init: KG_ICH 项目初始化

- data/: 非遗地理编码数据（GIS shapefile + CSV） - dofile/kg_project/: 知识图谱构建代码（纳入主仓库） - dofile/visulization/: 可视化数据与路线图 - officefile/: 文献、草稿、bib 文档 - officefile/latex/: Overleaf 同步目录（独立管理，不纳入） - output/: 输出目录 - logs/: 日志目录
2026-05-30 00:52:36 +08:00
commit 834cad729f
44 changed files with 8586 additions and 0 deletions
@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+import pandas as pd
+import json
+import time
+import os
+from urllib.request import urlopen, quote
+
+# 添加skill scripts到路径
+skill_dir = r'C:\Users\xiaopeng\.claude\skills\geocoding-cn\scripts'
+if skill_dir not in os.sys.path:
+    os.sys.path.insert(0, skill_dir)
+
+from coordinate_transform import CoordinateTransformer
+
+# 读取数据
+input_file = r'E:\Project\2026_KG_ICH\data\黑龙江国家级和省级非遗名单-地理编码-最终.xlsx'
+df = pd.read_excel(input_file)
+
+# 百度地图API配置
+AK = "L5SlQ1Kwmg6zaESvmc6RKG37yK2va7Ry"
+BASE_URL = 'https://api.map.baidu.com/geocoding/v3/'
+
+def geocode_with_retry(address):
+    """尝试多次地理编码，使用不同的地址格式"""
+    attempts = [
+        address,  # 原始地址
+        f"黑龙江省{address}",  # 添加省名
+        f"{address}黑龙江",  # 省名在后
+        f"中国黑龙江省{address}",  # 添加国家
+    ]
+
+    for attempt in attempts:
+        try:
+            encoded_address = quote(attempt)
+            url = f'{BASE_URL}?address={encoded_address}&output=json&ak={AK}'
+            req = urlopen(url, timeout=10)
+            response = req.read().decode()
+            result = json.loads(response)
+
+            if result['status'] == 0:
+                location = result['result']['location']
+                return location['lat'], location['lng'], attempt
+        except Exception as e:
+            continue
+
+        time.sleep(0.2)
+
+    return None, None, None
+
+# 问题记录索引（0-based）
+problematic_indices = [20, 127, 148, 161, 185, 199, 214, 58, 223]
+
+print("=== 重新地理编码问题记录 ===\n")
+
+success_count = 0
+for idx in problematic_indices:
+    if idx >= len(df):
+        continue
+
+    row = df.iloc[idx]
+    original_address = str(row.iloc[1])  # 项目保护单位列
+
+    print(f"Row {idx+1}: {original_address}")
+    print(f"   Old coords: {row['wgs84_lat']:.4f}N, {row['wgs84_lon']:.4f}E")
+
+    # 尝试重新地理编码
+    lat, lon, used_address = geocode_with_retry(original_address)
+
+    if lat and lon:
+        # 转换为WGS84
+        wgs_lon, wgs_lat = CoordinateTransformer.bd09_to_wgs84(lon, lat)
+
+        print(f"   New BD09: {lat:.4f}N, {lon:.4f}E")
+        print(f"   New WGS84: {wgs_lat:.4f}N, {wgs_lon:.4f}E")
+        print(f"   Used address: {used_address}")
+
+        # 检查是否在合理范围内
+        if 43 <= wgs_lat <= 53 and 121 <= wgs_lon <= 135:
+            print(f"   OK: Within Heilongjiang range")
+            # 更新数据
+            df.at[idx, 'bd09_lat'] = lat
+            df.at[idx, 'bd09_lon'] = lon
+            df.at[idx, 'wgs84_lat'] = wgs_lat
+            df.at[idx, 'wgs84_lon'] = wgs_lon
+            df.at[idx, 'geocode_status'] = 'success'
+            success_count += 1
+        else:
+            print(f"   WARNING: Still outside range (43-53N, 121-135E)")
+    else:
+        print(f"   FAILED: Geocoding failed")
+
+    print()
+    time.sleep(0.3)
+
+# 保存更新后的文件
+output_file = r'E:\Project\2026_KG_ICH\data\黑龙江国家级和省级非遗名单-地理编码-最终-修正.xlsx'
+df.to_excel(output_file, index=False)
+print(f"\n{'='*60}")
+print(f"Correction complete!")
+print(f"Successfully corrected: {success_count}/{len(problematic_indices)} records")
+print(f"Saved to: {output_file}")