import geopandas as gpd import pandas as pd import rasterio from rasterio.features import rasterize import numpy as np from shapely.geometry import mapping, box import os from tqdm import tqdm # 导入 tqdm 用于进度条 def merge_vectors_seven_categories(file_paths, output_vector_path): """ 合并7个地貌类型矢量图层并保存为GeoPackage格式（去掉cropland） 参数: file_paths: 包含7个矢量文件路径的列表 (按顺序: forest, water, shrub, wetland, jianzhu, grass, bareland) output_vector_path: 输出合并后的矢量文件路径（使用.gpkg格式） """ try: # 检查输入文件数量是否为7 if len(file_paths) != 7: raise ValueError("请提供正好7个矢量文件路径") for path in file_paths: if not os.path.exists(path): raise FileNotFoundError(f"文件不存在: {path}") # 定义7个类别（去掉cropland） categories = ['forest', 'water', 'shrub', 'wetland', 'jianzhu', 'grass', 'bareland'] category_values = {cat: i + 1 for i, cat in enumerate(categories)} # forest=1, water=2, ..., bareland=7 gdfs = [] for i, (path, category) in enumerate(zip(file_paths, categories), 1): print(f"正在读取第{i}个矢量文件: {path}") gdf = gpd.read_file(path, engine="pyogrio") gdf['category'] = category gdf['value'] = category_values[category] if 'Shape_Area' in gdf.columns: gdf['Shape_Area'] = gdf['Shape_Area'].clip(upper=1e9) gdfs.append(gdf) # 统一坐标系 base_crs = gdfs[0].crs for i, gdf in enumerate(gdfs[1:], 2): if gdf.crs != base_crs: print(f"第{i}个图层坐标系不同，正在转换为第一个图层的坐标系...") gdfs[i - 1] = gdf.to_crs(base_crs) print("正在合并图层...") merged_gdf = gpd.GeoDataFrame(pd.concat(gdfs, ignore_index=True)) merged_gdf = merged_gdf.set_geometry('geometry') if not output_vector_path.endswith('.gpkg'): output_vector_path = output_vector_path.replace('.shp', '.gpkg') print("输出格式已更改为GeoPackage以支持大文件") print(f"正在保存合并矢量结果到: {output_vector_path}") merged_gdf.to_file(output_vector_path, driver='GPKG', engine="pyogrio") print("矢量合并完成！") print(f"合并矢量保存为: {output_vector_path}") return output_vector_path except Exception as e: print(f"发生错误: {str(e)}") return None def rasterize_vector_by_blocks(input_vector_path, output_raster_path, raster_resolution=30, block_size=5000): """ 将合并后的矢量文件分块转为栅格，显示7个类别，背景值设为 value=8，添加进度条，不清理数据 参数: input_vector_path: 输入的合并矢量文件路径（.gpkg格式） output_raster_path: 输出栅格文件路径 raster_resolution: 输出栅格的分辨率（默认30米） block_size: 每个分块的宽度和高度（像素单位，默认5000） """ try: # 读取合并后的矢量文件 print(f"正在读取合并矢量文件: {input_vector_path}") merged_gdf = gpd.read_file(input_vector_path, engine="pyogrio") # 检查 value 字段是否有效 if 'value' not in merged_gdf.columns: raise ValueError("矢量文件中缺少 'value' 字段，请确保文件包含正确的分类值") if not merged_gdf['value'].between(1, 7).all(): print("警告: 'value' 字段包含无效值（应在 1-7 之间），可能导致数据丢失") merged_gdf = merged_gdf[merged_gdf['value'].between(1, 7)] # 按 value 字段排序，优先级高的类别（例如 value 较大）后处理，避免被覆盖 print("正在按 'value' 字段排序以确保优先级...") merged_gdf = merged_gdf.sort_values(by='value', ascending=True) # 计算总范围和栅格尺寸 bounds = merged_gdf.total_bounds # [minx, miny, maxx, maxy] total_width = int((bounds[2] - bounds[0]) / raster_resolution) total_height = int((bounds[3] - bounds[1]) / raster_resolution) if total_width <= 0 or total_height <= 0: raise ValueError(f"栅格尺寸无效: 宽度={total_width}, 高度={total_height}") # 创建栅格变换 transform = rasterio.transform.from_bounds(bounds[0], bounds[1], bounds[2], bounds[3], total_width, total_height) # 计算总分块数以设置进度条 total_blocks = ((total_height + block_size - 1) // block_size) * ((total_width + block_size - 1) // block_size) print(f"总分块数: {total_blocks}") # 创建并写入栅格文件，逐块写入以减少内存占用 with rasterio.open( output_raster_path, 'w', driver='GTiff', height=total_height, width=total_width, count=1, dtype=rasterio.uint8, crs=merged_gdf.crs, transform=transform, nodata=255 # 使用 255 作为 nodata 值，区分 value=8 的背景 ) as dst: # 分块处理并添加进度条 with tqdm(total=total_blocks, desc="栅格化进度") as pbar: for y in range(0, total_height, block_size): for x in range(0, total_width, block_size): block_height = min(block_size, total_height - y) block_width = min(block_size, total_width - x) # 计算当前分块的地理范围 block_minx = bounds[0] + x * raster_resolution block_maxy = bounds[3] - y * raster_resolution block_maxx = block_minx + block_width * raster_resolution block_miny = block_maxy - block_height * raster_resolution # 创建分块边界框 block_bounds = box(block_minx, block_miny, block_maxx, block_maxy) block_gdf = merged_gdf[merged_gdf.geometry.intersects(block_bounds)].copy() # 初始化分块为背景值 8 block_raster = np.full((block_height, block_width), 8, dtype=np.uint8) if not block_gdf.empty: # 分块栅格化 block_transform = rasterio.transform.from_bounds( block_minx, block_miny, block_maxx, block_miny, block_width, block_height ) shapes = ((mapping(geom), value) for geom, value in zip(block_gdf.geometry, block_gdf['value'])) block_raster = rasterize( shapes=shapes, out=block_raster, # 使用预初始化的数组 transform=block_transform, fill=8, # 未覆盖区域为 8 dtype=rasterio.uint8, all_touched=True # 确保所有触及的像素都被计入 ) # 直接写入当前分块到文件中 dst.write(block_raster, 1, window=((y, y + block_height), (x, x + block_width))) print(f"已完成分块栅格化: x={x}, y={y}, 宽度={block_width}, 高度={block_height}") pbar.update(1) print("栅格化完成！") print(f"栅格保存为: {output_raster_path}") print(f"栅格中类别值: 1=forest, 2=water, 3=shrub, 4=wetland, 5=jianzhu, 6=grass, 7=bareland, 8=background") except Exception as e: print(f"发生错误: {str(e)}") # 使用示例 if __name__ == "__main__": input_files = [ r"sddimaoshp/forest/sdforest.shp", r"sddimaoshp/water/sdwater.shp", r"sddimaoshp/shrub/sdshrub.shp", r"sddimaoshp/wetland/sdwetland.shp", r"sddimaoshp/jianzhu/jianzhu2.shp", r"sddimaoshp/grass/sdgrass.shp", r"sddimaoshp/bareland/sdbareland.shp" ] output_vector_file = r"sddimaoshp/hebingtif/shandongdimiao31.gpkg" output_raster_file = r"sddimaoshp/hebingtif/sddimao31.tif" # Step 1: 合并矢量 vector_path = merge_vectors_seven_categories(input_files, output_vector_file) # Step 2: 如果合并成功，进行分块栅格化 if vector_path: rasterize_vector_by_blocks(vector_path, output_raster_file, raster_resolution=10, block_size=5000)