AcidMap/Water/Python_codes/point_match.py

import csv
import math
from collections import defaultdict

def read_csv(file_path):
    """读取CSV文件并返回数据列表"""
    data = []
    try:
        with open(file_path, 'r') as file:
            reader = csv.DictReader(file)
            for row in reader:
                data.append(row)
        return data
    except FileNotFoundError:
        print(f"错误: 文件 {file_path} 未找到!")
        return []
    except Exception as e:
        print(f"错误: 读取文件 {file_path} 时发生错误: {e}")
        return []

def calculate_distance(lat1, lon1, lat2, lon2):
    """计算两点之间的欧几里得距离（经纬度距离）"""
    # 将经纬度转换为浮点数
    try:
        lat1 = float(lat1)
        lon1 = float(lon1)
        lat2 = float(lat2)
        lon2 = float(lon2)
    except ValueError:
        print("错误: 经纬度转换为浮点数失败")
        return float('inf')
    
    # 简单的欧几里得距离计算，适用于小范围区域
    # 如需更精确的距离计算（考虑地球曲率），可使用Haversine公式
    dx = lat2 - lat1
    dy = lon2 - lon1
    return math.sqrt(dx*dx + dy*dy)

def find_nearest_sample(farmland_point, sample_points, farmland_id=None):
    """为给定的耕地中心点找到最近的采样点并返回其cd值"""
    min_distance = float('inf')
    nearest_cd = None
    
    farm_lat = farmland_point.get('中心点经度')
    farm_lon = farmland_point.get('中心点纬度')
    farm_style = farmland_point.get('DLMC')
    
    if not farm_lat or not farm_lon:
        print(f"警告: 耕地 ID {farmland_id} 缺少经纬度信息")
        return None
    
    for sample in sample_points:
        sample_lat = sample.get('经度')
        sample_lon = sample.get('纬度')
        sample_cd = sample.get('Cd (ug/L)')
        
        if not sample_lat or not sample_lon or not sample_cd:
            continue
        
        distance = calculate_distance(farm_lat, farm_lon, sample_lat, sample_lon)
        if distance < min_distance:
            min_distance = distance
            nearest_cd = sample_cd
    nearest_cd = float(nearest_cd)
    A = 711 * 0.524
    B = 427 * 0.599
    C = 200 * 0.7
    if farm_style == "水浇地":
        nearest_cd = B*nearest_cd
    elif farm_style == "水田":
        nearest_cd = A*nearest_cd
    else:
        nearest_cd = C*nearest_cd
    return nearest_cd

def merge_data(farmland_data, sample_data):
    """合并耕地数据和最近的采样点cd数据"""
    merged_data = []
    unmatched_count = 0
    
    for farmland in farmland_data:
        farmland_id = farmland.get('id', '未知ID')
        nearest_cd = find_nearest_sample(farmland, sample_data, farmland_id)
        
        # 创建新的合并记录，只包含中心点坐标和cd值
        merged_record = {
            'lon': farmland.get('中心点经度'),
            'lan': farmland.get('中心点纬度'),
            'Prediction': nearest_cd
        }
        
        if nearest_cd is None:
            unmatched_count += 1
        
        merged_data.append(merged_record)
    
    if unmatched_count > 0:
        print(f"警告: {unmatched_count} 个耕地没有找到匹配的采样点cd值")
    
    return merged_data

def write_csv(data, output_file):
    """将数据写入CSV文件并指定字段顺序"""
    if not data:
        print("错误: 没有数据可写入")
        return
    
    # 显式指定字段顺序
    fieldnames = ['lon', 'lan', 'Prediction']
    
    try:
        with open(output_file, 'w', newline='', encoding='utf-8') as file:
            writer = csv.DictWriter(file, fieldnames=fieldnames)
            writer.writeheader()
            writer.writerows(data)
        print(f"成功将数据写入 {output_file}，字段顺序: {', '.join(fieldnames)}")
    except Exception as e:
        print(f"错误: 写入文件 {output_file} 时发生错误: {e}")

def main():
    """主函数 - 使用数据库数据进行点匹配"""
    import sys
    from pathlib import Path
    
    # 添加项目根目录到Python路径
    project_root = Path(__file__).parent.parent.parent
    sys.path.append(str(project_root))
    
    # 导入数据库服务
    from app.services.land_use_service import land_use_service
    
    # 设置要处理的土地类型
    land_type = "水浇地"
    
    # 从数据库获取土地利用数据
    print(f"正在从数据库读取 {land_type} 数据...")
    land_centers_df = land_use_service.get_land_centers_for_processing(land_type)
    
    if land_centers_df is None or land_centers_df.empty:
        print(f"数据库中没有找到 '{land_type}' 类型的土地利用数据")
        return
    
    print(f"已从数据库读取 {len(land_centers_df)} 条 {land_type} 记录")
    
    # 转换为字典格式以兼容现有函数
    farmland_data = []
    for _, row in land_centers_df.iterrows():
        farmland_data.append({
            'id': row['gid'],
            '中心点经度': row['center_lon'],
            '中心点纬度': row['center_lat'],
            'DLMC': row['dlmc']
        })
    
    # 配置文件路径
    sample_file = Path(__file__).parent.parent / "Data" / "SamplingPoint.csv"
    output_dir = Path(__file__).parent.parent / "Data"
    output_dir.mkdir(exist_ok=True)
    output_file = output_dir / f"matched_data_{land_type}_DB.csv"
    
    print("正在读取采样点数据...")
    sample_data = read_csv(str(sample_file))
    print(f"已读取 {len(sample_data)} 条采样点记录")
    
    if not farmland_data or not sample_data:
        print("错误: 缺少必要的数据")
        return
    
    # 合并数据
    print("正在匹配最近的采样点...")
    merged_data = merge_data(farmland_data, sample_data)
    
    # 写入结果
    print("正在写入结果...")
    write_csv(merged_data, str(output_file))
    print(f"总共处理了 {len(merged_data)} 个 {land_type} 面要素")

if __name__ == "__main__":
    main()