Scan a folder containing gpx files and detect potential tracking errors

clean_track.py

import lxml
from bs4 import BeautifulSoup

# https://medium.com/@petehouston/calculate-distance-of-two-locations-on-earth-using-python-1501b1944d97
from math import radians, sin, cos, asin, sqrt
def haversine(lon1, lat1, lon2, lat2):
    lon1, lat1, lon2, lat2 = map(radians, [lon1, lat1, lon2, lat2])
    dlon = lon2 - lon1
    dlat = lat2 - lat1
    a = sin(dlat / 2) ** 2 + cos(lat1) * cos(lat2) * sin(dlon / 2) ** 2
    return 2 * 6371 * asin(sqrt(a))

from dateutil import parser

normal_avg_ddist = 0.013137836943847864 * 50
normal_avg_dtime = 10.003996003996004 * 500
normal_avg_speed = 0.0016342546180846051 * 50

def detect_abnormal(fn):
    # fn = "trailwatch/449905.gpx"
    xml = BeautifulSoup(open(fn).read())

    points = []
    for trkpt in xml.findAll('trkpt'):
        points.append((
            float(trkpt.attrs['lon']),
            float(trkpt.attrs['lat']),
            parser.parse(trkpt.find('time').text)
        ))
        
    # print(points)

    speeds = []
    ddists = []
    dtimes = []
    for p1, p2 in zip(points[: -1], points[1: ]):
        ddist = haversine(p1[0], p1[1], p2[0], p2[1])
        dtime = (p2[2] - p1[2]).total_seconds()
        speed = ddist / dtime
        # print(speed)
        speeds.append(speed)
        ddists.append(ddist)
        dtimes.append(dtime)
        if ddist > normal_avg_ddist:
            print('ddst')
            return True
        if dtime > normal_avg_dtime:
            print('dtime')
            return True
        if speed > normal_avg_speed:
            print('speed')
            return True
    return False
    # print('avg ddist:', sum(ddists) / len(ddists))
    # print('avg dtime:', sum(dtimes) / len(dtimes))
    # print('avg speed:', sum(speeds) / len(speeds))

# print(detect_abnormal(''))

# avg ddist: 0.013137836943847864
# avg dtime: 10.003996003996004
# avg speed: 0.0016342546180846051

import datetime

def display_key_info(fn):
    xml = BeautifulSoup(open(fn).read())
    track = xml.find('trk')
    start_time = datetime.datetime.fromtimestamp(
        float(track.find('time').text))
    # print(start_time)
    info = track.find('info').text
    print(start_time, info, track.find('id').text, fn)

import os
for fn in os.listdir('trailwatch'):
    path = os.path.join('trailwatch', fn)
    if detect_abnormal(path):
        display_key_info(path)
    # print(path, detect_abnormal(path))

# display_key_info('trailwatch/222632.gpx')