pyreclaim 0.2.0__tar.gz → 0.4.0__tar.gz

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyreclaim
-Version: 0.2.0
+Version: 0.4.0
 Summary: Reservoir Estimation of Capacity Loss using AI based Methods
 Author-email: Sanchit Minocha <msanchit@uw.edu>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -698,12 +698,20 @@ Requires-Dist: joblib
 Requires-Dist: xgboost
 Requires-Dist: lightgbm
 Requires-Dist: catboost
+Requires-Dist: openpyxl
+Requires-Dist: netcdf4
+Requires-Dist: dask
+Requires-Dist: rioxarray
 Dynamic: license-file
 
 <div align="center">
   <img src="https://github.com/UW-SASWE/RECLAIM/raw/main/docs/_static/Reclaim_logo_clearBG.png" alt="Reservoir Estimation of Capacity Loss using AI-based Methods" width="500"/>
 </div>
-# Reservoir Estimation of Capacity Loss using AI-based Methods - RECLAIM
+
+
+# Reservoir Estimation of Capacity Loss using AI-based Methods (RECLAIM)
+
+---
 
 **First-of-its-kind globally scalable tool to predict reservoir sedimentation, screen vulnerable reservoirs, and pinpoint those struggling the most.**
 
@@ -727,8 +735,19 @@ Install the package via pip:
 ```bash
 pip install pyreclaim
 ```
+
 ---
+## Download Data
 
+To generate features for reservoirs using the **RECLAIM** framework and the [`pyreclaim`](https://pypi.org/project/pyreclaim/) Python package, you will need the global datasets.  
+
+You can download all required global datasets from the Zenodo Repository:  
+
+[Download Global Datasets](https://doi.org/10.5281/zenodo.17230533)  
+
+These datasets include land cover, soil, terrain/DEM derivatives, and vegetation gain/loss data, which are essential for computing reservoir and catchment features for RECLAIM.
+
+---
 ## Documentation
 
 The documentation is available [here](https://reclaimio.readthedocs.io/en/latest/).
@@ -748,7 +767,7 @@ from reclaim.reclaim import Reclaim
 reservoir_static = {
     "obc": 150.0,
     "hgt": 45.0,
-    "mrb": "Ganges",
+    "mrb": 4030033640,
     "lat": 25.6,
     "lon": 81.9,
     "reservoir_polygon": reservoir_polygon,

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/README.md

@@ -1,7 +1,11 @@
 <div align="center">
   <img src="https://github.com/UW-SASWE/RECLAIM/raw/main/docs/_static/Reclaim_logo_clearBG.png" alt="Reservoir Estimation of Capacity Loss using AI-based Methods" width="500"/>
 </div>
-# Reservoir Estimation of Capacity Loss using AI-based Methods - RECLAIM
+
+
+# Reservoir Estimation of Capacity Loss using AI-based Methods (RECLAIM)
+
+---
 
 **First-of-its-kind globally scalable tool to predict reservoir sedimentation, screen vulnerable reservoirs, and pinpoint those struggling the most.**
 
@@ -25,8 +29,19 @@ Install the package via pip:
 ```bash
 pip install pyreclaim
 ```
+
 ---
+## Download Data
 
+To generate features for reservoirs using the **RECLAIM** framework and the [`pyreclaim`](https://pypi.org/project/pyreclaim/) Python package, you will need the global datasets.  
+
+You can download all required global datasets from the Zenodo Repository:  
+
+[Download Global Datasets](https://doi.org/10.5281/zenodo.17230533)  
+
+These datasets include land cover, soil, terrain/DEM derivatives, and vegetation gain/loss data, which are essential for computing reservoir and catchment features for RECLAIM.
+
+---
 ## Documentation
 
