mi = esda.Moran(y["Yield (tn per ha)"].values, w, permutations=999)
             except:
                 breakpoint()
             results["Harvest Year"].append(year)
-            results["Moran's I"].append(mi.I)
+            try:
+                results["Moran's I"].append(mi.I)
+            except:
+                breakpoint()
             results["p-value"].append(mi.p_sim)
             results["Significant"].append(mi.p_sim < 0.1)
         else:
@@ -131,7 +152,7 @@ def compute_morans_i(merged_df, dg_country):
     return pd.DataFrame(results)
 
 
-def plot_moransi_time_series(results_df, country, crop, dir_output):
+def plot_morans_i_time_series(results_df, country, crop, dir_output):
     """
 
     Args:
@@ -194,12 +215,10 @@ def compute_spatial_autocorrelation(df_results, **kwargs):
     ]
     validate_inputs(df_results, required_columns)
 
-    merged_df, dg_country = preprocess_data(df_results, dg_country)
+    merged_df = preprocess_data(df_results, dg_country)
     if merged_df.empty:
         raise ValueError("No valid data available after preprocessing")
 
-    w_base, dg_country = create_base_weights(dg_country)
-
-    results_df = compute_morans_i(merged_df, dg_country)
+    results_df = compute_morans_i(merged_df)
 
-    plot_moransi_time_series(results_df, country, crop, dir_output)
+    plot_morans_i_time_series(results_df, country, crop, dir_output)

{geocif-0.1.30 → geocif-0.1.31/geocif.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geocif
-Version: 0.1.30
+Version: 0.1.31
 Summary: Models to visualize and forecast crop conditions and yields
 Home-page: https://ritviksahajpal.github.io/yield_forecasting/
 Author: Ritvik Sahajpal

{geocif-0.1.30 → geocif-0.1.31}/setup.py

@@ -50,6 +50,6 @@ setup(
     test_suite="tests",
     tests_require=test_requirements,
     url="https://ritviksahajpal.github.io/yield_forecasting/",
-    version="0.1.30",
+    version="0.1.31",
     zip_safe=False,
 )