oafuncs 0.0.98.14__py3-none-any.whl → 0.0.98.15__py3-none-any.whl

oafuncs/_script/data_interp.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python
+# coding=utf-8
+"""
+Author: Liu Kun && 16031215@qq.com
+Date: 2025-04-25 16:22:52
+LastEditors: Liu Kun && 16031215@qq.com
+LastEditTime: 2025-04-25 16:22:52
+FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\_script\\data_interp.py
+Description:
+EditPlatform: vscode
+ComputerInfo: XPS 15 9510
+SystemInfo: Windows 11
+Python Version: 3.12
+"""
+
+from typing import List, Union
+
+import numpy as np
+from scipy.interpolate import griddata
+
+from oafuncs.oa_tool import PEx
+
+
+def _interp_single_worker(*args):
+    """
+    用于PEx并行的单slice插值worker，参数为(t, z, source_data, origin_points, target_points, interpolation_method, target_shape)
+    """
+    data_slice, origin_points, target_points, interpolation_method, target_shape = args
+
+    # 过滤掉包含 NaN 的点
+    valid_mask = ~np.isnan(data_slice.ravel())
+    valid_data = data_slice.ravel()[valid_mask]
+    valid_points = origin_points[valid_mask]
+
+    if len(valid_data) < 10:  # 如果有效数据太少，用均值填充
+        return np.full(target_shape, np.nanmean(data_slice))
+
+    # 使用有效数据进行插值
+    result = griddata(valid_points, valid_data, target_points, method=interpolation_method)
+    result = result.reshape(target_shape)
+
+    # 检查插值结果中是否仍有 NaN，如果有，用最近邻插值填充
+    if np.any(np.isnan(result)):
+        # 使用最近邻方法填充剩余的 NaN 值
+        nan_mask = np.isnan(result)
+        result_nn = griddata(valid_points, valid_data, target_points[nan_mask.ravel()], method="nearest")
+        result.ravel()[nan_mask.ravel()] = result_nn
+
+    return result
+
+
+def interp_2d_func(
+    target_x_coordinates: Union[np.ndarray, List[float]],
+    target_y_coordinates: Union[np.ndarray, List[float]],
+    source_x_coordinates: Union[np.ndarray, List[float]],
+    source_y_coordinates: Union[np.ndarray, List[float]],
+    source_data: np.ndarray,
+    interpolation_method: str = "cubic",
+) -> np.ndarray:
+    """
+    Perform 2D interpolation on the last two dimensions of a multi-dimensional array.
+
+    Args:
+        target_x_coordinates (Union[np.ndarray, List[float]]): Target grid's x-coordinates.
+        target_y_coordinates (Union[np.ndarray, List[float]]): Target grid's y-coordinates.
+        source_x_coordinates (Union[np.ndarray, List[float]]): Original grid's x-coordinates.
+        source_y_coordinates (Union[np.ndarray, List[float]]): Original grid's y-coordinates.
+        source_data (np.ndarray): Multi-dimensional array with the last two dimensions as spatial.
+        interpolation_method (str, optional): Interpolation method. Defaults to "cubic".
+            >>> optional: 'linear', 'nearest', 'cubic', 'quintic', etc.
+        use_parallel (bool, optional): Enable parallel processing. Defaults to True.
+
+    Returns:
+        np.ndarray: Interpolated data array.
+
+    Raises:
+        ValueError: If input shapes are invalid.
+
+    Examples:
+        >>> target_x_coordinates = np.array([1, 2, 3])
+        >>> target_y_coordinates = np.array([4, 5, 6])
+        >>> source_x_coordinates = np.array([7, 8, 9])
+        >>> source_y_coordinates = np.array([10, 11, 12])
+        >>> source_data = np.random.rand(3, 3)
+        >>> result = interp_2d(target_x_coordinates, target_y_coordinates, source_x_coordinates, source_y_coordinates, source_data)
+        >>> print(result.shape)  # Expected output: (3, 3)
+    """
+    if len(target_y_coordinates.shape) == 1:
+        target_x_coordinates, target_y_coordinates = np.meshgrid(target_x_coordinates, target_y_coordinates)
+    if len(source_y_coordinates.shape) == 1:
+        source_x_coordinates, source_y_coordinates = np.meshgrid(source_x_coordinates, source_y_coordinates)
+
+    if source_x_coordinates.shape != source_data.shape[-2:] or source_y_coordinates.shape != source_data.shape[-2:]:
+        raise ValueError("[red]Shape of source_data does not match shape of source_x_coordinates or source_y_coordinates.[/red]")
+
+    target_points = np.column_stack((np.array(target_x_coordinates).ravel(), np.array(target_y_coordinates).ravel()))
+    origin_points = np.column_stack((np.array(source_x_coordinates).ravel(), np.array(source_y_coordinates).ravel()))
+
+    data_dims = len(source_data.shape)
+    # Ensure source_data is 4D for consistent processing (t, z, y, x)
+    if data_dims < 2:
+        raise ValueError(f"[red]Source data must have at least 2 dimensions, but got {data_dims}.[/red]")
+    elif data_dims > 4:
+        # Or handle cases with more than 4 dimensions if necessary
+        raise ValueError(f"[red]Source data has {data_dims} dimensions, but this function currently supports only up to 4.[/red]")
+
+    # Reshape to 4D by adding leading dimensions of size 1 if needed
+    num_dims_to_add = 4 - data_dims
+    new_shape = (1,) * num_dims_to_add + source_data.shape
+    new_src_data = source_data.reshape(new_shape)
+
+    t, z, y, x = new_src_data.shape
+
+    paras = []
+    target_shape = target_y_coordinates.shape
+    for t_index in range(t):
+        for z_index in range(z):
+            paras.append((new_src_data[t_index, z_index], origin_points, target_points, interpolation_method, target_shape))
+
+    with PEx() as excutor:
+        result = excutor.run(_interp_single_worker, paras)
+
+    return np.squeeze(np.array(result).reshape(t, z, *target_shape))

