oafuncs 0.0.98.19__py3-none-any.whl → 0.0.98.20__py3-none-any.whl

oafuncs/_script/data_interp.py

@@ -1,3 +1,18 @@
+#!/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: 2025-04-26 19:21:31
+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
@@ -8,10 +23,10 @@ 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)
+    用于PEx并行的单slice插值worker。
+    参数: data_slice, 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]
@@ -21,20 +36,16 @@ def _interp_single_worker(*args):
         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)
+    result = griddata(valid_points, valid_data, target_points, method=interpolation_method).reshape(target_shape)
+    # 对仍为 NaN 的点用最近邻填充
+    if np.isnan(result).any():
+        nn = griddata(valid_points, valid_data, target_points, method="nearest").reshape(target_shape)
+        result[np.isnan(result)] = nn[np.isnan(result)]
 
     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:
+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.
 
@@ -46,7 +57,6 @@ def interp_2d_func(
         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.
@@ -60,7 +70,7 @@ def interp_2d_func(
         >>> 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)
+        >>> result = interp_2d_func(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:
@@ -80,7 +90,7 @@ def interp_2d_func(
         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]")
+        raise ValueError(f"Source data has {data_dims} dimensions, but this function currently supports only up to 4.")
 
     # Reshape to 4D by adding leading dimensions of size 1 if needed
     num_dims_to_add = 4 - data_dims

oafuncs/_script/data_interp_geo.py

@@ -1,98 +1,167 @@
 from typing import List, Union
 
 import numpy as np
-from scipy.interpolate import RectBivariateSpline
+from scipy.interpolate import NearestNDInterpolator, griddata
 
 from oafuncs.oa_tool import PEx
-from oafuncs.oa_data import data_clip
-from oafuncs._script.data_interp import _fill_nan_nearest
 