 The documentation is available [here](https://reclaimio.readthedocs.io/en/latest/).
@@ -46,7 +61,7 @@ from reclaim.reclaim import Reclaim
 reservoir_static = {
     "obc": 150.0,
     "hgt": 45.0,
-    "mrb": "Ganges",
+    "mrb": 4030033640,
     "lat": 25.6,
     "lon": 81.9,
     "reservoir_polygon": reservoir_polygon,

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pyreclaim"
-version = "v0.2.0"
+version = "v0.4.0"
 authors = [
   { name="Sanchit Minocha", email="msanchit@uw.edu" },
 ]
@@ -30,6 +30,10 @@ dependencies = [
     "xgboost",
     "lightgbm",
     "catboost",
+    "openpyxl",
+    "netcdf4",
+    "dask",
+    "rioxarray"
 ]
 
 [project.urls]

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 
 setup(
     name = "pyreclaim",
-    version = "v0.2.0",
+    version = "v0.4.0",
     license = "GPL-3.0",
     package_dir = {"": "src"}
 )

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/pyreclaim.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyreclaim
-Version: 0.2.0
+Version: 0.4.0
 Summary: Reservoir Estimation of Capacity Loss using AI based Methods
 Author-email: Sanchit Minocha <msanchit@uw.edu>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -698,12 +698,20 @@ Requires-Dist: joblib
 Requires-Dist: xgboost
 Requires-Dist: lightgbm
 Requires-Dist: catboost
+Requires-Dist: openpyxl
+Requires-Dist: netcdf4
+Requires-Dist: dask
+Requires-Dist: rioxarray
 Dynamic: license-file
 
 <div align="center">
   <img src="https://github.com/UW-SASWE/RECLAIM/raw/main/docs/_static/Reclaim_logo_clearBG.png" alt="Reservoir Estimation of Capacity Loss using AI-based Methods" width="500"/>
 </div>
-# Reservoir Estimation of Capacity Loss using AI-based Methods - RECLAIM
+
+
+# Reservoir Estimation of Capacity Loss using AI-based Methods (RECLAIM)
+
+---
 
 **First-of-its-kind globally scalable tool to predict reservoir sedimentation, screen vulnerable reservoirs, and pinpoint those struggling the most.**
 
@@ -727,8 +735,19 @@ Install the package via pip:
 ```bash
 pip install pyreclaim
 ```
+
 ---
+## Download Data
 
+To generate features for reservoirs using the **RECLAIM** framework and the [`pyreclaim`](https://pypi.org/project/pyreclaim/) Python package, you will need the global datasets.  
+
+You can download all required global datasets from the Zenodo Repository:  
+
+[Download Global Datasets](https://doi.org/10.5281/zenodo.17230533)  
+
+These datasets include land cover, soil, terrain/DEM derivatives, and vegetation gain/loss data, which are essential for computing reservoir and catchment features for RECLAIM.
+
+---
 ## Documentation
 
 The documentation is available [here](https://reclaimio.readthedocs.io/en/latest/).
@@ -748,7 +767,7 @@ from reclaim.reclaim import Reclaim
 reservoir_static = {
     "obc": 150.0,
     "hgt": 45.0,
-    "mrb": "Ganges",
+    "mrb": 4030033640,
     "lat": 25.6,
     "lon": 81.9,
     "reservoir_polygon": reservoir_polygon,

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/pyreclaim.egg-info/requires.txt

@@ -11,3 +11,7 @@ joblib
 xgboost
 lightgbm
 catboost
+openpyxl
+netcdf4
+dask
+rioxarray

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/derived_features/feature_engineering_and_transformation.py

@@ -54,22 +54,28 @@ def engineer_and_transform_features(df: pd.DataFrame) -> pd.DataFrame:
         "SOUT": df["MAO"] * df["NSSC2_mean"],
     }
     