oafuncs/_script/netcdf_merge.py

@@ -96,8 +96,6 @@ def merge_nc(file_list: Union[str, List[str]], var_name: Optional[Union[str, Lis
 
     save_to_nc(target_filename, xr.Dataset(merged_data))
 
-    print(f'File "{target_filename}" has been successfully created.')
-
 
 # Example usage
 if __name__ == "__main__":

oafuncs/oa_data.py

@@ -20,9 +20,8 @@ import numpy as np
 import salem
 import xarray as xr
 from rich import print
-from scipy.interpolate import griddata, interp1d
+from scipy.interpolate import interp1d
 
-from oafuncs.oa_tool import PEx
 
 __all__ = ["interp_along_dim", "interp_2d", "ensure_list", "mask_shapefile"]
 
@@ -115,32 +114,7 @@ def interp_along_dim(
     return np.apply_along_axis(apply_interp_extrap, interpolation_axis, source_data)
 
 
-def _interp_single_worker(*args):
-    """
-    用于PEx并行的单slice插值worker，参数为(t, z, source_data, origin_points, target_points, interpolation_method, target_shape)
-    """
-    data_slice, origin_points, target_points, interpolation_method, target_shape = args
-
-    # 过滤掉包含 NaN 的点
-    valid_mask = ~np.isnan(data_slice.ravel())
-    valid_data = data_slice.ravel()[valid_mask]
-    valid_points = origin_points[valid_mask]
-
-    if len(valid_data) < 10:  # 如果有效数据太少，用均值填充
-        return np.full(target_shape, np.nanmean(data_slice))
 
-    # 使用有效数据进行插值
-    result = griddata(valid_points, valid_data, target_points, method=interpolation_method)
-    result = result.reshape(target_shape)
-
-    # 检查插值结果中是否仍有 NaN，如果有，用最近邻插值填充
-    if np.any(np.isnan(result)):
-        # 使用最近邻方法填充剩余的 NaN 值
-        nan_mask = np.isnan(result)
-        result_nn = griddata(valid_points, valid_data, target_points[nan_mask.ravel()], method="nearest")
-        result.ravel()[nan_mask.ravel()] = result_nn
-
-    return result
 
 
 def interp_2d(
@@ -149,7 +123,7 @@ def interp_2d(
     source_x_coordinates: Union[np.ndarray, List[float]],
     source_y_coordinates: Union[np.ndarray, List[float]],
     source_data: np.ndarray,
-    interpolation_method: str = "cubic",
+    interpolation_method: str = "linear",
 ) -> np.ndarray:
     """
     Perform 2D interpolation on the last two dimensions of a multi-dimensional array.
@@ -160,7 +134,8 @@ def interp_2d(
         source_x_coordinates (Union[np.ndarray, List[float]]): Original grid's x-coordinates.
         source_y_coordinates (Union[np.ndarray, List[float]]): Original grid's y-coordinates.
         source_data (np.ndarray): Multi-dimensional array with the last two dimensions as spatial.
-        interpolation_method (str, optional): Interpolation method. Defaults to "cubic".
+            >>> must be [y, x] or [*, y, x] or [*, *, y, x]
+        interpolation_method (str, optional): Interpolation method. Defaults to "linear".
             >>> optional: 'linear', 'nearest', 'cubic', 'quintic', etc.
         use_parallel (bool, optional): Enable parallel processing. Defaults to True.
 