 
-def _interp_single_worker(*args):
+def _normalize_lon(lon, ref_lon):
     """
-    单slice插值worker，参数为(data_slice, sx, sy, tx, ty, interpolation_method, data_min, data_max)
+    将经度数组 lon 归一化到与 ref_lon 相同的区间（[-180,180] 或 [0,360]）
+    并在经度分界（如180/-180, 0/360）附近自动拓宽，避免插值断裂。
     """
-    # 兼容PEx调用方式：args为tuple或list
-    if len(args) == 1 and isinstance(args[0], (tuple, list)):
-        args = args[0]
-    data_slice, sx, sy, tx, ty, interpolation_method, data_min, data_max = args
-    # 处理nan
-    if np.isnan(data_slice).any():
-        mask = np.isnan(data_slice)
-        if mask.any():
-            data_slice = _fill_nan_nearest(data_slice)
-    x1d = np.unique(sx[0, :])
-    y1d = np.unique(sy[:, 0])
-    if sx.shape != (len(y1d), len(x1d)) or sy.shape != (len(y1d), len(x1d)):
-        from scipy.interpolate import griddata
-
-        grid_points = np.column_stack((sx.ravel(), sy.ravel()))
-        grid_values = data_slice.ravel()
-        data_slice = griddata(grid_points, grid_values, (x1d[None, :], y1d[:, None]), method="linear")
-    if interpolation_method == "linear":
-        kx = ky = 1
+    lon = np.asarray(lon)
+    ref_lon = np.asarray(ref_lon)
+    if np.nanmax(ref_lon) > 180:
+        lon = np.where(lon < 0, lon + 360, lon)
     else:
-        kx = ky = 3
-    interp_func = RectBivariateSpline(y1d, x1d, data_slice, kx=kx, ky=ky)
-    out = interp_func(ty[:, 0], tx[0, :])
-    # 优化裁剪逻辑：超出范围的点设为nan，再用fill_nan_nearest填充
-    arr = np.asarray(out)
-    arr = data_clip(arr,data_min,data_max)
-    return arr
-
-
-def interp_2d_geo(
-    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:
+        lon = np.where(lon > 180, lon - 360, lon)
+    return lon
+
+
+def _expand_lonlat_for_dateline(points, values):
+    """
+    对经度分界（如180/-180, 0/360）附近的数据进行拓宽，避免插值断裂。
+    points: (N,2) [lon,lat]
+    values: (N,)
+    返回拓宽后的 points, values
+    """
+    lon = points[:, 0]
+    lat = points[:, 1]
+    expanded_points = [points]
+    expanded_values = [values]
+    if (np.nanmax(lon) > 170) and (np.nanmin(lon) < -170):
+        expanded_points.append(np.column_stack((lon + 360, lat)))
+        expanded_points.append(np.column_stack((lon - 360, lat)))
+        expanded_values.append(values)
+        expanded_values.append(values)
+    if (np.nanmax(lon) > 350) and (np.nanmin(lon) < 10):
+        expanded_points.append(np.column_stack((lon - 360, lat)))
+        expanded_points.append(np.column_stack((lon + 360, lat)))
+        expanded_values.append(values)
+        expanded_values.append(values)
+    points_new = np.vstack(expanded_points)
+    values_new = np.concatenate(expanded_values)
+    return points_new, values_new
+
+
+def _interp_single_worker(*args):
     """
-    更平滑的二维插值，采用RectBivariateSpline实现bicubic效果，接口与interp_2d兼容。
-    支持输入2D/3D/4D数据，最后两维为空间。
-    interpolation_method: "cubic"（默认，bicubic），"linear"（双线性）
-    插值后自动裁剪并用最近邻填充超限和NaN，范围取原始数据的nanmin/nanmax
+    用于PEx并行的单slice插值worker。
+    参数: data_slice, origin_points, target_points, interpolation_method, target_shape
+    球面插值：经纬度转球面坐标后插值
     """
-    # 保证输入为ndarray
-    tx = np.asarray(target_x_coordinates)
-    ty = np.asarray(target_y_coordinates)
-    sx = np.asarray(source_x_coordinates)
-    sy = np.asarray(source_y_coordinates)
-    data = np.asarray(source_data)
-
-    if ty.ndim == 1:
-        tx, ty = np.meshgrid(tx, ty)
-    if sy.ndim == 1:
-        sx, sy = np.meshgrid(sx, sy)
-
-    if sx.shape != data.shape[-2:] or sy.shape != data.shape[-2:]:
-        raise ValueError("Shape of source_data does not match shape of source_x_coordinates or source_y_coordinates.")
-
-    data_dims = data.ndim
+    data_slice, origin_points, target_points, interpolation_method, target_shape = args
+
+    # 经纬度归一化
+    origin_points = origin_points.copy()
+    target_points = target_points.copy()
+    origin_points[:, 0] = _normalize_lon(origin_points[:, 0], target_points[:, 0])
+    target_points[:, 0] = _normalize_lon(target_points[:, 0], origin_points[:, 0])
+
+    def lonlat2xyz(lon, lat):
+        lon_rad = np.deg2rad(lon)
+        lat_rad = np.deg2rad(lat)
+        x = np.cos(lat_rad) * np.cos(lon_rad)
+        y = np.cos(lat_rad) * np.sin(lon_rad)
+        z = np.sin(lat_rad)
+        return np.stack([x, y, z], axis=-1)
+
+    # 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:
+        return np.full(target_shape, np.nanmean(data_slice))
+
+    # 拓宽经度分界，避免如179/-181插值断裂
+    valid_points_exp, valid_data_exp = _expand_lonlat_for_dateline(valid_points, valid_data)
+
+    valid_xyz = lonlat2xyz(valid_points_exp[:, 0], valid_points_exp[:, 1])
+    target_xyz = lonlat2xyz(target_points[:, 0], target_points[:, 1])
+
+    # 使用 griddata 的 cubic 插值以获得更好平滑效果
+    result = griddata(valid_xyz, valid_data_exp, target_xyz, method=interpolation_method).reshape(target_shape)
+
+    # 用最近邻处理残余 NaN
+    if np.isnan(result).any():
+        nn_interp = NearestNDInterpolator(valid_xyz, valid_data_exp)
+        nn = nn_interp(target_xyz).reshape(target_shape)
+        result[np.isnan(result)] = nn[np.isnan(result)]
+
+    return result
+
+
+def interp_2d_func_geo(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 (spherical coordinates).
+    使用球面坐标系进行插值，适用于全球尺度的地理数据，能正确处理经度跨越日期线的情况。
+
+    Args:
+        target_x_coordinates (Union[np.ndarray, List[float]]): Target grid's longitude (-180 to 180 or 0 to 360).
+        target_y_coordinates (Union[np.ndarray, List[float]]): Target grid's latitude (-90 to 90).
+        source_x_coordinates (Union[np.ndarray, List[float]]): Original grid's longitude (-180 to 180 or 0 to 360).
+        source_y_coordinates (Union[np.ndarray, List[float]]): Original grid's latitude (-90 to 90).
+        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.
+
+    Returns:
+        np.ndarray: Interpolated data array.
+
+    Raises:
+        ValueError: If input shapes are invalid.
+
+    Examples:
+        >>> # 创建一个全球网格示例
+        >>> target_lon = np.arange(-180, 181, 1)  # 1度分辨率目标网格
+        >>> target_lat = np.arange(-90, 91, 1)
+        >>> source_lon = np.arange(-180, 181, 5)  # 5度分辨率源网格
+        >>> source_lat = np.arange(-90, 91, 5)
+        >>> # 创建一个简单的数据场 (例如温度场)
+        >>> source_data = np.cos(np.deg2rad(source_lat.reshape(-1, 1))) * np.cos(np.deg2rad(source_lon))
+        >>> # 插值到高分辨率网格
+        >>> result = interp_2d_geo(target_lon, target_lat, source_lon, source_lat, source_data)
+        >>> print(result.shape)  # Expected output: (181, 361)
+    """
+    # 验证输入数据范围
+    if np.nanmin(target_y_coordinates) < -90 or np.nanmax(target_y_coordinates) > 90:
+        raise ValueError("[red]Target latitude must be in range [-90, 90].[/red]")
+    if np.nanmin(source_y_coordinates) < -90 or np.nanmax(source_y_coordinates) > 90:
+        raise ValueError("[red]Source latitude must be in range [-90, 90].[/red]")
+
+    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)
     if data_dims < 2:
-        raise ValueError("Source data must have at least 2 dimensions.")
+        raise ValueError(f"[red]Source data must have at least 2 dimensions, but got {data_dims}.[/red]")
     elif data_dims > 4:
-        raise ValueError("Source data has more than 4 dimensions, not supported.")
+        raise ValueError(f"Source data has {data_dims} dimensions, but this function currently supports only up to 4.")
 