+    df = pd.concat([df, pd.DataFrame(feature_dict)], axis=1)
+
     # Land cover log-area features
     lc_cols = ['LCAS','LCC','LCG','LCT','LCS','LCHV','LCM','LCSV','LCBS','LCSG','LCWB']
     for col in lc_cols:
-        feature_dict[col] = df["CA"] * df[col] / 100
-    
-    df = pd.concat([df, pd.DataFrame(feature_dict)], axis=1)
-
+        df[col] = df["CA"] * df[col] / 100
+        
     # -------------------------
     # APPLY LOG TRANSFORMATIONS
     # -------------------------
     log_candidates = ['CA','DCA','OBC','HGT','RA','RP','FL',
                       'SA_mean','SA_mean_clip','SA_std','SA_kurt','PAI','MAI','MAO','I_std','O_std','MAR',
-                      'rain_per_area','GC','TE','ECLR','SIN','SOUT'] + lc_cols
+                      'ROBC','rain_per_area','GC','TE','RT','ECLR','ESR','SIN','SOUT'] + lc_cols
 
     for col in log_candidates:
         log_col = f'log_{col}'  # add prefix to avoid double log
-        df[log_col] = np.log(df[col].clip(lower=1e-15))
+        try:
+            df[log_col] = np.log(df[col].clip(lower=1e-15))
+        except Exception as e:
+            raise ValueError(f"Error applying log transform to column '{col}': {e}")
+    
+    # Process DLc as categorical column
+    df['DLC'] = df['DLC'].astype(int).fillna(0)
     
     return df

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/dynamic_features/reservoir_dynamic.py

@@ -142,7 +142,8 @@ def reservoir_based_dynamic_features(
                     path, time_col, data_col, func, feat, obs_period
                 )
                 results[feat] = df_feat.iloc[0, 0]  # single value
-            except Exception:
+            except Exception as e:
+                print(f"Failed to compute {feat} due to error: {e}. Setting as NaN.")
                 results[feat] = np.nan
 
     return pd.DataFrame([results])

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/dynamic_features/utils/ts_aggregate.py

@@ -37,6 +37,12 @@ def compute_ts_aggregate(
     df = pd.read_csv(ts_csv_path)
     if df.empty:
         raise ValueError(f"CSV at {ts_csv_path} is empty.")
+    
+    # Ensure columns exist
+    if time_column not in df.columns:
+        raise ValueError(f"Time column '{time_column}' not found in CSV.")
+    if value_column not in df.columns:
+        raise ValueError(f"Value column '{value_column}' not found in CSV.")
 
     # Ensure time column is datetime
     df[time_column] = pd.to_datetime(df[time_column], errors='coerce')

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/generate_features.py

@@ -12,17 +12,24 @@ from reclaim.derived_features.feature_engineering_and_transformation import engi
 
 
 def create_features_per_row(
+    idx: int,
+    observation_period: List[int],
     reservoir_static_params: dict,
     catchment_static_params: dict,
     reservoir_dynamic_info: dict = None,
     catchment_dynamic_info: dict = None,
-    observation_period: List[int] = None
 ) -> pd.DataFrame:
     """
     Compute all static, dynamic, and derived features for a single reservoir observation.
 
     Parameters
     ----------
+    idx : int
+        Index of the reservoir sedimentation observation (for tracking/logging purposes).
+    
+    observation_period : list of int
+        Two-element list [OSY, OEY] for observation start year and end year.
+        
     reservoir_static_params : dict
         Parameters for reservoir_based_static_features(). Expected keys:
             - obc : float, Original Built Capacity (MCM)
@@ -30,6 +37,7 @@ def create_features_per_row(
             - mrb : str, Major River Basin, optional
             - lat : float, Latitude (deg)
             - lon : float, Longitude (deg)
+            - by : int, Build Year
             - reservoir_polygon : shapely.geometry.Polygon
             - inlet_point : shapely.geometry.Point, optional
             - resolution : float, optional
@@ -61,9 +69,6 @@ def create_features_per_row(
             - "tmax":   {"path": str, "time_column": str, "data_column": str}
             - "wind":   {"path": str, "time_column": str, "data_column": str}
 