@@ -179,42 +154,16 @@ def interp_2d(
         >>> result = interp_2d(target_x_coordinates, target_y_coordinates, source_x_coordinates, source_y_coordinates, source_data)
         >>> print(result.shape)  # Expected output: (3, 3)
     """
-    if len(target_y_coordinates.shape) == 1:
-        target_x_coordinates, target_y_coordinates = np.meshgrid(target_x_coordinates, target_y_coordinates)
-    if len(source_y_coordinates.shape) == 1:
-        source_x_coordinates, source_y_coordinates = np.meshgrid(source_x_coordinates, source_y_coordinates)
-
-    if source_x_coordinates.shape != source_data.shape[-2:] or source_y_coordinates.shape != source_data.shape[-2:]:
-        raise ValueError("[red]Shape of source_data does not match shape of source_x_coordinates or source_y_coordinates.[/red]")
-
-    target_points = np.column_stack((np.array(target_y_coordinates).ravel(), np.array(target_x_coordinates).ravel()))
-    origin_points = np.column_stack((np.array(source_y_coordinates).ravel(), np.array(source_x_coordinates).ravel()))
-
-    data_dims = len(source_data.shape)
-    # Ensure source_data is 4D for consistent processing (t, z, y, x)
-    if data_dims < 2:
-        raise ValueError(f"[red]Source data must have at least 2 dimensions, but got {data_dims}.[/red]")
-    elif data_dims > 4:
-        # Or handle cases with more than 4 dimensions if necessary
-        raise ValueError(f"[red]Source data has {data_dims} dimensions, but this function currently supports only up to 4.[/red]")
-
-    # Reshape to 4D by adding leading dimensions of size 1 if needed
-    num_dims_to_add = 4 - data_dims
-    new_shape = (1,) * num_dims_to_add + source_data.shape
-    new_src_data = source_data.reshape(new_shape)
-
-    t, z, _, _ = new_src_data.shape
-
-    paras = []
-    target_shape = target_y_coordinates.shape
-    for t_index in range(t):
-        for z_index in range(z):
-            paras.append((new_src_data[t_index, z_index], origin_points, target_points, interpolation_method, target_shape))
-
-    with PEx() as excutor:
-        result = excutor.run(_interp_single_worker, paras)
-
-    return np.squeeze(np.array(result).reshape(t, z, *target_shape))
+    from ._script.data_interp import interp_2d_func
+    
+    return interp_2d_func(
+        target_x_coordinates=target_x_coordinates,
+        target_y_coordinates=target_y_coordinates,
+        source_x_coordinates=source_x_coordinates,
+        source_y_coordinates=source_y_coordinates,
+        source_data=source_data,
+        interpolation_method=interpolation_method,
+    )
 
 
 

{oafuncs-0.0.98.14.dist-info → oafuncs-0.0.98.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oafuncs
-Version: 0.0.98.14
+Version: 0.0.98.15
 Summary: Oceanic and Atmospheric Functions
 Home-page: https://github.com/Industry-Pays/OAFuncs
 Author: Kun Liu