     num_dims_to_add = 4 - data_dims
-    new_shape = (1,) * num_dims_to_add + data.shape
-    data4d = data.reshape(new_shape)
-    t, z, ny, nx = data4d.shape
+    new_shape = (1,) * num_dims_to_add + source_data.shape
+    new_src_data = source_data.reshape(new_shape)
 
-    data_min, data_max = np.nanmin(data), np.nanmax(data)
-    target_shape = ty.shape
+    t, z, y, x = new_src_data.shape
 
-    # 并行参数准备
     params = []
-    for ti in range(t):
-        for zi in range(z):
-            params.append((data4d[ti, zi], sx, sy, tx, ty, interpolation_method, data_min, data_max))
+    target_shape = target_y_coordinates.shape
+    for t_index in range(t):
+        for z_index in range(z):
+            params.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, params)
 
-    result = np.array(result).reshape(t, z, *target_shape)
-    result = np.squeeze(result)
-    return result
+    return np.squeeze(np.array(result).reshape(t, z, *target_shape))

oafuncs/_script/netcdf_merge.py

@@ -1,26 +1,10 @@
-#!/usr/bin/env python
-# coding=utf-8
-"""
-Author: Liu Kun && 16031215@qq.com
-Date: 2025-03-30 11:16:29
-LastEditors: Liu Kun && 16031215@qq.com
-LastEditTime: 2025-04-25 14:23:10
-FilePath: \\Python\\My_Funcs\\OAFuncs\\oafuncs\\_script\\netcdf_merge.py
-Description
-EditPlatform: vscode
-ComputerInfo: XPS 15 9510
-SystemInfo: Windows 11
-Python Version: 3.12
-"""
-
+import logging
 import os
 from typing import List, Optional, Union
-
 import numpy as np
 import xarray as xr
 
