{ "id": 239402, "title": "coordinate system", "url": "/competitions/indoor-location-navigation/discussion/239402", "author_name": "", "post_date": "2021-05-16T07:36:55.051126500Z", "votes": 1, "comment_count": 3, "views": 0, "content": "

Dear all,
\nI would like to understand the coordinates used for the floor plans. (I am a bit surprised that the data description does not mention this important detail at all)
\nIs there a projection algorithm that relates them to lat/lon ?
\nAny help would be greatly appreciated.

\n

Thanks!
\nMarkus

", "messages": [ { "id": "1309663", "postDate": "05/16/2021 07:36:55", "content": "

Dear all,
\nI would like to understand the coordinates used for the floor plans. (I am a bit surprised that the data description does not mention this important detail at all)
\nIs there a projection algorithm that relates them to lat/lon ?
\nAny help would be greatly appreciated.

\n

Thanks!
\nMarkus

", "rawMarkdown": "Dear all,\nI would like to understand the coordinates used for the floor plans. (I am a bit surprised that the data description does not mention this important detail at all)\nIs there a projection algorithm that relates them to lat/lon ?\nAny help would be greatly appreciated.\n\nThanks!\nMarkus", "votes": null }, { "id": "1309685", "postDate": "05/16/2021 07:57:10", "content": "

Hi @rapidminer, the coordinates can be converted to lat long using pyproj library. The following function was taken from @tomwarrens's wonderful notebook. In the notebook, he mentions that the values are in coordinates. For more information, kindly refer to his notebook.

\n
import pyproj\n\ndef get_lat_lon(point, proj = pyproj.Transformer.from_crs(3857, 4326, always_xy=True)):\n    try:\n        x1, y1 = point[0], point[1]\n        lon, lat = proj.transform(x1, y1)\n        return lat, lon\n    except:\n        return np.nan\n
", "rawMarkdown": "Hi @rapidminer, the coordinates can be converted to lat long using pyproj library. The following function was taken from @tomwarrens's wonderful [notebook](https://www.kaggle.com/tomwarrens/indoor-location-and-navigation-start). In the notebook, he mentions that the values are in coordinates. For more information, kindly refer to his notebook.\n\n```\nimport pyproj\n\ndef get_lat_lon(point, proj = pyproj.Transformer.from_crs(3857, 4326, always_xy=True)):\n try:\n x1, y1 = point[0], point[1]\n lon, lat = proj.transform(x1, y1)\n return lat, lon\n except:\n return np.nan\n\n```", "votes": null }, { "id": "1310037", "postDate": "05/16/2021 13:03:59", "content": "

In addition, don't forget to check https://www.kaggle.com/c/indoor-location-navigation/discussion/230558. Some maps are wrong.

", "rawMarkdown": "In addition, don't forget to check https://www.kaggle.com/c/indoor-location-navigation/discussion/230558. Some maps are wrong.", "votes": null }, { "id": "1311183", "postDate": "05/17/2021 07:58:49", "content": "

Thanks so much, this is VERY helpful and exactly what I was looking for.

", "rawMarkdown": "Thanks so much, this is VERY helpful and exactly what I was looking for.", "votes": null } ], "comments": [ { "id": 1309685, "author_name": "suryajrrafl", "author_url": "", "post_date": "05/16/2021 07:57:10", "content": "

Hi @rapidminer, the coordinates can be converted to lat long using pyproj library. The following function was taken from @tomwarrens's wonderful notebook. In the notebook, he mentions that the values are in coordinates. For more information, kindly refer to his notebook.

\n
import pyproj\n\ndef get_lat_lon(point, proj = pyproj.Transformer.from_crs(3857, 4326, always_xy=True)):\n    try:\n        x1, y1 = point[0], point[1]\n        lon, lat = proj.transform(x1, y1)\n        return lat, lon\n    except:\n        return np.nan\n
", "votes": null, "replies": [ { "id": 1310037, "author_name": "mamasinkgs", "author_url": "", "post_date": "05/16/2021 13:03:59", "content": "

In addition, don't forget to check https://www.kaggle.com/c/indoor-location-navigation/discussion/230558. Some maps are wrong.

", "votes": null, "replies": [] } ] }, { "id": 1311183, "author_name": "rapidminer", "author_url": "", "post_date": "05/17/2021 07:58:49", "content": "

Thanks so much, this is VERY helpful and exactly what I was looking for.

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1309663": "Dear all,\nI would like to understand the coordinates used for the floor plans. (I am a bit surprised that the data description does not mention this important detail at all)\nIs there a projection algorithm that relates them to lat/lon ?\nAny help would be greatly appreciated.\n\nThanks!\nMarkus", "1309685": "Hi @rapidminer, the coordinates can be converted to lat long using pyproj library. The following function was taken from @tomwarrens's wonderful [notebook](https://www.kaggle.com/tomwarrens/indoor-location-and-navigation-start). In the notebook, he mentions that the values are in coordinates. For more information, kindly refer to his notebook.\n\n```\nimport pyproj\n\ndef get_lat_lon(point, proj = pyproj.Transformer.from_crs(3857, 4326, always_xy=True)):\n try:\n x1, y1 = point[0], point[1]\n lon, lat = proj.transform(x1, y1)\n return lat, lon\n except:\n return np.nan\n\n```", "1310037": "In addition, don't forget to check https://www.kaggle.com/c/indoor-location-navigation/discussion/230558. Some maps are wrong.", "1311183": "Thanks so much, this is VERY helpful and exactly what I was looking for." }, "source": "meta" }