{oafuncs-0.0.98.14.dist-info → oafuncs-0.0.98.15.dist-info}/RECORD

@@ -1,6 +1,6 @@
 oafuncs/__init__.py,sha256=T_-VtnWWllV3Q91twT5Yt2sUapeA051QbPNnBxmg9nw,1456
 oafuncs/oa_cmap.py,sha256=DimWT4Bg7uE5Lx8hSw1REp7whpsR2pFRStAwk1cowEM,11494
-oafuncs/oa_data.py,sha256=PXn4EpSbLPHhYmNJXEStd8vIMwInl3a9O9sW2c9z-g0,11152
+oafuncs/oa_data.py,sha256=hngaxAi_r6PsHXzSeT3DMY_QdChWjuBMPOZNFvWU388,8442
 oafuncs/oa_date.py,sha256=WhM6cyD4G3IeghjLTHhAMtlvJbA7kwQG2sHnxdTgyso,6303
 oafuncs/oa_draw.py,sha256=Wj2QBgyIPpV_dxaDrH10jqj_puK9ZM9rd-si-3VrsrE,17631
 oafuncs/oa_file.py,sha256=j9gXJgPOJsliu4IOUc4bc-luW4yBvQyNCEmMyDVjUwQ,16404
@@ -11,8 +11,9 @@ oafuncs/oa_tool.py,sha256=rpPkLqWhqMmqlCc5wjL8qMTg3gThCkSrYJckbX_0iJc,8631
 oafuncs/_data/hycom.png,sha256=MadKs6Gyj5n9-TOu7L4atQfTXtF9dvN9w-tdU9IfygI,10945710
 oafuncs/_data/oafuncs.png,sha256=o3VD7wm-kwDea5E98JqxXl04_78cBX7VcdUt7uQXGiU,3679898
 oafuncs/_script/cprogressbar.py,sha256=UIgGcLFs-6IgWlITuBLaQqrpt4OAK3Mst5RlCiNfZdQ,15772
+oafuncs/_script/data_interp.py,sha256=70U-Jsoxd5g-7dEQt4IaDRuRV-M_1lEKMGOci86vSVE,5431
 oafuncs/_script/email.py,sha256=lL4HGKrr524-g0xLlgs-4u7x4-u7DtgNoD9AL8XJKj4,3058
-oafuncs/_script/netcdf_merge.py,sha256=-Ke-Da6US0tM63Os5Uyl4fAOZ_1CNVuEpWbo_r2btGU,4299
+oafuncs/_script/netcdf_merge.py,sha256=9hCyxfeUHnBzs50_0v0jzVfxpMxTX4dNTo0pmsp_T6g,4226
 oafuncs/_script/netcdf_modify.py,sha256=sGRUYNhfGgf9JV70rnBzw3bzuTRSXzBTL_RMDnDPeLQ,4552
 oafuncs/_script/netcdf_write.py,sha256=iO1Qv9bp6RLiw1D8Nrv7tX_8X-diUZaX3Nxhk6pJ5Nw,8556
 oafuncs/_script/parallel.py,sha256=T9Aie-e4LcbKlFTLZ0l4lhEN3SBVa84jRcrAsIm8s0I,8767
@@ -37,8 +38,8 @@ oafuncs/oa_sign/__init__.py,sha256=QKqTFrJDFK40C5uvk48GlRRbGFzO40rgkYwu6dYxatM,5
 oafuncs/oa_sign/meteorological.py,sha256=8091SHo2L8kl4dCFmmSH5NGVHDku5i5lSiLEG5DLnOQ,6489
 oafuncs/oa_sign/ocean.py,sha256=xrW-rWD7xBWsB5PuCyEwQ1Q_RDKq2KCLz-LOONHgldU,5932
 oafuncs/oa_sign/scientific.py,sha256=a4JxOBgm9vzNZKpJ_GQIQf7cokkraV5nh23HGbmTYKw,5064
-oafuncs-0.0.98.14.dist-info/licenses/LICENSE.txt,sha256=rMtLpVg8sKiSlwClfR9w_Dd_5WubTQgoOzE2PDFxzs4,1074
-oafuncs-0.0.98.14.dist-info/METADATA,sha256=1PncdzppTVKdYUjg_Njkg72cbwrri3GIrqexxl0_sVs,4273
-oafuncs-0.0.98.14.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
-oafuncs-0.0.98.14.dist-info/top_level.txt,sha256=bgC35QkXbN4EmPHEveg_xGIZ5i9NNPYWqtJqaKqTPsQ,8
-oafuncs-0.0.98.14.dist-info/RECORD,,
+oafuncs-0.0.98.15.dist-info/licenses/LICENSE.txt,sha256=rMtLpVg8sKiSlwClfR9w_Dd_5WubTQgoOzE2PDFxzs4,1074
+oafuncs-0.0.98.15.dist-info/METADATA,sha256=jTAHHAY0xOxy2z13wYD4x4JOOSfsUxrz1WVyzXNfi9o,4273
+oafuncs-0.0.98.15.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+oafuncs-0.0.98.15.dist-info/top_level.txt,sha256=bgC35QkXbN4EmPHEveg_xGIZ5i9NNPYWqtJqaKqTPsQ,8
+oafuncs-0.0.98.15.dist-info/RECORD,,