 from oafuncs import pbar
-import logging
 
 
 def merge_nc(file_list: Union[str, List[str]], var_name: Optional[Union[str, List[str]]] = None, dim_name: Optional[str] = None, target_filename: Optional[str] = None) -> None:
@@ -75,26 +59,41 @@ def merge_nc(file_list: Union[str, List[str]], var_name: Optional[Union[str, Lis
                 if dim_name in data_var.dims:
                     merged_data.setdefault(var, []).append(data_var)
                 elif var not in merged_data:
-                    # 判断类型，时间类型用NaT填充
-                    if np.issubdtype(data_var.dtype, np.datetime64):
-                        merged_data[var] = data_var.fillna(np.datetime64("NaT"))
-                    else:
-                        merged_data[var] = data_var.fillna(0)
+                    # 区分更细致的类型，不仅是时间型和非时间型
+                    if data_var.dtype.kind == "M":  # datetime64类型
+                        merged_data[var] = data_var  # 时间类型在save_to_nc处理
+                    elif data_var.dtype.kind in ["f", "i", "u"]:  # 数值类型
+                        # 对数值型变量用-32767填充NaN，而不是0
+                        merged_data[var] = data_var.fillna(-32767)
+                    else:  # 字符串或其他类型
+                        merged_data[var] = data_var  # 非数值类型保持原样
 
     for var in pbar(merged_data, description="Merging variables"):
         if isinstance(merged_data[var], list):
-            # 判断类型，时间类型用NaT填充
-            if np.issubdtype(merged_data[var][0].dtype, np.datetime64):
-                merged_data[var] = xr.concat(merged_data[var], dim=dim_name).fillna(np.datetime64("NaT"))
-            else:
-                merged_data[var] = xr.concat(merged_data[var], dim=dim_name).fillna(0)
+            # 区分更细致的类型处理
+            if merged_data[var][0].dtype.kind == "M":  # datetime64类型
+                merged_data[var] = xr.concat(merged_data[var], dim=dim_name)
+            elif merged_data[var][0].dtype.kind in ["f", "i", "u"]:  # 数值类型
+                # 使用-32767填充NaN，而不是0
+                merged_data[var] = xr.concat(merged_data[var], dim=dim_name).fillna(-32767)
+            else:  # 字符串或其他类型
+                merged_data[var] = xr.concat(merged_data[var], dim=dim_name)
+
+    # 在构建最终数据集前，再次检查确保所有数值型变量没有NaN
+    merged_ds = xr.Dataset(merged_data)
+    for var_name in merged_ds.data_vars:
+        var = merged_ds[var_name]
+        if var.dtype.kind in ["f", "i", "u"]:
+            if np.isnan(var.values).any():
+                logging.warning(f"变量 {var_name} 在合并后仍包含NaN值，将替换为-32767")
+                merged_ds[var_name] = var.fillna(-32767)
 
     if os.path.exists(target_filename):
         # print("Warning: The target file already exists. Removing it ...")
         logging.warning("The target file already exists. Removing it ...")
         os.remove(target_filename)
 
-    save_to_nc(target_filename, xr.Dataset(merged_data))
+    save_to_nc(target_filename, merged_ds)
 
 
 # Example usage

oafuncs/_script/netcdf_write.py

@@ -1,13 +1,55 @@
 import os
+import warnings
 
 import netCDF4 as nc
 import numpy as np
 import xarray as xr
-import warnings
 
 warnings.filterwarnings("ignore", category=RuntimeWarning)
 