-    observation_period : list of int, optional
-        Two-element list [OSY, OEY] for observation start year and end year.
-
     Returns
     -------
     pd.DataFrame
@@ -74,6 +79,14 @@ def create_features_per_row(
         - Catchment dynamic
         - Derived/log-transformed
     """
+    
+    # --- Observevation period features ---
+    osy, oey = observation_period
+    df_obs_period = pd.DataFrame({
+        "idx": [idx],
+        "OSY": [osy],
+        "OEY": [oey]
+    })
 
     # --- Static features ---
     df_res_static = reservoir_based_static_features(**reservoir_static_params)
@@ -88,9 +101,9 @@ def create_features_per_row(
 
     if catchment_dynamic_info is not None and observation_period is not None:
         df_catch_dyn = catchment_based_dynamic_features(catchment_dynamic_info, observation_period)
-
+    
     # --- Combine all static + dynamic ---
-    df_combined = pd.concat([df_res_static, df_catch_static, df_res_dyn, df_catch_dyn], axis=1)
+    df_combined = pd.concat([df_obs_period, df_res_static, df_catch_static, df_res_dyn, df_catch_dyn], axis=1)
 
     # --- Engineer + log-transform features ---
     df_final = engineer_and_transform_features(df_combined)
@@ -109,6 +122,10 @@ def create_features_multi(
     reservoirs_input : list of dict
         Each element should be a dictionary with the following keys:
         
+        - `idx` : int
+            Index of the reservoir sedimentation observation.
+        - `observation_period` : list of int
+            Two-element list `[OSY, OEY]` specifying the observation period.
         - `reservoir_static_params` : dict
             Parameters for `reservoir_based_static_features()`.
         - `catchment_static_params` : dict
@@ -117,8 +134,7 @@ def create_features_multi(
             Parameters for `reservoir_based_dynamic_features()`.
         - `catchment_dynamic_info` : dict
             Parameters for `catchment_based_dynamic_features()`.
-        - `observation_period` : list of int
-            Two-element list `[OSY, OEY]` specifying the observation period.
+        
 
     Returns
     -------
@@ -129,11 +145,12 @@ def create_features_multi(
     all_rows = []
     for idx, reservoir_info in enumerate(reservoirs_input):
         df_row = create_features_per_row(
+            idx=reservoir_info.get("idx"),
+            observation_period=reservoir_info.get("observation_period"),
             reservoir_static_params=reservoir_info.get("reservoir_static_params", {}),
             catchment_static_params=reservoir_info.get("catchment_static_params", {}),
             reservoir_dynamic_info=reservoir_info.get("reservoir_dynamic_info", None),
             catchment_dynamic_info=reservoir_info.get("catchment_dynamic_info", None),
-            observation_period=reservoir_info.get("observation_period", None),
         )
         all_rows.append(df_row)
 

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/reclaim.py

@@ -189,6 +189,8 @@ class Reclaim:
             if self.feature_order_list is not None:
                 # Reorder columns automatically
                 X = X[self.feature_order_list]
+                # for col in self.cat_features:
+                #     X[col] = X[col].astype("category")
         elif isinstance(X, np.ndarray):
             warnings.warn(
                     "Predicting with NumPy array: assumes column order matches training order. "
@@ -476,19 +478,21 @@ class Reclaim:
             load_dir = os.path.join(package_dir, "pretrained_model")
 
         # Load XGBoost
-        xgb_path = os.path.join(load_dir, f"{prefix}_xgb.json")
+        xgb_path = os.path.join(load_dir, f"{prefix}_xgb.pkl")
         if os.path.exists(xgb_path):
-            self.xgb_model = xgb.XGBRegressor()
-            self.xgb_model.load_model(xgb_path)
+            import xgboost as xgb
+            self.xgb_model = joblib.load(xgb_path)
 
