start testing for new version

hydromodel/__init__.py

@@ -1,5 +1,80 @@
-"""Top-level package for hydromodel."""
+"""
+Author: Wenyu Ouyang
+Date: 2024-02-09 15:56:48
+LastEditTime: 2024-03-22 09:12:40
+LastEditors: Wenyu Ouyang
+Description: Top-level package for hydromodel
+FilePath: \hydro-model-xaj\hydromodel\__init__.py
+Copyright (c) 2023-2024 Wenyu Ouyang. All rights reserved.
+"""
+
+import os
+from pathlib import Path
+from hydroutils import hydro_file
+import yaml
 
 __author__ = """Wenyu Ouyang"""
-__email__ = '[email protected]'
-__version__ = '0.0.1'
+__email__ = "[email protected]"
+__version__ = "0.0.1"
+
+
+CACHE_DIR = hydro_file.get_cache_dir()
+SETTING_FILE = os.path.join(Path.home(), "hydro_setting.yml")
+
+
+def read_setting(setting_path):
+    if not os.path.exists(setting_path):
+        raise FileNotFoundError(f"Configuration file not found: {setting_path}")
+
+    with open(setting_path, "r") as file:
+        setting = yaml.safe_load(file)
+
+    example_setting = (
+        "local_data_path:\n"
+        "  root: 'D:\\data\\waterism' # Update with your root data directory\n"
+        "  datasets-origin: 'D:\\data\\waterism\\datasets-origin' # datasets-origin is the directory you put downloaded datasets\n"
+        "  datasets-interim: 'D:\\data\\waterism\\datasets-interim' # the other choice for the directory you put downloaded datasets\n"
+        "  basins-origin: 'D:\\data\\waterism\\basins-origin' # the directory put your own data\n"
+        "  basins-interim: 'D:\\data\\waterism\\basins-interim' # the other choice for your own data"
+    )
+
+    if setting is None:
+        raise ValueError(
+            f"Configuration file is empty or has invalid format.\n\nExample configuration:\n{example_setting}"
+        )
+
+    # Define the expected structure
+    expected_structure = {
+        "local_data_path": [
+            "root",
+            "datasets-origin",
+            "datasets-interim",
+            "basins-origin",
+            "basins-interim",
+        ],
+    }
+
+    # Validate the structure
+    try:
+        for key, subkeys in expected_structure.items():
+            if key not in setting:
+                raise KeyError(f"Missing required key in config: {key}")
+
+            if isinstance(subkeys, list):
+                for subkey in subkeys:
+                    if subkey not in setting[key]:
+                        raise KeyError(f"Missing required subkey '{subkey}' in '{key}'")
+    except KeyError as e:
+        raise ValueError(
+            f"Incorrect configuration format: {e}\n\nExample configuration:\n{example_setting}"
+        ) from e
+
+    return setting
+
+
+try:
+    SETTING = read_setting(SETTING_FILE)
+except ValueError as e:
+    print(e)
+except Exception as e:
+    print(f"Unexpected error: {e}")

hydromodel/datasets/data_postprocess.py

@@ -3,13 +3,9 @@
 import pandas as pd
 import pathlib
 import spotpy
-from pathlib import Path
-import sys
 
 from hydroutils import hydro_file
 
-sys.path.append(os.path.dirname(Path(os.path.abspath(__file__)).parent.parent))
-import definitions
 from hydromodel.models.model_config import MODEL_PARAM_DICT
 from hydromodel.models.xaj import xaj
 
@@ -34,23 +30,15 @@ def read_save_sceua_calibrated_params(basin_id, save_dir, sceua_calibrated_file_
 
     """
     results = spotpy.analyser.load_csv_results(sceua_calibrated_file_name)
-<<<<<<< HEAD
     bestindex, bestobjf = spotpy.analyser.get_minlikeindex(
         results
     )  # 结果数组中具有最小目标函数的位置的索引
-=======
-    bestindex, bestobjf = spotpy.analyser.get_minlikeindex(results) #结果数组中具有最小目标函数的位置的索引
->>>>>>> wangjingyi1999-event
     best_model_run = results[bestindex]
     fields = [word for word in best_model_run.dtype.names if word.startswith("par")] 
     best_calibrate_params = pd.DataFrame(list(best_model_run[fields]))
     save_file = os.path.join(save_dir, basin_id + "_calibrate_params.txt")
     best_calibrate_params.to_csv(save_file, sep=",", index=False, header=True)
-<<<<<<< HEAD
     return np.array(best_calibrate_params).reshape(1, -1)  # 返回一列最佳的结果
-=======
-    return np.array(best_calibrate_params).reshape(1, -1)    #返回一列最佳的结果
->>>>>>> wangjingyi1999-event
 
 
 def summarize_parameters(result_dir, model_info: dict):
@@ -223,12 +211,8 @@ def read_and_save_et_ouputs(result_dir, fold: int):
     train_period = data_info_train["time"]
     test_period = data_info_test["time"]
     # TODO: basins_lump_p_pe_q_fold NAME need to be unified
-    train_np_file = os.path.join(
-        exp_dir, "data_info_fold" + str(fold) + "_train.npy"
-    )
-    test_np_file = os.path.join(
-        exp_dir, "data_info_fold" + str(fold) + "_test.npy"
-    )
+    train_np_file = os.path.join(exp_dir, f"data_info_fold{fold}_train.npy")
+    test_np_file = os.path.join(exp_dir, f"data_info_fold{fold}_test.npy")
     # train_np_file = os.path.join(exp_dir, f"basins_lump_p_pe_q_fold{fold}_train.npy")
     # test_np_file = os.path.join(exp_dir, f"basins_lump_p_pe_q_fold{fold}_test.npy")
     train_data = np.load(train_np_file)