 
+def _nan_to_fillvalue(ncfile):
+    """
+    将 NetCDF 文件中所有变量的 NaN 和掩码值替换为其 _FillValue 属性（若无则自动添加 _FillValue=-32767 并替换）。
+    同时处理掩码数组中的无效值。
+    仅对数值型变量（浮点型、整型）生效。
+    """
+    with nc.Dataset(ncfile, "r+") as ds:
+        for var_name in ds.variables:
+            var = ds.variables[var_name]
+            # 只处理数值类型变量 (f:浮点型, i:有符号整型, u:无符号整型)
+            if var.dtype.kind not in ["f", "i", "u"]:
+                continue
+
+            # 读取数据
+            arr = var[:]
+
+            # 确定填充值
+            if "_FillValue" in var.ncattrs():
+                fill_value = var.getncattr("_FillValue")
+            else:
+                fill_value = -32767
+                try:
+                    var.setncattr("_FillValue", fill_value)
+                except Exception:
+                    # 某些变量可能不允许动态添加 _FillValue
+                    continue
+
+            # 处理掩码数组
+            if hasattr(arr, "mask"):
+                # 如果是掩码数组，将掩码位置的值设为 fill_value
+                if np.any(arr.mask):
+                    # 转换为普通数组，掩码位置填入 fill_value
+                    arr = np.ma.filled(arr, fill_value=fill_value)
+
+            # 处理剩余NaN值
+            if np.any(np.isnan(arr)):
+                arr = np.nan_to_num(arr, nan=fill_value, posinf=fill_value, neginf=fill_value)
+
+            # 写回变量
+            var[:] = arr
+
+
 def _numpy_to_nc_type(numpy_type):
     """将 NumPy 数据类型映射到 NetCDF 数据类型"""
     numpy_to_nc = {
@@ -30,17 +72,22 @@ def _calculate_scale_and_offset(data, n=16):
     """
     计算数值型数据的 scale_factor 与 add_offset，
     将数据映射到 [0, 2**n - 1] 的范围。
-
-    要求 data 为数值型的 NumPy 数组，不允许全 NaN 值。
+    同时处理数据中的 NaN 值。
     """
     if not isinstance(data, np.ndarray):
         raise ValueError("Input data must be a NumPy array.")
 
-    data_min = np.nanmin(data)
-    data_max = np.nanmax(data)
+    # 先处理数据中的 NaN 和无穷值
+    clean_data = np.nan_to_num(data, nan=-32767, posinf=np.finfo(float).max, neginf=np.finfo(float).min)
 
-    if np.isnan(data_min) or np.isnan(data_max):
-        raise ValueError("Input data contains NaN values.")
+    # 计算有效值的最小最大值（排除填充值）
+    valid_mask = clean_data != -32767
+    if np.any(valid_mask):
+        data_min = np.min(clean_data[valid_mask])
+        data_max = np.max(clean_data[valid_mask])
+    else:
+        # 全都是填充值的情况，使用默认范围
+        data_min, data_max = 0, 1
 
     if data_max == data_min:
         scale_factor = 1.0
@@ -111,6 +158,7 @@ def save_to_nc(file, data, varname=None, coords=None, mode="w", scale_offset_swi
                 new_da.to_dataset(name=varname).to_netcdf(file, mode=mode, encoding=encoding)
             else:
                 data.to_dataset(name=varname).to_netcdf(file, mode=mode)
+            _nan_to_fillvalue(file)  # 替换 NaN 为 _FillValue
             return
 
         else:
@@ -139,6 +187,7 @@ def save_to_nc(file, data, varname=None, coords=None, mode="w", scale_offset_swi
                 new_ds.to_netcdf(file, mode=mode, encoding=encoding)
             else:
                 new_ds.to_netcdf(file, mode=mode)
+        _nan_to_fillvalue(file)  # 替换 NaN 为 _FillValue
         return
 
     # 处理纯 numpy 数组情况
@@ -172,6 +221,7 @@ def save_to_nc(file, data, varname=None, coords=None, mode="w", scale_offset_swi
                 dtype = _numpy_to_nc_type(data.dtype)
                 var = ncfile.createVariable(varname, dtype, dims, zlib=False)
                 var[:] = data
+        _nan_to_fillvalue(file)  # 替换 NaN 为 _FillValue
     except Exception as e:
         raise RuntimeError(f"netCDF4 保存失败: {str(e)}") from e
 

oafuncs/_script/parallel.py

@@ -6,6 +6,7 @@ import time
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from typing import Any, Callable, Dict, List, Optional, Tuple
 