         # Load LightGBM
-        lgb_path = os.path.join(load_dir, f"{prefix}_lgb.txt")
+        lgb_path = os.path.join(load_dir, f"{prefix}_lgb.pkl")
         if os.path.exists(lgb_path):
-            self.lgb_model = lgb.Booster(model_file=lgb_path)
+            import lightgbm as lgb
+            self.lgb_model = joblib.load(lgb_path)
 
         # Load CatBoost
         cat_path = os.path.join(load_dir, f"{prefix}_cat.cbm")
         if os.path.exists(cat_path):
+            from catboost import CatBoostRegressor
             self.cat_model = CatBoostRegressor()
             self.cat_model.load_model(cat_path)
 

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/static_features/reservoir_static.py

@@ -1,5 +1,6 @@
 import pandas as pd
 from shapely.geometry import Point, Polygon
+import numpy as np
 
 # Import utils
 from reclaim.static_features.utils.flow_length import find_actual_flow_path
@@ -13,6 +14,7 @@ def reservoir_based_static_features(
     mrb: str = None,
     lat: float = None,
     lon: float = None,
+    by: int = None,
     reservoir_polygon: Polygon = None,
     inlet_point: Point = None,
     resolution: float = None,
@@ -33,6 +35,8 @@ def reservoir_based_static_features(
         Latitude of dam location (degrees).
     lon : float, optional
         Longitude of dam location (degrees).
+    by : int, optional
+        Build year of the reservoir.
     reservoir_polygon : shapely.geometry.Polygon, optional
         Reservoir polygon geometry used to compute area and perimeter.
     dam_point : shapely.geometry.Point, optional
@@ -53,6 +57,7 @@ def reservoir_based_static_features(
         - MRB: Major River Basin
         - LAT: Latitude (deg)
         - LON: Longitude (deg)
+        - BY: Build Year
         - RA: Reservoir Area (sq km)
         - RP: Reservoir Perimeter (km)
         - FL: Flow Length (km)
@@ -67,6 +72,7 @@ def reservoir_based_static_features(
         "MRB": mrb,
         "LAT": lat,
         "LON": lon,
+        "BY": by,
         "RA": None,
         "RP": None,
         "FL": None,
@@ -85,8 +91,12 @@ def reservoir_based_static_features(
     dam_point = Point(lon, lat)
     if dam_point is not None and reservoir_polygon is not None:
         _, _, features["FL"], _ = (
-            find_actual_flow_path(dam_point, reservoir_polygon, inlet_point, resolution) / 1e3
-        )  # m → km
+            find_actual_flow_path(dam_point, reservoir_polygon, inlet_point, resolution) 
+        )  
+        if features["FL"]: 
+            features["FL"] = calculate_length_area_meters(features["FL"], area=False) / 1e3  # m → km
+        else:
+            features["FL"] = np.nan
 
     # AEC metrics
     if aec_df is not None:

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/static_features/utils/aec_shape.py

@@ -94,8 +94,8 @@ def concavity_index(df: pd.DataFrame) -> float:
     line = np.linspace(0, 1, len(area_norm))
 
     # Area under actual curve vs line
-    auc_curve = np.trapz(elev_norm, area_norm)
-    auc_line = np.trapz(line, area_norm)
+    auc_curve = np.trapezoid(elev_norm, area_norm)
+    auc_line = np.trapezoid(line, area_norm)
 
     concavity = auc_curve / auc_line if auc_line > 0 else np.nan
     return concavity

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/static_features/utils/area_perimeter.py

@@ -33,4 +33,4 @@ def calculate_length_area_meters(geometry, area= True):
         area_square_meters = scaled_geometry.area
         return length_meters, area_square_meters
     else:
-        return length_meters[0]
+        return length_meters

{pyreclaim-0.2.0 → pyreclaim-0.4.0}/src/reclaim/static_features/utils/catchment_agreggate.py

@@ -1,6 +1,7 @@
 import pandas as pd
 import numpy as np
 import xarray as xr
+import rioxarray
 import geopandas as gpd
 import regionmask
 from collections import Counter