吴裕雄--天生自然人工智能机器学习项目：地图数据及细胞图片数据处理报告

实验内容和原理
1. GML 地图数据清洗（30 分）
Gml 数据可以用记事本打开，可见里面有很多数据，其中我们需要提取红色区域的
数字，这类数字特征：前面是<gml:coordinates decimal="." cs="," ts=" ">-，后面是
</gml:coordinates>，66.94864210999998,44.998692232999986 就是表示一个点的横
坐标和纵坐标，这一块“66.94864210999998,44.998692232999986 -
66.94847150599998,44.99853494600001 -
66.94825196400001,44.997809570000015”，一共有 3 个点！！！三个点构成的图形
称为一条折线。下图一共 2 个折线，第二个折线 5 个点！！！请把这些数字保存
在一个 N*2 的一个数据集里面。其中前一个值表示 x,后一个表示 y。最后生成一个
txt 文档，具体如下
</gml:boundedBy>
 <gml:featureMember>
 <RoadSegment fid="C2006_RF_4005734">
 <rbUid>4005734</rbUid>
 <name>Richardson</name>
 <type>RD</type>
 <addrFmLeft>43</addrFmLeft>
 <addrFmRght>62</addrFmRght>
 <centreline>
 <gml:LineString srsName="">
 <gml:coordinates decimal="." cs="," ts=" ">-
66.94864210999998,44.998692232999986 -66.94847150599998,44.99853494600001 -
66.94825196400001,44.997809570000015 </gml:coordinates>
 </gml:LineString>
 </centreline>
 </RoadSegment>
 </gml:featureMember>
 <gml:featureMember>
 <RoadSegment fid="C2006_RF_4009492">
 <rbUid>4009492</rbUid>
 <name>Sherwood</name>
 <type>RD</type>
 <addrFmLeft>1</addrFmLeft>
 <addrToLeft>17</addrToLeft>
 <addrFmRght>2</addrFmRght>
 <addrToRght>18</addrToRght>
 <centreline>
 <gml:LineString srsName="">
 <gml:coordinates decimal="." cs="," ts=" ">-
64.874910613,46.370661702999996 -64.87512091600001,46.371108246000006 -
64.87525917200003,46.371348969999985 -64.875272655,46.371401115000026 -
64.87527750100003,46.371419871 </gml:coordinates>
%%%%%%%%%%%%%%%%txt 文档要求%%%%%%
67354//这个数字是总共的折线数目
3//3 个点，每个点横纵坐标间有个空格，两个点间有个回车
-66.94864210999998 44.99869223299998
-66.94847150599998 44.9985349460000
-66.94825196400001 44.99780957000001
5
-64.874910613 46.37066170299999
-64.87512091600001 46.37110824600000
-64.87525917200003 46.37134896999998
-64.875272655 46.37140111500002
-64.87527750100003 46.37141987
2
-65.87159661800001 46.18275623800002
-65.87176788199997 46.1823893100000
2
-66.06059955500001 46.0733558709999
-66.05884228500003 46.0738318720000
2
-64.539539321 46.22656682299998
-64.53880671000002 46.2268016930000