+
 import psutil
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
@@ -14,6 +15,7 @@ __all__ = ["ParallelExecutor"]
 
 
 class ParallelExecutor:
+    
     def __init__(
         self,
         max_workers: Optional[int] = None,
@@ -120,6 +122,7 @@ class ParallelExecutor:
                     self._executor = None
 
     def _execute_batch(self, func: Callable, params: List[Tuple], chunk_size: int) -> List[Any]:
+        from oafuncs.oa_tool import pbar
         if not params:
             return []
 
@@ -129,7 +132,7 @@ class ParallelExecutor:
         results = [None] * len(params)
         with self._get_executor() as executor:
             futures = {executor.submit(func, *args): idx for idx, args in enumerate(params)}
-            for future in as_completed(futures):
+            for future in pbar(as_completed(futures), "Parallel Tasks", total=len(futures)):
                 idx = futures[future]
                 try:
                     results[idx] = future.result(timeout=self.timeout_per_task)

oafuncs/oa_data.py

@@ -23,7 +23,7 @@ from rich import print
 from scipy.interpolate import interp1d
 
 
-__all__ = ["interp_along_dim", "interp_2d", "ensure_list", "mask_shapefile"]
+__all__ = ["interp_along_dim", "interp_2d", "interp_2d_geo", "ensure_list", "mask_shapefile"]
 
 
 def ensure_list(input_value: Any) -> List[str]:
@@ -120,7 +120,7 @@ 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 = "linear",
+    interpolation_method: str = "cubic",
 ) -> np.ndarray:
     """
     Perform 2D interpolation on the last two dimensions of a multi-dimensional array.
@@ -132,7 +132,7 @@ def interp_2d(
         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.
             >>> must be [y, x] or [*, y, x] or [*, *, y, x]
-        interpolation_method (str, optional): Interpolation method. Defaults to "linear".
+        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.
 
@@ -162,7 +162,47 @@ def interp_2d(
         interpolation_method=interpolation_method,
     )
 
+def interp_2d_geo(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 (spherical coordinates).
+    使用球面坐标系进行插值，适用于全球尺度的地理数据，能正确处理经度跨越日期线的情况。
+
+    Args:
+        target_x_coordinates (Union[np.ndarray, List[float]]): Target grid's longitude (-180 to 180 or 0 to 360).
+        target_y_coordinates (Union[np.ndarray, List[float]]): Target grid's latitude (-90 to 90).
+        source_x_coordinates (Union[np.ndarray, List[float]]): Original grid's longitude (-180 to 180 or 0 to 360).
+        source_y_coordinates (Union[np.ndarray, List[float]]): Original grid's latitude (-90 to 90).
+        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.
+
+    Returns:
+        np.ndarray: Interpolated data array.
+
+    Raises:
+        ValueError: If input shapes are invalid.
 
+    Examples:
+        >>> # 创建一个全球网格示例
+        >>> target_lon = np.arange(-180, 181, 1)  # 1度分辨率目标网格
+        >>> target_lat = np.arange(-90, 91, 1)
+        >>> source_lon = np.arange(-180, 181, 5)  # 5度分辨率源网格
+        >>> source_lat = np.arange(-90, 91, 5)
+        >>> # 创建一个简单的数据场 (例如温度场)
+        >>> source_data = np.cos(np.deg2rad(source_lat.reshape(-1, 1))) * np.cos(np.deg2rad(source_lon))
+        >>> # 插值到高分辨率网格
+        >>> result = interp_2d_geo(target_lon, target_lat, source_lon, source_lat, source_data)
+        >>> print(result.shape)  # Expected output: (181, 361)
+    """
+    from ._script.data_interp_geo import interp_2d_func_geo
+    interp_2d_func_geo(
+        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,
+    )
 
 def mask_shapefile(
     data_array: np.ndarray,

{oafuncs-0.0.98.19.dist-info → oafuncs-0.0.98.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: oafuncs
-Version: 0.0.98.19
+Version: 0.0.98.20
 Summary: Oceanic and Atmospheric Functions
 Home-page: https://github.com/Industry-Pays/OAFuncs
 Author: Kun Liu

{oafuncs-0.0.98.19.dist-info → oafuncs-0.0.98.20.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=y11xxaVNZ6_eveVjSG4PisRXYpKr_FFsBBh0mj_ss2g,8436
+oafuncs/oa_data.py,sha256=Aat9ktxxRGevaqQya3IJWfXeoEs-FCXGUcNE2pKnzfU,10931
 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
@@ -11,13 +11,13 @@ 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=KJ-p-UN3Op1MmtCoN4KdjFVHFE3GNHrTD3vBjzaYSjQ,4688
-oafuncs/_script/data_interp_geo.py,sha256=X89KxLYhpltWi0Sf96gIhBL3r1M5aExd_JCmgBmmvUc,3742
+oafuncs/_script/data_interp.py,sha256=EiZbt6n5BEaRKcng88UgX7TFPhKE6TLVZniS01awXjg,5146
+oafuncs/_script/data_interp_geo.py,sha256=ZRFb3fKRiYQViZNHd19eW20C9i38BsiIU8w0fG5mbqM,7789
 oafuncs/_script/email.py,sha256=lL4HGKrr524-g0xLlgs-4u7x4-u7DtgNoD9AL8XJKj4,3058
-oafuncs/_script/netcdf_merge.py,sha256=9hCyxfeUHnBzs50_0v0jzVfxpMxTX4dNTo0pmsp_T6g,4226
+oafuncs/_script/netcdf_merge.py,sha256=zasqrFpB2GHAjZ1LkrWtI7kpHu7uCjdIGf4C0lEraYA,4816
 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
+oafuncs/_script/netcdf_write.py,sha256=gEqeagAcu0_xa6cIuu7a5d9uXMEaGqnci02KNc5znEY,10672
+oafuncs/_script/parallel.py,sha256=07-BJVHxXJNlrOrhrSGt7qCZiKWq6dBvNDBA1AANYnI,8861
 oafuncs/_script/parallel_test.py,sha256=0GBqZOX7IaCOKF2t1y8N8YYu53GJ33OkfsWgpvZNqM4,372
 oafuncs/_script/plot_dataset.py,sha256=zkSEnO_-biyagorwWXPoihts_cwuvripzEt-l9bHJ2E,13989
 oafuncs/_script/replace_file_content.py,sha256=eCFZjnZcwyRvy6b4mmIfBna-kylSZTyJRfgXd6DdCjk,5982
@@ -39,8 +39,8 @@ 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-0.0.98.19.dist-info/licenses/LICENSE.txt,sha256=rMtLpVg8sKiSlwClfR9w_Dd_5WubTQgoOzE2PDFxzs4,1074
-oafuncs-0.0.98.19.dist-info/METADATA,sha256=PJ_1BA6QOeA2QHSb61jwOFA2pDD2H4QT--m3tf_f44I,4273
-oafuncs-0.0.98.19.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
-oafuncs-0.0.98.19.dist-info/top_level.txt,sha256=bgC35QkXbN4EmPHEveg_xGIZ5i9NNPYWqtJqaKqTPsQ,8
-oafuncs-0.0.98.19.dist-info/RECORD,,
+oafuncs-0.0.98.20.dist-info/licenses/LICENSE.txt,sha256=rMtLpVg8sKiSlwClfR9w_Dd_5WubTQgoOzE2PDFxzs4,1074
+oafuncs-0.0.98.20.dist-info/METADATA,sha256=QgOUX1DWWv2bLiGauzfcJsKtuGQfyJkinMJoCO7FRdI,4273
+oafuncs-0.0.98.20.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+oafuncs-0.0.98.20.dist-info/top_level.txt,sha256=bgC35QkXbN4EmPHEveg_xGIZ5i9NNPYWqtJqaKqTPsQ,8
+oafuncs-0.0.98.20.dist-info/RECORD,,